system

Abstract

We provide the system. [Solution] A means of analyzing user behavior using a generative artificial intelligence model and notifying users of the importance of everyday tasks, A means of providing voice notifications to users based on the analysis results, A means for collecting user feedback and transmitting data to a communication device to update the analysis results, A system that includes this.

Description

Technical Field

[0005]

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is a need to reduce inefficiencies and indirect impacts on the surroundings caused by individuals postponing tasks that should be performed daily. However, users often find it difficult to recognize the importance of these tasks, and there is a problem that delays become the norm because there is no mechanism to receive notifications at appropriate times. The purpose of this invention is to effectively solve these problems by making the user clearly recognize the importance of tasks and prompting actions in a timely manner.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides a system that analyzes user behavior using a generative artificial intelligence model and notifies the user of the importance of a task based on the results. Specifically, a device equipped with a generative AI model analyzes user behavior in real time and makes voice notifications based on the analysis results, thereby making the user aware of the importance of the current task. Furthermore, by collecting feedback from the user and sending the data to a server, the generative AI model continuously optimizes itself according to the activity status. Through this mechanism, the device manages the user's behavior and promotes efficient task execution.

[0006] A "generative artificial intelligence model" is a machine learning algorithm that analyzes user behavior and habits to generate appropriate feedback and notifications.

[0007] A "user" is an individual who receives notifications and feedback from a device while performing everyday tasks.

[0008] "Behavioral analysis" is the process of analyzing a user's actions and habits to identify patterns and trends.

[0009] "Voice notification" is a method of using voice to provide information to a user when a device is using voice.

[0010] "Feedback collection" is the process by which users input information into their devices regarding task completion status and their responses to device notifications.

[0011] A "server" is a central system that stores user behavior data and performs the calculations necessary to update the generated AI model.

[0012] A "communication device" is a device used to transmit and receive data between devices or between a device and a server. [Brief explanation of the drawing]

[0013] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

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

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

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

[0019] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), and the like.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

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

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

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

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

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0034] This invention is a system that uses a generative artificial intelligence model to analyze the importance of multiple tasks that users should perform on a daily basis in real time and provide appropriate feedback. The operation of the entire system is described below from the perspectives of the server, terminal, and user.

[0035] Server Role

[0036] The server first stores user behavior data collected periodically from the device. This includes information about the frequency and timing of task execution. Based on this data, the server maintains the generated AI model and trains it to learn new behavior patterns. After a personalized model is generated for each user, the server sends this updated model to the device.

[0037] Terminal role

[0038] The device receives an AI model sent from the server and monitors the user's current behavior in real time. By analyzing behavioral patterns, if the device determines that the importance of a particular task has increased, it uses its voice output function to notify the user of this information. For example, the device might give a timely notification such as, "It's time to start preparing the meal," prompting the user to take action at the appropriate time.

[0039] User roles

[0040] Users recognize the importance of a task by receiving voice notifications from their device and choose appropriate actions. Upon completing a task, the user inputs feedback on its completion status into their device. This feedback is sent to a server and used as data to further improve the accuracy and usefulness of the AI ​​model.

[0041] Specific example

[0042] Specifically, suppose a user tends to neglect their pre-work preparations every Monday. This system recognizes this pattern and sends a voice notification on Monday morning saying, "Please start getting ready." Upon receiving this notification, the user can proceed with their preparations as planned and prevent unnecessary delays.

[0043] This embodiment of the invention aims to improve the quality of life by streamlining the management of users' daily tasks and enabling them to work together, with the server, terminal, and user each fulfilling their respective roles.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server receives user behavior data from the device. This data includes task start and completion times, frequency, etc. The server analyzes this data to discover new behavioral patterns.

[0047] Step 2:

[0048] The server updates the generated AI model based on the analyzed data. This model is customized for each individual, reflecting the specific behavioral habits of each user. The updated model is then sent to the device.

[0049] Step 3:

[0050] The device receives an updated generative AI model from the server. The device then uses this model to monitor the user's real-time behavior. The monitoring focuses on tasks that should be performed on a daily basis.

[0051] Step 4:

[0052] Based on the information obtained from monitoring results, the device provides users with voice notifications about the importance of tasks. For example, as the time for a scheduled task approaches, the device will remind the user with a message such as, "It's time for that task now."

[0053] Step 5:

[0054] The user receives an audio notification from their device and performs the task. After completing the task, the user enters the task completion status on their device and sends feedback.

[0055] Step 6:

[0056] The device sends user feedback to the server, which is then prepared for use in the next model update. This improves the accuracy of the AI ​​model and enables more effective task management.

[0057] (Example 1)

[0058] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0059] In modern society, users face numerous challenges and tasks on a daily basis, requiring them to appropriately prioritize and efficiently manage them. However, conventional systems have limitations in terms of providing immediate and personalized notifications based on user behavior, and in thoroughly analyzing behavioral patterns to improve future interactions. Therefore, there is a need for a system that is more highly personalized and enables efficient task management.

[0060] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0061] In this invention, the server includes means for updating the artificial intelligence generation technology using behavioral information collected from the user's terminal and analyzing new behavioral trends; means for using an output device to notify the user of high-priority tasks by voice based on the analysis results; and means for collecting responses from the user regarding the task completion status and passing information to a data transmission device to improve the model in accordance with the analysis results. This enables real-time task management and notification tailored to the behavioral patterns of individual users.

[0062] "User" refers to an individual or organization that uses this system, provides behavioral data, and takes action based on the notifications it receives.

[0063] A "terminal" refers to a device that a user directly operates, which receives data from a server and monitors the user's actions.

[0064] "Behavioral information" refers to data about the timing, frequency, and time required for tasks that users perform in their daily lives.

[0065] "Generative artificial intelligence technology" refers to a technology that uses applied programs to analyze user behavior patterns and generate and update models that are useful for notifying users of future tasks.

[0066] "Behavioral tendencies" refer to patterns or trends extracted from a user's past behavioral information and are used to predict future behavior.

[0067] "High-priority issues" are tasks that are deemed particularly important based on user behavior, and are therefore prioritized for notification by the system.

[0068] An "output device" refers to a device that transmits notifications from the system to the user via voice or visual means.

[0069] "Response" refers to the information that users input into their devices upon completing a task, and this data is used to improve the AI ​​model.

[0070] A "data transmission device" refers to a device that sends responses collected from a terminal to a server for analysis and model improvement.

[0071] This invention is a system that uses a generative AI model to streamline task management based on user behavior data. The system is operated through the interaction of a server, a terminal, and a user.

[0072] Server Role

[0073] The server collects user behavior data transmitted from the terminal and stores it in a database. This data includes task timing, frequency, and duration. The server runs a generative AI model using Python and TENSORFLOW® and updates the model based on the collected data. This allows the model to learn new behavioral trends and prepares to provide personalized task notifications to users.

[0074] Terminal role

[0075] The device receives updated AI models from the server and monitors the user's current behavior in real time. The device is equipped with a voice output function using the Google® Text-to-Speech API and provides voice notifications to the user based on the AI ​​model's analysis results. For example, the device can provide timely notifications such as "Now is the time to do XX," prompting the user to take appropriate action.

[0076] User roles

[0077] Users receive voice notifications from their devices and perform their daily tasks. Upon completing a task, they input feedback on its completion status into their device. This feedback is sent to a server and used to further improve the accuracy of the AI ​​model.

[0078] Specific example

[0079] As a concrete example, suppose a user has a habit of cleaning on weekends. The system learns this pattern and helps them perform the task efficiently by notifying them at the appropriate time that "it's time to start cleaning."

[0080] Example of a prompt

[0081] An example of a prompt to input into a generative AI model is, "Based on user behavior pattern data, accurately predict the next priority task and calculate the optimal notification time." Using this prompt, the model can provide better notifications.

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The server collects user behavior information from the terminal and stores it in a database. The input consists of information about the timing and frequency of the user's actions, which is sent from the terminal to the server. The server receives this information and stores it in the database. Specifically, the data is securely transferred via the HTTPS protocol and stored in a MySQL® database.

[0085] Step 2:

[0086] The server runs a generative AI model based on collected behavioral data to analyze new behavioral trends. The input is behavioral data stored in a database, which the server retrieves and applies to the AI ​​model. Python and TensorFlow are used to analyze the data and extract new behavioral patterns. The output is a personalized behavioral trend model.

[0087] Step 3:

[0088] The server sends this behavioral tendency model to the terminal. The input is the previously generated AI model, which the server encodes and sends to the terminal. The output is the updated AI model that the terminal receives. Specifically, the server packages the AI ​​model in JSON format and sends it to the terminal.

[0089] Step 4:

[0090] The device monitors user behavior in real time using the received generated AI model. Input consists of the AI ​​model received from the server and the user's current behavior data. The device references this data and performs data analysis according to the AI ​​model's instructions. As output, notification information is generated when a specific task is deemed important.

[0091] Step 5:

[0092] The device notifies the user via voice about high-priority tasks. The input is the important task identified by the AI ​​model, which the device converts into speech using the Google Text-to-Speech API. The output is the voice notification that the user hears. Specifically, the device calls a speech synthesis API to generate a specific message such as, "It's time to start [task]."

[0093] Step 6:

[0094] The user performs a task based on a voice notification and provides feedback on its completion status to the device. The input is the notified task and its execution result, which the user evaluates and inputs as feedback data to the device. The output is the user's feedback information sent from the device to the server.

[0095] Step 7:

[0096] The server receives feedback information sent from the terminal and uses it to improve the AI ​​model. The input is user feedback information, which the server uses to retrain the AI ​​model. The output is the feedback-applied model that will be reflected in the next AI model update. Specifically, the server analyzes the feedback data and incorporates it into the AI ​​model's learning process.

[0097] (Application Example 1)

[0098] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0099] With conventional technology, it has been difficult to analyze customer purchasing behavior in real time and effectively optimize sales promotion activities in stores. In particular, there is a need to understand customer movements and purchasing intentions and provide sales promotion information that matches them at the appropriate time, but there is currently a lack of concrete means to do so.

[0100] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0101] In this invention, the server includes means for analyzing user behavior using a generative artificial intelligence model and notifying the user of the importance of daily tasks; means for providing voice notifications to the user based on the analysis results; means for collecting user feedback and transmitting data to a communication device to update the analysis results; means for analyzing user purchasing behavior and providing sales promotion information to increase purchasing intent; and means for monitoring customer movements in the store in real time and notifying sales staff. This enables the optimization of sales promotion activities and increases sales in physical stores.

[0102] A "generative artificial intelligence model" is an artificial intelligence program built to analyze user behavior data and make predictions and suggestions tailored to specific purposes.

[0103] "User behavior" refers to a collection of data about human movement and decision-making in daily life and specific environments.

[0104] "Purchasing behavior" refers to the series of actions and decision-making processes that consumers take from selecting a product or service to making a purchase.

[0105] "Sales promotion information" refers to marketing data such as special offers, discounts, and campaigns provided to consumers to increase their desire to purchase products.

[0106] "Real-time monitoring" means instantly confirming and understanding events and conditions that are actually happening in real time.

[0107] "Sales staff" refers to the human resources responsible for customer service, product recommendations, and sales activities within a store.

[0108] The following system is constructed as an embodiment of this invention.

[0109] The server accumulates user behavior data and purchasing behavior data, and analyzes it using generative artificial intelligence models. Leveraging machine learning platforms like TensorFlow, the server evaluates user behavior patterns and purchasing intent in real time, generating personalized sales promotion information. The generated information is immediately sent to the terminal using real-time processing technologies such as Node.js.

[0110] The terminal is integrated into wearable devices such as smart glasses and notifies sales staff in real time of sales promotion information received from a server. The terminal has a simple user interface and provides information through voice feedback and visual displays, helping staff to make appropriate approaches to customers.

[0111] Users respond to customers based on their movements and reactions within the store, following prompts. These prompts might be in the format of, for example, "Analyze the customer's movements within the store and propose sales promotions to increase their purchase intent." This allows sales staff to make suggestions to customers at the optimal time, streamlining store operations.

[0112] For example, if a user shows high interest in a new product, the terminal will notify staff of promotional information the moment the user touches the product. Based on this information, staff can then inform the customer, for instance, "This product is currently on sale for 20% off." This can further stimulate customer purchasing intent and increase store sales.

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] The server receives customer behavior data acquired from sensors within the store. This data includes information such as when customers touch products and their movement patterns within the store. The server preprocesses this data and formats it as input data for the generated AI model.

[0116] Step 2:

[0117] The server inputs the formatted behavioral data into a generating AI model to predict the user's purchasing behavior. This calculation quantifies the likelihood that a user is highly likely to purchase a particular product. The resulting predictions are used to create sales promotion information.

