System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting behavior data of a user; means for accumulating the collected behavior data; means for analyzing the accumulated behavior data and extracting a behavior pattern; means for suggesting a next behavior based on the extracted behavior pattern; and means for presenting the suggested behavior 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 modern society, busy lifestyles mean that people often forget their daily tasks and schedules. This makes it difficult to efficiently manage daily life, resulting in a decline in quality of life. In particular, there are frequent moments when people forget what they were trying to do, resulting in a waste of time and effort. The purpose of this invention is to improve this situation and provide a system that efficiently supports users in remembering forgotten actions and taking the next action. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. First, a means for collecting user behavioral data is provided. This means captures the user's daily actions and events and stores them as digital data. Next, a means for storing the collected behavioral data is provided. This means securely stores the collected data in a database for subsequent analysis. Furthermore, a means for analyzing the stored behavioral data and extracting behavioral patterns is provided. This allows the system to learn the user's behavioral tendencies and predict their next action. Next, a means for suggesting a next action based on the extracted behavioral patterns is provided. This means can specifically indicate actions the user has forgotten or the next action they should take. Finally, a means for presenting the suggested action to the user. This means can prompt the user for the next action at an appropriate time when they are unsure, improving the efficiency and quality of their life. This system can present suggestions in response to the user's voice input, and can also collect visual information in addition to behavioral data to perform more advanced analysis.

[0006] "User behavior data" refers to information about various actions and events performed by users, such as adding events to a calendar, filling out a shopping list, and logging application usage.

[0007] "Means of collection" refers to the methods and technologies used to capture and introduce user behavior data into a system, including sensors, applications, digital forms, etc.

[0008] "Storage means" refers to the methods and techniques used to store collected behavioral data in a database or storage system, so that it can be used for subsequent analysis and recommendation generation.

[0009] "Means for analysis" refers to methods and technologies for analyzing accumulated behavioral data and extracting user behavior patterns, including machine learning algorithms and data mining techniques.

[0010] "Behavioral patterns" refer to trends in a series of user actions and habits extracted through analysis, which can be used to predict the user's next actions.

[0011] "Suggestion methods" refers to methods and technologies for recommending the next action to the user based on the extracted behavioral patterns, allowing the user to take appropriate action when they are unsure.

[0012] "Presentation means" refers to the method or technology used to notify or display the suggested action to the user, including a display, voice assistant, or mobile application.

[0013] "Means for responding to voice input" refers to methods and technologies for responding appropriately to a user's voice commands and suggesting actions, including voice recognition technology and natural language processing technology.

[0014] "Visual information" refers to information acquired through cameras and sensors, which can be used to analyze the user's surroundings and behavior. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] This invention is a system for supporting the daily life of a user, specifically, a system that records the user's behavior and suggests the next action based on the record. This system includes a series of processes that collect, accumulate, and analyze the user's behavior data, suggest the next action based on the extracted behavioral patterns, and notify the user of the suggestion.

[0037] The system operates through interactions between the terminal, the server, and the user. The specific operation of each component is explained below.

[0038] Data collection

[0039] Terminal

[0040] When a user adds an event to their calendar using their smartphone, the information is captured. For example, if a user types "Jogging at 08:00 on 2023-09-01," the event is detected by the device.

[0041] server

[0042] The device sends the detected information to a server, which stores it in a database, including the specific date and time and details of the event.

[0043] Data accumulation

[0044] server

[0045] The server securely stores the behavioral data sent from the device in a database, which systematically stores the user's past behavioral data and is used in subsequent analysis processes.

[0046] Data analysis

[0047] server

[0048] The server runs algorithms to analyze the stored data, using machine learning and data mining techniques to extract user behavioral patterns, such as jogging every morning at 8am.

[0049] Generate action suggestions

[0050] server

[0051] Based on the results of the data analysis, the server will suggest the user's next action. This suggestion is generated based on the user's past behavioral patterns. For example, if a user requests "Tell me what to do next," a specific suggestion such as "The next action is jogging" will be generated.

[0052] Presenting the proposal

[0053] Terminal

[0054] The proposed actions are sent to the device and displayed on the user's smartphone or other device. When the user verbally asks the device, "Tell me what to do next," the device immediately notifies the user of the suggestions received from the server.

[0055] Specific examples

[0056] For example, if a user adds a meeting to their calendar for 2 p.m., the system behaves as follows:

[0057] User: Opens the calendar app on their smartphone and enters "2023-09-01 14:00 Meeting."

[0058] Device: Detects schedules and sends information to the server.

[0059] Server: Receives the schedule information and stores it in a database.

[0060] Server: Periodically analyzes stored data to learn patterns of users performing work-related tasks around 2 p.m.

[0061] User: At 1:45 PM, voice requests "Tell me what to do next."

[0062] Terminal: Sends a request to the server, receives the suggestion, and notifies the user, displaying "Next action is a meeting."

[0063] In this way, the present invention can efficiently manage the user's daily life and prevent them from forgetting to take photos or getting lost. Each component of the system captures, stores, and analyzes the user's actions, and appropriately suggests the next action to take, improving the user's quality of life.

[0064] The processing flow will be explained below.

[0065] Step 1:

[0066] A user adds an event to a calendar app. The user uses their smartphone to enter specific event information (e.g., "2023-09-01 08:00 Jogging").

[0067] Step 2:

[0068] The device detects the events entered by the user. The device detects that the calendar app has been updated and captures the event information as new event data.

[0069] Step 3:

[0070] The device sends the captured schedule information to the server, and the device uploads the detected behavior data to the server via the Internet.

[0071] Step 4:

[0072] The server receives the schedule information sent from the device. The received data includes the date, time, and event details.

[0073] Step 5:

[0074] The server stores the received data in a database, where it accumulates this new data along with existing user behavior data.

[0075] Step 6:

[0076] The server analyzes the behavioral data stored in the database. Using machine learning algorithms, the server extracts the user's behavioral patterns. For example, it discovers that the user jogs every morning at 8:00.

[0077] Step 7:

[0078] The server then suggests the next action based on the user's behavioral patterns. In this process, the server predicts the user's best next action based on the analysis results and generates a suggestion, creating specific instructions such as "The next action is jogging."

[0079] Step 8:

[0080] The server sends the proposal to the terminal, which prepares the proposal to be notified to the user at the appropriate time.

[0081] Step 9:

[0082] The user makes a voice request saying, "Tell me what to do next." The user then asks for confirmation of the next action via their smartphone or voice assistant.

[0083] Step 10:

[0084] The terminal detects the user's voice request and forwards the request to the server. The terminal uses voice recognition technology to analyze the user's request and sends a corresponding request to the server.

[0085] Step 11:

[0086] The server responds to the user's request and returns pre-generated action suggestions to the terminal, providing the action suggestions that best fit the user's current situation.

[0087] Step 12:

[0088] The device notifies the user of the proposed activity. The device notifies the user by displaying or announcing the activity, such as "The next activity is jogging."

[0089] This series of steps helps users smoothly manage their schedules and next actions, which are often forgotten in daily life. Each step records the user's actions and suggests the next action based on them, improving the quality of life.

[0090] Example 1

[0091] 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."

[0092] In users' daily lives, there is a need to clarify the next action to be taken and manage it efficiently. However, conventional systems have low accuracy in collecting user behavioral information and suggesting appropriate actions, and lack the ability to respond quickly to the user's voice input. This makes it difficult for users to understand their next action and to receive appropriate support to improve their quality of life.

[0093] 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.

[0094] In this invention, the server includes a means for accumulating user behavior information, a means for analyzing behavioral patterns using a machine learning algorithm and generating a next action, and a means for converting the generated action into a prompt sentence format and transmitting it to the terminal, thereby enabling the user's behavior to be analyzed with high accuracy and the next action to be appropriately suggested.

[0095] "User behavior information" is data on activities and events that a user engages in in their daily life.

[0096] "Means of collection" refers to a mechanism for detecting user behavior information and acquiring that information.

[0097] "Storage means" refers to a mechanism for storing and managing collected behavioral information.

[0098] "Means of analysis and extraction of behavioral patterns" refers to a mechanism that analyzes accumulated behavioral information using machine learning algorithms and the like to discover user behavioral patterns.

[0099] The "means for suggesting the next action" is a mechanism for generating the next action that the user should take based on the extracted behavioral pattern.

[0100] The "means for presenting to the user" is a mechanism for notifying the user's terminal of the proposed action.

[0101] "Means for detecting information from the terminal and transferring it to the server" is a mechanism for transmitting data collected from the terminal to the server.

[0102] "Means for analyzing behavioral patterns using machine learning algorithms" refers to a mechanism for analyzing collected data using machine learning technology and extracting behavioral patterns.

[0103] The "means for generating behavior" is the process for determining the user's next behavior based on the analysis results.

[0104] The "means for converting into a prompt sentence format and sending to the terminal" is a mechanism for converting the proposed action into a format (prompt sentence) that is easy for the user to understand and sending that information to the terminal.

[0105] This invention is a system for supporting users' daily lives, characterized by collecting and analyzing user behavioral information and suggesting the user's next action based on that information. The system operates through interactions between the terminal, server, and user. The specific operation of each component is explained below.

[0106] Data collection

[0107] Terminal

[0108] When a user adds an event to their calendar using their smartphone, the information is captured. For example, if a user enters "2023-09-01 08:00 Jogging," the event is detected by the device.

[0109] Data transmission

[0110] Terminal

[0111] The calendar app detects the input and sends this information to the system's data collection module, which sends the data in JSON format to the server as an HTTP POST request.

[0112] Data accumulation

[0113] server

[0114] The received information is parsed and stored in a database (e.g., PostgreSQL), which contains the user ID, event date and time, and event details.

[0115] Data analysis

[0116] server

[0117] The accumulated data is analyzed using Python's scikit-learn library. User behavior patterns are extracted using machine learning algorithms (e.g., Gaussian Mixture Models). The Pandas library is used for data preprocessing.

[0118] Generate action suggestions

[0119] server

[0120] As a result of the analysis, the next action is suggested. For example, if it is determined that the user jogs at 8 o'clock every morning, the system generates a suggestion such as "Your next action is to jog." This suggestion is converted into a prompt sentence format and saved in the database.

[0121] Presenting the proposal

[0122] Terminal

[0123] When a user requests "Tell me what to do next" by voice, the request is sent to the server. The server notifies the user of the suggestions received. The user is informed via a screen display or voice assistant that "The next action is jogging."

[0124] Specific examples

[0125] For example, if a user adds a meeting to their calendar for 2 p.m., the system behaves as follows:

[0126] User: Opens the calendar app on their smartphone and enters "2023-09-01 14:00 Meeting."

[0127] Device: Detects schedules and sends information to the server.

[0128] Server: Receives the schedule information and stores it in a database.

[0129] Server: Periodically analyzes stored data to learn patterns of users performing work-related tasks around 2 p.m.

[0130] User: At 1:45 PM, voice requests "Tell me what to do next."

[0131] Terminal: Sends a request to the server, receives the suggestion, and notifies the user, displaying "Next action is a meeting."

[0132] Prompt Sentence Examples

[0133] "Suggest next action. Based on the latest behavioral pattern data, the user is available at 1:30 PM."

[0134] In this way, the present invention efficiently manages the user's daily life and prevents the user from being confused about what to do by suggesting appropriate next actions. Each component of the system captures, stores, and analyzes the user's actions and suggests appropriate next actions to improve the user's quality of life.

[0135] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0136] Step 1:

[0137] User

[0138] The user opens the calendar app on their smartphone and enters a new appointment, for example, "2023-09-01 08:00 Jogging." This entry is detected by the device.

[0139] Input: Enter a new event into the calendar app

[0140] Output: Detected event data (date, time, content)

[0141] Step 2:

[0142] Terminal

[0143] The device collects event data from the calendar app and makes an HTTP POST request to send it to the server in JSON format.

[0144] Specific operation: Acquires event data, converts it to JSON format, and sends it to the server.

[0145] Input: Detected event data (date, time, content)

[0146] Output: Event data sent to the server in JSON format

[0147] Step 3:

[0148] server

[0149] The server receives the HTTP request and analyzes the event data sent. After analyzing, it stores the data in a database. The database contains the user ID, event date and time, and event details.

[0150] Specific behavior: Parse the received event data and execute a query to insert it into the database.

[0151] Input: Event data in JSON format

[0152] Output: Event entries stored in the database

[0153] Step 4:

[0154] server

[0155] The accumulated data is periodically analyzed. Python's scikit-learn is used to extract user behavior patterns based on past behavior data. The algorithm used is Gaussian Mixture Models.

[0156] Specific operation: Data preprocessing with Pandas, running machine learning models with scikit-learn, and extracting patterns

[0157] Input: Past behavioral data stored in a database

[0158] Output: Extracted behavioral patterns

[0159] Step 5:

[0160] server

[0161] As a result of the data analysis, the next action is suggested based on the behavioral pattern. For example, a suggested sentence such as "The next action is jogging" is generated. This suggestion is converted into a prompt sentence format and saved in a database.

[0162] Specific behavior: Determine the next action based on the behavior pattern, generate a prompt sentence, and save it.

[0163] Input: Extracted behavioral patterns

[0164] Output: Next action saved as a prompt

[0165] Step 6:

[0166] User

[0167] The user makes a voice request saying, "Tell me what to do next." This request is sent from the device to the server.

[0168] Input: User's voice request

[0169] Output: Request sent to the server

[0170] Step 7:

[0171] Terminal

[0172] The device receives the suggested next action from the server and notifies the user, for example, by notifying the user through a voice assistant that "The next action is jogging."

[0173] Specific behavior: Use an app or voice assistant to receive a response from the server and notify the user.

[0174] Input: Proposal received from the server

[0175] Output: Notification to the user (text or audio)

[0176] (Application example 1)

[0177] 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."

[0178] In modern manufacturing, improving work efficiency within factories requires accurately understanding worker behavior patterns and proposing optimal work at the right time. However, traditional manual work instructions and recording placed a heavy burden on workers and made efficient work management difficult. Furthermore, the lack of an automatic suggestion system based on worker behavior patterns limited the ability to improve work efficiency throughout the factory.

[0179] 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.

[0180] In this invention, the server includes means for collecting user behavior data, means for storing the collected behavior data, and means for analyzing the stored behavior data and extracting behavioral patterns. This allows the server to suggest a next action based on the user's behavior data, send a command to a device that operates an object based on the suggestion, and have the device execute the next action based on the command. This improves work efficiency in factories and reduces the burden on workers.

[0181] The "means for collecting user behavioral data" refers to a means for detecting and recording information about schedules and behaviors entered by a user using a smartphone, tablet device, or the like.

[0182] "Means for storing collected behavioral data" refers to a database or storage for safely storing collected user behavioral data and using it for subsequent analysis.

[0183] "Means for analyzing accumulated behavioral data and extracting behavioral patterns" refers to means for analyzing and extracting users' daily behavioral patterns based on accumulated behavioral data using machine learning algorithms and data mining techniques.

[0184] The "means for proposing the next action based on the extracted behavioral pattern" is a means for generating and proposing an appropriate next action to the user based on the behavioral pattern obtained by analysis.

[0185] The "means for presenting a proposed action to the user" refers to a means for visually or audibly notifying the user of the generated proposal for the next action.

[0186] The "means for sending commands to equipment that operates objects based on the proposed action" refers to a means for sending specific work instructions to robots and other work equipment in the factory based on the content of the proposal.

[0187] The "means by which the equipment that received the command executes the next action" refers to the means by which the robot or work equipment actually performs the specified work based on the received command.

[0188] The system of this invention is a robotic assistant system that improves work efficiency in factories. This system includes a function to collect, store, and analyze user behavior data and suggest the next action. It also sends commands to machines that manipulate objects based on the suggested action, and the machines actually execute the next action, thereby improving work efficiency in factories.

[0189] The specific components of this system and their processing will now be described.

[0190] Programs and their processing

[0191] Data collection

[0192] The user inputs work instructions using a smartphone or tablet device. For example, they input an instruction such as "Assemble part A at 14:00 on 2023-09-01." This information is detected and sent from the device to the server. The device can be a general smartphone (for example, an iPhone or Android device) or tablet. Data is sent using an HTTP request, using the requests library.

[0193] Data accumulation

[0194] The server securely stores the work instruction information received from the terminal in a database. This database stores the user's past work data. Suitable database software is MySQL or PostgreSQL.

[0195] Data analysis

[0196] The server analyzes the accumulated data and runs algorithms to extract behavioral patterns, such as machine learning algorithms (such as scikit-learn) and data mining techniques, making it possible to predict when and what tasks a user will perform.

[0197] Generate action suggestions

[0198] Based on the results of the data analysis, the server will suggest the user's next action, which will indicate what the user should do next, generating specific instructions such as "The next action is to assemble part B."

[0199] Submitting proposals and issuing directives

[0200] The suggestions are sent to the device and the user is notified visually and audibly. At the same time, specific work instructions based on the suggested actions are sent to robots and other work equipment in the factory. When the command is sent to the robot, it executes the suggested action. The equipment is typically a typical factory robot (e.g., an industrial robot arm) and is often controlled through an API.

[0201] Specific examples

[0202] For example, one day, a user enters "2023-09-01 14:00 Assemble part A" into their smartphone calendar. The system captures this information and sends it to the server. The server stores the information in a database, analyzes it, and learns a pattern of performing work-related tasks around 2:00 PM. If the user makes a voice request at 1:45 PM saying, "Tell me what to do next," the device notifies the user of the server's suggestion, displaying, "The next action is to assemble part B." At the same time, the server instructs the robot to "assemble part B," and the robot executes the suggested action.

[0203] Prompt Sentence Examples

[0204] User: Enters "2023-10-01 09:00 Assemble part A" on the smartphone.

[0205] System: This information is sent to the server and stored in a database.

[0206] Server: Suggests the next action (e.g., assemble part B) based on past data.

[0207] User: At 9 AM, voice requests "Tell me what to do next."

[0208] System: Display "Your next action is to assemble part B."

[0209] As described above, the present invention aims to improve work efficiency in factories and reduce the burden on workers by analyzing user behavior and proposing the next action.

[0210] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0211] Step 1:

[0212] Users input work instructions using smartphones or tablet devices.

[0213] Specifically, the user opens a calendar app and enters instructions such as "Assemble part A at 2023-09-01 14:00." This data becomes the input data.

[0214] Step 2:

[0215] The terminal detects the input work instruction information and transmits it to the server.

[0216] The application on the terminal sends the input data to the server using an HTTP request, and the server receives the information. The output is the work instruction data sent to the server.

[0217] Step 3:

[0218] The server stores the received work instruction information in a database.

[0219] Specifically, the server uses a MySQL or PostgreSQL database to record the data it receives (for example, the date, time, and content of a work order), which then becomes the input data for subsequent analysis.

[0220] Step 4:

[0221] The server analyzes various work data stored in the database and extracts behavioral patterns.

[0222] For example, the server uses a machine learning library such as scikit-learn to analyze the accumulated data and learn the user's behavioral patterns. This analysis extracts the tendency for users to perform specific tasks at specific times. The output is the user's behavioral patterns.

[0223] Step 5:

[0224] The server suggests the next action based on the extracted behavioral pattern.

[0225] Based on machine learning algorithms, it predicts the next task the user should perform and generates a suggestion, such as "Your next action is to assemble part B."

[0226] Step 6:

[0227] The proposed action is transmitted to the terminal and notified to the user visually or audibly.

[0228] The server sends the generated suggestions to the device, which then displays the information on the user's smartphone or tablet. The input is the suggestion data from the server, and the output is displayed as a notification on the device.

[0229] Step 7:

[0230] Based on the proposal, the server sends specific work instructions to the robots in the factory.

[0231] Based on the proposed actions, the server issues work instructions to the robot using an API. The input is the work instructions from the server, and the output is a command to the robot.

[0232] Step 8:

[0233] Upon receiving the command, the robot performs the next action according to the command.

[0234] For example, a robot starts assembling part B. The input is the received work instruction, and the output is the actual work action.

[0235] This allows the entire system to work together to manage the user's actions and effectively suggest and execute the next action.

[0236] 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.

[0237] This invention is a system for supporting users in their daily lives. Specifically, it is a system that records the user's behavioral data and suggests the next action based on the record. In particular, it is characterized by combining an emotion engine that recognizes the user's emotions and suggests actions according to the user's emotions.