[0118] Step 3:

[0119] The server generates sales promotion information based on predicted values. This information includes discounts and campaign details for specific products. This information is then formatted as notification data for sales staff.

[0120] Step 4:

[0121] The terminal receives sales promotion information transmitted from the server in real time. The terminal then notifies sales staff of this information audibly or visually through a wearable device such as smart glasses.

[0122] Step 5:

[0123] Users can provide appropriate sales promotions to customers based on notifications from their devices. Specifically, they verbally communicate special offers for products that customers have shown interest in. By following these prompts, users can provide timely and effective customer service.

[0124] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0125] This invention is a system that combines a generative artificial intelligence model and an emotion engine to effectively notify users of the importance of their daily tasks and facilitate their completion. The operation of the system is described below from the perspectives of the server, terminal, and user.

[0126] Server Role

[0127] The server first stores user behavioral and emotional data sent from the terminal. Behavioral data includes task frequency, start time, and completion time, while emotional data includes information indicating the user's emotional state. The server analyzes this data using a generative artificial intelligence model to extract behavioral and emotional patterns. Based on the analysis results, the server updates the generative AI model and the emotional model, and sends customized information to the terminal for each user.

[0128] Terminal role

[0129] The device receives a generative AI model and an emotion model provided by the server. Based on these models, the device monitors the user's real-time behavior and emotional state. The device determines how the user's emotional state affects task performance and provides voice notifications at the optimal time. For example, if the user is feeling stressed, the device may adjust the timing and use a gentler tone of voice when notifying the user.

[0130] User roles

[0131] The user receives an audio notification from their device and begins working on the notified task. Upon completing the task, the user inputs the result as feedback into their device. They can also report their emotional state at that time. This feedback is sent to a server and used to further improve the AI ​​model.

[0132] Specific example

[0133] Specifically, the system identifies a pattern where users tend to procrastinate on household tasks and experience stress on weekday evenings. This system aims to help users tackle tasks more effectively by providing thoughtful voice notifications on weekday evenings, such as "Relax and start your chores slowly."

[0134] Embodiments of the present invention enable task management that takes emotions into consideration, thereby improving the user's efficiency and quality of life.

[0135] The following describes the processing flow.

[0136] Step 1:

[0137] The server receives user behavioral and emotional data transmitted from the terminal. This behavioral data includes task execution time, frequency, and degree of completion, while the emotional data includes emotional states detected from the user's facial expressions and tone of voice. The server securely stores this data.

[0138] Step 2:

[0139] The server updates the generative AI model and the emotion model using the accumulated data. The generative AI model works to capture the characteristics of the user's behavioral patterns, and the emotion model analyzes the impact of the user's emotional state on their ability to perform tasks. The updated models are then ready to be sent to the terminal to provide the next notification.

[0140] Step 3:

[0141] The device receives AI models and emotion models sent from the server. Using these models, the device begins analyzing the user's daily behavior and emotions in real time. Based on the analysis results, it determines the optimal timing and content of task notifications.

[0142] Step 4:

[0143] The device uses the analysis results to create voice notifications tailored to the user's emotional state. For example, if it detects that the user is feeling stressed, it might issue a gentle notification such as, "Let's take a short break before starting the task."

[0144] Step 5:

[0145] The user receives voice notifications from the device and performs the instructed task. During and after task execution, they input their current emotional state and task progress as feedback to the device.

[0146] Step 6:

[0147] The device sends user feedback to the server. This feedback includes information about the user's task completion rate and changes in their emotions. The server uses this feedback to inform future model updates and continuously improve the system.

[0148] (Example 2)

[0149] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0150] In modern times, it is crucial to respond quickly and accurately to the everyday challenges faced by individual users and to promote efficient action. However, it is difficult to effectively consider the user's emotional state and provide notifications at the optimal time, which can result in difficulties in efficiently completing tasks. This invention aims to solve these problems and improve the efficiency of users' actions and their quality of life through emotionally sensitive notifications.

[0151] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0152] In this invention, the server includes means for analyzing the behavioral and emotional information of individual users using a generative artificial intelligence model to extract novel behavioral and emotional patterns, means for providing considerate voice notifications to users based on the extracted patterns, and means for collecting feedback from users regarding their achievement status and emotions and transmitting information to a service provider to improve the accuracy of the model. This enables accurate understanding of the user's emotional state and notification at the optimal timing.

[0153] A "generative artificial intelligence model" is an algorithm that analyzes user behavior and emotion data to extract individual behavior and emotion patterns and generate information and notifications that are optimal for the user.

[0154] "Behavioral information" refers to data such as the frequency, start time, and end time of tasks that users perform on a daily basis, and forms the basis for analyzing user behavior patterns.

[0155] "Emotional information" refers to data such as the stress and satisfaction a user experiences while performing a task. This information forms the basis for understanding the user's emotional state and effectively adjusting notification content.

[0156] "Behavioral patterns" refer to specific tendencies that indicate how users tend to perform tasks, obtained by analyzing collected behavioral information.

[0157] An "emotional pattern" is a specific tendency that indicates what emotional state a user is most often in, obtained by analyzing collected emotional information.

[0158] "Thoughtful notifications" are notifications delivered at the optimal time and with the most relevant content, based on the user's behavioral and emotional patterns, enabling them to manage tasks more efficiently.

[0159] "Feedback" refers to information about the user's achievement and feelings upon completing a task, which is used to improve the accuracy of the AI ​​model.

[0160] "Providing equipment" refers to the entirety of hardware and software, including servers and user terminals, used for sending and receiving data and providing analysis results and notifications.

[0161] This invention is a system for optimizing task management in a user's daily life, while taking their emotions into consideration. Specific embodiments of this system are described below from the perspectives of the server, terminal, and user.

[0162] Server operation

[0163] The server is primarily responsible for data storage and analysis. It collects behavioral and emotional information transmitted from users' terminals and uses a database to store it. For example, it manages each user's data using a database management system such as SQL. Next, the collected data is analyzed using a generative artificial intelligence model. Programming languages ​​and libraries such as Python and TensorFlow are used here to extract behavioral and emotional patterns for each user. Based on the analysis results, the generative AI model and emotional model are updated to keep them up-to-date.

[0164] Terminal operation

[0165] The device receives a generative AI model and an emotion model provided by the server. Sensors are used on the device to monitor the user's real-time behavior and emotional state. A voice output device is used to notify the user at the optimal time. For example, if the user is calm, a normal alert is issued, and if stress is detected, the tone of voice is softened.

[0166] User roles

[0167] The user receives an audio notification from their device and begins working on the notified task. Upon completion of the task, feedback on the achievement status and emotional state is sent back to the device. This information is then sent back to the server and used to further improve the AI ​​model.

[0168] Specific example

[0169] For example, if analysis reveals that users tend to feel stressed on weekday evenings, this system can provide gentle voice notifications such as, "Let's make the most of your relaxation time tonight," thereby creating an environment where users can focus on their tasks while reducing their stress.

[0170] Example of a prompt

[0171] "Generate gentle, relaxing notifications during the times when users are most likely to experience stress."

[0172] A specific embodiment of this invention enables task management that takes into account the user's emotional state, thereby improving behavioral efficiency and quality of life.

[0173] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0174] Step 1:

[0175] The server collects behavioral and emotional information transmitted from the user's device. It receives user operation history and sensor data as input and stores it in an SQL database. Specifically, it prepares for analysis of task start and end times, user heart rate, and facial expression data.

[0176] Step 2:

[0177] The server analyzes the collected behavioral and emotional information. A generative artificial intelligence model is used for this analysis. The input is the data collected in step 1, and the output is behavioral and emotional patterns. Specifically, Python and TensorFlow are used to analyze data trends and incorporate them into the model.

[0178] Step 3:

[0179] The server updates the generated AI model and emotion model based on the analysis results. The input is the pattern calculated in step 2, which is used to adjust and optimize the model. The output is the latest model parameter set. Updating the model improves the accuracy of user-specific notifications.

[0180] Step 4:

[0181] The server sends the updated generative AI model and sentiment model to the user's device. The device receives this and prepares to monitor real-time behavior and sentiment. Specifically, it instantiates the model on the device and begins preparing notifications.

[0182] Step 5:

[0183] The device monitors the user's behavior and emotions in real time and provides voice notifications at the optimal time. Inputs include real-time data from sensors and models transmitted from a server, which are used to generate notifications. The output is a thoughtful voice notification delivered to the user. For example, if a stressed state is detected, the voice tone is adjusted based on the data.

[0184] Step 6:

[0185] After completing a task, the user enters feedback into the terminal. This feedback includes information about the task's completion status and the user's feelings, and is sent to the server via the terminal. The server receives this feedback and uses it to further optimize the model. The output is an improved model.

[0186] This step enables task management that takes user emotions into consideration, leading to improved efficiency and quality of life.

[0187] (Application Example 2)

[0188] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0189] In modern work environments, performing tasks without considering the emotional state of workers can lead to decreased efficiency. This is especially true in heavy industry and assembly lines, where high levels of stress among workers can easily lead to errors and reduced efficiency. To address this problem, task notifications and support tailored to the emotional state of workers are necessary.

[0190] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0191] In this invention, the server includes means for analyzing the user's behavior and emotions and notifying them of the importance of daily tasks; means for providing voice notifications to the user based on the analysis results; means for analyzing the user's emotional state and selecting appropriate notification content and methods; means for collecting user feedback and transmitting data to a communication device to update the analysis results; and means for improving emotions and work efficiency in the work environment through multiple work support devices. This enables optimization of the work environment according to the user's emotional state and efficient task management.

[0192] A "generative artificial intelligence model" is an artificial intelligence system that learns based on given data and can automatically generate the optimal output for a specific task.

[0193] "Behavioral analysis" is the process of collecting data on users' actions and task performance, and then analyzing that data to reveal patterns and trends.

[0194] "Emotional state" refers to an indicator of a user's psychological state and mood, which is measured and analyzed through behavior, facial expressions, tone of voice, etc.

[0195] "Voice notifications" refer to a method of communicating information to users using speech synthesis or recorded voices.

[0196] "Collecting feedback" is the activity of gathering information such as the completion status and emotional state of tasks provided by users, and using that information to improve the system.

[0197] A "work support device" is a tool or mechanical device installed in the work environment to assist work and improve efficiency and safety.

[0198] To carry out this invention, the following system is used.

[0199] The server analyzes user behavior and emotional data using a generative artificial intelligence model. Behavioral data includes tasks performed by the user, their frequency, and timing. Emotional data includes indicators of the user's psychological state, which are obtained from sensors such as smart glasses. Based on this data, the server generates customized information for each user and determines the content and optimal timing of notifications.

[0200] The device receives generative AI models and emotion analysis models provided by the server and monitors the user's behavior and emotions in real time. Specifically, the device monitors the user's condition via smart glasses and provides voice notifications according to their emotional state. For example, if the user is feeling stressed, the device provides appropriate support by using gentler wording and tone in the notifications.

[0201] Users receive voice notifications from their devices and perform or adjust tasks accordingly. After completing a task, they input the results as feedback into their device. This feedback is sent to a server and used to further refine and improve the AI ​​model.

[0202] As a concrete example, in a factory environment, if fatigue is detected from the facial expressions and movements of workers performing assembly line tasks, the terminal will offer advice such as, "Why don't you take a short break?" Furthermore, if the work is deemed to be progressing smoothly, it will provide positive feedback such as, "You're on a good pace, keep it up!"

[0203] An example of a prompt message is, "If work efficiency is declining, consider ways to provide workers with appropriate, emotion-based feedback." This prompt is used to train generative AI models, enabling more accurate sentiment analysis and notifications.

[0204] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0205] Step 1:

[0206] The server receives user behavioral and emotional data through sensors such as smart glasses. This input data includes the timing and frequency of the user's work, as well as psychological indicators related to facial expressions and voice tone. The server stores this data in a database.

[0207] Step 2:

[0208] The server analyzes the accumulated data using a generative artificial intelligence model. This analysis extracts behavioral and emotional patterns to understand the user's task performance and mental state. The output of the analysis is information about these patterns, which is used in the next step.

[0209] Step 3:

[0210] Based on the analysis results, the server uses a generated AI model to determine the appropriate content and timing of task notifications. At this stage, a notification message is generated that takes into account the user's psychological state. This output information is then sent to the terminal.

[0211] Step 4:

[0212] The terminal provides voice notifications to the user based on notification information received from the server. It takes notification information from the server as input and provides voice notifications to the user at the appropriate timing and tone as output. These notifications help optimize the user's work efficiency.

[0213] Step 5:

[0214] The user receives an audio notification from their device and performs the notified task. After completing the task, the user inputs feedback into the device, including the result and their emotional state. This feedback is used in the next step.

[0215] Step 6:

[0216] The device sends user feedback to the server. This input includes the user's work results and emotional state, and is used to update the generated AI model as output. The server receives this feedback and retrains the AI ​​model to further optimize future notifications.

[0217] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0218] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0219] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0220] [Second Embodiment]

[0221] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0222] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0223] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0224] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0225] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0226] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0227] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0228] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0229] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0230] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0231] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0232] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0233] This invention is a system that uses a generative artificial intelligence model to analyze the importance of multiple tasks that users should perform on a daily basis in real time and provide appropriate feedback. The operation of the entire system is described below from the perspectives of the server, terminal, and user.

[0234] Server Role

[0235] The server first stores user behavior data collected periodically from the device. This includes information about the frequency and timing of task execution. Based on this data, the server maintains the generated AI model and trains it to learn new behavior patterns. After a personalized model is generated for each user, the server sends this updated model to the device.

[0236] Terminal role

[0237] The device receives an AI model sent from the server and monitors the user's current behavior in real time. By analyzing behavioral patterns, if the device determines that the importance of a particular task has increased, it uses its voice output function to notify the user of this information. For example, the device might give a timely notification such as, "It's time to start preparing the meal," prompting the user to take action at the appropriate time.

[0238] User roles

[0239] Users recognize the importance of a task by receiving voice notifications from their device and choose appropriate actions. Upon completing a task, the user inputs feedback on its completion status into their device. This feedback is sent to a server and used as data to further improve the accuracy and usefulness of the AI ​​model.

[0240] Specific example

[0241] Specifically, suppose a user tends to neglect their pre-work preparations every Monday. This system recognizes this pattern and sends a voice notification on Monday morning saying, "Please start getting ready." Upon receiving this notification, the user can proceed with their preparations as planned and prevent unnecessary delays.

[0242] This embodiment of the invention aims to improve the quality of life by streamlining the management of users' daily tasks and enabling them to work together, with the server, terminal, and user each fulfilling their respective roles.

[0243] The following describes the processing flow.

[0244] Step 1:

[0245] The server receives user behavior data from the device. This data includes task start and completion times, frequency, etc. The server analyzes this data to discover new behavioral patterns.

[0246] Step 2:

[0247] The server updates the generated AI model based on the analyzed data. This model is customized for each individual, reflecting the specific behavioral habits of each user. The updated model is then sent to the device.

[0248] Step 3:

[0249] The device receives an updated generative AI model from the server. The device then uses this model to monitor the user's real-time behavior. The monitoring focuses on tasks that should be performed on a daily basis.

[0250] Step 4:

[0251] Based on the information obtained from monitoring results, the device provides users with voice notifications about the importance of tasks. For example, as the time for a scheduled task approaches, the device will remind the user with a message such as, "It's time for that task now."

[0252] Step 5:

[0253] The user receives an audio notification from their device and performs the task. After completing the task, the user enters the task completion status on their device and sends feedback.

[0254] Step 6:

[0255] The device sends user feedback to the server, which is then prepared for use in the next model update. This improves the accuracy of the AI ​​model and enables more effective task management.

[0256] (Example 1)

[0257] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0258] In modern society, users face numerous challenges and tasks on a daily basis, requiring them to appropriately prioritize and efficiently manage them. However, conventional systems have limitations in terms of providing immediate and personalized notifications based on user behavior, and in thoroughly analyzing behavioral patterns to improve future interactions. Therefore, there is a need for a system that is more highly personalized and enables efficient task management.

[0259] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0260] In this invention, the server includes means for updating the artificial intelligence generation technology using behavioral information collected from the user's terminal and analyzing new behavioral trends; means for using an output device to notify the user of high-priority tasks by voice based on the analysis results; and means for collecting responses from the user regarding the task completion status and passing information to a data transmission device to improve the model in accordance with the analysis results. This enables real-time task management and notification tailored to the behavioral patterns of individual users.

[0261] "User" refers to an individual or organization that uses this system, provides behavioral data, and takes action based on the notifications it receives.

[0262] A "terminal" refers to a device that a user directly operates, which receives data from a server and monitors the user's actions.

[0263] "Behavioral information" refers to data about the timing, frequency, and time required for tasks that users perform in their daily lives.

[0264] "Generative artificial intelligence technology" refers to a technology that uses applied programs to analyze user behavior patterns and generate and update models that are useful for notifying users of future tasks.

[0265] "Behavioral tendencies" refer to patterns or trends extracted from a user's past behavioral information and are used to predict future behavior.

[0266] "High-priority issues" are tasks that are deemed particularly important based on user behavior, and are therefore prioritized for notification by the system.

[0267] An "output device" refers to a device that transmits notifications from the system to the user via voice or visual means.

[0268] "Response" refers to the information that users input into their devices upon completing a task, and this data is used to improve the AI ​​model.

[0269] A "data transmission device" refers to a device that sends responses collected from a terminal to a server for analysis and model improvement.

[0270] This invention is a system that uses a generative AI model to streamline task management based on user behavior data. The system is operated through the interaction of a server, a terminal, and a user.

[0271] Server Role

[0272] The server collects user behavior data transmitted from the device and stores it in a database. This data includes task timing, frequency, and duration. The server runs a generated AI model using Python and TensorFlow and updates the model based on the collected data. This allows the model to learn new behavioral trends and prepares to provide personalized task notifications to users.

[0273] Terminal role

[0274] The device receives updated AI models from the server and monitors the user's current behavior in real time. The device is equipped with a voice output function using the Google Text-to-Speech API and provides voice notifications to the user based on the AI ​​model's analysis results. For example, the device can provide timely notifications such as "Now is the time to do XX," prompting the user to take appropriate action.

[0275] User roles

[0276] Users receive voice notifications from their devices and perform their daily tasks. Upon completing a task, they input feedback on its completion status into their device. This feedback is sent to a server and used to further improve the accuracy of the AI ​​model.

[0277] Specific example

[0278] As a concrete example, suppose a user has a habit of cleaning on weekends. The system learns this pattern and helps them perform the task efficiently by notifying them at the appropriate time that "it's time to start cleaning."

[0279] Example of a prompt

[0280] As an example of a prompt sentence to be input into the generative AI model, "Based on the user's behavior pattern data, accurately predict the next priority task and calculate the optimal notification time" can be considered. By using this prompt, the model can provide better notifications.

[0281] The flow of the specific process in Example 1 will be described using FIG. 11.

[0282] Step 1:

[0283] The server collects the user's behavior information from the terminal and stores it in the database. As input, information regarding the timing and frequency of the user's behavior is transmitted from the terminal to the server. The server receives this and stores it in the database. As a specific operation, data is securely transferred via the HTTPS protocol and stored in a MySQL database.

[0284] Step 2:

[0285] The server executes the generative AI model based on the collected behavior information and analyzes the new behavior trends. As input, the behavior information stored in the database is acquired by the server and applied to the AI model. Here, Python and TensorFlow are used to analyze the data and extract new behavior patterns. As output, a personalized behavior trend model is generated.

[0286] Step 3:

[0287] The server transmits this behavior trend model to the terminal. The input is the previously generated AI model, and the server encodes this and transmits it to the terminal. The output is the updated AI model received by the terminal. As a specific operation, the server packages the AI model in JSON format and performs the process of transmitting it to the terminal.

[0288] Step 4:

[0289] The device monitors user behavior in real time using the received generated AI model. Input consists of the AI ​​model received from the server and the user's current behavior data. The device references this data and performs data analysis according to the AI ​​model's instructions. As output, notification information is generated when a specific task is deemed important.

[0290] Step 5:

[0291] The device notifies the user via voice about high-priority tasks. The input is the important task identified by the AI ​​model, which the device converts into speech using the Google Text-to-Speech API. The output is the voice notification that the user hears. Specifically, the device calls a speech synthesis API to generate a specific message such as, "It's time to start [task]."

[0292] Step 6:

[0293] The user performs a task based on a voice notification and provides feedback on its completion status to the device. The input is the notified task and its execution result, which the user evaluates and inputs as feedback data to the device. The output is the user's feedback information sent from the device to the server.

[0294] Step 7:

[0295] The server receives feedback information sent from the terminal and uses it to improve the AI ​​model. The input is user feedback information, which the server uses to retrain the AI ​​model. The output is the feedback-applied model that will be reflected in the next AI model update. Specifically, the server analyzes the feedback data and incorporates it into the AI ​​model's learning process.

[0296] (Application Example 1)

[0297] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0298] With conventional technology, it has been difficult to analyze customer purchasing behavior in real time and effectively optimize sales promotion activities in stores. In particular, there is a need to understand customer movements and purchasing intentions and provide sales promotion information that matches them at the appropriate time, but there is currently a lack of concrete means to do so.

[0299] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0300] In this invention, the server includes means for analyzing user behavior using a generative artificial intelligence model and notifying the user of the importance of daily tasks; means for providing voice notifications to the user based on the analysis results; means for collecting user feedback and transmitting data to a communication device to update the analysis results; means for analyzing user purchasing behavior and providing sales promotion information to increase purchasing intent; and means for monitoring customer movements in the store in real time and notifying sales staff. This enables the optimization of sales promotion activities and increases sales in physical stores.

[0301] A "generative artificial intelligence model" is an artificial intelligence program built to analyze user behavior data and make predictions and suggestions tailored to specific purposes.

[0302] "User behavior" refers to a collection of data about human movement and decision-making in daily life and specific environments.

[0303] "Purchasing behavior" refers to the series of actions and decision-making processes that consumers take from selecting a product or service to making a purchase.

[0304] "Sales promotion information" refers to marketing-related data such as privileges, discount information, and campaigns provided to consumers to enhance their willingness to purchase products.

[0305] "Real-time monitoring" means immediately checking and grasping ongoing events or states in reality at that moment.

[0306] "Sales staff" refers to human resources responsible for customer service, product recommendations, and sales activities in the store.

[0307] As a form for implementing this invention, the following system is constructed.

[0308] The server accumulates users' behavioral data and purchase behavior data and analyzes them using a generated artificial intelligence model. The server utilizes a machine learning platform such as TensorFlow to evaluate users' behavior patterns and purchase willingness in real time and generate personalized sales promotion information. The generated information is immediately transmitted to the terminal using real-time processing technologies such as Node.js.

[0309] The terminal is incorporated into wearable devices such as smart glasses and notifies the sales staff of the sales promotion information received from the server in real time. The terminal has a simple user interface and supports the staff to make appropriate approaches to customers by providing information through voice feedback and visual displays.

[0310] The user responds to customers according to the prompt text based on the movements and reactions of customers in the store. This prompt text is, for example, in the form of "Analyze the movements of customers in the store and propose sales promotions to increase the willingness to purchase." As a result, the sales staff can propose to customers at the optimal timing, and the store operation business is made more efficient.

[0311] For example, if a user shows high interest in a new product, the terminal will notify staff of promotional information the moment the user touches the product. Based on this information, staff can then inform the customer, for instance, "This product is currently on sale for 20% off." This can further stimulate customer purchasing intent and increase store sales.

[0312] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0313] Step 1:

[0314] The server receives customer behavior data acquired from sensors within the store. This data includes information such as when customers touch products and their movement patterns within the store. The server preprocesses this data and formats it as input data for the generated AI model.

[0315] Step 2:

[0316] The server inputs the formatted behavioral data into a generating AI model to predict the user's purchasing behavior. This calculation quantifies the likelihood that a user is highly likely to purchase a particular product. The resulting predictions are used to create sales promotion information.

[0317] Step 3:

[0318] The server generates sales promotion information based on predicted values. This information includes discounts and campaign details for specific products. This information is then formatted as notification data for sales staff.

[0319] Step 4:

[0320] The terminal receives sales promotion information transmitted from the server in real time. The terminal then notifies sales staff of this information audibly or visually through a wearable device such as smart glasses.

[0321] Step 5:

[0322] Users can provide appropriate sales promotions to customers based on notifications from their devices. Specifically, they verbally communicate special offers for products that customers have shown interest in. By following these prompts, users can provide timely and effective customer service.

[0323] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0324] This invention is a system that combines a generative artificial intelligence model and an emotion engine to effectively notify users of the importance of their daily tasks and facilitate their completion. The operation of the system is described below from the perspectives of the server, terminal, and user.

[0325] Server Role

[0326] The server first stores user behavioral and emotional data sent from the terminal. Behavioral data includes task frequency, start time, and completion time, while emotional data includes information indicating the user's emotional state. The server analyzes this data using a generative artificial intelligence model to extract behavioral and emotional patterns. Based on the analysis results, the server updates the generative AI model and the emotional model, and sends customized information to the terminal for each user.

[0327] Terminal role

[0328] The device receives a generative AI model and an emotion model provided by the server. Based on these models, the device monitors the user's real-time behavior and emotional state. The device determines how the user's emotional state affects task performance and provides voice notifications at the optimal time. For example, if the user is feeling stressed, the device may adjust the timing and use a gentler tone of voice when notifying the user.