[0238] The system operates through interactions between the terminal, server, emotion engine, and user. The specific operation of each component is explained below.

[0239] Data collection and storage

[0240] Terminal

[0241] When a user adds an event to their calendar using their smartphone, the information is captured. For example, if a user enters "Jogging at 08:00 on 2023-09-01," the event is detected by the device.

[0242] server

[0243] The device sends the detected information to a server, which stores it in a database, including the specific date and time and details of the event.

[0244] Data analysis

[0245] server

[0246] The server runs algorithms to analyze the accumulated data. Here, machine learning algorithms are used to extract user behavioral patterns. For example, a user may learn that they jog every morning at 8:00.

[0247] Generate action suggestions

[0248] server

[0249] Based on the results of the data analysis, the server will suggest the user's next action. This suggestion is generated based on the user's past behavioral patterns, and will create specific instructions such as "The next action is to go jogging."

[0250] Emotion Recognition and Regulation

[0251] Emotion Engine

[0252] The emotion engine recognizes emotions by analyzing the user's facial expressions and vocal tone, and this information is used to tailor the next suggested action. For example, if the user is feeling stressed, it will suggest actions to help them relax.

[0253] Presenting the proposal

[0254] Terminal

[0255] The suggested actions are sent to the device and displayed on the user's smartphone or other device. When the user makes a voice request such as "Tell me what to do next," the device immediately notifies the user of the suggestions received from the server.

[0256] Specific examples

[0257] For example, if a user adds a meeting to their calendar for 2 p.m., the system behaves as follows:

[0258] User: Opens the calendar app on their smartphone and enters "2023-09-01 14:00 Meeting."

[0259] Device: Detects schedules and sends information to the server.

[0260] Server: Receives the schedule information and stores it in a database.

[0261] Server: Periodically analyzes stored data to learn patterns of users performing work-related tasks around 2 p.m.

[0262] User: At 1:45 PM, voice requests "Tell me what to do next."

[0263] Terminal: Sends a request to the server, receives the suggestion, and notifies the user, displaying "Next action is a meeting."

[0264] Emotion engine: If a user is feeling stressed during a meeting, the system will provide additional advice such as "take a deep breath to relax a bit."

[0265] This series of steps helps users smoothly manage their schedules and next actions, which are often forgotten in daily life. The addition of an emotion engine enables more detailed action suggestions based on the user's emotional state, further improving quality of life. Each step enriches the user's life by recording the user's actions and suggesting the next action based on them.

[0266] The processing flow will be explained below.

[0267] Step 1:

[0268] A user adds an event to a calendar app. The user uses their smartphone to enter specific event information (e.g., "2023-09-01 08:00 Jogging").

[0269] Step 2:

[0270] The device detects the events entered by the user. The device detects that the calendar app has been updated and captures the event information as new event data.

[0271] Step 3:

[0272] The device sends the captured schedule information to the server, and the device uploads the detected behavior data to the server via the Internet.

[0273] Step 4:

[0274] The server receives the schedule information sent from the device. The received data includes the date, time, and event details.

[0275] Step 5:

[0276] The server stores the received data in a database, where it accumulates this new data along with existing user behavior data.

[0277] Step 6:

[0278] The server analyzes the behavioral data stored in the database. Using machine learning algorithms, the server extracts the user's behavioral patterns. For example, it discovers that the user jogs every morning at 8:00.

[0279] Step 7:

[0280] The server then suggests the next action based on the user's behavioral patterns. In this process, the server predicts the user's best next action based on the analysis results and generates a suggestion, creating specific instructions such as "The next action is jogging."

[0281] Step 8:

[0282] The emotion engine recognizes the user's emotions. The emotion engine analyzes the user's facial expressions and vocal tone to determine their current emotional state. For example, if the user is feeling stressed, that information will be reflected.

[0283] Step 9:

[0284] The server adjusts the suggestions based on the information obtained from the emotion engine. For example, if it determines that the user is feeling stressed, it adds a relaxing activity ("take a deep breath") to the next action suggestions.

[0285] Step 10:

[0286] The server sends the final proposal to the device, which prepares it for notification to the user at the appropriate time.

[0287] Step 11:

[0288] The user makes a voice request saying, "Tell me what to do next." The user then asks for confirmation of the next action via their smartphone or voice assistant.

[0289] Step 12:

[0290] The terminal detects the user's voice request and forwards the request to the server. The terminal uses voice recognition technology to analyze the user's request and sends a corresponding request to the server.

[0291] Step 13:

[0292] The server responds to the user's request and returns pre-generated action suggestions to the terminal, providing the action suggestions that best fit the user's current situation.

[0293] Step 14:

[0294] The device notifies the user of the suggested action. The device uses a display or voice notification to let the user know, "The next action is jogging." If the user is feeling stressed, the device also provides additional advice for relaxation ("take a deep breath").

[0295] This series of steps helps users smoothly manage their schedules and next actions, which are often forgotten in daily life. The addition of an emotion engine makes it possible to provide detailed action suggestions based on the user's emotional state, further improving quality of life.

[0296] Example 2

[0297] 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."

[0298] Conventional behavior suggestion systems can make suggestions based on the user's behavioral data, but they cannot make suggestions that take into account the user's emotional state. As a result, they cannot make optimal suggestions when the user is stressed or in a specific emotional state, making it difficult to improve user satisfaction. In addition, interactive suggestions based on voice input have not been sufficiently implemented.

[0299] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting user behavioral data, means for storing the collected behavioral data, means for analyzing the stored behavioral data and extracting behavioral patterns, means for proposing a next action based on the extracted behavioral pattern, means for presenting the proposed action to the user, and means for recognizing the user's emotions and adjusting the next action proposal. This enables more personalized action proposals taking into account the user's emotional state, thereby significantly improving user satisfaction.

[0300] "User behavioral data" refers to information about various activities that a user performs in their daily life, including, for example, calendar entries, tasks, and daily habits.

[0301] "Means of collection" refers to hardware and software used to obtain behavioral data from users, such as smartphone calendar apps and sensors.

[0302] "Storage means" refers to a database or storage system for storing collected data.

[0303] "Means of analysis and extraction of behavioral patterns" refers to algorithms and software, such as machine learning algorithms, that can be used to find useful information and trends from accumulated data.

[0304] "Suggestion methods" refers to algorithms or software that recommend the next action to the user based on the extracted behavioral patterns.

[0305] "Presentation means" refers to the interface or device used to notify the user of the suggested action, such as a smartphone notification feature or voice assistant.

[0306] "Means for recognizing emotions and adjusting next action suggestions" refers to software or hardware, such as facial recognition technology or voice analysis technology, that analyzes the user's emotions and changes next action suggestions in response to those emotions.

[0307] "Responding to voice input" refers to a system that executes corresponding functions in response to a user's voice input of instructions or questions.

[0308] "Visual information" refers to image data and video data such as a user's facial expressions and gestures.

[0309] This invention is a system for supporting users' daily lives, specifically a system that records user behavioral data and suggests next actions based on that data. Furthermore, it is characterized by combining an emotion engine that recognizes the user's emotions and suggests actions based on the user's emotions. The system operates through the user's terminal, a server, the emotion engine, and the interactions between them.

[0310] Data collection and storage

[0311] Terminal

[0312] The device mainly refers to devices such as smartphones and tablets. When a user adds an event to a calendar app using such a device, the information is automatically captured. For example, if a user enters "Jogging at 08:00 on 2023-09-01" in the calendar, this information is detected by the device.

[0313] server

[0314] The collected data is sent from the device to a server, which stores the received information in a database and manages data for each user, including specific dates, times, and details of events.

[0315] Data analysis

[0316] server

[0317] The server runs an algorithm to analyze the stored data. For example, a machine learning algorithm is used to extract the user's behavioral patterns. This analysis may reveal that the user has a habit of performing a certain activity at a specific time each day (for example, jogging at 8:00 AM every morning).

[0318] Generate action suggestions

[0319] server

[0320] Based on the analysis results, the server will suggest the next action, for example, generating specific instructions such as "Next action is jogging." This suggestion is based on the user's past behavioral patterns.

[0321] Emotion recognition and behavioral suggestion adjustment

[0322] Emotion Engine

[0323] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and voice to recognize their emotions. The results of this recognition are sent to the server and used to adjust the next action suggestion. For example, if the user is feeling stressed, the engine will suggest actions to help them relax.

[0324] Presenting the proposal

[0325] Terminal

[0326] The suggestions are sent to the device and displayed on the user's smartphone or other device. When the user makes a voice request, "Tell me what to do next," the device immediately displays the suggestions received from the server.

[0327] Specific examples

[0328] For example, if a user adds a meeting to their calendar for 2:00 PM, the sequence of actions is as follows:

[0329] User: Opens the calendar app on their smartphone and enters "2023-09-01 14:00 Meeting."

[0330] Device: Detects schedules and sends information to the server.

[0331] Server: Receives the schedule information and saves it in the database. "2023-09-01 14:00 Meeting" is recorded as data for each user.

[0332] Server: Periodically analyzes stored data to learn patterns of users performing work-related tasks around 2 p.m.

[0333] User: At 1:45 PM, voice requests "Tell me what to do next."

[0334] Terminal: Sends a request to the server, receives the suggestion, and notifies the user, displaying "Next action is a meeting."

[0335] Emotion engine: If a user is feeling stressed during a meeting, the system will provide additional advice such as "Take a deep breath to relax a bit." This analysis is performed by the emotion engine, which analyzes the user's facial expressions and voice.

[0336] Prompt Sentence Examples

[0337] Below is an example of a prompt sentence to input to the generative AI model.

[0338] Please explain the steps involved in the system that suggests actions based on the user's emotions.

[0339] 1. The user enters an event into the calendar app on their smartphone.

[0340] 2. The device detects this appointment and sends it to the server.

[0341] 3. The server saves the appointment information in a database.

[0342] 4. The server analyzes the stored data and learns user behavior patterns.

[0343] 5. The server suggests the next action.

[0344] 6. The emotion engine recognizes the user's emotions and adjusts suggested actions if necessary.

[0345] 7. The device notifies the user of the suggested action.

[0346] An example would be "When a user schedules a meeting for 2 PM."

[0347] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0348] Step 1:

[0349] User

[0350] The user opens the calendar app on their smartphone and enters an appointment. For example, they enter "2023-09-01 14:00 Meeting." This entry becomes the basic data for future processing.

[0351] Input: Events entered in the calendar (text format)

[0352] Output: Capture of schedule information (text format)

[0353] What happens: A user manually enters an event into a calendar app. This information is stored on the device as text data.

[0354] Step 2:

[0355] Terminal

[0356] The device captures the schedule information entered by the user and automatically sends it to the server, where the date, time, and event details are obtained.

[0357] Input: Schedule information entered by the user (text format)

[0358] Output: Schedule information sent to the server (text format)

[0359] Specific operation: The device detects the entered schedule information in real time and sends that information to the server's API endpoint.

[0360] Step 3:

[0361] server

[0362] The server stores the schedule information received from the device in a database, which is linked to the user ID and date and time information.

[0363] Input: Schedule information sent from the device (text format)

[0364] Output: Schedule information stored in the database (database records)

[0365] Specific operation: When the server receives the event information, it creates a new record in the database and saves it. The saved information includes the user ID, date and time, and event details.

[0366] Step 4:

[0367] server

[0368] The server runs machine learning algorithms to analyze the stored schedule information, thereby extracting user behavior patterns.

[0369] Input: User behavior data stored in a database (database records)

[0370] Output: Extracted behavioral patterns (model data)

[0371] How it works: The server periodically reads the behavioral data in the database and uses machine learning algorithms to analyze and extract behavioral patterns, such as repeating behavior during specific times of the day.

[0372] Step 5:

[0373] server

[0374] Based on the results of the data analysis, an algorithm is run to suggest next steps, which are generated based on past behavioral patterns.

[0375] Input: Behavioral pattern (model data)

[0376] Output: Next action suggestions (text format)

[0377] Specific operation: Based on the extracted behavioral patterns, the server uses an algorithm to determine the next action the user should take and generates a suggested text data. For example, a suggestion such as "The next action is jogging" is created.

[0378] Step 6:

[0379] Emotion Engine

[0380] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and voice to recognize their emotions, and adjusts the next action suggestions accordingly.

[0381] Input: User's facial expressions and voice data (multimedia format)

[0382] Output: Recognized emotion data (text and numeric format)

[0383] Specific operation: The emotion engine analyzes the user's facial expressions captured by the camera and the voice data collected by the microphone, and extracts the user's emotional state as text and numerical data, which is sent to the server to adjust the next action suggestion.

[0384] Step 7:

[0385] server

[0386] The server adjusts the suggested actions based on the emotion data sent from the emotion engine. If the user is feeling stressed, the server will suggest additional actions to help them relax.

[0387] Input: Emotion data (text and numerical format), next action suggestions (text format)

[0388] Output: Adjusted action proposals (text format)

[0389] Specific actions: The server analyzes the emotion data and modifies the original action suggestions as needed, for example, to include specific advice such as "take a deep breath to relax a bit" if the user is feeling stressed.

[0390] Step 8:

[0391] Terminal

[0392] The adjusted action suggestions are sent to the device and notified to the user. The suggestions are also displayed when the user makes a voice request such as "Tell me what to do next."

[0393] Input: Adjusted action proposal (text format)

[0394] Output: Action suggestions displayed to the user (in text format)

[0395] Specific operation: The device receives the adjusted action suggestions from the server and presents them to the user via notifications or voice assistants. The user can then confirm the suggested action and smoothly carry out the next action.

[0396] The above is a description of the specific processing steps of this system and their detailed operation.

[0397] (Application example 2)

[0398] 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."

[0399] Conventional food delivery services only provide users with meal options, but do not offer personalized suggestions based on their emotional state or behavioral patterns. As a result, users find it difficult to select the meal that best suits their current emotional state and situation, and are unable to receive appropriate suggestions for health management or stress relief. This leaves users with insufficient support for improving their quality of life and enjoying a comfortable daily life.

[0400] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0401] In this invention, the server includes means for collecting user behavioral data, emotion engine means for analyzing the emotional state, and means for adjusting the next action based on the emotional state, thereby optimizing the next action based on the user's emotional state and behavioral patterns, and making it possible to suggest meals that have a relaxing effect or that suit the user's preferences as needed.

[0402] "Behavioral data" is information relating to the user's daily activities, tasks, schedules, and the like.

[0403] An "emotion engine" is a software or hardware mechanism for analyzing a user's emotional state.

[0404] "Next Action" refers to the next action or task that the user should perform.

[0405] A "behavioral pattern" is a tendency or regularity of behavior extracted from a user's past behavioral data.

[0406] The "adjustment means" is a means for optimizing the next action suggestion based on the emotional state analyzed by the emotion engine.

[0407] A "suggested action" is an instruction for next action that the system presents to the user based on the analyzed behavioral data and emotional state.

[0408] "Visual information" refers to information that is visually recognized, such as the user's facial expressions and actions.

[0409] "Emotional information" is data relating to the user's emotional state, and is information obtained from voice tone, facial expressions, and the like.

[0410] "Means of collection" refers to devices and software for capturing user behavioral data and emotional information.

[0411] The "means for presenting suggestions" is a means for displaying or notifying the user of suggestions for the next action or meal.

[0412] This invention is directed to a smartphone application for food delivery services. The system collects and analyzes user behavioral and emotional data to suggest optimal meals to users.

[0413] System configuration

[0414] Hardware and Software

[0415] The system uses the following hardware and software:

[0416] Smartphone: Used to provide the user interface and collect data.

[0417] Emotion Engine: Software that analyzes the user's emotional state. In this case, we use the TextBlob library.

[0418] Server: A server for storing and analyzing user behavioral and emotional data.

[0419] Food Delivery API: An external API that processes food orders.

[0420] Data collection and storage

[0421] Smartphone: The user uses a calendar app to enter activity data (e.g., a jogging schedule), and this information is sent from the smartphone to the server.

[0422] Server: The server receives the data and stores it in a database, including the date and time of the activity and detailed information.

[0423] Emotion engine: Collects and analyzes emotional data from user text and voice input.

[0424] Data analysis

[0425] Server: Runs algorithms to analyze the accumulated behavioral and emotional data. Machine learning algorithms are used here to extract user behavior patterns.

[0426] Emotion Engine: Uses the TextBlob library to parse the user's input text (emotion data) and generate an emotion score.

[0427] Generating behavioral and dietary suggestions

[0428] Server: Based on the analysis results, the server will suggest the next action and the best meal. For example, if the user is feeling stressed, it will suggest a meal that will have a relaxing effect.

[0429] Smartphone: Suggested activities and meals are presented to the user via their smartphone. When the user requests the next action by voice, the server immediately notifies them of the suggestion.

[0430] Specific examples

[0431] For example, if a user enters "2023-09-01 14:00 meeting" into a calendar app, the system will behave as follows:

[0432] Original invention in action:

[0433] User: Opens the calendar app on their smartphone and enters "2023-09-01 14:00 Meeting."

[0434] Device: Detects schedules and sends information to the server.

[0435] Server: Receives the schedule information and stores it in a database.

[0436] Server: Periodically analyzes stored data to learn patterns of users performing work-related tasks around 2 p.m.

[0437] User: At 1:45 PM, voice requests "Tell me what to do next."

[0438] Terminal: Sends a request to the server, receives the suggestion, and notifies the user, displaying "Next action is a meeting."

[0439] Emotion engine: If a user is feeling stressed during a meeting, the system will provide additional advice such as "take a deep breath to relax a bit."

[0440] Examples of application improvements:

[0441] User: A user who feels stressed types "I'm feeling stressed right now" into a smartphone app.

[0442] Emotion engine: The analyze_emotion function generates a negative emotion score from "stress."

[0443] Suggestion: The app suggests to the user, "Why not order a hot soup to help you relax?"

[0444] Ordering: If the user accepts the suggestion, the app will automatically place the soup order.

[0445] Example prompt sentence:

[0446] "If a user types 'I am feeling stressed,' generate a negative emotion score and suggest foods that will help them relax."

[0447] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0448] Step 1:

[0449] User behavioral data entry

[0450] A user uses a calendar application on their smartphone to enter action data such as "2023-09-01 14:00 Meeting."

[0451] Input: Behavioral data entered by the user into their smartphone (date, time, and content)

[0452] Output: Behavioral data is stored in an application on the smartphone.

[0453] Step 2:

[0454] Transmission of behavioral data by the device

[0455] The device transmits the detected behavioral data to the server, where the behavioral data is converted into an appropriate format and sent to the server via the network.

[0456] Input: Behavioral data stored on the smartphone

[0457] Output: Behavioral data is sent to and received by the server.

[0458] Step 3:

[0459] Data storage by server

[0460] The server stores the received behavioral data in a database, which stores the date, time, and event details.

[0461] Input: Behavioral data sent to the server

[0462] Output: The behavioral data is stored in a database on the server.

[0463] Step 4:

[0464] Emotional data collection and analysis using an emotion engine

[0465] When a user types "I'm feeling stressed right now" into their smartphone, the emotion engine analyzes the input and generates an emotion score. In this example, the TextBlob library is used.

[0466] Input: Emotion data entered by the user (e.g., feeling stressed)

[0467] Output: A sentiment score (e.g., a negative sentiment score) is generated.

[0468] Step 5:

[0469] Server analysis of behavioral patterns

[0470] The server analyzes the accumulated behavioral and emotional data and uses machine learning algorithms to extract behavioral patterns.

[0471] Input: Behavioral data and emotion scores stored in a database

[0472] Output: Analysis of user behavior patterns

[0473] Step 6:

[0474] Server-generated next action and meal suggestions

[0475] The server then suggests the next action or meal based on the analysis results. For example, it suggests a meal with a relaxing effect (e.g., soup) based on the emotion score.

[0476] Input: Behavioral pattern analysis results and sentiment score

[0477] Output: Suggested behavior and dietary recommendations

[0478] Step 7:

[0479] Proposal presentation by device

[0480] The device displays and notifies the user of the suggestions received from the server. If the user requests the next action by voice, the suggestions are displayed immediately.