[0329] User roles

[0330] The user receives an audio notification from their device and begins working on the notified task. Upon completing the task, the user inputs the result as feedback into their device. They can also report their emotional state at that time. This feedback is sent to a server and used to further improve the AI ​​model.

[0331] Specific example

[0332] Specifically, the system identifies a pattern where users tend to procrastinate on household tasks and experience stress on weekday evenings. This system aims to help users tackle tasks more effectively by providing thoughtful voice notifications on weekday evenings, such as "Relax and start your chores slowly."

[0333] Embodiments of the present invention enable task management that takes emotions into consideration, thereby improving the user's efficiency and quality of life.

[0334] The following describes the processing flow.

[0335] Step 1:

[0336] The server receives user behavioral and emotional data transmitted from the terminal. This behavioral data includes task execution time, frequency, and degree of completion, while the emotional data includes emotional states detected from the user's facial expressions and tone of voice. The server securely stores this data.

[0337] Step 2:

[0338] The server updates the generative AI model and the emotion model using the accumulated data. The generative AI model works to capture the characteristics of the user's behavioral patterns, and the emotion model analyzes the impact of the user's emotional state on their ability to perform tasks. The updated models are then ready to be sent to the terminal to provide the next notification.

[0339] Step 3:

[0340] The device receives AI models and emotion models sent from the server. Using these models, the device begins analyzing the user's daily behavior and emotions in real time. Based on the analysis results, it determines the optimal timing and content of task notifications.

[0341] Step 4:

[0342] The device uses the analysis results to create voice notifications tailored to the user's emotional state. For example, if it detects that the user is feeling stressed, it might issue a gentle notification such as, "Let's take a short break before starting the task."

[0343] Step 5:

[0344] The user receives voice notifications from the device and performs the instructed task. During and after task execution, they input their current emotional state and task progress as feedback to the device.

[0345] Step 6:

[0346] The device sends user feedback to the server. This feedback includes information about the user's task completion rate and changes in their emotions. The server uses this feedback to inform future model updates and continuously improve the system.

[0347] (Example 2)

[0348] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0349] In modern times, it is crucial to respond quickly and accurately to the everyday challenges faced by individual users and to promote efficient action. However, it is difficult to effectively consider the user's emotional state and provide notifications at the optimal time, which can result in difficulties in efficiently completing tasks. This invention aims to solve these problems and improve the efficiency of users' actions and their quality of life through emotionally sensitive notifications.

[0350] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0351] In this invention, the server includes means for analyzing the behavioral and emotional information of individual users using a generative artificial intelligence model to extract novel behavioral and emotional patterns, means for providing considerate voice notifications to users based on the extracted patterns, and means for collecting feedback from users regarding their achievement status and emotions and transmitting information to a service provider to improve the accuracy of the model. This enables accurate understanding of the user's emotional state and notification at the optimal timing.

[0352] A "generative artificial intelligence model" is an algorithm that analyzes user behavior and emotion data to extract individual behavior and emotion patterns and generate information and notifications that are optimal for the user.

[0353] "Behavioral information" refers to data such as the frequency, start time, and end time of tasks that users perform on a daily basis, and forms the basis for analyzing user behavior patterns.

[0354] "Emotional information" refers to data such as the stress and satisfaction a user experiences while performing a task. This information forms the basis for understanding the user's emotional state and effectively adjusting notification content.

[0355] "Behavioral patterns" refer to specific tendencies that indicate how users tend to perform tasks, obtained by analyzing collected behavioral information.

[0356] An "emotional pattern" is a specific tendency that indicates what emotional state a user is most often in, obtained by analyzing collected emotional information.

[0357] "Thoughtful notifications" are notifications delivered at the optimal time and with the most relevant content, based on the user's behavioral and emotional patterns, enabling them to manage tasks more efficiently.

[0358] "Feedback" refers to information about the user's achievement and feelings upon completing a task, which is used to improve the accuracy of the AI ​​model.

[0359] "Providing equipment" refers to the entirety of hardware and software, including servers and user terminals, used for sending and receiving data and providing analysis results and notifications.

[0360] This invention is a system for optimizing task management in a user's daily life, while taking their emotions into consideration. Specific embodiments of this system are described below from the perspectives of the server, terminal, and user.

[0361] Server operation

[0362] The server is primarily responsible for data storage and analysis. It collects behavioral and emotional information transmitted from users' terminals and uses a database to store it. For example, it manages each user's data using a database management system such as SQL. Next, the collected data is analyzed using a generative artificial intelligence model. Programming languages ​​and libraries such as Python and TensorFlow are used here to extract behavioral and emotional patterns for each user. Based on the analysis results, the generative AI model and emotional model are updated to keep them up-to-date.

[0363] Terminal operation

[0364] The device receives a generative AI model and an emotion model provided by the server. Sensors are used on the device to monitor the user's real-time behavior and emotional state. A voice output device is used to notify the user at the optimal time. For example, if the user is calm, a normal alert is issued, and if stress is detected, the tone of voice is softened.

[0365] User roles

[0366] The user receives an audio notification from their device and begins working on the notified task. Upon completion of the task, feedback on the achievement status and emotional state is sent back to the device. This information is then sent back to the server and used to further improve the AI ​​model.

[0367] Specific example

[0368] For example, if analysis reveals that users tend to feel stressed on weekday evenings, this system can provide gentle voice notifications such as, "Let's make the most of your relaxation time tonight," thereby creating an environment where users can focus on their tasks while reducing their stress.

[0369] Example of a prompt

[0370] "Generate gentle, relaxing notifications during the times when users are most likely to experience stress."

[0371] A specific embodiment of this invention enables task management that takes into account the user's emotional state, thereby improving behavioral efficiency and quality of life.

[0372] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0373] Step 1:

[0374] The server collects behavioral and emotional information transmitted from the user's device. It receives user operation history and sensor data as input and stores it in an SQL database. Specifically, it prepares for analysis of task start and end times, user heart rate, and facial expression data.

[0375] Step 2:

[0376] The server analyzes the collected behavioral and emotional information. A generative artificial intelligence model is used for this analysis. The input is the data collected in step 1, and the output is behavioral and emotional patterns. Specifically, Python and TensorFlow are used to analyze data trends and incorporate them into the model.

[0377] Step 3:

[0378] The server updates the generated AI model and emotion model based on the analysis results. The input is the pattern calculated in step 2, which is used to adjust and optimize the model. The output is the latest model parameter set. Updating the model improves the accuracy of user-specific notifications.

[0379] Step 4:

[0380] The server sends the updated generative AI model and sentiment model to the user's device. The device receives this and prepares to monitor real-time behavior and sentiment. Specifically, it instantiates the model on the device and begins preparing notifications.

[0381] Step 5:

[0382] The device monitors the user's behavior and emotions in real time and provides voice notifications at the optimal time. Inputs include real-time data from sensors and models transmitted from a server, which are used to generate notifications. The output is a thoughtful voice notification delivered to the user. For example, if a stressed state is detected, the voice tone is adjusted based on the data.

[0383] Step 6:

[0384] After completing a task, the user enters feedback into the terminal. This feedback includes information about the task's completion status and the user's feelings, and is sent to the server via the terminal. The server receives this feedback and uses it to further optimize the model. The output is an improved model.

[0385] This step enables task management that takes user emotions into consideration, leading to improved efficiency and quality of life.

[0386] (Application Example 2)

[0387] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0388] In modern work environments, performing tasks without considering the emotional state of workers can lead to decreased efficiency. This is especially true in heavy industry and assembly lines, where high levels of stress among workers can easily lead to errors and reduced efficiency. To address this problem, task notifications and support tailored to the emotional state of workers are necessary.

[0389] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0390] In this invention, the server includes means for analyzing the user's behavior and emotions and notifying them of the importance of daily tasks; means for providing voice notifications to the user based on the analysis results; means for analyzing the user's emotional state and selecting appropriate notification content and methods; means for collecting user feedback and transmitting data to a communication device to update the analysis results; and means for improving emotions and work efficiency in the work environment through multiple work support devices. This enables optimization of the work environment according to the user's emotional state and efficient task management.

[0391] A "generative artificial intelligence model" is an artificial intelligence system that learns based on given data and can automatically generate the optimal output for a specific task.

[0392] "Behavioral analysis" is the process of collecting data on users' actions and task performance, and then analyzing that data to reveal patterns and trends.

[0393] "Emotional state" refers to an indicator of a user's psychological state and mood, which is measured and analyzed through behavior, facial expressions, tone of voice, etc.

[0394] "Voice notifications" refer to a method of communicating information to users using speech synthesis or recorded voices.

[0395] "Collecting feedback" is the activity of gathering information such as the completion status and emotional state of tasks provided by users, and using that information to improve the system.

[0396] A "work support device" is a tool or mechanical device installed in the work environment to assist work and improve efficiency and safety.

[0397] To carry out this invention, the following system is used.

[0398] The server analyzes user behavior and emotional data using a generative artificial intelligence model. Behavioral data includes tasks performed by the user, their frequency, and timing. Emotional data includes indicators of the user's psychological state, which are obtained from sensors such as smart glasses. Based on this data, the server generates customized information for each user and determines the content and optimal timing of notifications.

[0399] The device receives generative AI models and emotion analysis models provided by the server and monitors the user's behavior and emotions in real time. Specifically, the device monitors the user's condition via smart glasses and provides voice notifications according to their emotional state. For example, if the user is feeling stressed, the device provides appropriate support by using gentler wording and tone in the notifications.

[0400] Users receive voice notifications from their devices and perform or adjust tasks accordingly. After completing a task, they input the results as feedback into their device. This feedback is sent to a server and used to further refine and improve the AI ​​model.

[0401] As a concrete example, in a factory environment, if fatigue is detected from the facial expressions and movements of workers performing assembly line tasks, the terminal will offer advice such as, "Why don't you take a short break?" Furthermore, if the work is deemed to be progressing smoothly, it will provide positive feedback such as, "You're on a good pace, keep it up!"

[0402] An example of a prompt message is, "If work efficiency is declining, consider ways to provide workers with appropriate, emotion-based feedback." This prompt is used to train generative AI models, enabling more accurate sentiment analysis and notifications.

[0403] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0404] Step 1:

[0405] The server receives user behavioral and emotional data through sensors such as smart glasses. This input data includes the timing and frequency of the user's work, as well as psychological indicators related to facial expressions and voice tone. The server stores this data in a database.

[0406] Step 2:

[0407] The server analyzes the accumulated data using a generative artificial intelligence model. This analysis extracts behavioral and emotional patterns to understand the user's task performance and mental state. The output of the analysis is information about these patterns, which is used in the next step.

[0408] Step 3:

[0409] Based on the analysis results, the server uses a generated AI model to determine the appropriate content and timing of task notifications. At this stage, a notification message is generated that takes into account the user's psychological state. This output information is then sent to the terminal.

[0410] Step 4:

[0411] The terminal provides voice notifications to the user based on notification information received from the server. It takes notification information from the server as input and provides voice notifications to the user at the appropriate timing and tone as output. These notifications help optimize the user's work efficiency.

[0412] Step 5:

[0413] The user receives an audio notification from their device and performs the notified task. After completing the task, the user inputs feedback into the device, including the result and their emotional state. This feedback is used in the next step.

[0414] Step 6:

[0415] The device sends user feedback to the server. This input includes the user's work results and emotional state, and is used to update the generated AI model as output. The server receives this feedback and retrains the AI ​​model to further optimize future notifications.

[0416] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0417] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0418] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0419] [Third Embodiment]

[0420] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0421] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0422] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0423] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0424] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0425] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0426] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0427] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0428] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0429] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0430] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0431] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0432] This invention is a system that uses a generative artificial intelligence model to analyze the importance of multiple tasks that users should perform on a daily basis in real time and provide appropriate feedback. The operation of the entire system is described below from the perspectives of the server, terminal, and user.

[0433] Server Role

[0434] The server first stores user behavior data collected periodically from the device. This includes information about the frequency and timing of task execution. Based on this data, the server maintains the generated AI model and trains it to learn new behavior patterns. After a personalized model is generated for each user, the server sends this updated model to the device.

[0435] Terminal role

[0436] The device receives an AI model sent from the server and monitors the user's current behavior in real time. By analyzing behavioral patterns, if the device determines that the importance of a particular task has increased, it uses its voice output function to notify the user of this information. For example, the device might give a timely notification such as, "It's time to start preparing the meal," prompting the user to take action at the appropriate time.

[0437] User roles

[0438] Users recognize the importance of a task by receiving voice notifications from their device and choose appropriate actions. Upon completing a task, the user inputs feedback on its completion status into their device. This feedback is sent to a server and used as data to further improve the accuracy and usefulness of the AI ​​model.

[0439] Specific example

[0440] Specifically, suppose a user tends to neglect their pre-work preparations every Monday. This system recognizes this pattern and sends a voice notification on Monday morning saying, "Please start getting ready." Upon receiving this notification, the user can proceed with their preparations as planned and prevent unnecessary delays.

[0441] This embodiment of the invention aims to improve the quality of life by streamlining the management of users' daily tasks and enabling them to work together, with the server, terminal, and user each fulfilling their respective roles.

[0442] The following describes the processing flow.

[0443] Step 1:

[0444] The server receives user behavior data from the device. This data includes task start and completion times, frequency, etc. The server analyzes this data to discover new behavioral patterns.

[0445] Step 2:

[0446] The server updates the generated AI model based on the analyzed data. This model is customized for each individual, reflecting the specific behavioral habits of each user. The updated model is then sent to the device.

[0447] Step 3:

[0448] The device receives an updated generative AI model from the server. The device then uses this model to monitor the user's real-time behavior. The monitoring focuses on tasks that should be performed on a daily basis.

[0449] Step 4:

[0450] Based on the information obtained from monitoring results, the device provides users with voice notifications about the importance of tasks. For example, as the time for a scheduled task approaches, the device will remind the user with a message such as, "It's time for that task now."

[0451] Step 5:

[0452] The user receives an audio notification from their device and performs the task. After completing the task, the user enters the task completion status on their device and sends feedback.

[0453] Step 6:

[0454] The device sends user feedback to the server, which is then prepared for use in the next model update. This improves the accuracy of the AI ​​model and enables more effective task management.

[0455] (Example 1)

[0456] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0457] In modern society, users face numerous challenges and tasks on a daily basis, requiring them to appropriately prioritize and efficiently manage them. However, conventional systems have limitations in terms of providing immediate and personalized notifications based on user behavior, and in thoroughly analyzing behavioral patterns to improve future interactions. Therefore, there is a need for a system that is more highly personalized and enables efficient task management.

[0458] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0459] In this invention, the server includes means for updating the artificial intelligence generation technology using behavioral information collected from the user's terminal and analyzing new behavioral trends; means for using an output device to notify the user of high-priority tasks by voice based on the analysis results; and means for collecting responses from the user regarding the task completion status and passing information to a data transmission device to improve the model in accordance with the analysis results. This enables real-time task management and notification tailored to the behavioral patterns of individual users.

[0460] "User" refers to an individual or organization that uses this system, provides behavioral data, and takes action based on the notifications it receives.

[0461] A "terminal" refers to a device that a user directly operates, which receives data from a server and monitors the user's actions.

[0462] "Behavioral information" refers to data about the timing, frequency, and time required for tasks that users perform in their daily lives.

[0463] "Generative artificial intelligence technology" refers to a technology that uses applied programs to analyze user behavior patterns and generate and update models that are useful for notifying users of future tasks.

[0464] "Behavioral tendencies" refer to patterns or trends extracted from a user's past behavioral information and are used to predict future behavior.

[0465] "High-priority issues" are tasks that are deemed particularly important based on user behavior, and are therefore prioritized for notification by the system.

[0466] An "output device" refers to a device that transmits notifications from the system to the user via voice or visual means.

[0467] "Response" refers to the information that users input into their devices upon completing a task, and this data is used to improve the AI ​​model.

[0468] A "data transmission device" refers to a device that sends responses collected from a terminal to a server for analysis and model improvement.

[0469] This invention is a system that uses a generative AI model to streamline task management based on user behavior data. The system is operated through the interaction of a server, a terminal, and a user.

[0470] Server Role

[0471] The server collects user behavior data transmitted from the device and stores it in a database. This data includes task timing, frequency, and duration. The server runs a generated AI model using Python and TensorFlow and updates the model based on the collected data. This allows the model to learn new behavioral trends and prepares to provide personalized task notifications to users.

[0472] Terminal role

[0473] The device receives updated AI models from the server and monitors the user's current behavior in real time. The device is equipped with a voice output function using the Google Text-to-Speech API and provides voice notifications to the user based on the AI ​​model's analysis results. For example, the device can provide timely notifications such as "Now is the time to do XX," prompting the user to take appropriate action.

[0474] User roles

[0475] Users receive voice notifications from their devices and perform their daily tasks. Upon completing a task, they input feedback on its completion status into their device. This feedback is sent to a server and used to further improve the accuracy of the AI ​​model.

[0476] Specific example

[0477] As a concrete example, suppose a user has a habit of cleaning on weekends. The system learns this pattern and helps them perform the task efficiently by notifying them at the appropriate time that "it's time to start cleaning."

[0478] Example of a prompt

[0479] An example of a prompt to input into a generative AI model is, "Based on user behavior pattern data, accurately predict the next priority task and calculate the optimal notification time." Using this prompt, the model can provide better notifications.

[0480] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0481] Step 1:

[0482] The server collects user behavior information from the terminal and stores it in a database. The input consists of information about the timing and frequency of the user's actions, which is sent from the terminal to the server. The server receives this information and stores it in the database. Specifically, the data is securely transferred via the HTTPS protocol and stored in a MySQL database.

[0483] Step 2:

[0484] The server runs a generative AI model based on collected behavioral data to analyze new behavioral trends. The input is behavioral data stored in a database, which the server retrieves and applies to the AI ​​model. Python and TensorFlow are used to analyze the data and extract new behavioral patterns. The output is a personalized behavioral trend model.

[0485] Step 3:

[0486] The server sends this behavioral tendency model to the terminal. The input is the previously generated AI model, which the server encodes and sends to the terminal. The output is the updated AI model that the terminal receives. Specifically, the server packages the AI ​​model in JSON format and sends it to the terminal.

[0487] Step 4:

[0488] The device monitors user behavior in real time using the received generated AI model. Input consists of the AI ​​model received from the server and the user's current behavior data. The device references this data and performs data analysis according to the AI ​​model's instructions. As output, notification information is generated when a specific task is deemed important.

[0489] Step 5:

[0490] The device notifies the user via voice about high-priority tasks. The input is the important task identified by the AI ​​model, which the device converts into speech using the Google Text-to-Speech API. The output is the voice notification that the user hears. Specifically, the device calls a speech synthesis API to generate a specific message such as, "It's time to start [task]."

[0491] Step 6:

[0492] The user performs a task based on a voice notification and provides feedback on its completion status to the device. The input is the notified task and its execution result, which the user evaluates and inputs as feedback data to the device. The output is the user's feedback information sent from the device to the server.

[0493] Step 7:

[0494] The server receives feedback information sent from the terminal and uses it to improve the AI ​​model. The input is user feedback information, which the server uses to retrain the AI ​​model. The output is the feedback-applied model that will be reflected in the next AI model update. Specifically, the server analyzes the feedback data and incorporates it into the AI ​​model's learning process.

[0495] (Application Example 1)

[0496] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0497] With conventional technology, it has been difficult to analyze customer purchasing behavior in real time and effectively optimize sales promotion activities in stores. In particular, there is a need to understand customer movements and purchasing intentions and provide sales promotion information that matches them at the appropriate time, but there is currently a lack of concrete means to do so.

[0498] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0499] In this invention, the server includes means for analyzing user behavior using a generative artificial intelligence model and notifying the user of the importance of daily tasks; means for providing voice notifications to the user based on the analysis results; means for collecting user feedback and transmitting data to a communication device to update the analysis results; means for analyzing user purchasing behavior and providing sales promotion information to increase purchasing intent; and means for monitoring customer movements in the store in real time and notifying sales staff. This enables the optimization of sales promotion activities and increases sales in physical stores.

[0500] A "generative artificial intelligence model" is an artificial intelligence program built to analyze user behavior data and make predictions and suggestions tailored to specific purposes.

[0501] "User behavior" refers to a collection of data about human movement and decision-making in daily life and specific environments.

[0502] "Purchasing behavior" refers to the series of actions and decision-making processes that consumers take from selecting a product or service to making a purchase.

[0503] "Sales promotion information" refers to marketing data such as special offers, discounts, and campaigns provided to consumers to increase their desire to purchase products.

[0504] "Real-time monitoring" means instantly confirming and understanding events and conditions that are actually happening in real time.

[0505] "Sales staff" refers to the human resources responsible for customer service, product recommendations, and sales activities within a store.

[0506] The following system is constructed as an embodiment of this invention.

[0507] The server accumulates user behavior data and purchasing behavior data, and analyzes it using generative artificial intelligence models. Leveraging machine learning platforms like TensorFlow, the server evaluates user behavior patterns and purchasing intent in real time, generating personalized sales promotion information. The generated information is immediately sent to the terminal using real-time processing technologies such as Node.js.

[0508] The terminal is integrated into wearable devices such as smart glasses and notifies sales staff in real time of sales promotion information received from a server. The terminal has a simple user interface and provides information through voice feedback and visual displays, helping staff to make appropriate approaches to customers.

[0509] Users respond to customers based on their movements and reactions within the store, following prompts. These prompts might be in the format of, for example, "Analyze the customer's movements within the store and propose sales promotions to increase their purchase intent." This allows sales staff to make suggestions to customers at the optimal time, streamlining store operations.

[0510] For example, if a user shows high interest in a new product, the terminal will notify staff of promotional information the moment the user touches the product. Based on this information, staff can then inform the customer, for instance, "This product is currently on sale for 20% off." This can further stimulate customer purchasing intent and increase store sales.

[0511] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0512] Step 1:

[0513] The server receives customer behavior data acquired from sensors within the store. This data includes information such as when customers touch products and their movement patterns within the store. The server preprocesses this data and formats it as input data for the generated AI model.

[0514] Step 2:

[0515] The server inputs the formatted behavioral data into a generating AI model to predict the user's purchasing behavior. This calculation quantifies the likelihood that a user is highly likely to purchase a particular product. The resulting predictions are used to create sales promotion information.

[0516] Step 3:

[0517] The server generates sales promotion information based on predicted values. This information includes discounts and campaign details for specific products. This information is then formatted as notification data for sales staff.

[0518] Step 4:

[0519] The terminal receives sales promotion information transmitted from the server in real time. The terminal then notifies sales staff of this information audibly or visually through a wearable device such as smart glasses.

[0520] Step 5:

[0521] Users can provide appropriate sales promotions to customers based on notifications from their devices. Specifically, they verbally communicate special offers for products that customers have shown interest in. By following these prompts, users can provide timely and effective customer service.

[0522] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0523] This invention is a system that combines a generative artificial intelligence model and an emotion engine to effectively notify users of the importance of their daily tasks and facilitate their completion. The operation of the system is described below from the perspectives of the server, terminal, and user.

[0524] Server Role

[0525] The server first stores user behavioral and emotional data sent from the terminal. Behavioral data includes task frequency, start time, and completion time, while emotional data includes information indicating the user's emotional state. The server analyzes this data using a generative artificial intelligence model to extract behavioral and emotional patterns. Based on the analysis results, the server updates the generative AI model and the emotional model, and sends customized information to the terminal for each user.

[0526] Terminal role

[0527] The device receives a generative AI model and an emotion model provided by the server. Based on these models, the device monitors the user's real-time behavior and emotional state. The device determines how the user's emotional state affects task performance and provides voice notifications at the optimal time. For example, if the user is feeling stressed, the device may adjust the timing and use a gentler tone of voice when notifying the user.

[0528] User roles

[0529] The user receives an audio notification from their device and begins working on the notified task. Upon completing the task, the user inputs the result as feedback into their device. They can also report their emotional state at that time. This feedback is sent to a server and used to further improve the AI ​​model.

[0530] Specific example

[0531] Specifically, the system identifies a pattern where users tend to procrastinate on household tasks and experience stress on weekday evenings. This system aims to help users tackle tasks more effectively by providing thoughtful voice notifications on weekday evenings, such as "Relax and start your chores slowly."

[0532] Embodiments of the present invention enable task management that takes emotions into consideration, thereby improving the user's efficiency and quality of life.

[0533] The following describes the processing flow.

[0534] Step 1:

[0535] The server receives user behavioral and emotional data transmitted from the terminal. This behavioral data includes task execution time, frequency, and degree of completion, while the emotional data includes emotional states detected from the user's facial expressions and tone of voice. The server securely stores this data.

[0536] Step 2:

[0537] The server updates the generative AI model and the emotion model using the accumulated data. The generative AI model works to capture the characteristics of the user's behavioral patterns, and the emotion model analyzes the impact of the user's emotional state on their ability to perform tasks. The updated models are then ready to be sent to the terminal to provide the next notification.

[0538] Step 3:

[0539] The device receives AI models and emotion models sent from the server. Using these models, the device begins analyzing the user's daily behavior and emotions in real time. Based on the analysis results, it determines the optimal timing and content of task notifications.