[0481] Input: Proposal sent from the server

[0482] Output: Display and notification of suggestions on smartphone

[0483] Step 8:

[0484] User review and order

[0485] If the user accepts the suggested meal, the device sends the order to the food delivery API. If the order is successful, a confirmation message is displayed to the user.

[0486] Input: The result of the user reviewing the suggestion (e.g., ordering a meal)

[0487] Output: Places an order to the food delivery API and displays a confirmation message

[0488] Example of using a generative AI model and prompt:

[0489] "If a user types 'I am feeling stressed,' generate a negative emotion score and suggest foods that will help them relax."

[0490] 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.

[0491] 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.

[0492] 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.

[0493] [Second embodiment]

[0494] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0495] 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.

[0496] 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).

[0497] 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.

[0498] 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.

[0499] 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).

[0500] 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. 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.

[0501] 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.

[0502] 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.

[0503] 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.

[0504] 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.

[0505] 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."

[0506] This invention is a system for supporting the daily life of a user, specifically, a system that records the user's behavior and suggests the next action based on the record. This system includes a series of processes that collect, accumulate, and analyze the user's behavior data, suggest the next action based on the extracted behavioral patterns, and notify the user of the suggestion.

[0507] The system operates through interactions between the terminal, the server, and the user. The specific operation of each component is explained below.

[0508] Data collection

[0509] Terminal

[0510] When a user adds an event to their calendar using their smartphone, the information is captured. For example, if a user types "Jogging at 08:00 on 2023-09-01," the event is detected by the device.

[0511] server

[0512] The device sends the detected information to a server, which stores it in a database, including the specific date and time and details of the event.

[0513] Data accumulation

[0514] server

[0515] The server securely stores the behavioral data sent from the device in a database, which systematically stores the user's past behavioral data and is used in subsequent analysis processes.

[0516] Data analysis

[0517] server

[0518] The server runs algorithms to analyze the stored data, using machine learning and data mining techniques to extract user behavioral patterns, such as jogging every morning at 8am.

[0519] Generate action suggestions

[0520] server

[0521] Based on the results of the data analysis, the server will suggest the user's next action. This suggestion is generated based on the user's past behavioral patterns. For example, if a user requests "Tell me what to do next," a specific suggestion such as "The next action is jogging" will be generated.

[0522] Presenting the proposal

[0523] Terminal

[0524] The proposed actions are sent to the device and displayed on the user's smartphone or other device. When the user verbally asks the device, "Tell me what to do next," the device immediately notifies the user of the suggestions received from the server.

[0525] Specific examples

[0526] For example, if a user adds a meeting to their calendar for 2 p.m., the system behaves as follows:

[0527] User: Opens the calendar app on their smartphone and enters "2023-09-01 14:00 Meeting."

[0528] Device: Detects schedules and sends information to the server.

[0529] Server: Receives the schedule information and stores it in a database.

[0530] Server: Periodically analyzes stored data to learn patterns of users performing work-related tasks around 2 p.m.

[0531] User: At 1:45 PM, voice requests "Tell me what to do next."

[0532] Terminal: Sends a request to the server, receives the suggestion, and notifies the user, displaying "Next action is a meeting."

[0533] In this way, the present invention can efficiently manage the user's daily life and prevent them from forgetting to take photos or getting lost. Each component of the system captures, stores, and analyzes the user's actions, and appropriately suggests the next action to take, improving the user's quality of life.

[0534] The processing flow will be explained below.

[0535] Step 1:

[0536] A user adds an event to a calendar app. The user uses their smartphone to enter specific event information (e.g., "2023-09-01 08:00 Jogging").

[0537] Step 2:

[0538] The device detects the events entered by the user. The device detects that the calendar app has been updated and captures the event information as new event data.

[0539] Step 3:

[0540] The device sends the captured schedule information to the server, and the device uploads the detected behavior data to the server via the Internet.

[0541] Step 4:

[0542] The server receives the schedule information sent from the device. The received data includes the date, time, and event details.

[0543] Step 5:

[0544] The server stores the received data in a database, where it accumulates this new data along with existing user behavior data.

[0545] Step 6:

[0546] The server analyzes the behavioral data stored in the database. Using machine learning algorithms, the server extracts the user's behavioral patterns. For example, it discovers that the user jogs every morning at 8:00.

[0547] Step 7:

[0548] The server then suggests the next action based on the user's behavioral patterns. In this process, the server predicts the user's best next action based on the analysis results and generates a suggestion, creating specific instructions such as "The next action is jogging."

[0549] Step 8:

[0550] The server sends the proposal to the terminal, which prepares the proposal to be notified to the user at the appropriate time.

[0551] Step 9:

[0552] The user makes a voice request saying, "Tell me what to do next." The user then asks for confirmation of the next action via their smartphone or voice assistant.

[0553] Step 10:

[0554] The terminal detects the user's voice request and forwards the request to the server. The terminal uses voice recognition technology to analyze the user's request and sends a corresponding request to the server.

[0555] Step 11:

[0556] The server responds to the user's request and returns pre-generated action suggestions to the terminal, providing the action suggestions that best fit the user's current situation.

[0557] Step 12:

[0558] The device notifies the user of the proposed activity. The device notifies the user by displaying or announcing the activity, such as "The next activity is jogging."

[0559] This series of steps helps users smoothly manage their schedules and next actions, which are often forgotten in daily life. Each step records the user's actions and suggests the next action based on them, improving the quality of life.

[0560] Example 1

[0561] 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."

[0562] In users' daily lives, there is a need to clarify the next action to be taken and manage it efficiently. However, conventional systems have low accuracy in collecting user behavioral information and suggesting appropriate actions, and lack the ability to respond quickly to the user's voice input. This makes it difficult for users to understand their next action and to receive appropriate support to improve their quality of life.

[0563] 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.

[0564] In this invention, the server includes a means for accumulating user behavior information, a means for analyzing behavioral patterns using a machine learning algorithm and generating a next action, and a means for converting the generated action into a prompt sentence format and transmitting it to the terminal, thereby enabling the user's behavior to be analyzed with high accuracy and the next action to be appropriately suggested.

[0565] "User behavior information" is data on activities and events that a user engages in in their daily life.

[0566] "Means of collection" refers to a mechanism for detecting user behavior information and acquiring that information.

[0567] "Storage means" refers to a mechanism for storing and managing collected behavioral information.

[0568] "Means of analysis and extraction of behavioral patterns" refers to a mechanism that analyzes accumulated behavioral information using machine learning algorithms and the like to discover user behavioral patterns.

[0569] The "means for suggesting the next action" is a mechanism for generating the next action that the user should take based on the extracted behavioral pattern.

[0570] The "means for presenting to the user" is a mechanism for notifying the user's terminal of the proposed action.

[0571] "Means for detecting information from the terminal and transferring it to the server" is a mechanism for transmitting data collected from the terminal to the server.

[0572] "Means for analyzing behavioral patterns using machine learning algorithms" refers to a mechanism for analyzing collected data using machine learning technology and extracting behavioral patterns.

[0573] The "means for generating behavior" is the process for determining the user's next behavior based on the analysis results.

[0574] The "means for converting into a prompt sentence format and sending to the terminal" is a mechanism for converting the proposed action into a format (prompt sentence) that is easy for the user to understand and sending that information to the terminal.

[0575] This invention is a system for supporting users' daily lives, characterized by collecting and analyzing user behavioral information and suggesting the user's next action based on that information. The system operates through interactions between the terminal, server, and user. The specific operation of each component is explained below.

[0576] Data collection

[0577] Terminal

[0578] When a user adds an event to their calendar using their smartphone, the information is captured. For example, if a user enters "2023-09-01 08:00 Jogging," the event is detected by the device.

[0579] Data transmission

[0580] Terminal

[0581] The calendar app detects the input and sends this information to the system's data collection module, which sends the data in JSON format to the server as an HTTP POST request.

[0582] Data accumulation

[0583] server

[0584] The received information is parsed and stored in a database (e.g., PostgreSQL), which contains the user ID, event date and time, and event details.

[0585] Data analysis

[0586] server

[0587] The accumulated data is analyzed using Python's scikit-learn library. User behavior patterns are extracted using machine learning algorithms (e.g., Gaussian Mixture Models). The Pandas library is used for data preprocessing.

[0588] Generate action suggestions

[0589] server

[0590] As a result of the analysis, the next action is suggested. For example, if it is determined that the user jogs at 8 o'clock every morning, the system generates a suggestion such as "Your next action is to jog." This suggestion is converted into a prompt sentence format and saved in the database.

[0591] Presenting the proposal

[0592] Terminal

[0593] When a user requests "Tell me what to do next" by voice, the request is sent to the server. The server notifies the user of the suggestions received. The user is informed via a screen display or voice assistant that "The next action is jogging."

[0594] Specific examples

[0595] For example, if a user adds a meeting to their calendar for 2 p.m., the system behaves as follows:

[0596] User: Opens the calendar app on their smartphone and enters "2023-09-01 14:00 Meeting."

[0597] Device: Detects schedules and sends information to the server.

[0598] Server: Receives the schedule information and stores it in a database.

[0599] Server: Periodically analyzes stored data to learn patterns of users performing work-related tasks around 2 p.m.

[0600] User: At 1:45 PM, voice requests "Tell me what to do next."

[0601] Terminal: Sends a request to the server, receives the suggestion, and notifies the user, displaying "Next action is a meeting."

[0602] Prompt Sentence Examples

[0603] "Suggest next action. Based on the latest behavioral pattern data, the user is available at 1:30 PM."

[0604] In this way, the present invention efficiently manages the user's daily life and prevents the user from being confused about what to do by suggesting appropriate next actions. Each component of the system captures, stores, and analyzes the user's actions and suggests appropriate next actions to improve the user's quality of life.

[0605] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0606] Step 1:

[0607] User

[0608] The user opens the calendar app on their smartphone and enters a new appointment, for example, "2023-09-01 08:00 Jogging." This entry is detected by the device.

[0609] Input: Enter a new event into the calendar app

[0610] Output: Detected event data (date, time, content)

[0611] Step 2:

[0612] Terminal

[0613] The device collects event data from the calendar app and makes an HTTP POST request to send it to the server in JSON format.

[0614] Specific operation: Acquires event data, converts it to JSON format, and sends it to the server.

[0615] Input: Detected event data (date, time, content)

[0616] Output: Event data sent to the server in JSON format

[0617] Step 3:

[0618] server

[0619] The server receives the HTTP request and analyzes the event data sent. After analyzing, it stores the data in a database. The database contains the user ID, event date and time, and event details.

[0620] Specific behavior: Parse the received event data and execute a query to insert it into the database.

[0621] Input: Event data in JSON format

[0622] Output: Event entries stored in the database

[0623] Step 4:

[0624] server

[0625] The accumulated data is periodically analyzed. Python's scikit-learn is used to extract user behavior patterns based on past behavior data. The algorithm used is Gaussian Mixture Models.

[0626] Specific operation: Data preprocessing with Pandas, running machine learning models with scikit-learn, and extracting patterns

[0627] Input: Past behavioral data stored in a database

[0628] Output: Extracted behavioral patterns

[0629] Step 5:

[0630] server

[0631] As a result of the data analysis, the next action is suggested based on the behavioral pattern. For example, a suggested sentence such as "The next action is jogging" is generated. This suggestion is converted into a prompt sentence format and saved in a database.

[0632] Specific behavior: Determine the next action based on the behavior pattern, generate a prompt sentence, and save it.

[0633] Input: Extracted behavioral patterns

[0634] Output: Next action saved as a prompt

[0635] Step 6:

[0636] User

[0637] The user makes a voice request saying, "Tell me what to do next." This request is sent from the device to the server.

[0638] Input: User's voice request

[0639] Output: Request sent to the server

[0640] Step 7:

[0641] Terminal

[0642] The device receives the suggested next action from the server and notifies the user, for example, by notifying the user through a voice assistant that "The next action is jogging."

[0643] Specific behavior: Use an app or voice assistant to receive a response from the server and notify the user.

[0644] Input: Proposal received from the server

[0645] Output: Notification to the user (text or audio)

[0646] (Application example 1)

[0647] 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."

[0648] In modern manufacturing, improving work efficiency within factories requires accurately understanding worker behavior patterns and proposing optimal work at the right time. However, traditional manual work instructions and recording placed a heavy burden on workers and made efficient work management difficult. Furthermore, the lack of an automatic suggestion system based on worker behavior patterns limited the ability to improve work efficiency throughout the factory.

[0649] 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.

[0650] In this invention, the server includes means for collecting user behavior data, means for storing the collected behavior data, and means for analyzing the stored behavior data and extracting behavioral patterns. This allows the server to suggest a next action based on the user's behavior data, send a command to a device that operates an object based on the suggestion, and have the device execute the next action based on the command. This improves work efficiency in factories and reduces the burden on workers.

[0651] The "means for collecting user behavioral data" refers to a means for detecting and recording information about schedules and behaviors entered by a user using a smartphone, tablet device, or the like.

[0652] "Means for storing collected behavioral data" refers to a database or storage for safely storing collected user behavioral data and using it for subsequent analysis.

[0653] "Means for analyzing accumulated behavioral data and extracting behavioral patterns" refers to means for analyzing and extracting users' daily behavioral patterns based on accumulated behavioral data using machine learning algorithms and data mining techniques.

[0654] The "means for proposing the next action based on the extracted behavioral pattern" is a means for generating and proposing an appropriate next action to the user based on the behavioral pattern obtained by analysis.

[0655] The "means for presenting a proposed action to the user" refers to a means for visually or audibly notifying the user of the generated proposal for the next action.

[0656] The "means for sending commands to equipment that operates objects based on the proposed action" refers to a means for sending specific work instructions to robots and other work equipment in the factory based on the content of the proposal.

[0657] The "means by which the equipment that received the command executes the next action" refers to the means by which the robot or work equipment actually performs the specified work based on the received command.

[0658] The system of this invention is a robotic assistant system that improves work efficiency in factories. This system includes a function to collect, store, and analyze user behavior data and suggest the next action. It also sends commands to machines that manipulate objects based on the suggested action, and the machines actually execute the next action, thereby improving work efficiency in factories.

[0659] The specific components of this system and their processing will now be described.

[0660] Programs and their processing

[0661] Data collection

[0662] The user inputs work instructions using a smartphone or tablet device. For example, they input an instruction such as "Assemble part A at 14:00 on 2023-09-01." This information is detected and sent from the device to the server. The device can be a general smartphone (for example, an iPhone or Android device) or tablet. Data is sent using an HTTP request, using the requests library.

[0663] Data accumulation

[0664] The server securely stores the work instruction information received from the terminal in a database. This database stores the user's past work data. Suitable database software is MySQL or PostgreSQL.

[0665] Data analysis

[0666] The server analyzes the accumulated data and runs algorithms to extract behavioral patterns, such as machine learning algorithms (such as scikit-learn) and data mining techniques, making it possible to predict when and what tasks a user will perform.

[0667] Generate action suggestions

[0668] Based on the results of the data analysis, the server will suggest the user's next action, which will indicate what the user should do next, generating specific instructions such as "The next action is to assemble part B."

[0669] Submitting proposals and issuing directives

[0670] The suggestions are sent to the device and the user is notified visually and audibly. At the same time, specific work instructions based on the suggested actions are sent to robots and other work equipment in the factory. When the command is sent to the robot, it executes the suggested action. The equipment is typically a typical factory robot (e.g., an industrial robot arm) and is often controlled through an API.

[0671] Specific examples

[0672] For example, one day, a user enters "2023-09-01 14:00 Assemble part A" into their smartphone calendar. The system captures this information and sends it to the server. The server stores the information in a database, analyzes it, and learns a pattern of performing work-related tasks around 2:00 PM. If the user makes a voice request at 1:45 PM saying, "Tell me what to do next," the device notifies the user of the server's suggestion, displaying, "The next action is to assemble part B." At the same time, the server instructs the robot to "assemble part B," and the robot executes the suggested action.

[0673] Prompt Sentence Examples

[0674] User: Enters "2023-10-01 09:00 Assemble part A" on the smartphone.

[0675] System: This information is sent to the server and stored in a database.

[0676] Server: Suggests the next action (e.g., assemble part B) based on past data.

[0677] User: At 9 AM, voice requests "Tell me what to do next."

[0678] System: Display "Your next action is to assemble part B."

[0679] As described above, the present invention aims to improve work efficiency in factories and reduce the burden on workers by analyzing user behavior and proposing the next action.

[0680] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0681] Step 1:

[0682] Users input work instructions using smartphones or tablet devices.

[0683] Specifically, the user opens a calendar app and enters instructions such as "Assemble part A at 2023-09-01 14:00." This data becomes the input data.

[0684] Step 2:

[0685] The terminal detects the input work instruction information and transmits it to the server.

[0686] The application on the terminal sends the input data to the server using an HTTP request, and the server receives the information. The output is the work instruction data sent to the server.

[0687] Step 3:

[0688] The server stores the received work instruction information in a database.

[0689] Specifically, the server uses a MySQL or PostgreSQL database to record the data it receives (for example, the date, time, and content of a work order), which then becomes the input data for subsequent analysis.

[0690] Step 4:

[0691] The server analyzes various work data stored in the database and extracts behavioral patterns.

[0692] For example, the server uses a machine learning library such as scikit-learn to analyze the accumulated data and learn the user's behavioral patterns. This analysis extracts the tendency for users to perform specific tasks at specific times. The output is the user's behavioral patterns.

[0693] Step 5:

[0694] The server suggests the next action based on the extracted behavioral pattern.

[0695] Based on machine learning algorithms, it predicts the next task the user should perform and generates a suggestion, such as "Your next action is to assemble part B."

[0696] Step 6:

[0697] The proposed action is transmitted to the terminal and notified to the user visually or audibly.

[0698] The server sends the generated suggestions to the device, which then displays the information on the user's smartphone or tablet. The input is the suggestion data from the server, and the output is displayed as a notification on the device.

[0699] Step 7:

[0700] Based on the proposal, the server sends specific work instructions to the robots in the factory.

[0701] Based on the proposed actions, the server issues work instructions to the robot using an API. The input is the work instructions from the server, and the output is a command to the robot.

[0702] Step 8:

[0703] Upon receiving the command, the robot performs the next action according to the command.

[0704] For example, a robot starts assembling part B. The input is the received work instruction, and the output is the actual work action.

[0705] This allows the entire system to work together to manage the user's actions and effectively suggest and execute the next action.

[0706] 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.

[0707] This invention is a system for supporting users in their daily lives. Specifically, it is a system that records the user's behavioral data and suggests the next action based on the record. In particular, it is characterized by combining an emotion engine that recognizes the user's emotions and suggests actions according to the user's emotions.

[0708] The system operates through interactions between the terminal, server, emotion engine, and user. The specific operation of each component is explained below.

[0709] Data collection and storage

[0710] Terminal

[0711] When a user adds an event to their calendar using their smartphone, the information is captured. For example, if a user enters "Jogging at 08:00 on 2023-09-01," the event is detected by the device.

[0712] server

[0713] The device sends the detected information to a server, which stores it in a database, including the specific date and time and details of the event.

[0714] Data analysis

[0715] server

[0716] The server runs algorithms to analyze the accumulated data. Here, machine learning algorithms are used to extract user behavioral patterns. For example, a user may learn that they jog every morning at 8:00.

[0717] Generate action suggestions

[0718] server

[0719] Based on the results of the data analysis, the server will suggest the user's next action. This suggestion is generated based on the user's past behavioral patterns, and will create specific instructions such as "The next action is to go jogging."

[0720] Emotion Recognition and Regulation

[0721] Emotion Engine

[0722] The emotion engine recognizes emotions by analyzing the user's facial expressions and vocal tone, and this information is used to tailor the next suggested action. For example, if the user is feeling stressed, it will suggest actions to help them relax.

[0723] Presenting the proposal

[0724] Terminal

[0725] The suggested actions are sent to the device and displayed on the user's smartphone or other device. When the user makes a voice request such as "Tell me what to do next," the device immediately notifies the user of the suggestions received from the server.

[0726] Specific examples

[0727] For example, if a user adds a meeting to their calendar for 2 p.m., the system behaves as follows:

[0728] User: Opens the calendar app on their smartphone and enters "2023-09-01 14:00 Meeting."

[0729] Device: Detects schedules and sends information to the server.

[0730] Server: Receives the schedule information and stores it in a database.

[0731] Server: Periodically analyzes stored data to learn patterns of users performing work-related tasks around 2 p.m.

[0732] User: At 1:45 PM, voice requests "Tell me what to do next."

[0733] Terminal: Sends a request to the server, receives the suggestion, and notifies the user, displaying "Next action is a meeting."

[0734] Emotion engine: If a user is feeling stressed during a meeting, the system will provide additional advice such as "take a deep breath to relax a bit."

[0735] This series of steps helps users smoothly manage their schedules and next actions, which are often forgotten in daily life. The addition of an emotion engine enables more detailed action suggestions based on the user's emotional state, further improving quality of life. Each step enriches the user's life by recording the user's actions and suggesting the next action based on them.

[0736] The processing flow will be explained below.

[0737] Step 1:

[0738] A user adds an event to a calendar app. The user uses their smartphone to enter specific event information (e.g., "2023-09-01 08:00 Jogging").

[0739] Step 2:

[0740] The device detects the events entered by the user. The device detects that the calendar app has been updated and captures the event information as new event data.

[0741] Step 3:

[0742] The device sends the captured schedule information to the server, and the device uploads the detected behavior data to the server via the Internet.

[0743] Step 4:

[0744] The server receives the schedule information sent from the device. The received data includes the date, time, and event details.

[0745] Step 5:

[0746] The server stores the received data in a database, where it accumulates this new data along with existing user behavior data.

[0747] Step 6:

[0748] The server analyzes the behavioral data stored in the database. Using machine learning algorithms, the server extracts the user's behavioral patterns. For example, it discovers that the user jogs every morning at 8:00.

[0749] Step 7:

[0750] The server then suggests the next action based on the user's behavioral patterns. In this process, the server predicts the user's best next action based on the analysis results and generates a suggestion, creating specific instructions such as "The next action is jogging."

[0751] Step 8:

[0752] The emotion engine recognizes the user's emotions. The emotion engine analyzes the user's facial expressions and vocal tone to determine their current emotional state. For example, if the user is feeling stressed, that information will be reflected.

[0753] Step 9:

[0754] The server adjusts the suggestions based on the information obtained from the emotion engine. For example, if it determines that the user is feeling stressed, it adds a relaxing activity ("take a deep breath") to the next action suggestions.

[0755] Step 10:

[0756] The server sends the final proposal to the device, which prepares it for notification to the user at the appropriate time.

[0757] Step 11:

[0758] The user makes a voice request saying, "Tell me what to do next." The user then asks for confirmation of the next action via their smartphone or voice assistant.

[0759] Step 12:

[0760] The terminal detects the user's voice request and forwards the request to the server. The terminal uses voice recognition technology to analyze the user's request and sends a corresponding request to the server.

[0761] Step 13:

[0762] The server responds to the user's request and returns pre-generated action suggestions to the terminal, providing the action suggestions that best fit the user's current situation.

[0763] Step 14:

[0764] The device notifies the user of the suggested action. The device uses a display or voice notification to let the user know, "The next action is jogging." If the user is feeling stressed, the device also provides additional advice for relaxation ("take a deep breath").

[0765] This series of steps helps users smoothly manage their schedules and next actions, which are often forgotten in daily life. The addition of an emotion engine makes it possible to provide detailed action suggestions based on the user's emotional state, further improving quality of life.

[0766] Example 2

[0767] 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."

[0768] Conventional behavior suggestion systems can make suggestions based on the user's behavioral data, but they cannot make suggestions that take into account the user's emotional state. As a result, they cannot make optimal suggestions when the user is stressed or in a specific emotional state, making it difficult to improve user satisfaction. In addition, interactive suggestions based on voice input have not been sufficiently implemented.

[0769] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting user behavioral data, means for storing the collected behavioral data, means for analyzing the stored behavioral data and extracting behavioral patterns, means for proposing a next action based on the extracted behavioral pattern, means for presenting the proposed action to the user, and means for recognizing the user's emotions and adjusting the next action proposal. This enables more personalized action proposals taking into account the user's emotional state, thereby significantly improving user satisfaction.

[0770] "User behavioral data" refers to information about various activities that a user performs in their daily life, including, for example, calendar entries, tasks, and daily habits.

[0771] "Means of collection" refers to hardware and software used to obtain behavioral data from users, such as smartphone calendar apps and sensors.

[0772] "Storage means" refers to a database or storage system for storing collected data.

[0773] "Means of analysis and extraction of behavioral patterns" refers to algorithms and software, such as machine learning algorithms, that can be used to find useful information and trends from accumulated data.

[0774] "Suggestion methods" refers to algorithms or software that recommend the next action to the user based on the extracted behavioral patterns.

[0775] "Presentation means" refers to the interface or device used to notify the user of the suggested action, such as a smartphone notification feature or voice assistant.

[0776] "Means for recognizing emotions and adjusting next action suggestions" refers to software or hardware, such as facial recognition technology or voice analysis technology, that analyzes the user's emotions and changes next action suggestions in response to those emotions.

[0777] "Responding to voice input" refers to a system that executes corresponding functions in response to a user's voice input of instructions or questions.

[0778] "Visual information" refers to image data and video data such as a user's facial expressions and gestures.

[0779] This invention is a system for supporting users' daily lives, specifically a system that records user behavioral data and suggests next actions based on that data. Furthermore, it is characterized by combining an emotion engine that recognizes the user's emotions and suggests actions based on the user's emotions. The system operates through the user's terminal, a server, the emotion engine, and the interactions between them.

[0780] Data collection and storage

[0781] Terminal

[0782] The device mainly refers to devices such as smartphones and tablets. When a user adds an event to a calendar app using such a device, the information is automatically captured. For example, if a user enters "Jogging at 08:00 on 2023-09-01" in the calendar, this information is detected by the device.

[0783] server

[0784] The collected data is sent from the device to a server, which stores the received information in a database and manages data for each user, including specific dates, times, and details of events.

[0785] Data analysis

[0786] server

[0787] The server runs an algorithm to analyze the stored data. For example, a machine learning algorithm is used to extract the user's behavioral patterns. This analysis may reveal that the user has a habit of performing a certain activity at a specific time each day (for example, jogging at 8:00 AM every morning).

[0788] Generate action suggestions

[0789] server

[0790] Based on the analysis results, the server will suggest the next action, for example, generating specific instructions such as "Next action is jogging." This suggestion is based on the user's past behavioral patterns.

[0791] Emotion recognition and behavioral suggestion adjustment

[0792] Emotion Engine

[0793] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and voice to recognize their emotions. The results of this recognition are sent to the server and used to adjust the next action suggestion. For example, if the user is feeling stressed, the engine will suggest actions to help them relax.

[0794] Presenting the proposal

[0795] Terminal

[0796] The suggestions are sent to the device and displayed on the user's smartphone or other device. When the user makes a voice request, "Tell me what to do next," the device immediately displays the suggestions received from the server.

[0797] Specific examples

[0798] For example, if a user adds a meeting to their calendar for 2:00 PM, the sequence of actions is as follows:

[0799] User: Opens the calendar app on their smartphone and enters "2023-09-01 14:00 Meeting."

[0800] Device: Detects schedules and sends information to the server.

[0801] Server: Receives the schedule information and saves it in the database. "2023-09-01 14:00 Meeting" is recorded as data for each user.

[0802] Server: Periodically analyzes stored data to learn patterns of users performing work-related tasks around 2 p.m.

[0803] User: At 1:45 PM, voice requests "Tell me what to do next."

[0804] Terminal: Sends a request to the server, receives the suggestion, and notifies the user, displaying "Next action is a meeting."

[0805] Emotion engine: If a user is feeling stressed during a meeting, the system will provide additional advice such as "Take a deep breath to relax a bit." This analysis is performed by the emotion engine, which analyzes the user's facial expressions and voice.

[0806] Prompt Sentence Examples

[0807] Below is an example of a prompt sentence to input to the generative AI model.

[0808] Please explain the steps involved in the system that suggests actions based on the user's emotions.

[0809] 1. The user enters an event into the calendar app on their smartphone.

[0810] 2. The device detects this appointment and sends it to the server.

[0811] 3. The server saves the appointment information in a database.

[0812] 4. The server analyzes the stored data and learns user behavior patterns.

[0813] 5. The server suggests the next action.

[0814] 6. The emotion engine recognizes the user's emotions and adjusts suggested actions if necessary.

[0815] 7. The device notifies the user of the suggested action.

[0816] An example would be "When a user schedules a meeting for 2 PM."

[0817] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0818] Step 1:

[0819] User

[0820] The user opens the calendar app on their smartphone and enters an appointment. For example, they enter "2023-09-01 14:00 Meeting." This entry becomes the basic data for future processing.

[0821] Input: Events entered in the calendar (text format)

[0822] Output: Capture of schedule information (text format)

[0823] What happens: A user manually enters an event into a calendar app. This information is stored on the device as text data.

[0824] Step 2:

[0825] Terminal

[0826] The device captures the schedule information entered by the user and automatically sends it to the server, where the date, time, and event details are obtained.

[0827] Input: Schedule information entered by the user (text format)

[0828] Output: Schedule information sent to the server (text format)

[0829] Specific operation: The device detects the entered schedule information in real time and sends that information to the server's API endpoint.

[0830] Step 3:

[0831] server

[0832] The server stores the schedule information received from the device in a database, which is linked to the user ID and date and time information.

[0833] Input: Schedule information sent from the device (text format)

[0834] Output: Schedule information stored in the database (database records)

[0835] Specific operation: When the server receives the event information, it creates a new record in the database and saves it. The saved information includes the user ID, date and time, and event details.

[0836] Step 4:

[0837] server

[0838] The server runs machine learning algorithms to analyze the stored schedule information, thereby extracting user behavior patterns.

[0839] Input: User behavior data stored in a database (database records)

[0840] Output: Extracted behavioral patterns (model data)

[0841] How it works: The server periodically reads the behavioral data in the database and uses machine learning algorithms to analyze and extract behavioral patterns, such as repeating behavior during specific times of the day.

[0842] Step 5:

[0843] server

[0844] Based on the results of the data analysis, an algorithm is run to suggest next steps, which are generated based on past behavioral patterns.

[0845] Input: Behavioral pattern (model data)

[0846] Output: Next action suggestions (text format)

[0847] Specific operation: Based on the extracted behavioral patterns, the server uses an algorithm to determine the next action the user should take and generates a suggested text data. For example, a suggestion such as "The next action is jogging" is created.

[0848] Step 6:

[0849] Emotion Engine

[0850] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and voice to recognize their emotions, and adjusts the next action suggestions accordingly.

[0851] Input: User's facial expressions and voice data (multimedia format)

[0852] Output: Recognized emotion data (text and numeric format)

[0853] Specific operation: The emotion engine analyzes the user's facial expressions captured by the camera and the voice data collected by the microphone, and extracts the user's emotional state as text and numerical data, which is sent to the server to adjust the next action suggestion.

[0854] Step 7:

[0855] server

[0856] The server adjusts the suggested actions based on the emotion data sent from the emotion engine. If the user is feeling stressed, the server will suggest additional actions to help them relax.

[0857] Input: Emotion data (text and numerical format), next action suggestions (text format)

[0858] Output: Adjusted action proposals (text format)

[0859] Specific actions: The server analyzes the emotion data and modifies the original action suggestions as needed, for example, to include specific advice such as "take a deep breath to relax a bit" if the user is feeling stressed.

[0860] Step 8:

[0861] Terminal

[0862] The adjusted action suggestions are sent to the device and notified to the user. The suggestions are also displayed when the user makes a voice request such as "Tell me what to do next."

[0863] Input: Adjusted action proposal (text format)

[0864] Output: Action suggestions displayed to the user (in text format)

[0865] Specific operation: The device receives the adjusted action suggestions from the server and presents them to the user via notifications or voice assistants. The user can then confirm the suggested action and smoothly carry out the next action.

[0866] The above is a description of the specific processing steps of this system and their detailed operation.

[0867] (Application example 2)

[0868] 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."

[0869] Conventional food delivery services only provide users with meal options, but do not offer personalized suggestions based on their emotional state or behavioral patterns. As a result, users find it difficult to select the meal that best suits their current emotional state and situation, and are unable to receive appropriate suggestions for health management or stress relief. This leaves users with insufficient support for improving their quality of life and enjoying a comfortable daily life.

[0870] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0871] In this invention, the server includes means for collecting user behavioral data, emotion engine means for analyzing the emotional state, and means for adjusting the next action based on the emotional state, thereby optimizing the next action based on the user's emotional state and behavioral patterns, and making it possible to suggest meals that have a relaxing effect or that suit the user's preferences as needed.

[0872] "Behavioral data" is information relating to the user's daily activities, tasks, schedules, and the like.

[0873] An "emotion engine" is a software or hardware mechanism for analyzing a user's emotional state.

[0874] "Next Action" refers to the next action or task that the user should perform.

[0875] A "behavioral pattern" is a tendency or regularity of behavior extracted from a user's past behavioral data.

[0876] The "adjustment means" is a means for optimizing the next action suggestion based on the emotional state analyzed by the emotion engine.

[0877] A "suggested action" is an instruction for next action that the system presents to the user based on the analyzed behavioral data and emotional state.

[0878] "Visual information" refers to information that is visually recognized, such as the user's facial expressions and actions.

[0879] "Emotional information" is data relating to the user's emotional state, and is information obtained from voice tone, facial expressions, and the like.

[0880] "Means of collection" refers to devices and software for capturing user behavioral data and emotional information.

[0881] The "means for presenting suggestions" is a means for displaying or notifying the user of suggestions for the next action or meal.

[0882] This invention is directed to a smartphone application for food delivery services. The system collects and analyzes user behavioral and emotional data to suggest optimal meals to users.

[0883] System configuration

[0884] Hardware and Software

[0885] The system uses the following hardware and software:

[0886] Smartphone: Used to provide the user interface and collect data.

[0887] Emotion Engine: Software that analyzes the user's emotional state. In this case, we use the TextBlob library.

[0888] Server: A server for storing and analyzing user behavioral and emotional data.

[0889] Food Delivery API: An external API that processes food orders.

[0890] Data collection and storage

[0891] Smartphone: The user uses a calendar app to enter activity data (e.g., a jogging schedule), and this information is sent from the smartphone to the server.

[0892] Server: The server receives the data and stores it in a database, including the date and time of the activity and detailed information.

[0893] Emotion engine: Collects and analyzes emotional data from user text and voice input.

[0894] Data analysis

[0895] Server: Runs algorithms to analyze the accumulated behavioral and emotional data. Machine learning algorithms are used here to extract user behavior patterns.

[0896] Emotion Engine: Uses the TextBlob library to parse the user's input text (emotion data) and generate an emotion score.

[0897] Generating behavioral and dietary suggestions

[0898] Server: Based on the analysis results, the server will suggest the next action and the best meal. For example, if the user is feeling stressed, it will suggest a meal that will have a relaxing effect.

[0899] Smartphone: Suggested activities and meals are presented to the user via their smartphone. When the user requests the next action by voice, the server immediately notifies them of the suggestion.

[0900] Specific examples

[0901] For example, if a user enters "2023-09-01 14:00 meeting" into a calendar app, the system will behave as follows:

[0902] Original invention in action:

[0903] User: Opens the calendar app on their smartphone and enters "2023-09-01 14:00 Meeting."

[0904] Device: Detects schedules and sends information to the server.

[0905] Server: Receives the schedule information and stores it in a database.

[0906] Server: Periodically analyzes stored data to learn patterns of users performing work-related tasks around 2 p.m.

[0907] User: At 1:45 PM, voice requests "Tell me what to do next."

[0908] Terminal: Sends a request to the server, receives the suggestion, and notifies the user, displaying "Next action is a meeting."

[0909] Emotion engine: If a user is feeling stressed during a meeting, the system will provide additional advice such as "take a deep breath to relax a bit."

[0910] Examples of application improvements:

[0911] User: A user who feels stressed types "I'm feeling stressed right now" into a smartphone app.

[0912] Emotion engine: The analyze_emotion function generates a negative emotion score from "stress."

[0913] Suggestion: The app suggests to the user, "Why not order a hot soup to help you relax?"

[0914] Ordering: If the user accepts the suggestion, the app will automatically place the soup order.

[0915] Example prompt sentence:

[0916] "If a user types 'I am feeling stressed,' generate a negative emotion score and suggest foods that will help them relax."

[0917] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0918] Step 1:

[0919] User behavioral data entry

[0920] A user uses a calendar application on their smartphone to enter action data such as "2023-09-01 14:00 Meeting."

[0921] Input: Behavioral data entered by the user into their smartphone (date, time, and content)

[0922] Output: Behavioral data is stored in an application on the smartphone.

[0923] Step 2:

[0924] Transmission of behavioral data by the device

[0925] The device transmits the detected behavioral data to the server, where the behavioral data is converted into an appropriate format and sent to the server via the network.

[0926] Input: Behavioral data stored on the smartphone

[0927] Output: Behavioral data is sent to and received by the server.

[0928] Step 3:

[0929] Data storage by server

[0930] The server stores the received behavioral data in a database, which stores the date, time, and event details.

[0931] Input: Behavioral data sent to the server

[0932] Output: The behavioral data is stored in a database on the server.

[0933] Step 4:

[0934] Emotional data collection and analysis using an emotion engine

[0935] When a user types "I'm feeling stressed right now" into their smartphone, the emotion engine analyzes the input and generates an emotion score. In this example, the TextBlob library is used.

[0936] Input: Emotion data entered by the user (e.g., feeling stressed)

[0937] Output: A sentiment score (e.g., a negative sentiment score) is generated.

[0938] Step 5:

[0939] Server analysis of behavioral patterns

[0940] The server analyzes the accumulated behavioral and emotional data and uses machine learning algorithms to extract behavioral patterns.

[0941] Input: Behavioral data and emotion scores stored in a database

[0942] Output: Analysis of user behavior patterns

[0943] Step 6:

[0944] Server-generated next action and meal suggestions

[0945] The server then suggests the next action or meal based on the analysis results. For example, it suggests a meal with a relaxing effect (e.g., soup) based on the emotion score.

[0946] Input: Behavioral pattern analysis results and sentiment score

[0947] Output: Suggested behavior and dietary recommendations

[0948] Step 7:

[0949] Proposal presentation by device

[0950] The device displays and notifies the user of the suggestions received from the server. If the user requests the next action by voice, the suggestions are displayed immediately.

[0951] Input: Proposal sent from the server

[0952] Output: Display and notification of suggestions on smartphone

[0953] Step 8:

[0954] User review and order

[0955] If the user accepts the suggested meal, the device sends the order to the food delivery API. If the order is successful, a confirmation message is displayed to the user.

[0956] Input: The result of the user reviewing the suggestion (e.g., ordering a meal)

[0957] Output: Places an order to the food delivery API and displays a confirmation message

[0958] Example of using a generative AI model and prompt:

[0959] "If a user types 'I am feeling stressed,' generate a negative emotion score and suggest foods that will help them relax."

[0960] 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.

[0961] 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.

[0962] 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.

[0963] [Third embodiment]

[0964] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0965] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0966] 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).

[0967] 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.

[0968] 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.

[0969] 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).

[0970] 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.

[0971] 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.

[0972] 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.

[0973] 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.

[0974] 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.

[0975] 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."

[0976] This invention is a system for supporting the daily life of a user, specifically, a system that records the user's behavior and suggests the next action based on the record. This system includes a series of processes that collect, accumulate, and analyze the user's behavior data, suggest the next action based on the extracted behavioral patterns, and notify the user of the suggestion.

[0977] The system operates through interactions between the terminal, the server, and the user. The specific operation of each component is explained below.

[0978] Data collection

[0979] Terminal

[0980] When a user adds an event to their calendar using their smartphone, the information is captured. For example, if a user types "Jogging at 08:00 on 2023-09-01," the event is detected by the device.

[0981] server

[0982] The device sends the detected information to a server, which stores it in a database, including the specific date and time and details of the event.

[0983] Data accumulation

[0984] server

[0985] The server securely stores the behavioral data sent from the device in a database, which systematically stores the user's past behavioral data and is used in subsequent analysis processes.