[0540] Step 4:

[0541] The device uses the analysis results to create voice notifications tailored to the user's emotional state. For example, if it detects that the user is feeling stressed, it might issue a gentle notification such as, "Let's take a short break before starting the task."

[0542] Step 5:

[0543] The user receives voice notifications from the device and performs the instructed task. During and after task execution, they input their current emotional state and task progress as feedback to the device.

[0544] Step 6:

[0545] The device sends user feedback to the server. This feedback includes information about the user's task completion rate and changes in their emotions. The server uses this feedback to inform future model updates and continuously improve the system.

[0546] (Example 2)

[0547] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0548] In modern times, it is crucial to respond quickly and accurately to the everyday challenges faced by individual users and to promote efficient action. However, it is difficult to effectively consider the user's emotional state and provide notifications at the optimal time, which can result in difficulties in efficiently completing tasks. This invention aims to solve these problems and improve the efficiency of users' actions and their quality of life through emotionally sensitive notifications.

[0549] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0550] In this invention, the server includes means for analyzing the behavioral and emotional information of individual users using a generative artificial intelligence model to extract novel behavioral and emotional patterns, means for providing considerate voice notifications to users based on the extracted patterns, and means for collecting feedback from users regarding their achievement status and emotions and transmitting information to a service provider to improve the accuracy of the model. This enables accurate understanding of the user's emotional state and notification at the optimal timing.

[0551] A "generative artificial intelligence model" is an algorithm that analyzes user behavior and emotion data to extract individual behavior and emotion patterns and generate information and notifications that are optimal for the user.

[0552] "Behavioral information" refers to data such as the frequency, start time, and end time of tasks that users perform on a daily basis, and forms the basis for analyzing user behavior patterns.

[0553] "Emotional information" refers to data such as the stress and satisfaction a user experiences while performing a task. This information forms the basis for understanding the user's emotional state and effectively adjusting notification content.

[0554] "Behavioral patterns" refer to specific tendencies that indicate how users tend to perform tasks, obtained by analyzing collected behavioral information.

[0555] An "emotional pattern" is a specific tendency that indicates what emotional state a user is most often in, obtained by analyzing collected emotional information.

[0556] "Thoughtful notifications" are notifications delivered at the optimal time and with the most relevant content, based on the user's behavioral and emotional patterns, enabling them to manage tasks more efficiently.

[0557] "Feedback" refers to information about the user's achievement and feelings upon completing a task, which is used to improve the accuracy of the AI ​​model.

[0558] "Providing equipment" refers to the entirety of hardware and software, including servers and user terminals, used for sending and receiving data and providing analysis results and notifications.

[0559] This invention is a system for optimizing task management in a user's daily life, while taking their emotions into consideration. Specific embodiments of this system are described below from the perspectives of the server, terminal, and user.

[0560] Server operation

[0561] The server is primarily responsible for data storage and analysis. It collects behavioral and emotional information transmitted from users' terminals and uses a database to store it. For example, it manages each user's data using a database management system such as SQL. Next, the collected data is analyzed using a generative artificial intelligence model. Programming languages ​​and libraries such as Python and TensorFlow are used here to extract behavioral and emotional patterns for each user. Based on the analysis results, the generative AI model and emotional model are updated to keep them up-to-date.

[0562] Terminal operation

[0563] The device receives a generative AI model and an emotion model provided by the server. Sensors are used on the device to monitor the user's real-time behavior and emotional state. A voice output device is used to notify the user at the optimal time. For example, if the user is calm, a normal alert is issued, and if stress is detected, the tone of voice is softened.

[0564] User roles

[0565] The user receives an audio notification from their device and begins working on the notified task. Upon completion of the task, feedback on the achievement status and emotional state is sent back to the device. This information is then sent back to the server and used to further improve the AI ​​model.

[0566] Specific example

[0567] For example, if analysis reveals that users tend to feel stressed on weekday evenings, this system can provide gentle voice notifications such as, "Let's make the most of your relaxation time tonight," thereby creating an environment where users can focus on their tasks while reducing their stress.

[0568] Example of a prompt

[0569] "Generate gentle, relaxing notifications during the times when users are most likely to experience stress."

[0570] A specific embodiment of this invention enables task management that takes into account the user's emotional state, thereby improving behavioral efficiency and quality of life.

[0571] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0572] Step 1:

[0573] The server collects behavioral and emotional information transmitted from the user's device. It receives user operation history and sensor data as input and stores it in an SQL database. Specifically, it prepares for analysis of task start and end times, user heart rate, and facial expression data.

[0574] Step 2:

[0575] The server analyzes the collected behavioral and emotional information. A generative artificial intelligence model is used for this analysis. The input is the data collected in step 1, and the output is behavioral and emotional patterns. Specifically, Python and TensorFlow are used to analyze data trends and incorporate them into the model.

[0576] Step 3:

[0577] The server updates the generated AI model and emotion model based on the analysis results. The input is the pattern calculated in step 2, which is used to adjust and optimize the model. The output is the latest model parameter set. Updating the model improves the accuracy of user-specific notifications.

[0578] Step 4:

[0579] The server sends the updated generative AI model and sentiment model to the user's device. The device receives this and prepares to monitor real-time behavior and sentiment. Specifically, it instantiates the model on the device and begins preparing notifications.

[0580] Step 5:

[0581] The device monitors the user's behavior and emotions in real time and provides voice notifications at the optimal time. Inputs include real-time data from sensors and models transmitted from a server, which are used to generate notifications. The output is a thoughtful voice notification delivered to the user. For example, if a stressed state is detected, the voice tone is adjusted based on the data.

[0582] Step 6:

[0583] After completing a task, the user enters feedback into the terminal. This feedback includes information about the task's completion status and the user's feelings, and is sent to the server via the terminal. The server receives this feedback and uses it to further optimize the model. The output is an improved model.

[0584] This step enables task management that takes user emotions into consideration, leading to improved efficiency and quality of life.

[0585] (Application Example 2)

[0586] Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0587] In modern work environments, performing tasks without considering the emotional state of workers can lead to decreased efficiency. This is especially true in heavy industry and assembly lines, where high levels of stress among workers can easily lead to errors and reduced efficiency. To address this problem, task notifications and support tailored to the emotional state of workers are necessary.

[0588] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0589] In this invention, the server includes means for analyzing the user's behavior and emotions and notifying them of the importance of daily tasks; means for providing voice notifications to the user based on the analysis results; means for analyzing the user's emotional state and selecting appropriate notification content and methods; means for collecting user feedback and transmitting data to a communication device to update the analysis results; and means for improving emotions and work efficiency in the work environment through multiple work support devices. This enables optimization of the work environment according to the user's emotional state and efficient task management.

[0590] A "generative artificial intelligence model" is an artificial intelligence system that learns based on given data and can automatically generate the optimal output for a specific task.

[0591] "Behavioral analysis" is the process of collecting data on users' actions and task performance, and then analyzing that data to reveal patterns and trends.

[0592] "Emotional state" refers to an indicator of a user's psychological state and mood, which is measured and analyzed through behavior, facial expressions, tone of voice, etc.

[0593] "Voice notifications" refer to a method of communicating information to users using speech synthesis or recorded voices.

[0594] "Collecting feedback" is the activity of gathering information such as the completion status and emotional state of tasks provided by users, and using that information to improve the system.

[0595] A "work support device" is a tool or mechanical device installed in the work environment to assist work and improve efficiency and safety.

[0596] To carry out this invention, the following system is used.

[0597] The server analyzes user behavior and emotional data using a generative artificial intelligence model. Behavioral data includes tasks performed by the user, their frequency, and timing. Emotional data includes indicators of the user's psychological state, which are obtained from sensors such as smart glasses. Based on this data, the server generates customized information for each user and determines the content and optimal timing of notifications.

[0598] The device receives generative AI models and emotion analysis models provided by the server and monitors the user's behavior and emotions in real time. Specifically, the device monitors the user's condition via smart glasses and provides voice notifications according to their emotional state. For example, if the user is feeling stressed, the device provides appropriate support by using gentler wording and tone in the notifications.

[0599] Users receive voice notifications from their devices and perform or adjust tasks accordingly. After completing a task, they input the results as feedback into their device. This feedback is sent to a server and used to further refine and improve the AI ​​model.

[0600] As a concrete example, in a factory environment, if fatigue is detected from the facial expressions and movements of workers performing assembly line tasks, the terminal will offer advice such as, "Why don't you take a short break?" Furthermore, if the work is deemed to be progressing smoothly, it will provide positive feedback such as, "You're on a good pace, keep it up!"

[0601] An example of a prompt message is, "If work efficiency is declining, consider ways to provide workers with appropriate, emotion-based feedback." This prompt is used to train generative AI models, enabling more accurate sentiment analysis and notifications.

[0602] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0603] Step 1:

[0604] The server receives user behavioral and emotional data through sensors such as smart glasses. This input data includes the timing and frequency of the user's work, as well as psychological indicators related to facial expressions and voice tone. The server stores this data in a database.

[0605] Step 2:

[0606] The server analyzes the accumulated data using a generative artificial intelligence model. This analysis extracts behavioral and emotional patterns to understand the user's task performance and mental state. The output of the analysis is information about these patterns, which is used in the next step.

[0607] Step 3:

[0608] Based on the analysis results, the server uses a generated AI model to determine the appropriate content and timing of task notifications. At this stage, a notification message is generated that takes into account the user's psychological state. This output information is then sent to the terminal.

[0609] Step 4:

[0610] The terminal provides voice notifications to the user based on notification information received from the server. It takes notification information from the server as input and provides voice notifications to the user at the appropriate timing and tone as output. These notifications help optimize the user's work efficiency.

[0611] Step 5:

[0612] The user receives an audio notification from their device and performs the notified task. After completing the task, the user inputs feedback into the device, including the result and their emotional state. This feedback is used in the next step.

[0613] Step 6:

[0614] The device sends user feedback to the server. This input includes the user's work results and emotional state, and is used to update the generated AI model as output. The server receives this feedback and retrains the AI ​​model to further optimize future notifications.

[0615] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0616] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0617] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0618] [Fourth Embodiment]

[0619] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0620] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0621] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0622] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0623] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0624] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0625] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0626] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0627] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0628] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0629] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0630] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0631] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0632] This invention is a system that uses a generative artificial intelligence model to analyze the importance of multiple tasks that users should perform on a daily basis in real time and provide appropriate feedback. The operation of the entire system is described below from the perspectives of the server, terminal, and user.

[0633] Server Role

[0634] The server first stores user behavior data collected periodically from the device. This includes information about the frequency and timing of task execution. Based on this data, the server maintains the generated AI model and trains it to learn new behavior patterns. After a personalized model is generated for each user, the server sends this updated model to the device.

[0635] Terminal role

[0636] The device receives an AI model sent from the server and monitors the user's current behavior in real time. By analyzing behavioral patterns, if the device determines that the importance of a particular task has increased, it uses its voice output function to notify the user of this information. For example, the device might give a timely notification such as, "It's time to start preparing the meal," prompting the user to take action at the appropriate time.

[0637] User roles

[0638] Users recognize the importance of a task by receiving voice notifications from their device and choose appropriate actions. Upon completing a task, the user inputs feedback on its completion status into their device. This feedback is sent to a server and used as data to further improve the accuracy and usefulness of the AI ​​model.

[0639] Specific example

[0640] Specifically, suppose a user tends to neglect their pre-work preparations every Monday. This system recognizes this pattern and sends a voice notification on Monday morning saying, "Please start getting ready." Upon receiving this notification, the user can proceed with their preparations as planned and prevent unnecessary delays.

[0641] This embodiment of the invention aims to improve the quality of life by streamlining the management of users' daily tasks and enabling them to work together, with the server, terminal, and user each fulfilling their respective roles.

[0642] The following describes the processing flow.

[0643] Step 1:

[0644] The server receives user behavior data from the device. This data includes task start and completion times, frequency, etc. The server analyzes this data to discover new behavioral patterns.

[0645] Step 2:

[0646] The server updates the generated AI model based on the analyzed data. This model is customized for each individual, reflecting the specific behavioral habits of each user. The updated model is then sent to the device.

[0647] Step 3:

[0648] The device receives an updated generative AI model from the server. The device then uses this model to monitor the user's real-time behavior. The monitoring focuses on tasks that should be performed on a daily basis.

[0649] Step 4:

[0650] Based on the information obtained from monitoring results, the device provides users with voice notifications about the importance of tasks. For example, as the time for a scheduled task approaches, the device will remind the user with a message such as, "It's time for that task now."

[0651] Step 5:

[0652] The user receives an audio notification from their device and performs the task. After completing the task, the user enters the task completion status on their device and sends feedback.