[0986] Data analysis

[0987] server

[0988] The server runs algorithms to analyze the stored data, using machine learning and data mining techniques to extract user behavioral patterns, such as jogging every morning at 8am.

[0989] Generate action suggestions

[0990] server

[0991] Based on the results of the data analysis, the server will suggest the user's next action. This suggestion is generated based on the user's past behavioral patterns. For example, if a user requests "Tell me what to do next," a specific suggestion such as "The next action is jogging" will be generated.

[0992] Presenting the proposal

[0993] Terminal

[0994] The proposed actions are sent to the device and displayed on the user's smartphone or other device. When the user verbally asks the device, "Tell me what to do next," the device immediately notifies the user of the suggestions received from the server.

[0995] Specific examples

[0996] For example, if a user adds a meeting to their calendar for 2 p.m., the system behaves as follows:

[0997] User: Opens the calendar app on their smartphone and enters "2023-09-01 14:00 Meeting."

[0998] Device: Detects schedules and sends information to the server.

[0999] Server: Receives the schedule information and stores it in a database.

[1000] Server: Periodically analyzes stored data to learn patterns of users performing work-related tasks around 2 p.m.

[1001] User: At 1:45 PM, voice requests "Tell me what to do next."

[1002] Terminal: Sends a request to the server, receives the suggestion, and notifies the user, displaying "Next action is a meeting."

[1003] In this way, the present invention can efficiently manage the user's daily life and prevent them from forgetting to take photos or getting lost. Each component of the system captures, stores, and analyzes the user's actions, and appropriately suggests the next action to take, improving the user's quality of life.

[1004] The processing flow will be explained below.

[1005] Step 1:

[1006] A user adds an event to a calendar app. The user uses their smartphone to enter specific event information (e.g., "2023-09-01 08:00 Jogging").

[1007] Step 2:

[1008] The device detects the events entered by the user. The device detects that the calendar app has been updated and captures the event information as new event data.

[1009] Step 3:

[1010] The device sends the captured schedule information to the server, and the device uploads the detected behavior data to the server via the Internet.

[1011] Step 4:

[1012] The server receives the schedule information sent from the device. The received data includes the date, time, and event details.

[1013] Step 5:

[1014] The server stores the received data in a database, where it accumulates this new data along with existing user behavior data.

[1015] Step 6:

[1016] The server analyzes the behavioral data stored in the database. Using machine learning algorithms, the server extracts the user's behavioral patterns. For example, it discovers that the user jogs every morning at 8:00.

[1017] Step 7:

[1018] The server then suggests the next action based on the user's behavioral patterns. In this process, the server predicts the user's best next action based on the analysis results and generates a suggestion, creating specific instructions such as "The next action is jogging."

[1019] Step 8:

[1020] The server sends the proposal to the terminal, which prepares the proposal to be notified to the user at the appropriate time.

[1021] Step 9:

[1022] The user makes a voice request saying, "Tell me what to do next." The user then asks for confirmation of the next action via their smartphone or voice assistant.

[1023] Step 10:

[1024] The terminal detects the user's voice request and forwards the request to the server. The terminal uses voice recognition technology to analyze the user's request and sends a corresponding request to the server.

[1025] Step 11:

[1026] The server responds to the user's request and returns pre-generated action suggestions to the terminal, providing the action suggestions that best fit the user's current situation.

[1027] Step 12:

[1028] The device notifies the user of the proposed activity. The device notifies the user by displaying or announcing the activity, such as "The next activity is jogging."

[1029] This series of steps helps users smoothly manage their schedules and next actions, which are often forgotten in daily life. Each step records the user's actions and suggests the next action based on them, improving the quality of life.

[1030] Example 1

[1031] 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."

[1032] In users' daily lives, there is a need to clarify the next action to be taken and manage it efficiently. However, conventional systems have low accuracy in collecting user behavioral information and suggesting appropriate actions, and lack the ability to respond quickly to the user's voice input. This makes it difficult for users to understand their next action and to receive appropriate support to improve their quality of life.

[1033] 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.

[1034] In this invention, the server includes a means for accumulating user behavior information, a means for analyzing behavioral patterns using a machine learning algorithm and generating a next action, and a means for converting the generated action into a prompt sentence format and transmitting it to the terminal, thereby enabling the user's behavior to be analyzed with high accuracy and the next action to be appropriately suggested.

[1035] "User behavior information" is data on activities and events that a user engages in in their daily life.

[1036] "Means of collection" refers to a mechanism for detecting user behavior information and acquiring that information.

[1037] "Storage means" refers to a mechanism for storing and managing collected behavioral information.

[1038] "Means of analysis and extraction of behavioral patterns" refers to a mechanism that analyzes accumulated behavioral information using machine learning algorithms and the like to discover user behavioral patterns.

[1039] The "means for suggesting the next action" is a mechanism for generating the next action that the user should take based on the extracted behavioral pattern.

[1040] The "means for presenting to the user" is a mechanism for notifying the user's terminal of the proposed action.

[1041] "Means for detecting information from the terminal and transferring it to the server" is a mechanism for transmitting data collected from the terminal to the server.

[1042] "Means for analyzing behavioral patterns using machine learning algorithms" refers to a mechanism for analyzing collected data using machine learning technology and extracting behavioral patterns.

[1043] The "means for generating behavior" is the process for determining the user's next behavior based on the analysis results.

[1044] The "means for converting into a prompt sentence format and sending to the terminal" is a mechanism for converting the proposed action into a format (prompt sentence) that is easy for the user to understand and sending that information to the terminal.

[1045] This invention is a system for supporting users' daily lives, characterized by collecting and analyzing user behavioral information and suggesting the user's next action based on that information. The system operates through interactions between the terminal, server, and user. The specific operation of each component is explained below.

[1046] Data collection

[1047] Terminal

[1048] When a user adds an event to their calendar using their smartphone, the information is captured. For example, if a user enters "2023-09-01 08:00 Jogging," the event is detected by the device.

[1049] Data transmission

[1050] Terminal

[1051] The calendar app detects the input and sends this information to the system's data collection module, which sends the data in JSON format to the server as an HTTP POST request.

[1052] Data accumulation

[1053] server

[1054] The received information is parsed and stored in a database (e.g., PostgreSQL), which contains the user ID, event date and time, and event details.

[1055] Data analysis

[1056] server

[1057] The accumulated data is analyzed using Python's scikit-learn library. User behavior patterns are extracted using machine learning algorithms (e.g., Gaussian Mixture Models). The Pandas library is used for data preprocessing.

[1058] Generate action suggestions

[1059] server

[1060] As a result of the analysis, the next action is suggested. For example, if it is determined that the user jogs at 8 o'clock every morning, the system generates a suggestion such as "Your next action is to jog." This suggestion is converted into a prompt sentence format and saved in the database.

[1061] Presenting the proposal

[1062] Terminal

[1063] When a user requests "Tell me what to do next" by voice, the request is sent to the server. The server notifies the user of the suggestions received. The user is informed via a screen display or voice assistant that "The next action is jogging."

[1064] Specific examples

[1065] For example, if a user adds a meeting to their calendar for 2 p.m., the system behaves as follows:

[1066] User: Opens the calendar app on their smartphone and enters "2023-09-01 14:00 Meeting."

[1067] Device: Detects schedules and sends information to the server.

[1068] Server: Receives the schedule information and stores it in a database.

[1069] Server: Periodically analyzes stored data to learn patterns of users performing work-related tasks around 2 p.m.

[1070] User: At 1:45 PM, voice requests "Tell me what to do next."

[1071] Terminal: Sends a request to the server, receives the suggestion, and notifies the user, displaying "Next action is a meeting."

[1072] Prompt Sentence Examples

[1073] "Suggest next action. Based on the latest behavioral pattern data, the user is available at 1:30 PM."

[1074] In this way, the present invention efficiently manages the user's daily life and prevents the user from being confused about what to do by suggesting appropriate next actions. Each component of the system captures, stores, and analyzes the user's actions and suggests appropriate next actions to improve the user's quality of life.

[1075] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1076] Step 1:

[1077] User

[1078] The user opens the calendar app on their smartphone and enters a new appointment, for example, "2023-09-01 08:00 Jogging." This entry is detected by the device.

[1079] Input: Enter a new event into the calendar app

[1080] Output: Detected event data (date, time, content)

[1081] Step 2:

[1082] Terminal

[1083] The device collects event data from the calendar app and makes an HTTP POST request to send it to the server in JSON format.

[1084] Specific operation: Acquires event data, converts it to JSON format, and sends it to the server.

[1085] Input: Detected event data (date, time, content)

[1086] Output: Event data sent to the server in JSON format

[1087] Step 3:

[1088] server

[1089] The server receives the HTTP request and analyzes the event data sent. After analyzing, it stores the data in a database. The database contains the user ID, event date and time, and event details.

[1090] Specific behavior: Parse the received event data and execute a query to insert it into the database.

[1091] Input: Event data in JSON format

[1092] Output: Event entries stored in the database

[1093] Step 4:

[1094] server

[1095] The accumulated data is periodically analyzed. Python's scikit-learn is used to extract user behavior patterns based on past behavior data. The algorithm used is Gaussian Mixture Models.

[1096] Specific operation: Data preprocessing with Pandas, running machine learning models with scikit-learn, and extracting patterns

[1097] Input: Past behavioral data stored in a database

[1098] Output: Extracted behavioral patterns

[1099] Step 5:

[1100] server

[1101] As a result of the data analysis, the next action is suggested based on the behavioral pattern. For example, a suggested sentence such as "The next action is jogging" is generated. This suggestion is converted into a prompt sentence format and saved in a database.

[1102] Specific behavior: Determine the next action based on the behavior pattern, generate a prompt sentence, and save it.

[1103] Input: Extracted behavioral patterns

[1104] Output: Next action saved as a prompt

[1105] Step 6:

[1106] User

[1107] The user makes a voice request saying, "Tell me what to do next." This request is sent from the device to the server.

[1108] Input: User's voice request

[1109] Output: Request sent to the server

[1110] Step 7:

[1111] Terminal

[1112] The device receives the suggested next action from the server and notifies the user, for example, by notifying the user through a voice assistant that "The next action is jogging."

[1113] Specific behavior: Use an app or voice assistant to receive a response from the server and notify the user.

[1114] Input: Proposal received from the server

[1115] Output: Notification to the user (text or audio)

[1116] (Application example 1)

[1117] 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."

[1118] In modern manufacturing, improving work efficiency within factories requires accurately understanding worker behavior patterns and proposing optimal work at the right time. However, traditional manual work instructions and recording placed a heavy burden on workers and made efficient work management difficult. Furthermore, the lack of an automatic suggestion system based on worker behavior patterns limited the ability to improve work efficiency throughout the factory.

[1119] 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.

[1120] In this invention, the server includes means for collecting user behavior data, means for storing the collected behavior data, and means for analyzing the stored behavior data and extracting behavioral patterns. This allows the server to suggest a next action based on the user's behavior data, send a command to a device that operates an object based on the suggestion, and have the device execute the next action based on the command. This improves work efficiency in factories and reduces the burden on workers.

[1121] The "means for collecting user behavioral data" refers to a means for detecting and recording information about schedules and behaviors entered by a user using a smartphone, tablet device, or the like.

[1122] "Means for storing collected behavioral data" refers to a database or storage for safely storing collected user behavioral data and using it for subsequent analysis.

[1123] "Means for analyzing accumulated behavioral data and extracting behavioral patterns" refers to means for analyzing and extracting users' daily behavioral patterns based on accumulated behavioral data using machine learning algorithms and data mining techniques.

[1124] The "means for proposing the next action based on the extracted behavioral pattern" is a means for generating and proposing an appropriate next action to the user based on the behavioral pattern obtained by analysis.

[1125] The "means for presenting a proposed action to the user" refers to a means for visually or audibly notifying the user of the generated proposal for the next action.

[1126] The "means for sending commands to equipment that operates objects based on the proposed action" refers to a means for sending specific work instructions to robots and other work equipment in the factory based on the content of the proposal.

[1127] The "means by which the equipment that received the command executes the next action" refers to the means by which the robot or work equipment actually performs the specified work based on the received command.

[1128] The system of this invention is a robotic assistant system that improves work efficiency in factories. This system includes a function to collect, store, and analyze user behavior data and suggest the next action. It also sends commands to machines that manipulate objects based on the suggested action, and the machines actually execute the next action, thereby improving work efficiency in factories.

[1129] The specific components of this system and their processing will now be described.

[1130] Programs and their processing

[1131] Data collection

[1132] The user inputs work instructions using a smartphone or tablet device. For example, they input an instruction such as "Assemble part A at 14:00 on 2023-09-01." This information is detected and sent from the device to the server. The device can be a general smartphone (for example, an iPhone or Android device) or tablet. Data is sent using an HTTP request, using the requests library.

[1133] Data accumulation

[1134] The server securely stores the work instruction information received from the terminal in a database. This database stores the user's past work data. Suitable database software is MySQL or PostgreSQL.

[1135] Data analysis

[1136] The server analyzes the accumulated data and runs algorithms to extract behavioral patterns, such as machine learning algorithms (such as scikit-learn) and data mining techniques, making it possible to predict when and what tasks a user will perform.

[1137] Generate action suggestions

[1138] Based on the results of the data analysis, the server will suggest the user's next action, which will indicate what the user should do next, generating specific instructions such as "The next action is to assemble part B."

[1139] Submitting proposals and issuing directives

[1140] The suggestions are sent to the device and the user is notified visually and audibly. At the same time, specific work instructions based on the suggested actions are sent to robots and other work equipment in the factory. When the command is sent to the robot, it executes the suggested action. The equipment is typically a typical factory robot (e.g., an industrial robot arm) and is often controlled through an API.

[1141] Specific examples

[1142] For example, one day, a user enters "2023-09-01 14:00 Assemble part A" into their smartphone calendar. The system captures this information and sends it to the server. The server stores the information in a database, analyzes it, and learns a pattern of performing work-related tasks around 2:00 PM. If the user makes a voice request at 1:45 PM saying, "Tell me what to do next," the device notifies the user of the server's suggestion, displaying, "The next action is to assemble part B." At the same time, the server instructs the robot to "assemble part B," and the robot executes the suggested action.

[1143] Prompt Sentence Examples

[1144] User: Enters "2023-10-01 09:00 Assemble part A" on the smartphone.

[1145] System: This information is sent to the server and stored in a database.

[1146] Server: Suggests the next action (e.g., assemble part B) based on past data.

[1147] User: At 9 AM, voice requests "Tell me what to do next."

[1148] System: Display "Your next action is to assemble part B."

[1149] As described above, the present invention aims to improve work efficiency in factories and reduce the burden on workers by analyzing user behavior and proposing the next action.

[1150] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1151] Step 1:

[1152] Users input work instructions using smartphones or tablet devices.

[1153] Specifically, the user opens a calendar app and enters instructions such as "Assemble part A at 2023-09-01 14:00." This data becomes the input data.

[1154] Step 2:

[1155] The terminal detects the input work instruction information and transmits it to the server.

[1156] The application on the terminal sends the input data to the server using an HTTP request, and the server receives the information. The output is the work instruction data sent to the server.

[1157] Step 3:

[1158] The server stores the received work instruction information in a database.

[1159] Specifically, the server uses a MySQL or PostgreSQL database to record the data it receives (for example, the date, time, and content of a work order), which then becomes the input data for subsequent analysis.

[1160] Step 4:

[1161] The server analyzes various work data stored in the database and extracts behavioral patterns.

[1162] For example, the server uses a machine learning library such as scikit-learn to analyze the accumulated data and learn the user's behavioral patterns. This analysis extracts the tendency for users to perform specific tasks at specific times. The output is the user's behavioral patterns.

[1163] Step 5:

[1164] The server suggests the next action based on the extracted behavioral pattern.

[1165] Based on machine learning algorithms, it predicts the next task the user should perform and generates a suggestion, such as "Your next action is to assemble part B."

[1166] Step 6:

[1167] The proposed action is transmitted to the terminal and notified to the user visually or audibly.

[1168] The server sends the generated suggestions to the device, which then displays the information on the user's smartphone or tablet. The input is the suggestion data from the server, and the output is displayed as a notification on the device.

[1169] Step 7:

[1170] Based on the proposal, the server sends specific work instructions to the robots in the factory.

[1171] Based on the proposed actions, the server issues work instructions to the robot using an API. The input is the work instructions from the server, and the output is a command to the robot.

[1172] Step 8:

[1173] Upon receiving the command, the robot performs the next action according to the command.

[1174] For example, a robot starts assembling part B. The input is the received work instruction, and the output is the actual work action.

[1175] This allows the entire system to work together to manage the user's actions and effectively suggest and execute the next action.

[1176] 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.

[1177] This invention is a system for supporting users in their daily lives. Specifically, it is a system that records the user's behavioral data and suggests the next action based on the record. In particular, it is characterized by combining an emotion engine that recognizes the user's emotions and suggests actions according to the user's emotions.

[1178] The system operates through interactions between the terminal, server, emotion engine, and user. The specific operation of each component is explained below.

[1179] Data collection and storage

[1180] Terminal

[1181] When a user adds an event to their calendar using their smartphone, the information is captured. For example, if a user enters "Jogging at 08:00 on 2023-09-01," the event is detected by the device.

[1182] server

[1183] The device sends the detected information to a server, which stores it in a database, including the specific date and time and details of the event.

[1184] Data analysis

[1185] server

[1186] The server runs algorithms to analyze the accumulated data. Here, machine learning algorithms are used to extract user behavioral patterns. For example, a user may learn that they jog every morning at 8:00.

[1187] Generate action suggestions

[1188] server

[1189] Based on the results of the data analysis, the server will suggest the user's next action. This suggestion is generated based on the user's past behavioral patterns, and will create specific instructions such as "The next action is to go jogging."

[1190] Emotion Recognition and Regulation

[1191] Emotion Engine

[1192] The emotion engine recognizes emotions by analyzing the user's facial expressions and vocal tone, and this information is used to tailor the next suggested action. For example, if the user is feeling stressed, it will suggest actions to help them relax.

[1193] Presenting the proposal

[1194] Terminal

[1195] The suggested actions are sent to the device and displayed on the user's smartphone or other device. When the user makes a voice request such as "Tell me what to do next," the device immediately notifies the user of the suggestions received from the server.

[1196] Specific examples

[1197] For example, if a user adds a meeting to their calendar for 2 p.m., the system behaves as follows:

[1198] User: Opens the calendar app on their smartphone and enters "2023-09-01 14:00 Meeting."

[1199] Device: Detects schedules and sends information to the server.

[1200] Server: Receives the schedule information and stores it in a database.

[1201] Server: Periodically analyzes stored data to learn patterns of users performing work-related tasks around 2 p.m.

[1202] User: At 1:45 PM, voice requests "Tell me what to do next."

[1203] Terminal: Sends a request to the server, receives the suggestion, and notifies the user, displaying "Next action is a meeting."

[1204] Emotion engine: If a user is feeling stressed during a meeting, the system will provide additional advice such as "take a deep breath to relax a bit."

[1205] This series of steps helps users smoothly manage their schedules and next actions, which are often forgotten in daily life. The addition of an emotion engine enables more detailed action suggestions based on the user's emotional state, further improving quality of life. Each step enriches the user's life by recording the user's actions and suggesting the next action based on them.

[1206] The processing flow will be explained below.

[1207] Step 1:

[1208] A user adds an event to a calendar app. The user uses their smartphone to enter specific event information (e.g., "2023-09-01 08:00 Jogging").

[1209] Step 2:

[1210] The device detects the events entered by the user. The device detects that the calendar app has been updated and captures the event information as new event data.

[1211] Step 3:

[1212] The device sends the captured schedule information to the server, and the device uploads the detected behavior data to the server via the Internet.

[1213] Step 4:

[1214] The server receives the schedule information sent from the device. The received data includes the date, time, and event details.

[1215] Step 5:

[1216] The server stores the received data in a database, where it accumulates this new data along with existing user behavior data.

[1217] Step 6:

[1218] The server analyzes the behavioral data stored in the database. Using machine learning algorithms, the server extracts the user's behavioral patterns. For example, it discovers that the user jogs every morning at 8:00.

[1219] Step 7:

[1220] The server then suggests the next action based on the user's behavioral patterns. In this process, the server predicts the user's best next action based on the analysis results and generates a suggestion, creating specific instructions such as "The next action is jogging."

[1221] Step 8:

[1222] The emotion engine recognizes the user's emotions. The emotion engine analyzes the user's facial expressions and vocal tone to determine their current emotional state. For example, if the user is feeling stressed, that information will be reflected.

[1223] Step 9:

[1224] The server adjusts the suggestions based on the information obtained from the emotion engine. For example, if it determines that the user is feeling stressed, it adds a relaxing activity ("take a deep breath") to the next action suggestions.

[1225] Step 10:

[1226] The server sends the final proposal to the device, which prepares it for notification to the user at the appropriate time.

[1227] Step 11:

[1228] The user makes a voice request saying, "Tell me what to do next." The user then asks for confirmation of the next action via their smartphone or voice assistant.

[1229] Step 12:

[1230] The terminal detects the user's voice request and forwards the request to the server. The terminal uses voice recognition technology to analyze the user's request and sends a corresponding request to the server.

[1231] Step 13:

[1232] The server responds to the user's request and returns pre-generated action suggestions to the terminal, providing the action suggestions that best fit the user's current situation.

[1233] Step 14:

[1234] The device notifies the user of the suggested action. The device uses a display or voice notification to let the user know, "The next action is jogging." If the user is feeling stressed, the device also provides additional advice for relaxation ("take a deep breath").

[1235] This series of steps helps users smoothly manage their schedules and next actions, which are often forgotten in daily life. The addition of an emotion engine makes it possible to provide detailed action suggestions based on the user's emotional state, further improving quality of life.

[1236] Example 2

[1237] 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."

[1238] Conventional behavior suggestion systems can make suggestions based on the user's behavioral data, but they cannot make suggestions that take into account the user's emotional state. As a result, they cannot make optimal suggestions when the user is stressed or in a specific emotional state, making it difficult to improve user satisfaction. In addition, interactive suggestions based on voice input have not been sufficiently implemented.

[1239] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting user behavioral data, means for storing the collected behavioral data, means for analyzing the stored behavioral data and extracting behavioral patterns, means for proposing a next action based on the extracted behavioral pattern, means for presenting the proposed action to the user, and means for recognizing the user's emotions and adjusting the next action proposal. This enables more personalized action proposals taking into account the user's emotional state, thereby significantly improving user satisfaction.

[1240] "User behavioral data" refers to information about various activities that a user performs in their daily life, including, for example, calendar entries, tasks, and daily habits.

[1241] "Means of collection" refers to hardware and software used to obtain behavioral data from users, such as smartphone calendar apps and sensors.

[1242] "Storage means" refers to a database or storage system for storing collected data.

[1243] "Means of analysis and extraction of behavioral patterns" refers to algorithms and software, such as machine learning algorithms, that can be used to find useful information and trends from accumulated data.

[1244] "Suggestion methods" refers to algorithms or software that recommend the next action to the user based on the extracted behavioral patterns.

[1245] "Presentation means" refers to the interface or device used to notify the user of the suggested action, such as a smartphone notification feature or voice assistant.

[1246] "Means for recognizing emotions and adjusting next action suggestions" refers to software or hardware, such as facial recognition technology or voice analysis technology, that analyzes the user's emotions and changes next action suggestions in response to those emotions.

[1247] "Responding to voice input" refers to a system that executes corresponding functions in response to a user's voice input of instructions or questions.

[1248] "Visual information" refers to image data and video data such as a user's facial expressions and gestures.

[1249] This invention is a system for supporting users' daily lives, specifically a system that records user behavioral data and suggests next actions based on that data. Furthermore, it is characterized by combining an emotion engine that recognizes the user's emotions and suggests actions based on the user's emotions. The system operates through the user's terminal, a server, the emotion engine, and the interactions between them.

[1250] Data collection and storage

[1251] Terminal

[1252] The device mainly refers to devices such as smartphones and tablets. When a user adds an event to a calendar app using such a device, the information is automatically captured. For example, if a user enters "Jogging at 08:00 on 2023-09-01" in the calendar, this information is detected by the device.

[1253] server

[1254] The collected data is sent from the device to a server, which stores the received information in a database and manages data for each user, including specific dates, times, and details of events.

[1255] Data analysis

[1256] server

[1257] The server runs an algorithm to analyze the stored data. For example, a machine learning algorithm is used to extract the user's behavioral patterns. This analysis may reveal that the user has a habit of performing a certain activity at a specific time each day (for example, jogging at 8:00 AM every morning).

[1258] Generate action suggestions

[1259] server

[1260] Based on the analysis results, the server will suggest the next action, for example, generating specific instructions such as "Next action is jogging." This suggestion is based on the user's past behavioral patterns.

[1261] Emotion recognition and behavioral suggestion adjustment

[1262] Emotion Engine

[1263] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and voice to recognize their emotions. The results of this recognition are sent to the server and used to adjust the next action suggestion. For example, if the user is feeling stressed, the engine will suggest actions to help them relax.

[1264] Presenting the proposal

[1265] Terminal

[1266] The suggestions are sent to the device and displayed on the user's smartphone or other device. When the user makes a voice request, "Tell me what to do next," the device immediately displays the suggestions received from the server.

[1267] Specific examples

[1268] For example, if a user adds a meeting to their calendar for 2:00 PM, the sequence of actions is as follows:

[1269] User: Opens the calendar app on their smartphone and enters "2023-09-01 14:00 Meeting."

[1270] Device: Detects schedules and sends information to the server.

[1271] Server: Receives the schedule information and saves it in the database. "2023-09-01 14:00 Meeting" is recorded as data for each user.

[1272] Server: Periodically analyzes stored data to learn patterns of users performing work-related tasks around 2 p.m.

[1273] User: At 1:45 PM, voice requests "Tell me what to do next."

[1274] Terminal: Sends a request to the server, receives the suggestion, and notifies the user, displaying "Next action is a meeting."

[1275] Emotion engine: If a user is feeling stressed during a meeting, the system will provide additional advice such as "Take a deep breath to relax a bit." This analysis is performed by the emotion engine, which analyzes the user's facial expressions and voice.

[1276] Prompt Sentence Examples

[1277] Below is an example of a prompt sentence to input to the generative AI model.

[1278] Please explain the steps involved in the system that suggests actions based on the user's emotions.

[1279] 1. The user enters an event into the calendar app on their smartphone.

[1280] 2. The device detects this appointment and sends it to the server.

[1281] 3. The server saves the appointment information in a database.

[1282] 4. The server analyzes the stored data and learns user behavior patterns.

[1283] 5. The server suggests the next action.

[1284] 6. The emotion engine recognizes the user's emotions and adjusts suggested actions if necessary.

[1285] 7. The device notifies the user of the suggested action.

[1286] An example would be "When a user schedules a meeting for 2 PM."

[1287] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1288] Step 1:

[1289] User

[1290] The user opens the calendar app on their smartphone and enters an appointment. For example, they enter "2023-09-01 14:00 Meeting." This entry becomes the basic data for future processing.

[1291] Input: Events entered in the calendar (text format)

[1292] Output: Capture of schedule information (text format)

[1293] What happens: A user manually enters an event into a calendar app. This information is stored on the device as text data.

[1294] Step 2:

[1295] Terminal

[1296] The device captures the schedule information entered by the user and automatically sends it to the server, where the date, time, and event details are obtained.

[1297] Input: Schedule information entered by the user (text format)

[1298] Output: Schedule information sent to the server (text format)

[1299] Specific operation: The device detects the entered schedule information in real time and sends that information to the server's API endpoint.

[1300] Step 3:

[1301] server

[1302] The server stores the schedule information received from the device in a database, which is linked to the user ID and date and time information.

[1303] Input: Schedule information sent from the device (text format)

[1304] Output: Schedule information stored in the database (database records)

[1305] Specific operation: When the server receives the event information, it creates a new record in the database and saves it. The saved information includes the user ID, date and time, and event details.

[1306] Step 4:

[1307] server

[1308] The server runs machine learning algorithms to analyze the stored schedule information, thereby extracting user behavior patterns.

[1309] Input: User behavior data stored in a database (database records)

[1310] Output: Extracted behavioral patterns (model data)

[1311] How it works: The server periodically reads the behavioral data in the database and uses machine learning algorithms to analyze and extract behavioral patterns, such as repeating behavior during specific times of the day.

[1312] Step 5:

[1313] server

[1314] Based on the results of the data analysis, an algorithm is run to suggest next steps, which are generated based on past behavioral patterns.

[1315] Input: Behavioral pattern (model data)

[1316] Output: Next action suggestions (text format)

[1317] Specific operation: Based on the extracted behavioral patterns, the server uses an algorithm to determine the next action the user should take and generates a suggested text data. For example, a suggestion such as "The next action is jogging" is created.

[1318] Step 6:

[1319] Emotion Engine

[1320] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and voice to recognize their emotions, and adjusts the next action suggestions accordingly.

[1321] Input: User's facial expressions and voice data (multimedia format)

[1322] Output: Recognized emotion data (text and numeric format)

[1323] Specific operation: The emotion engine analyzes the user's facial expressions captured by the camera and the voice data collected by the microphone, and extracts the user's emotional state as text and numerical data, which is sent to the server to adjust the next action suggestion.

[1324] Step 7:

[1325] server

[1326] The server adjusts the suggested actions based on the emotion data sent from the emotion engine. If the user is feeling stressed, the server will suggest additional actions to help them relax.

[1327] Input: Emotion data (text and numerical format), next action suggestions (text format)

[1328] Output: Adjusted action proposals (text format)

[1329] Specific actions: The server analyzes the emotion data and modifies the original action suggestions as needed, for example, to include specific advice such as "take a deep breath to relax a bit" if the user is feeling stressed.

[1330] Step 8:

[1331] Terminal

[1332] The adjusted action suggestions are sent to the device and notified to the user. The suggestions are also displayed when the user makes a voice request such as "Tell me what to do next."

[1333] Input: Adjusted action proposal (text format)

[1334] Output: Action suggestions displayed to the user (in text format)

[1335] Specific operation: The device receives the adjusted action suggestions from the server and presents them to the user via notifications or voice assistants. The user can then confirm the suggested action and smoothly carry out the next action.

[1336] The above is a description of the specific processing steps of this system and their detailed operation.

[1337] (Application example 2)

[1338] 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."

[1339] Conventional food delivery services only provide users with meal options, but do not offer personalized suggestions based on their emotional state or behavioral patterns. As a result, users find it difficult to select the meal that best suits their current emotional state and situation, and are unable to receive appropriate suggestions for health management or stress relief. This leaves users with insufficient support for improving their quality of life and enjoying a comfortable daily life.

[1340] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1341] In this invention, the server includes means for collecting user behavioral data, emotion engine means for analyzing the emotional state, and means for adjusting the next action based on the emotional state, thereby optimizing the next action based on the user's emotional state and behavioral patterns, and making it possible to suggest meals that have a relaxing effect or that suit the user's preferences as needed.

[1342] "Behavioral data" is information relating to the user's daily activities, tasks, schedules, and the like.

[1343] An "emotion engine" is a software or hardware mechanism for analyzing a user's emotional state.

[1344] "Next Action" refers to the next action or task that the user should perform.

[1345] A "behavioral pattern" is a tendency or regularity of behavior extracted from a user's past behavioral data.

[1346] The "adjustment means" is a means for optimizing the next action suggestion based on the emotional state analyzed by the emotion engine.

[1347] A "suggested action" is an instruction for next action that the system presents to the user based on the analyzed behavioral data and emotional state.

[1348] "Visual information" refers to information that is visually recognized, such as the user's facial expressions and actions.

[1349] "Emotional information" is data relating to the user's emotional state, and is information obtained from voice tone, facial expressions, and the like.

[1350] "Means of collection" refers to devices and software for capturing user behavioral data and emotional information.

[1351] The "means for presenting suggestions" is a means for displaying or notifying the user of suggestions for the next action or meal.

[1352] This invention is directed to a smartphone application for food delivery services. The system collects and analyzes user behavioral and emotional data to suggest optimal meals to users.

[1353] System configuration

[1354] Hardware and Software

[1355] The system uses the following hardware and software:

[1356] Smartphone: Used to provide the user interface and collect data.

[1357] Emotion Engine: Software that analyzes the user's emotional state. In this case, we use the TextBlob library.

[1358] Server: A server for storing and analyzing user behavioral and emotional data.

[1359] Food Delivery API: An external API that processes food orders.

[1360] Data collection and storage

[1361] Smartphone: The user uses a calendar app to enter activity data (e.g., a jogging schedule), and this information is sent from the smartphone to the server.

[1362] Server: The server receives the data and stores it in a database, including the date and time of the activity and detailed information.

[1363] Emotion engine: Collects and analyzes emotional data from user text and voice input.

[1364] Data analysis

[1365] Server: Runs algorithms to analyze the accumulated behavioral and emotional data. Machine learning algorithms are used here to extract user behavior patterns.

[1366] Emotion Engine: Uses the TextBlob library to parse the user's input text (emotion data) and generate an emotion score.

[1367] Generating behavioral and dietary suggestions

[1368] Server: Based on the analysis results, the server will suggest the next action and the best meal. For example, if the user is feeling stressed, it will suggest a meal that will have a relaxing effect.

[1369] Smartphone: Suggested activities and meals are presented to the user via their smartphone. When the user requests the next action by voice, the server immediately notifies them of the suggestion.

[1370] Specific examples

[1371] For example, if a user enters "2023-09-01 14:00 meeting" into a calendar app, the system will behave as follows:

[1372] Original invention in action:

[1373] User: Opens the calendar app on their smartphone and enters "2023-09-01 14:00 Meeting."

[1374] Device: Detects schedules and sends information to the server.

[1375] Server: Receives the schedule information and stores it in a database.

[1376] Server: Periodically analyzes stored data to learn patterns of users performing work-related tasks around 2 p.m.

[1377] User: At 1:45 PM, voice requests "Tell me what to do next."

[1378] Terminal: Sends a request to the server, receives the suggestion, and notifies the user, displaying "Next action is a meeting."

[1379] Emotion engine: If a user is feeling stressed during a meeting, the system will provide additional advice such as "take a deep breath to relax a bit."

[1380] Examples of application improvements:

[1381] User: A user who feels stressed types "I'm feeling stressed right now" into a smartphone app.

[1382] Emotion engine: The analyze_emotion function generates a negative emotion score from "stress."

[1383] Suggestion: The app suggests to the user, "Why not order a hot soup to help you relax?"

[1384] Ordering: If the user accepts the suggestion, the app will automatically place the soup order.

[1385] Example prompt sentence:

[1386] "If a user types 'I am feeling stressed,' generate a negative emotion score and suggest foods that will help them relax."

[1387] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1388] Step 1:

[1389] User behavioral data entry

[1390] A user uses a calendar application on their smartphone to enter action data such as "2023-09-01 14:00 Meeting."

[1391] Input: Behavioral data entered by the user into their smartphone (date, time, and content)

[1392] Output: Behavioral data is stored in an application on the smartphone.

[1393] Step 2:

[1394] Transmission of behavioral data by the device

[1395] The device transmits the detected behavioral data to the server, where the behavioral data is converted into an appropriate format and sent to the server via the network.

[1396] Input: Behavioral data stored on the smartphone

[1397] Output: Behavioral data is sent to and received by the server.

[1398] Step 3:

[1399] Data storage by server

[1400] The server stores the received behavioral data in a database, which stores the date, time, and event details.

[1401] Input: Behavioral data sent to the server

[1402] Output: The behavioral data is stored in a database on the server.

[1403] Step 4:

[1404] Emotional data collection and analysis using an emotion engine

[1405] When a user types "I'm feeling stressed right now" into their smartphone, the emotion engine analyzes the input and generates an emotion score. In this example, the TextBlob library is used.

[1406] Input: Emotion data entered by the user (e.g., feeling stressed)

[1407] Output: A sentiment score (e.g., a negative sentiment score) is generated.

[1408] Step 5:

[1409] Server analysis of behavioral patterns

[1410] The server analyzes the accumulated behavioral and emotional data and uses machine learning algorithms to extract behavioral patterns.

[1411] Input: Behavioral data and emotion scores stored in a database

[1412] Output: Analysis of user behavior patterns

[1413] Step 6:

[1414] Server-generated next action and meal suggestions

[1415] The server then suggests the next action or meal based on the analysis results. For example, it suggests a meal with a relaxing effect (e.g., soup) based on the emotion score.

[1416] Input: Behavioral pattern analysis results and sentiment score

[1417] Output: Suggested behavior and dietary recommendations

[1418] Step 7:

[1419] Proposal presentation by device

[1420] The device displays and notifies the user of the suggestions received from the server. If the user requests the next action by voice, the suggestions are displayed immediately.

[1421] Input: Proposal sent from the server

[1422] Output: Display and notification of suggestions on smartphone

[1423] Step 8:

[1424] User review and order

[1425] If the user accepts the suggested meal, the device sends the order to the food delivery API. If the order is successful, a confirmation message is displayed to the user.

[1426] Input: The result of the user reviewing the suggestion (e.g., ordering a meal)

[1427] Output: Places an order to the food delivery API and displays a confirmation message

[1428] Example of using a generative AI model and prompt:

[1429] "If a user types 'I am feeling stressed,' generate a negative emotion score and suggest foods that will help them relax."

[1430] 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.

[1431] 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.

[1432] 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.

[1433] [Fourth embodiment]

[1434] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1435] 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.

[1436] 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).

[1437] 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.

[1438] 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.

[1439] 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).

[1440] 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.

[1441] 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.

[1442] 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.

[1443] 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.

[1444] 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.

[1445] 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.

[1446] 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."

[1447] This invention is a system for supporting the daily life of a user, specifically, a system that records the user's behavior and suggests the next action based on the record. This system includes a series of processes that collect, accumulate, and analyze the user's behavior data, suggest the next action based on the extracted behavioral patterns, and notify the user of the suggestion.

[1448] The system operates through interactions between the terminal, the server, and the user. The specific operation of each component is explained below.

[1449] Data collection

[1450] Terminal

[1451] When a user adds an event to their calendar using their smartphone, the information is captured. For example, if a user types "Jogging at 08:00 on 2023-09-01," the event will be detected by the device.

[1452] server

[1453] The device sends the detected information to a server, which stores it in a database, including the specific date and time and details of the event.

[1454] Data accumulation

[1455] server

[1456] The server securely stores the behavioral data sent from the device in a database, which systematically stores the user's past behavioral data and is used in subsequent analysis processes.

[1457] Data analysis

[1458] server

[1459] The server runs algorithms to analyze the stored data, using machine learning and data mining techniques to extract user behavioral patterns, such as jogging every morning at 8am.

[1460] Generate action suggestions

[1461] server

[1462] Based on the results of the data analysis, the server will suggest the user's next action. This suggestion is generated based on the user's past behavioral patterns. For example, if a user requests "Tell me what to do next," a specific suggestion such as "The next action is jogging" will be generated.

[1463] Presenting the proposal

[1464] Terminal

[1465] The proposed actions are sent to the device and displayed on the user's smartphone or other device. When the user verbally asks the device, "Tell me what to do next," the device immediately notifies the user of the suggestions received from the server.

[1466] Specific examples

[1467] For example, if a user adds a meeting to their calendar for 2 p.m., the system behaves as follows:

[1468] User: Opens the calendar app on their smartphone and enters "2023-09-01 14:00 Meeting."

[1469] Device: Detects schedules and sends information to the server.

[1470] Server: Receives the schedule information and stores it in a database.

[1471] Server: Periodically analyzes stored data to learn patterns of users performing work-related tasks around 2 p.m.

[1472] User: At 1:45 PM, voice requests "Tell me what to do next."

[1473] Terminal: Sends a request to the server, receives the suggestion, and notifies the user, displaying "Next action is a meeting."

[1474] In this way, the present invention can efficiently manage the user's daily life and prevent them from forgetting to take photos or getting lost. Each component of the system captures, stores, and analyzes the user's actions, and then appropriately suggests the next action to take, thereby improving the user's quality of life.

[1475] The processing flow will be explained below.

[1476] Step 1:

[1477] A user adds an event to a calendar app. The user uses their smartphone to enter specific event information (e.g., "2023-09-01 08:00 Jogging").