[0653] Step 6:

[0654] The device sends user feedback to the server, which is then prepared for use in the next model update. This improves the accuracy of the AI ​​model and enables more effective task management.

[0655] (Example 1)

[0656] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0657] In modern society, users face numerous challenges and tasks on a daily basis, requiring them to appropriately prioritize and efficiently manage them. However, conventional systems have limitations in terms of providing immediate and personalized notifications based on user behavior, and in thoroughly analyzing behavioral patterns to improve future interactions. Therefore, there is a need for a system that is more highly personalized and enables efficient task management.

[0658] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0659] In this invention, the server includes means for updating the artificial intelligence generation technology using behavioral information collected from the user's terminal and analyzing new behavioral trends; means for using an output device to notify the user of high-priority tasks by voice based on the analysis results; and means for collecting responses from the user regarding the task completion status and passing information to a data transmission device to improve the model in accordance with the analysis results. This enables real-time task management and notification tailored to the behavioral patterns of individual users.

[0660] "User" refers to an individual or organization that uses this system, provides behavioral data, and takes action based on the notifications it receives.

[0661] A "terminal" refers to a device that a user directly operates, which receives data from a server and monitors the user's actions.

[0662] "Behavioral information" refers to data about the timing, frequency, and time required for tasks that users perform in their daily lives.

[0663] "Generative artificial intelligence technology" refers to a technology that uses applied programs to analyze user behavior patterns and generate and update models that are useful for notifying users of future tasks.

[0664] "Behavioral tendencies" refer to patterns or trends extracted from a user's past behavioral information and are used to predict future behavior.

[0665] "High-priority issues" are tasks that are deemed particularly important based on user behavior, and are therefore prioritized for notification by the system.

[0666] An "output device" refers to a device that transmits notifications from the system to the user via voice or visual means.

[0667] "Response" refers to the information that users input into their devices upon completing a task, and this data is used to improve the AI ​​model.

[0668] A "data transmission device" refers to a device that sends responses collected from a terminal to a server for analysis and model improvement.

[0669] This invention is a system that uses a generative AI model to streamline task management based on user behavior data. The system is operated through the interaction of a server, a terminal, and a user.

[0670] Server Role

[0671] The server collects user behavior data transmitted from the device and stores it in a database. This data includes task timing, frequency, and duration. The server runs a generated AI model using Python and TensorFlow and updates the model based on the collected data. This allows the model to learn new behavioral trends and prepares to provide personalized task notifications to users.

[0672] Terminal role

[0673] The device receives updated AI models from the server and monitors the user's current behavior in real time. The device is equipped with a voice output function using the Google Text-to-Speech API and provides voice notifications to the user based on the AI ​​model's analysis results. For example, the device can provide timely notifications such as "Now is the time to do XX," prompting the user to take appropriate action.

[0674] User roles

[0675] Users receive voice notifications from their devices and perform their daily tasks. Upon completing a task, they input feedback on its completion status into their device. This feedback is sent to a server and used to further improve the accuracy of the AI ​​model.

[0676] Specific example

[0677] As a concrete example, suppose a user has a habit of cleaning on weekends. The system learns this pattern and helps them perform the task efficiently by notifying them at the appropriate time that "it's time to start cleaning."

[0678] Example of a prompt

[0679] An example of a prompt to input into a generative AI model is, "Based on user behavior pattern data, accurately predict the next priority task and calculate the optimal notification time." Using this prompt, the model can provide better notifications.

[0680] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0681] Step 1:

[0682] The server collects user behavior information from the terminal and stores it in a database. The input consists of information about the timing and frequency of the user's actions, which is sent from the terminal to the server. The server receives this information and stores it in the database. Specifically, the data is securely transferred via the HTTPS protocol and stored in a MySQL database.

[0683] Step 2:

[0684] The server runs a generative AI model based on collected behavioral data to analyze new behavioral trends. The input is behavioral data stored in a database, which the server retrieves and applies to the AI ​​model. Python and TensorFlow are used to analyze the data and extract new behavioral patterns. The output is a personalized behavioral trend model.

[0685] Step 3:

[0686] The server sends this behavioral tendency model to the terminal. The input is the previously generated AI model, which the server encodes and sends to the terminal. The output is the updated AI model that the terminal receives. Specifically, the server packages the AI ​​model in JSON format and sends it to the terminal.

[0687] Step 4:

[0688] The device monitors user behavior in real time using the received generated AI model. Input consists of the AI ​​model received from the server and the user's current behavior data. The device references this data and performs data analysis according to the AI ​​model's instructions. As output, notification information is generated when a specific task is deemed important.

[0689] Step 5:

[0690] The device notifies the user via voice about high-priority tasks. The input is the important task identified by the AI ​​model, which the device converts into speech using the Google Text-to-Speech API. The output is the voice notification that the user hears. Specifically, the device calls a speech synthesis API to generate a specific message such as, "It's time to start [task]."

[0691] Step 6:

[0692] The user performs a task based on a voice notification and provides feedback on its completion status to the device. The input is the notified task and its execution result, which the user evaluates and inputs as feedback data to the device. The output is the user's feedback information sent from the device to the server.

[0693] Step 7:

[0694] The server receives feedback information sent from the terminal and uses it to improve the AI ​​model. The input is user feedback information, which the server uses to retrain the AI ​​model. The output is the feedback-applied model that will be reflected in the next AI model update. Specifically, the server analyzes the feedback data and incorporates it into the AI ​​model's learning process.

[0695] (Application Example 1)

[0696] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0697] With conventional technology, it has been difficult to analyze customer purchasing behavior in real time and effectively optimize sales promotion activities in stores. In particular, there is a need to understand customer movements and purchasing intentions and provide sales promotion information that matches them at the appropriate time, but there is currently a lack of concrete means to do so.

[0698] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0699] In this invention, the server includes means for analyzing user behavior using a generative artificial intelligence model and notifying the user of the importance of daily tasks; means for providing voice notifications to the user based on the analysis results; means for collecting user feedback and transmitting data to a communication device to update the analysis results; means for analyzing user purchasing behavior and providing sales promotion information to increase purchasing intent; and means for monitoring customer movements in the store in real time and notifying sales staff. This enables the optimization of sales promotion activities and increases sales in physical stores.

[0700] A "generative artificial intelligence model" is an artificial intelligence program built to analyze user behavior data and make predictions and suggestions tailored to specific purposes.

[0701] "User behavior" refers to a collection of data about human movement and decision-making in daily life and specific environments.

[0702] "Purchasing behavior" refers to the series of actions and decision-making processes that consumers take from selecting a product or service to making a purchase.

[0703] "Sales promotion information" refers to marketing data such as special offers, discounts, and campaigns provided to consumers to increase their desire to purchase products.

[0704] "Real-time monitoring" means instantly confirming and understanding events and conditions that are actually happening in real time.

[0705] "Sales staff" refers to the human resources responsible for customer service, product recommendations, and sales activities within a store.

[0706] The following system is constructed as an embodiment of this invention.

[0707] The server accumulates user behavior data and purchasing behavior data, and analyzes it using generative artificial intelligence models. Leveraging machine learning platforms like TensorFlow, the server evaluates user behavior patterns and purchasing intent in real time, generating personalized sales promotion information. The generated information is immediately sent to the terminal using real-time processing technologies such as Node.js.

[0708] The terminal is integrated into wearable devices such as smart glasses and notifies sales staff in real time of sales promotion information received from a server. The terminal has a simple user interface and provides information through voice feedback and visual displays, helping staff to make appropriate approaches to customers.

[0709] Users respond to customers based on their movements and reactions within the store, following prompts. These prompts might be in the format of, for example, "Analyze the customer's movements within the store and propose sales promotions to increase their purchase intent." This allows sales staff to make suggestions to customers at the optimal time, streamlining store operations.

[0710] For example, if a user shows high interest in a new product, the terminal will notify staff of promotional information the moment the user touches the product. Based on this information, staff can then inform the customer, for instance, "This product is currently on sale for 20% off." This can further stimulate customer purchasing intent and increase store sales.

[0711] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0712] Step 1:

[0713] The server receives customer behavior data acquired from sensors within the store. This data includes information such as when customers touch products and their movement patterns within the store. The server preprocesses this data and formats it as input data for the generated AI model.

[0714] Step 2:

[0715] The server inputs the formatted behavioral data into a generating AI model to predict the user's purchasing behavior. This calculation quantifies the likelihood that a user is highly likely to purchase a particular product. The resulting predictions are used to create sales promotion information.

[0716] Step 3:

[0717] The server generates sales promotion information based on predicted values. This information includes discounts and campaign details for specific products. This information is then formatted as notification data for sales staff.

[0718] Step 4:

[0719] The terminal receives sales promotion information transmitted from the server in real time. The terminal then notifies sales staff of this information audibly or visually through a wearable device such as smart glasses.

[0720] Step 5:

[0721] Users can provide appropriate sales promotions to customers based on notifications from their devices. Specifically, they verbally communicate special offers for products that customers have shown interest in. By following these prompts, users can provide timely and effective customer service.

[0722] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0723] This invention is a system that combines a generative artificial intelligence model and an emotion engine to effectively notify users of the importance of their daily tasks and facilitate their completion. The operation of the system is described below from the perspectives of the server, terminal, and user.

[0724] Server Role

[0725] The server first stores user behavioral and emotional data sent from the terminal. Behavioral data includes task frequency, start time, and completion time, while emotional data includes information indicating the user's emotional state. The server analyzes this data using a generative artificial intelligence model to extract behavioral and emotional patterns. Based on the analysis results, the server updates the generative AI model and the emotional model, and sends customized information to the terminal for each user.

[0726] Terminal role

[0727] The device receives a generative AI model and an emotion model provided by the server. Based on these models, the device monitors the user's real-time behavior and emotional state. The device determines how the user's emotional state affects task performance and provides voice notifications at the optimal time. For example, if the user is feeling stressed, the device may adjust the timing and use a gentler tone of voice when notifying the user.

[0728] User roles

[0729] The user receives an audio notification from their device and begins working on the notified task. Upon completing the task, the user inputs the result as feedback into their device. They can also report their emotional state at that time. This feedback is sent to a server and used to further improve the AI ​​model.

[0730] Specific example

[0731] Specifically, the system identifies a pattern where users tend to procrastinate on household tasks and experience stress on weekday evenings. This system aims to help users tackle tasks more effectively by providing thoughtful voice notifications on weekday evenings, such as "Relax and start your chores slowly."

[0732] Embodiments of the present invention enable task management that takes emotions into consideration, thereby improving the user's efficiency and quality of life.

[0733] The following describes the processing flow.

[0734] Step 1:

[0735] The server receives user behavioral and emotional data transmitted from the terminal. This behavioral data includes task execution time, frequency, and degree of completion, while the emotional data includes emotional states detected from the user's facial expressions and tone of voice. The server securely stores this data.

[0736] Step 2:

[0737] The server updates the generative AI model and the emotion model using the accumulated data. The generative AI model works to capture the characteristics of the user's behavioral patterns, and the emotion model analyzes the impact of the user's emotional state on their ability to perform tasks. The updated models are then ready to be sent to the terminal to provide the next notification.

[0738] Step 3:

[0739] The device receives AI models and emotion models sent from the server. Using these models, the device begins analyzing the user's daily behavior and emotions in real time. Based on the analysis results, it determines the optimal timing and content of task notifications.

[0740] Step 4:

[0741] The device uses the analysis results to create voice notifications tailored to the user's emotional state. For example, if it detects that the user is feeling stressed, it might issue a gentle notification such as, "Let's take a short break before starting the task."

[0742] Step 5:

[0743] The user receives voice notifications from the device and performs the instructed task. During and after task execution, they input their current emotional state and task progress as feedback to the device.

[0744] Step 6:

[0745] The device sends user feedback to the server. This feedback includes information about the user's task completion rate and changes in their emotions. The server uses this feedback to inform future model updates and continuously improve the system.

[0746] (Example 2)

[0747] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0748] In modern times, it is crucial to respond quickly and accurately to the everyday challenges faced by individual users and to promote efficient action. However, it is difficult to effectively consider the user's emotional state and provide notifications at the optimal time, which can result in difficulties in efficiently completing tasks. This invention aims to solve these problems and improve the efficiency of users' actions and their quality of life through emotionally sensitive notifications.

[0749] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0750] In this invention, the server includes means for analyzing the behavioral and emotional information of individual users using a generative artificial intelligence model to extract novel behavioral and emotional patterns, means for providing considerate voice notifications to users based on the extracted patterns, and means for collecting feedback from users regarding their achievement status and emotions and transmitting information to a service provider to improve the accuracy of the model. This enables accurate understanding of the user's emotional state and notification at the optimal timing.

[0751] A "generative artificial intelligence model" is an algorithm that analyzes user behavior and emotion data to extract individual behavior and emotion patterns and generate information and notifications that are optimal for the user.