[1478] Step 2:

[1479] The device detects the events entered by the user. The device detects that the calendar app has been updated and captures the event information as new event data.

[1480] Step 3:

[1481] The device sends the captured schedule information to the server, and the device uploads the detected behavior data to the server via the Internet.

[1482] Step 4:

[1483] The server receives the schedule information sent from the device. The received data includes the date, time, and event details.

[1484] Step 5:

[1485] The server stores the received data in a database, where it accumulates this new data along with existing user behavior data.

[1486] Step 6:

[1487] The server analyzes the behavioral data stored in the database. Using machine learning algorithms, the server extracts user behavior patterns. For example, it discovers that a user jogs every morning at 8:00.

[1488] Step 7:

[1489] The server then suggests the next action based on the user's behavioral patterns. In this process, the server predicts the user's best next action based on the analysis results and generates a suggestion, creating specific instructions such as "The next action is jogging."

[1490] Step 8:

[1491] The server sends the proposal to the terminal, which prepares the proposal to be notified to the user at the appropriate time.

[1492] Step 9:

[1493] The user makes a voice request saying, "Tell me what to do next." The user then asks for confirmation of the next action via their smartphone or voice assistant.

[1494] Step 10:

[1495] The terminal detects the user's voice request and forwards the request to the server. The terminal uses voice recognition technology to analyze the user's request and sends a corresponding request to the server.

[1496] Step 11:

[1497] The server responds to the user's request and returns pre-generated action suggestions to the terminal, providing the action suggestions that best fit the user's current situation.

[1498] Step 12:

[1499] The device notifies the user of the proposed activity. The device notifies the user by displaying or announcing the activity, such as "The next activity is jogging."

[1500] This series of steps helps users smoothly manage their schedules and next actions, which are often forgotten in daily life. Each step records the user's actions and suggests the next action based on them, improving the quality of life.

[1501] Example 1

[1502] 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."

[1503] In users' daily lives, there is a need to clarify the next action to be taken and manage it efficiently. However, conventional systems have low accuracy in collecting user behavioral information and suggesting appropriate actions, and lack the ability to respond quickly to the user's voice input. This makes it difficult for users to understand their next action and to receive appropriate support to improve their quality of life.

[1504] 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.

[1505] In this invention, the server includes a means for accumulating user behavior information, a means for analyzing behavioral patterns using a machine learning algorithm and generating a next action, and a means for converting the generated action into a prompt sentence format and transmitting it to the terminal, thereby enabling the user's behavior to be analyzed with high accuracy and the next action to be appropriately suggested.

[1506] "User behavior information" is data on activities and events that a user engages in in their daily life.

[1507] "Means of collection" refers to a mechanism for detecting user behavior information and acquiring that information.

[1508] "Storage means" refers to a mechanism for storing and managing collected behavioral information.

[1509] "Means of analysis and extraction of behavioral patterns" refers to a mechanism that analyzes accumulated behavioral information using machine learning algorithms and the like to discover user behavioral patterns.

[1510] The "means for suggesting the next action" is a mechanism for generating the next action that the user should take based on the extracted behavioral pattern.

[1511] "Means for presenting to the user" refers to a mechanism for notifying the user's terminal of the proposed action.

[1512] "Means for detecting information from the terminal and transferring it to the server" is a mechanism for transmitting data collected from the terminal to the server.

[1513] "Means for analyzing behavioral patterns using machine learning algorithms" refers to a mechanism for analyzing collected data using machine learning technology and extracting behavioral patterns.

[1514] The "means for generating behavior" is the process for determining the user's next behavior based on the analysis results.

[1515] The "means for converting into a prompt sentence format and sending to the terminal" is a mechanism for converting the proposed action into a format (prompt sentence) that is easy for the user to understand and sending that information to the terminal.

[1516] This invention is a system for supporting users' daily lives, characterized by collecting and analyzing user behavioral information and suggesting the user's next action based on that information. The system operates through interactions between the terminal, server, and user. The specific operation of each component is explained below.

[1517] Data collection

[1518] Terminal

[1519] When a user adds an event to their calendar using their smartphone, the information is captured. For example, if a user enters "2023-09-01 08:00 Jogging," the event is detected by the device.

[1520] Data transmission

[1521] Terminal

[1522] The calendar app detects the input and sends this information to the system's data collection module, which sends the data in JSON format to the server as an HTTP POST request.

[1523] Data accumulation

[1524] server

[1525] The received information is parsed and stored in a database (e.g., PostgreSQL), which contains the user ID, event date and time, and event details.

[1526] Data analysis

[1527] server

[1528] The accumulated data is analyzed using Python's scikit-learn library. User behavior patterns are extracted using machine learning algorithms (e.g., Gaussian Mixture Models). The Pandas library is used for data preprocessing.

[1529] Generate action suggestions

[1530] server

[1531] As a result of the analysis, the next action is suggested. For example, if it is determined that the user jogs at 8 o'clock every morning, the system generates a suggestion such as "Your next action is to jog." This suggestion is converted into a prompt sentence format and saved in the database.

[1532] Presenting the proposal

[1533] Terminal

[1534] When a user requests "Tell me what to do next" by voice, the request is sent to the server. The server notifies the user of the suggestions received. The user is informed via a screen display or voice assistant that "The next action is jogging."

[1535] Specific examples

[1536] For example, if a user adds a meeting to their calendar for 2 p.m., the system behaves as follows:

[1537] User: Opens the calendar app on their smartphone and enters "2023-09-01 14:00 Meeting."

[1538] Device: Detects schedules and sends information to the server.

[1539] Server: Receives the schedule information and stores it in a database.

[1540] Server: Periodically analyzes stored data to learn patterns of users performing work-related tasks around 2 p.m.

[1541] User: At 1:45 PM, voice requests "Tell me what to do next."

[1542] Terminal: Sends a request to the server, receives the suggestion, and notifies the user, displaying "Next action is a meeting."

[1543] Prompt Sentence Examples

[1544] "Suggest next action. Based on the latest behavioral pattern data, the user is available at 1:30 PM."

[1545] In this way, the present invention efficiently manages the user's daily life and prevents the user from being confused about what to do by suggesting appropriate next actions. Each component of the system captures, stores, and analyzes the user's actions and suggests appropriate next actions to improve the user's quality of life.

[1546] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1547] Step 1:

[1548] User

[1549] The user opens the calendar app on their smartphone and enters a new appointment, for example, "2023-09-01 08:00 Jogging." This entry is detected by the device.

[1550] Input: Enter a new event into the calendar app

[1551] Output: Detected event data (date, time, content)

[1552] Step 2:

[1553] Terminal

[1554] The device collects event data from the calendar app and makes an HTTP POST request to send it to the server in JSON format.

[1555] Specific operation: Acquires event data, converts it to JSON format, and sends it to the server.

[1556] Input: Detected event data (date, time, content)

[1557] Output: Event data sent to the server in JSON format

[1558] Step 3:

[1559] server

[1560] The server receives the HTTP request and analyzes the event data sent. After analyzing, it stores the data in a database. The database contains the user ID, event date and time, and event details.

[1561] Specific behavior: Parse the received event data and execute a query to insert it into the database.

[1562] Input: Event data in JSON format

[1563] Output: Event entries stored in the database

[1564] Step 4:

[1565] server

[1566] The accumulated data is periodically analyzed. Python's scikit-learn is used to extract user behavior patterns based on past behavior data. The algorithm used is Gaussian Mixture Models.

[1567] Specific operation: Data preprocessing with Pandas, running machine learning models with scikit-learn, and extracting patterns

[1568] Input: Past behavioral data stored in a database

[1569] Output: Extracted behavioral patterns

[1570] Step 5:

[1571] server

[1572] As a result of the data analysis, the next action is suggested based on the behavioral pattern. For example, a suggested sentence such as "The next action is jogging" is generated. This suggestion is converted into a prompt sentence format and saved in a database.

[1573] Specific behavior: Determine the next action based on the behavior pattern, generate a prompt sentence, and save it.

[1574] Input: Extracted behavioral patterns

[1575] Output: Next action saved as a prompt

[1576] Step 6:

[1577] User

[1578] The user makes a voice request saying, "Tell me what to do next." This request is sent from the device to the server.

[1579] Input: User's voice request

[1580] Output: Request sent to server

[1581] Step 7:

[1582] Terminal

[1583] The device receives the suggested next action from the server and notifies the user, for example, by notifying the user through a voice assistant that "The next action is jogging."

[1584] Specific behavior: Use an app or voice assistant to receive a response from the server and notify the user.

[1585] Input: Proposal received from the server

[1586] Output: Notification to the user (text or audio)

[1587] (Application example 1)

[1588] 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."

[1589] In modern manufacturing, improving work efficiency within factories requires accurately understanding worker behavior patterns and proposing optimal work at the right time. However, traditional manual work instructions and recording placed a heavy burden on workers and made efficient work management difficult. Furthermore, the lack of an automatic suggestion system based on worker behavior patterns limited the ability to improve work efficiency throughout the factory.

[1590] 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.

[1591] In this invention, the server includes means for collecting user behavior data, means for storing the collected behavior data, and means for analyzing the stored behavior data and extracting behavioral patterns. This allows the server to suggest a next action based on the user's behavior data, send a command to a device that operates an object based on the suggestion, and have the device execute the next action based on the command. This improves work efficiency in factories and reduces the burden on workers.

[1592] The "means for collecting user behavioral data" refers to a means for detecting and recording information about schedules and behaviors entered by a user using a smartphone, tablet device, or the like.

[1593] "Means for storing collected behavioral data" refers to a database or storage for safely storing collected user behavioral data and using it for subsequent analysis.

[1594] "Means for analyzing accumulated behavioral data and extracting behavioral patterns" refers to means for analyzing and extracting users' daily behavioral patterns based on accumulated behavioral data using machine learning algorithms and data mining techniques.

[1595] The "means for proposing the next action based on the extracted behavioral pattern" is a means for generating and proposing an appropriate next action to the user based on the behavioral pattern obtained by analysis.

[1596] The "means for presenting a proposed action to the user" refers to a means for visually or audibly notifying the user of the generated proposal for the next action.

[1597] The "means for sending commands to equipment that operates objects based on the proposed actions" refers to a means for sending specific work instructions to robots and other work equipment in the factory based on the content of the proposal.

[1598] The "means by which the equipment that received the command executes the next action" refers to the means by which the robot or work equipment actually performs the specified work based on the received command.

[1599] The system of this invention is a robotic assistant system that improves work efficiency in factories. This system includes a function to collect, store, and analyze user behavior data and suggest the next action. It also sends commands to machines that manipulate objects based on the suggested action, and the machines actually execute the next action, thereby improving work efficiency in factories.

[1600] The specific components of this system and their processing will now be described.

[1601] Programs and their processing

[1602] Data collection

[1603] The user inputs work instructions using a smartphone or tablet device. For example, they input an instruction such as "Assemble part A at 14:00 on 2023-09-01." This information is detected and sent from the device to the server. The device can be a general smartphone (for example, an iPhone or Android device) or tablet. Data is sent using an HTTP request, using the requests library.

[1604] Data accumulation

[1605] The server securely stores the work instruction information received from the terminal in a database. This database stores the user's past work data. Suitable database software is MySQL or PostgreSQL.

[1606] Data analysis

[1607] The server analyzes the accumulated data and runs algorithms to extract behavioral patterns, such as machine learning algorithms (such as scikit-learn) and data mining techniques, making it possible to predict when and what tasks a user will perform.

[1608] Generate action suggestions

[1609] Based on the results of the data analysis, the server will suggest the user's next action, which will indicate what the user should do next, generating specific instructions such as "The next action is to assemble part B."

[1610] Submitting proposals and issuing directives

[1611] The suggestions are sent to the device and the user is notified visually and audibly. At the same time, specific work instructions based on the suggested actions are sent to robots and other work equipment in the factory. When the command is sent to the robot, it executes the suggested action. The equipment is typically a typical factory robot (e.g., an industrial robot arm) and is often controlled through an API.

[1612] Specific examples

[1613] For example, one day, a user enters "2023-09-01 14:00 Assemble part A" into their smartphone calendar. The system captures this information and sends it to the server. The server stores the information in a database, analyzes it, and learns a pattern of performing work-related tasks around 2:00 PM. If the user makes a voice request at 1:45 PM saying, "Tell me what to do next," the device notifies the user of the server's suggestion, displaying, "The next action is to assemble part B." At the same time, the server instructs the robot to "assemble part B," and the robot executes the suggested action.

[1614] Prompt Sentence Examples

[1615] User: Enters "2023-10-01 09:00 Assemble part A" on the smartphone.

[1616] System: This information is sent to the server and stored in a database.

[1617] Server: Suggests the next action (e.g., assemble part B) based on past data.

[1618] User: At 9 AM, voice requests "Tell me what to do next."

[1619] System: Display "Your next action is to assemble part B."

[1620] As described above, the present invention aims to improve work efficiency in factories and reduce the burden on workers by analyzing user behavior and proposing the next action.

[1621] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1622] Step 1:

[1623] Users input work instructions using smartphones or tablet devices.

[1624] Specifically, the user opens a calendar app and enters instructions such as "Assemble part A at 2023-09-01 14:00." This data becomes the input data.

[1625] Step 2:

[1626] The terminal detects the input work instruction information and transmits it to the server.

[1627] The application on the terminal sends the input data to the server using an HTTP request, and the server receives the information. The output is the work instruction data sent to the server.

[1628] Step 3:

[1629] The server stores the received work instruction information in a database.

[1630] Specifically, the server uses a MySQL or PostgreSQL database to record the data it receives (for example, the date, time, and content of a work order), which then becomes the input data for subsequent analysis.

[1631] Step 4:

[1632] The server analyzes various work data stored in the database and extracts behavioral patterns.

[1633] For example, the server uses a machine learning library such as scikit-learn to analyze the accumulated data and learn the user's behavioral patterns. This analysis extracts the tendency for users to perform specific tasks at specific times. The output is the user's behavioral patterns.

[1634] Step 5:

[1635] The server suggests the next action based on the extracted behavioral pattern.

[1636] Based on machine learning algorithms, it predicts the next task the user should perform and generates a suggestion, such as "Your next action is to assemble part B."

[1637] Step 6:

[1638] The proposed action is transmitted to the terminal and notified to the user visually or audibly.

[1639] The server sends the generated suggestions to the device, which then displays the information on the user's smartphone or tablet. The input is the suggestion data from the server, and the output is displayed as a notification on the device.

[1640] Step 7:

[1641] Based on the proposal, the server sends specific work instructions to the robots in the factory.

[1642] Based on the proposed actions, the server issues work instructions to the robot using an API. The input is the work instructions from the server, and the output is a command to the robot.

[1643] Step 8:

[1644] Upon receiving the command, the robot performs the next action according to the command.

[1645] For example, a robot starts assembling part B. The input is the received work instruction, and the output is the actual work action.

[1646] This allows the entire system to work together to manage the user's actions and effectively suggest and execute the next action.

[1647] 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.

[1648] This invention is a system for supporting users in their daily lives. Specifically, it is a system that records the user's behavioral data and suggests the next action based on that data. In particular, it is characterized by combining an emotion engine that recognizes the user's emotions and suggests actions according to the user's emotions.

[1649] The system operates through interactions between the terminal, server, emotion engine, and user. The specific operation of each component is explained below.

[1650] Data collection and storage

[1651] Terminal

[1652] When a user adds an event to their calendar using their smartphone, the information is captured. For example, if a user enters "Jogging at 08:00 on 2023-09-01," the event is detected by the device.

[1653] server

[1654] The device sends the detected information to a server, which stores it in a database, including the specific date and time and details of the event.

[1655] Data analysis

[1656] server

[1657] The server runs algorithms to analyze the accumulated data. Here, machine learning algorithms are used to extract user behavioral patterns. For example, a user may learn that they jog every morning at 8:00.

[1658] Generate action suggestions

[1659] server

[1660] Based on the results of the data analysis, the server will suggest the user's next action. This suggestion is generated based on the user's past behavioral patterns, and will create specific instructions such as "The next action is to go jogging."

[1661] Emotion Recognition and Regulation

[1662] Emotion Engine

[1663] The emotion engine recognizes emotions by analyzing the user's facial expressions and vocal tone, and this information is used to tailor the next suggested action. For example, if the user is feeling stressed, it will suggest actions to help them relax.

[1664] Presenting the proposal

[1665] Terminal

[1666] The proposed actions are sent to the device and displayed on the user's smartphone or other device. When the user makes a voice request such as "Tell me what to do next," the device immediately notifies the user of the suggestions received from the server.

[1667] Specific examples

[1668] For example, if a user adds a meeting to their calendar for 2 p.m., the system behaves as follows:

[1669] User: Opens the calendar app on their smartphone and enters "2023-09-01 14:00 Meeting."

[1670] Device: Detects schedules and sends information to the server.

[1671] Server: Receives the schedule information and stores it in a database.

[1672] Server: Periodically analyzes stored data to learn patterns of users performing work-related tasks around 2 p.m.

[1673] User: At 1:45 PM, voice requests "Tell me what to do next."

[1674] Terminal: Sends a request to the server, receives the suggestion, and notifies the user, displaying "Next action is a meeting."

[1675] Emotion engine: If a user is feeling stressed during a meeting, the system will provide additional advice such as "take a deep breath to relax a bit."

[1676] This series of steps helps users smoothly manage their schedules and next actions, which are often forgotten in daily life. The addition of an emotion engine enables more detailed action suggestions based on the user's emotional state, further improving quality of life. Each step enriches the user's life by recording the user's actions and suggesting the next action based on them.

[1677] The processing flow will be explained below.

[1678] Step 1:

[1679] A user adds an event to a calendar app. The user uses their smartphone to enter specific event information (e.g., "2023-09-01 08:00 Jogging").

[1680] Step 2:

[1681] The device detects the events entered by the user. The device detects that the calendar app has been updated and captures the event information as new event data.

[1682] Step 3:

[1683] The device sends the captured schedule information to the server, and the device uploads the detected behavior data to the server via the Internet.

[1684] Step 4:

[1685] The server receives the schedule information sent from the device. The received data includes the date, time, and event details.

[1686] Step 5:

[1687] The server stores the received data in a database, where it accumulates this new data along with existing user behavior data.

[1688] Step 6:

[1689] The server analyzes the behavioral data stored in the database. Using machine learning algorithms, the server extracts user behavior patterns. For example, it discovers that a user jogs every morning at 8:00.

[1690] Step 7:

[1691] The server then suggests the next action based on the user's behavioral patterns. In this process, the server predicts the user's best next action based on the analysis results and generates a suggestion, creating specific instructions such as "The next action is jogging."

[1692] Step 8:

[1693] The emotion engine recognizes the user's emotions. The emotion engine analyzes the user's facial expressions and vocal tone to determine their current emotional state. For example, if the user is feeling stressed, that information will be reflected.

[1694] Step 9:

[1695] The server adjusts the suggestions based on the information obtained from the emotion engine. For example, if it determines that the user is feeling stressed, it adds a relaxing activity ("take a deep breath") to the next action suggestions.

[1696] Step 10:

[1697] The server sends the final proposal to the device, which prepares it for notification to the user at the appropriate time.

[1698] Step 11:

[1699] The user makes a voice request saying, "Tell me what to do next." The user then asks for confirmation of the next action via their smartphone or voice assistant.

[1700] Step 12:

[1701] The terminal detects the user's voice request and forwards the request to the server. The terminal uses voice recognition technology to analyze the user's request and sends a corresponding request to the server.

[1702] Step 13:

[1703] The server responds to the user's request and returns pre-generated action suggestions to the terminal, providing the action suggestions that best fit the user's current situation.

[1704] Step 14:

[1705] The device notifies the user of the suggested action. The device uses a display or voice notification to let the user know, "The next action is jogging." If the user is feeling stressed, the device also provides additional advice for relaxation ("take a deep breath").

[1706] This series of steps helps users smoothly manage their schedules and next actions, which are often forgotten in daily life. The addition of an emotion engine makes it possible to provide detailed action suggestions based on the user's emotional state, further improving quality of life.

[1707] Example 2

[1708] 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."

[1709] Conventional behavior suggestion systems can make suggestions based on the user's behavioral data, but they cannot make suggestions that take into account the user's emotional state. As a result, they cannot make optimal suggestions when the user is stressed or in a specific emotional state, making it difficult to improve user satisfaction. In addition, interactive suggestions based on voice input have not been sufficiently implemented.

[1710] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting user behavioral data, means for storing the collected behavioral data, means for analyzing the stored behavioral data and extracting behavioral patterns, means for proposing a next action based on the extracted behavioral pattern, means for presenting the proposed action to the user, and means for recognizing the user's emotions and adjusting the next action proposal. This enables more personalized action proposals taking into account the user's emotional state, thereby significantly improving user satisfaction.

[1711] "User behavioral data" refers to information about various activities that a user performs in their daily life, including, for example, calendar entries, tasks, and daily habits.

[1712] "Means of collection" refers to hardware and software used to obtain behavioral data from users, such as smartphone calendar apps and sensors.

[1713] "Storage means" refers to a database or storage system for storing collected data.

[1714] "Means of analysis and extraction of behavioral patterns" refers to algorithms and software, such as machine learning algorithms, that can be used to find useful information and trends from accumulated data.

[1715] "Suggestion methods" refers to algorithms or software that recommend the next action to the user based on the extracted behavioral patterns.

[1716] "Presentation means" refers to an interface or device used to notify the user of the suggested action, such as a smartphone notification feature or a voice assistant.

[1717] "Means for recognizing emotions and adjusting next action suggestions" refers to software or hardware, such as facial recognition technology or voice analysis technology, that analyzes the user's emotions and changes next action suggestions in response to those emotions.

[1718] "Responding to voice input" refers to a system that executes corresponding functions in response to a user's voice input of instructions or questions.

[1719] "Visual information" refers to image data and video data such as a user's facial expressions and gestures.

[1720] This invention is a system for supporting users' daily lives, specifically a system that records user behavioral data and suggests next actions based on that data. Furthermore, it is characterized by combining an emotion engine that recognizes the user's emotions and suggests actions based on the user's emotions. The system operates through the user's terminal, a server, the emotion engine, and the interactions between them.

[1721] Data collection and storage

[1722] Terminal

[1723] The device mainly refers to devices such as smartphones and tablets. When a user adds an event to a calendar app using such a device, the information is automatically captured. For example, if a user enters "Jogging at 08:00 on 2023-09-01" in the calendar, this information is detected by the device.

[1724] server

[1725] The collected data is sent from the device to a server, which stores the received information in a database and manages data for each user, including specific dates, times, and details of events.

[1726] Data analysis

[1727] server

[1728] The server runs an algorithm to analyze the stored data. For example, a machine learning algorithm is used to extract the user's behavioral patterns. This analysis may reveal that the user has a habit of performing a certain activity at a specific time each day (for example, jogging at 8:00 AM every morning).

[1729] Generate action suggestions

[1730] server

[1731] Based on the analysis results, the server will suggest the next action, for example, generating specific instructions such as "Next action is jogging." This suggestion is based on the user's past behavioral patterns.

[1732] Emotion recognition and behavioral suggestion adjustment

[1733] Emotion Engine

[1734] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and voice to recognize their emotions. The results of this recognition are sent to the server and used to adjust the next action suggestion. For example, if the user is feeling stressed, the engine will suggest actions to help them relax.

[1735] Presenting the proposal

[1736] Terminal

[1737] The suggestions are sent to the device and displayed on the user's smartphone or other device. When the user makes a voice request, "Tell me what to do next," the device immediately displays the suggestions received from the server.

[1738] Specific examples

[1739] For example, if a user adds a meeting to their calendar for 2:00 PM, the sequence of actions is as follows:

[1740] User: Opens the calendar app on their smartphone and enters "2023-09-01 14:00 Meeting."

[1741] Device: Detects schedules and sends information to the server.

[1742] Server: Receives the schedule information and saves it in the database. "2023-09-01 14:00 Meeting" is recorded as data for each user.

[1743] Server: Periodically analyzes stored data to learn patterns of users performing work-related tasks around 2 p.m.

[1744] User: At 1:45 PM, voice requests "Tell me what to do next."

[1745] Terminal: Sends a request to the server, receives the suggestion, and notifies the user, displaying "Next action is a meeting."

[1746] Emotion Engine: If a user is feeling stressed during a meeting, the system will provide additional advice such as "Take a deep breath to relax a bit." This analysis is performed by the emotion engine, which analyzes the user's facial expressions and voice.

[1747] Prompt Sentence Examples

[1748] Below is an example of a prompt sentence to input to the generative AI model.

[1749] Please explain the steps involved in the system that suggests actions based on the user's emotions.

[1750] 1. The user enters an event into the calendar app on their smartphone.

[1751] 2. The device detects this appointment and sends it to the server.

[1752] 3. The server saves the appointment information in a database.

[1753] 4. The server analyzes the stored data and learns user behavior patterns.

[1754] 5. The server suggests the next action.

[1755] 6. The emotion engine recognizes the user's emotions and adjusts suggested actions if necessary.

[1756] 7. The device notifies the user of the suggested action.

[1757] An example would be "When a user schedules a meeting for 2 PM."

[1758] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1759] Step 1:

[1760] User

[1761] The user opens the calendar app on their smartphone and enters an appointment, for example, "2023-09-01 14:00 Meeting." This entry becomes the basis for future processing.

[1762] Input: Events entered in the calendar (text format)

[1763] Output: Capture of schedule information (text format)

[1764] What happens: A user manually enters an event into a calendar app. This information is stored on the device as text data.

[1765] Step 2:

[1766] Terminal

[1767] The device captures the schedule information entered by the user and automatically sends it to the server, where the date, time, and event details are obtained.

[1768] Input: Schedule information entered by the user (text format)

[1769] Output: Schedule information sent to the server (text format)

[1770] Specific operation: The device detects the entered schedule information in real time and sends that information to the server's API endpoint.

[1771] Step 3:

[1772] server

[1773] The server stores the schedule information received from the device in a database, which is linked to the user ID and date and time information.

[1774] Input: Schedule information sent from the device (text format)

[1775] Output: Schedule information stored in the database (database records)

[1776] Specific operation: When the server receives the event information, it creates a new record in the database and saves it. The saved information includes the user ID, date and time, and event details.

[1777] Step 4:

[1778] server

[1779] The server runs machine learning algorithms to analyze the stored schedule information, thereby extracting user behavior patterns.

[1780] Input: User behavior data stored in a database (database records)

[1781] Output: Extracted behavioral patterns (model data)

[1782] How it works: The server periodically reads the behavioral data in the database and uses machine learning algorithms to analyze and extract behavioral patterns, such as repeating behavior during specific times of the day.

[1783] Step 5:

[1784] server

[1785] Based on the results of the data analysis, an algorithm is run to suggest next steps, which are generated based on past behavioral patterns.

[1786] Input: Behavioral pattern (model data)

[1787] Output: Next action suggestions (text format)

[1788] Specific operation: Based on the extracted behavioral patterns, the server uses an algorithm to determine the next action the user should take and generates a suggested text data. For example, a suggestion such as "The next action is jogging" is created.

[1789] Step 6:

[1790] Emotion Engine

[1791] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and voice to recognize their emotions, and adjusts the next action suggestions accordingly.

[1792] Input: User's facial expressions and voice data (multimedia format)

[1793] Output: Recognized emotion data (text and numeric format)

[1794] Specific operation: The emotion engine analyzes the user's facial expressions captured by the camera and the voice data collected by the microphone, and extracts the user's emotional state as text and numerical data, which is sent to the server to adjust the next action suggestion.

[1795] Step 7:

[1796] server

[1797] The server adjusts the suggested actions based on the emotion data sent from the emotion engine. If the user is feeling stressed, the server will suggest additional actions to help them relax.

[1798] Input: Emotion data (text and numerical format), next action suggestions (text format)

[1799] Output: Adjusted action proposals (text format)

[1800] Specific actions: The server analyzes the emotion data and modifies the original action suggestions as needed, for example, if the user is feeling stressed, it may include specific advice such as "take a deep breath to relax a bit."

[1801] Step 8:

[1802] Terminal

[1803] The adjusted action suggestions are sent to the device and notified to the user. The suggestions are also displayed when the user makes a voice request such as "Tell me what to do next."

[1804] Input: Adjusted action proposal (text format)

[1805] Output: Action suggestions displayed to the user (in text format)

[1806] Specific operation: The device receives the adjusted action suggestions from the server and presents them to the user via notifications or voice assistants. The user can then confirm the suggested action and smoothly carry out the next action.

[1807] The above is a description of the specific processing steps of this system and their detailed operation.

[1808] (Application example 2)

[1809] 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."

[1810] Conventional food delivery services only provide users with meal options, but do not offer personalized suggestions based on their emotional state or behavioral patterns. As a result, users find it difficult to select the meal that best suits their current emotional state and situation, and are unable to receive appropriate suggestions for health management or stress relief. This leaves users with insufficient support for improving their quality of life and enjoying a comfortable daily life.

[1811] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1812] In this invention, the server includes means for collecting user behavioral data, emotion engine means for analyzing the emotional state, and means for adjusting the next action based on the emotional state, thereby optimizing the next action based on the user's emotional state and behavioral patterns, and making it possible to suggest meals that have a relaxing effect or that suit the user's preferences as needed.

[1813] "Behavioral data" is information relating to the user's daily activities, tasks, schedules, and the like.

[1814] An "emotion engine" is a software or hardware mechanism for analyzing a user's emotional state.

[1815] "Next Action" refers to the next action or task that the user should perform.

[1816] A "behavioral pattern" is a tendency or regularity of behavior extracted from a user's past behavioral data.

[1817] The "adjustment means" is a means for optimizing the next action suggestion based on the emotional state analyzed by the emotion engine.

[1818] A "suggested action" is an instruction for next action that the system presents to the user based on the analyzed behavioral data and emotional state.

[1819] "Visual information" refers to information that is visually recognized, such as the user's facial expressions and actions.

[1820] "Emotional information" is data relating to the user's emotional state, and is information obtained from voice tone, facial expressions, and the like.

[1821] "Means of collection" refers to devices and software for capturing user behavioral data and emotional information.

[1822] The "means for presenting suggestions" is a means for displaying or notifying the user of suggestions for the next action or meal.

[1823] This invention is directed to a smartphone application for food delivery services. The system collects and analyzes user behavioral and emotional data to suggest optimal meals to users.

[1824] System configuration

[1825] Hardware and Software

[1826] The system uses the following hardware and software:

[1827] Smartphone: Used to provide the user interface and collect data.

[1828] Emotion Engine: Software that analyzes the user's emotional state. In this case, we use the TextBlob library.

[1829] Server: A server for storing and analyzing user behavioral and emotional data.

[1830] Food Delivery API: An external API that processes food orders.

[1831] Data collection and storage

[1832] Smartphone: The user uses a calendar app to enter activity data (e.g., a jogging schedule), and this information is sent from the smartphone to the server.

[1833] Server: The server receives the data and stores it in a database, including the date and time of the activity and detailed information.

[1834] Emotion engine: Collects and analyzes emotional data from user text and voice input.

[1835] Data analysis

[1836] Server: Runs algorithms to analyze the accumulated behavioral and emotional data. Machine learning algorithms are used here to extract user behavior patterns.

[1837] Emotion Engine: Uses the TextBlob library to parse the user's input text (emotion data) and generate an emotion score.

[1838] Generating behavioral and dietary suggestions

[1839] Server: Based on the analysis results, the server will suggest the next action and the best meal. For example, if the user is feeling stressed, it will suggest a meal that will have a relaxing effect.

[1840] Smartphone: Suggested activities and meals are presented to the user via their smartphone. When the user requests the next action by voice, the server immediately notifies them of the suggestion.

[1841] Specific examples

[1842] For example, if a user enters "2023-09-01 14:00 meeting" into a calendar app, the system will behave as follows:

[1843] Original invention in action:

[1844] User: Opens the calendar app on their smartphone and enters "2023-09-01 14:00 Meeting."

[1845] Device: Detects schedules and sends information to the server.

[1846] Server: Receives the schedule information and stores it in a database.

[1847] Server: Periodically analyzes stored data to learn patterns of users performing work-related tasks around 2 p.m.

[1848] User: At 1:45 PM, voice requests "Tell me what to do next."

[1849] Terminal: Sends a request to the server, receives the suggestion, and notifies the user, displaying "Next action is a meeting."

[1850] Emotion engine: If a user is feeling stressed during a meeting, the system will provide additional advice such as "take a deep breath to relax a bit."

[1851] Examples of application improvements:

[1852] User: A user who feels stressed types "I'm feeling stressed right now" into a smartphone app.

[1853] Emotion engine: The analyze_emotion function generates a negative emotion score from "stress."

[1854] Suggestion: The app suggests to the user, "Why not order a hot soup to help you relax?"

[1855] Ordering: If the user accepts the suggestion, the app will automatically place the soup order.

[1856] Example prompt sentence:

[1857] "If a user types 'I am feeling stressed,' generate a negative emotion score and suggest foods that will help them relax."

[1858] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1859] Step 1:

[1860] User behavioral data entry

[1861] A user uses a calendar application on their smartphone to enter action data such as "2023-09-01 14:00 Meeting."

[1862] Input: Behavioral data entered by the user into their smartphone (date, time, and content)

[1863] Output: Behavioral data is stored in an application on the smartphone.

[1864] Step 2:

[1865] Transmission of behavioral data by the device

[1866] The device sends the detected behavioral data to the server, where the behavioral data is converted into an appropriate format and sent to the server via the network.

[1867] Input: Behavioral data stored on the smartphone

[1868] Output: Behavioral data is sent to and received by the server.

[1869] Step 3:

[1870] Data storage by server

[1871] The server stores the received behavioral data in a database, which stores the date, time, and event details.

[1872] Input: Behavioral data sent to the server

[1873] Output: The behavioral data is stored in a database on the server.

[1874] Step 4:

[1875] Emotional data collection and analysis using an emotion engine

[1876] When a user types "I'm feeling stressed right now" into their smartphone, the emotion engine analyzes the input and generates an emotion score. In this example, the TextBlob library is used.

[1877] Input: Emotion data entered by the user (e.g., feeling stressed)

[1878] Output: A sentiment score (e.g., a negative sentiment score) is generated.

[1879] Step 5:

[1880] Server analysis of behavioral patterns

[1881] The server analyzes the accumulated behavioral and emotional data and uses machine learning algorithms to extract behavioral patterns.

[1882] Input: Behavioral data and emotion scores stored in a database

[1883] Output: Analysis of user behavior patterns

[1884] Step 6:

[1885] Server-generated next action and meal suggestions

[1886] The server then suggests the next action or meal based on the analysis results. For example, it suggests a meal with a relaxing effect (e.g., soup) based on the emotion score.

[1887] Input: Behavioral pattern analysis results and sentiment score

[1888] Output: Suggested behavior and dietary recommendations

[1889] Step 7:

[1890] Proposal presentation by device

[1891] The device displays and notifies the user of the suggestions received from the server. If the user requests the next action by voice, the suggestions are displayed immediately.

[1892] Input: Proposal sent from the server

[1893] Output: Display and notification of suggestions on smartphone

[1894] Step 8:

[1895] User review and order

[1896] If the user accepts the suggested meal, the device sends the order to the food delivery API. If the order is successful, a confirmation message is displayed to the user.

[1897] Input: The result of the user reviewing the suggestion (e.g., ordering a meal)

[1898] Output: Places an order to the food delivery API and displays a confirmation message

[1899] Example of using a generative AI model and prompt:

[1900] "If a user types 'I am feeling stressed,' generate a negative emotion score and suggest foods that will help them relax."

[1901] 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.

[1902] 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.

[1903] 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.

[1904] 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.

[1905] 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.

[1906] 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.

[1907] 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).

[1908] 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.

[1909] 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."

[1910] 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.

[1911] 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).

[1912] 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.

[1913] 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.

[1914] 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.

[1915] 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.

[1916] 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.

[1917] 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.

[1918] 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.

[1919] 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.

[1920] 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.

[1921] 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.

[1922] The following is further disclosed regarding the above embodiment.

[1923] (Claim 1)

[1924] a means for collecting user behavior data;

[1925] a means for storing the collected behavioral data;

[1926] A means for analyzing the accumulated behavioral data and extracting behavioral patterns;

[1927] A means for suggesting the next action based on the extracted behavioral pattern;

[1928] means for presenting suggested actions to a user;

[1929] A system including:

[1930] (Claim 2)

[1931] 10. The system of claim 1, wherein the system presents suggested actions in response to a user's voice input.

[1932] (Claim 3)

[1933] 10. The system of claim 1, further comprising means for collecting and utilizing visual information in addition to behavioral data for analysis.

[1934] "Example 1"

[1935] (Claim 1)

[1936] A means for collecting user behavior information;

[1937] a means for storing the collected behavioral information;

[1938] A means for analyzing the accumulated behavioral information and extracting behavioral patterns;

[1939] A means for suggesting the next action based on the extracted behavioral pattern;

[1940] means for presenting suggested actions to a user;

[1941] A means for detecting information from the terminal and transferring it to a server;

[1942] a means for analyzing the behavioral patterns using a machine learning algorithm on the server and generating a next action;

[1943] means for converting the proposed action into a prompt sentence format and transmitting the same to the terminal;

[1944] A system including:

[1945] (Claim 2)

[1946] 10. The system of claim 1, wherein the system presents suggested actions in response to a user's voice input.

[1947] (Claim 3)

[1948] 10. The system of claim 1, further comprising means for collecting and analyzing visual information in addition to behavioral information.

[1949] "Application Example 1"

[1950] (Claim 1)

[1951] a means for collecting user behavior data;

[1952] a means for storing the collected behavioral data;

[1953] A means for analyzing the accumulated behavioral data and extracting behavioral patterns;

[1954] A means for suggesting the next action based on the extracted behavioral pattern;

[1955] means for presenting suggested actions to a user;

[1956] means for transmitting a command to a device that manipulates the object based on the proposed action;

[1957] A means for the device receiving the command to execute the next action;

[1958] A system including:

[1959] (Claim 2)

[1960] 10. The system of claim 1, wherein the system presents suggested actions in response to a user's voice input.

[1961] (Claim 3)

[1962] 10. The system of claim 1, further comprising means for collecting and utilizing visual information in addition to behavioral data for analysis.

[1963] "Example 2: Combining Emotion Engines"

[1964] (Claim 1)

[1965] a means for collecting user behavior data;

[1966] a means for storing the collected behavioral data;

[1967] A means for analyzing the accumulated behavioral data and extracting behavioral patterns;

[1968] A means for suggesting the next action based on the extracted behavioral pattern;

[1969] means for presenting suggested actions to a user;

[1970] a means for recognizing the user's emotions and adjusting the next action suggestions;

[1971] A system including:

[1972] (Claim 2)

[1973] 10. The system of claim 1, wherein the system presents suggested actions in response to a user's voice input.

[1974] (Claim 3)

[1975] 10. The system of claim 1, further comprising means for collecting and utilizing visual information in addition to behavioral data for analysis.

[1976] "Application example 2 when combining emotion engines"

[1977] (Claim 1)

[1978] a means for collecting user behavior data;

[1979] a means for storing the collected behavioral data;

[1980] A means for analyzing the accumulated behavioral data and extracting behavioral patterns;

[1981] A means for suggesting the next action based on the extracted behavioral pattern;

[1982] emotion engine means for analyzing the user's emotional state;

[1983] a means of adjusting subsequent actions based on emotional state;

[1984] means for presenting the adjusted suggested actions to the user;

[1985] A system including:

[1986] (Claim 2)

[1987] 10. The system of claim 1, wherein the system presents suggested actions in response to a user's voice input.

[1988] (Claim 3)

[1989] 10. The system of claim 1, further comprising means for collecting and utilizing visual and emotional information in addition to behavioral data for analysis. [Explanation of symbols]

[1990] 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 collecting user behavior data; a means for storing the collected behavioral data; A means for analyzing the accumulated behavioral data and extracting behavioral patterns; A means for suggesting the next action based on the extracted behavioral pattern; means for presenting suggested actions to a user; A system including:

2. 10. The system of claim 1, wherein the system presents suggested actions in response to a user's voice input.

3. 10. The system of claim 1, further comprising means for collecting and analyzing visual information in addition to behavioral data.

Images