[0752] "Behavioral information" refers to data such as the frequency, start time, and end time of tasks that users perform on a daily basis, and forms the basis for analyzing user behavior patterns.

[0753] "Emotional information" refers to data such as the stress and satisfaction a user experiences while performing a task. This information forms the basis for understanding the user's emotional state and effectively adjusting notification content.

[0754] "Behavioral patterns" refer to specific tendencies that indicate how users tend to perform tasks, obtained by analyzing collected behavioral information.

[0755] An "emotional pattern" is a specific tendency that indicates what emotional state a user is most often in, obtained by analyzing collected emotional information.

[0756] "Thoughtful notifications" are notifications delivered at the optimal time and with the most relevant content, based on the user's behavioral and emotional patterns, enabling them to manage tasks more efficiently.

[0757] "Feedback" refers to information about the user's achievement and feelings upon completing a task, which is used to improve the accuracy of the AI ​​model.

[0758] "Providing equipment" refers to the entirety of hardware and software, including servers and user terminals, used for sending and receiving data and providing analysis results and notifications.

[0759] This invention is a system for optimizing task management in a user's daily life, while taking their emotions into consideration. Specific embodiments of this system are described below from the perspectives of the server, terminal, and user.

[0760] Server operation

[0761] The server is primarily responsible for data storage and analysis. It collects behavioral and emotional information transmitted from users' terminals and uses a database to store it. For example, it manages each user's data using a database management system such as SQL. Next, the collected data is analyzed using a generative artificial intelligence model. Programming languages ​​and libraries such as Python and TensorFlow are used here to extract behavioral and emotional patterns for each user. Based on the analysis results, the generative AI model and emotional model are updated to keep them up-to-date.

[0762] Terminal operation

[0763] The device receives a generative AI model and an emotion model provided by the server. Sensors are used on the device to monitor the user's real-time behavior and emotional state. A voice output device is used to notify the user at the optimal time. For example, if the user is calm, a normal alert is issued, and if stress is detected, the tone of voice is softened.

[0764] User roles

[0765] The user receives an audio notification from their device and begins working on the notified task. Upon completion of the task, feedback on the achievement status and emotional state is sent back to the device. This information is then sent back to the server and used to further improve the AI ​​model.

[0766] Specific example

[0767] For example, if analysis reveals that users tend to feel stressed on weekday evenings, this system can provide gentle voice notifications such as, "Let's make the most of your relaxation time tonight," thereby creating an environment where users can focus on their tasks while reducing their stress.

[0768] Example of a prompt

[0769] "Generate gentle, relaxing notifications during the times when users are most likely to experience stress."

[0770] A specific embodiment of this invention enables task management that takes into account the user's emotional state, thereby improving behavioral efficiency and quality of life.

[0771] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0772] Step 1:

[0773] The server collects behavioral and emotional information transmitted from the user's device. It receives user operation history and sensor data as input and stores it in an SQL database. Specifically, it prepares for analysis of task start and end times, user heart rate, and facial expression data.

[0774] Step 2:

[0775] The server analyzes the collected behavioral and emotional information. A generative artificial intelligence model is used for this analysis. The input is the data collected in step 1, and the output is behavioral and emotional patterns. Specifically, Python and TensorFlow are used to analyze data trends and incorporate them into the model.

[0776] Step 3:

[0777] The server updates the generated AI model and emotion model based on the analysis results. The input is the pattern calculated in step 2, which is used to adjust and optimize the model. The output is the latest model parameter set. Updating the model improves the accuracy of user-specific notifications.

[0778] Step 4:

[0779] The server sends the updated generative AI model and sentiment model to the user's device. The device receives this and prepares to monitor real-time behavior and sentiment. Specifically, it instantiates the model on the device and begins preparing notifications.

[0780] Step 5:

[0781] The device monitors the user's behavior and emotions in real time and provides voice notifications at the optimal time. Inputs include real-time data from sensors and models transmitted from a server, which are used to generate notifications. The output is a thoughtful voice notification delivered to the user. For example, if a stressed state is detected, the voice tone is adjusted based on the data.

[0782] Step 6:

[0783] After completing a task, the user enters feedback into the terminal. This feedback includes information about the task's completion status and the user's feelings, and is sent to the server via the terminal. The server receives this feedback and uses it to further optimize the model. The output is an improved model.

[0784] This step enables task management that takes user emotions into consideration, leading to improved efficiency and quality of life.

[0785] (Application Example 2)

[0786] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0787] In modern work environments, performing tasks without considering the emotional state of workers can lead to decreased efficiency. This is especially true in heavy industry and assembly lines, where high levels of stress among workers can easily lead to errors and reduced efficiency. To address this problem, task notifications and support tailored to the emotional state of workers are necessary.

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

[0789] In this invention, the server includes means for analyzing the user's behavior and emotions and notifying them of the importance of daily tasks; means for providing voice notifications to the user based on the analysis results; means for analyzing the user's emotional state and selecting appropriate notification content and methods; means for collecting user feedback and transmitting data to a communication device to update the analysis results; and means for improving emotions and work efficiency in the work environment through multiple work support devices. This enables optimization of the work environment according to the user's emotional state and efficient task management.

[0790] A "generative artificial intelligence model" is an artificial intelligence system that learns based on given data and can automatically generate the optimal output for a specific task.

[0791] "Behavioral analysis" is the process of collecting data on users' actions and task performance, and then analyzing that data to reveal patterns and trends.

[0792] "Emotional state" refers to an indicator of a user's psychological state and mood, which is measured and analyzed through behavior, facial expressions, tone of voice, etc.

[0793] "Voice notifications" refer to a method of communicating information to users using speech synthesis or recorded voices.

[0794] "Collecting feedback" is the activity of gathering information such as the completion status and emotional state of tasks provided by users, and using that information to improve the system.

[0795] A "work support device" is a tool or mechanical device installed in the work environment to assist work and improve efficiency and safety.

[0796] To carry out this invention, the following system is used.

[0797] The server analyzes user behavior and emotional data using a generative artificial intelligence model. Behavioral data includes tasks performed by the user, their frequency, and timing. Emotional data includes indicators of the user's psychological state, which are obtained from sensors such as smart glasses. Based on this data, the server generates customized information for each user and determines the content and optimal timing of notifications.

[0798] The device receives generative AI models and emotion analysis models provided by the server and monitors the user's behavior and emotions in real time. Specifically, the device monitors the user's condition via smart glasses and provides voice notifications according to their emotional state. For example, if the user is feeling stressed, the device provides appropriate support by using gentler wording and tone in the notifications.

[0799] Users receive voice notifications from their devices and perform or adjust tasks accordingly. After completing a task, they input the results as feedback into their device. This feedback is sent to a server and used to further refine and improve the AI ​​model.

[0800] As a concrete example, in a factory environment, if fatigue is detected from the facial expressions and movements of workers performing assembly line tasks, the terminal will offer advice such as, "Why don't you take a short break?" Furthermore, if the work is deemed to be progressing smoothly, it will provide positive feedback such as, "You're on a good pace, keep it up!"

[0801] An example of a prompt message is, "If work efficiency is declining, consider ways to provide workers with appropriate, emotion-based feedback." This prompt is used to train generative AI models, enabling more accurate sentiment analysis and notifications.

[0802] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0803] Step 1:

[0804] The server receives user behavioral and emotional data through sensors such as smart glasses. This input data includes the timing and frequency of the user's work, as well as psychological indicators related to facial expressions and voice tone. The server stores this data in a database.

[0805] Step 2:

[0806] The server analyzes the accumulated data using a generative artificial intelligence model. This analysis extracts behavioral and emotional patterns to understand the user's task performance and mental state. The output of the analysis is information about these patterns, which is used in the next step.

[0807] Step 3:

[0808] Based on the analysis results, the server uses a generated AI model to determine the appropriate content and timing of task notifications. At this stage, a notification message is generated that takes into account the user's psychological state. This output information is then sent to the terminal.

[0809] Step 4:

[0810] The terminal provides voice notifications to the user based on notification information received from the server. It takes notification information from the server as input and provides voice notifications to the user at the appropriate timing and tone as output. These notifications help optimize the user's work efficiency.

[0811] Step 5:

[0812] The user receives an audio notification from their device and performs the notified task. After completing the task, the user inputs feedback into the device, including the result and their emotional state. This feedback is used in the next step.

[0813] Step 6:

[0814] The device sends user feedback to the server. This input includes the user's work results and emotional state, and is used to update the generated AI model as output. The server receives this feedback and retrains the AI ​​model to further optimize future notifications.

[0815] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0816] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0817] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0818] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0819] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0820] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0821] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0822] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0823] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0824] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0825] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0826] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0827] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0828] 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.

[0829] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0830] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0831] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0832] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0833] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0834] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0835] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0836] The following is further disclosed regarding the embodiments described above.

[0837] (Claim 1)

[0838] A means of analyzing user behavior using a generative artificial intelligence model and notifying users of the importance of everyday tasks,

[0839] A means of providing voice notifications to users based on the analysis results,

[0840] A means for collecting user feedback and transmitting data to a communication device to update the analysis results,

[0841] A system that includes this.

[0842] (Claim 2)

[0843] The system according to claim 1, which automatically adjusts the timing of issue notifications using the analysis results.

[0844] (Claim 3)

[0845] The system according to claim 1, which stores user behavior data on a server and analyzes behavior patterns.

[0846] "Example 1"

[0847] (Claim 1)

[0848] A means of updating artificial intelligence generation technology using behavioral information collected from users' devices and analyzing new behavioral trends,

[0849] A means of using an output device to notify users of high-priority issues via voice based on the analysis results,

[0850] A means for collecting responses from users regarding task completion status and passing information to a data transmission device to improve the model based on the analyzed results,

[0851] A system that includes this.

[0852] (Claim 2)

[0853] The system according to claim 1, which automatically sets a notification of an issue at an appropriate time based on the results of the analysis.

[0854] (Claim 3)

[0855] The system according to claim 1, which stores user behavior information in a central processing unit and analyzes the behavioral patterns.

[0856] "Application Example 1"

[0857] (Claim 1)

[0858] A means of analyzing user behavior using a generative artificial intelligence model and notifying users of the importance of everyday tasks,

[0859] A means of providing voice notifications to users based on the analysis results,

[0860] A means for collecting user feedback and transmitting data to a communication device to update the analysis results,

[0861] A means of analyzing users' purchasing behavior and providing sales promotion information to increase purchasing intent,

[0862] A means of monitoring customer movements within the store in real time and notifying sales staff,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, which automatically adjusts the timing of issue notifications using analysis results and optimizes sales promotion activities.

[0866] (Claim 3)

[0867] The system according to claim 1, which stores user behavior data on a server and analyzes behavioral patterns and purchasing behavior.

[0868] "Example 2 of combining an emotion engine"

[0869] (Claim 1)

[0870] A method for analyzing individual users' behavioral and emotional information using a generative artificial intelligence model to extract novel behavioral and emotional patterns,

[0871] A means of providing considerate voice notifications to users based on extracted patterns,

[0872] A means for collecting feedback from users regarding their achievement status and emotions, and transmitting that information to a device to improve the accuracy of the model,

[0873] A system that includes this.

[0874] (Claim 2)

[0875] The system according to claim 1, which automatically selects appropriate notification timing and adjustment content considering the analyzed emotional patterns.

[0876] (Claim 3)

[0877] The system according to claim 1, which collects user behavior information and emotional state and stores them in a collection device, and analyzes them using AI technology.

[0878] "Application example 2 when combining with an emotional engine"

[0879] (Claim 1)

[0880] A means of analyzing user behavior using a generative artificial intelligence model and notifying users of the importance of everyday tasks,

[0881] A means of providing voice notifications to users based on the analysis results,

[0882] A means for analyzing the user's emotional state and selecting appropriate notification content and method,

[0883] A means for collecting user feedback and transmitting data to a communication device to update the analysis results,

[0884] A means to improve emotions and work efficiency in the work environment through multiple work support devices,

[0885] A system that includes this.

[0886] (Claim 2)

[0887] The system according to claim 1, which automatically adjusts the timing and method of notification of issues using the analysis results.

[0888] (Claim 3)

[0889] The system according to claim 1, which stores user behavior data and emotional data on a server and analyzes behavior patterns and emotional patterns. [Explanation of symbols]

[0890] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of analyzing user behavior using a generative artificial intelligence model and notifying users of the importance of everyday tasks, A means of providing voice notifications to users based on the analysis results, A means for collecting user feedback and transmitting data to a communication device to update the analysis results, A system that includes this.

2. The system according to claim 1, which automatically adjusts the timing of task notifications using the analysis results.

3. The system according to claim 1, which stores user behavior data on a server and analyzes behavior patterns.

Images