System

Abstract

A system is provided.SOLUTION: A system, comprising: means for collecting text data of a user; means for pre-processing the collected text data; means for training an artificial intelligence model to learn characteristic behavior and thinking of the user using the pre-processed text data; means for generating a reply that mimics the behavior of the user in real-time using the artificial intelligence model; and means for providing the generated reply to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Parents today face a great deal of stress and strain in raising children, especially when a consistent educational approach and response is required. It is also often difficult for busy parents to maintain high-quality communication with their children. Furthermore, parents often lack consistency when communicating their ideas and educational approaches to their children, which can lead to confusion for the children. This creates a problem that makes it difficult to achieve effective parenting and education. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting user text data, a means for preprocessing the collected text data, a means for training an AI model that learns the user's characteristic speech, behavior, and way of thinking using the preprocessed text data, a means for generating responses that mimic the user's speech and behavior in real time using the AI ​​model, and a means for providing the generated responses to the user. The system also includes a means for continuously updating the AI ​​model and retraining it based on the latest user text data, and a means for adjusting the AI ​​model based on feedback provided by the user, thereby enabling the AI ​​model to always reflect the user's latest thinking and educational policies. In this way, the system maintains high-quality, consistent communication between parents and children, providing support for achieving more ideal parenting.

[0006] "User" refers to a person who uses the system, and primarily refers to parents who are raising children.

[0007] "Text data" refers to textual information such as sentences, statements, and messages generated by users.

[0008] "Means of collection" refers to the method or mechanism for obtaining user text data.

[0009] "Preprocessing means" refers to methods and mechanisms for formatting collected text data into a form that is easy to analyze.

[0010] An "artificial intelligence model" refers to a machine learning algorithm that learns a user's characteristic behavior and way of thinking and generates responses based on that.

[0011] "Training means" refers to the method or process by which an AI model is given data and trained.

[0012] "Means for generating responses" refers to a method or mechanism that uses a trained artificial intelligence model to create responses based on the user's behavior.

[0013] "Means for providing" refers to the method or mechanism for delivering the generated response to the user or child.

[0014] "Continuous updating" refers to the methods and processes used to retrain an AI model with the latest user information.

[0015] "Feedback" refers to a user providing input on a system's response or functionality.

[0016] "Tuning" refers to a method or process for optimizing the operation of an artificial intelligence model based on user feedback. [Brief explanation of the drawings]

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

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

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

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0038] This invention is a system that collects users' text data, analyzes it using an AI model, and generates and provides responses that reflect the user's characteristic behavior and way of thinking. This system functions in cooperation between a server, a terminal, and the user.

[0039] First, users install a dedicated application on their devices. Through this application, users record their own speech and messages on a daily basis. The device collects this text data and sends it to a server at regular intervals. The collected data is first preprocessed. The server performs data preprocessing, including filtering unnecessary data, normalizing, and tokenizing. The preprocessed data is used as training data for the AI ​​model.

[0040] The server then uses the preprocessed data to train an AI model that learns the user's characteristic behaviors and thoughts. This training process enables the AI ​​model to generate responses that reflect the user's phrasing, catchphrases, and educational principles.

[0041] The device is responsible for real-time dialogue with the child. For example, when a child types a question into the device, such as "What shall we play today?", that information is sent to the server. The server inputs the received question into an AI model and generates the most appropriate response. That response is then provided to the child via the device. For example, a response such as "Shall we play ball in the park today?" is generated and conveyed to the child.

[0042] Furthermore, the present invention features continuous learning. By collecting daily updates from users, periodically preprocessing them, and retraining the AI ​​model, it is possible to always reflect the user's latest thinking and educational policies. Users can also provide feedback, which the server uses to adjust the AI ​​model. In this way, the system is continuously optimized to meet the user's needs.

[0043] As a specific example, suppose a user asks, "I'm worried about how to get my child to develop a good study habit." In this case, the device sends the consultation to the server. The server uses an AI model to generate advice such as, "Why don't you try creating a schedule together that determines study time?" and provides this advice to the user via the device. In this way, the present invention supports high-quality, consistent communication between parents and children, providing assistance for achieving more ideal parenting.

[0044] Through the above process, the present invention provides a new means for reducing stress and burden on parents in the modern child-rearing environment and for realizing effective and consistent education.

[0045] The processing flow will be explained below.

[0046] Step 1:

[0047] Users install a dedicated application on their devices and use it on a daily basis. The devices record the user's comments and messages and collect this text data at regular intervals.

[0048] Step 2:

[0049] The device encrypts the collected text data and sends it securely to the server.

[0050] Step 3:

[0051] The server stores the received text data in a database, which is then filtered to remove unnecessary information and spam.

[0052] Step 4:

[0053] The server normalizes the stored text data, specifically by standardizing full-width and half-width characters, removing unnecessary spaces and special characters, and formatting the data.

[0054] Step 5:

[0055] The server tokenizes the normalized text data, splitting it into words and converting it into a format that is easy for the AI ​​model to learn.

[0056] Step 6:

[0057] The server uses the tokenized data to train an AI model, which learns the user's characteristic behaviors and thoughts. Specifically, it uses natural language processing algorithms and optimizes the model through a multi-layer neural network.

[0058] Step 7:

[0059] The server stores the trained AI model and distributes it to devices as needed, while the AI ​​model is continuously updated to reflect the user's latest information.

[0060] Step 8:

[0061] The device is responsible for real-time interaction with the user and the child. When the child speaks to the device, the speech is sent to the server in text format.

[0062] Step 9:

[0063] The server tokenizes the received text data and feeds it into a trained AI model, which mimics the user's behavior and thoughts to generate appropriate responses.

[0064] Step 10:

[0065] The server sends the generated response to the device, which then provides the response to the child as voice or text. For example, if the child asks, "What shall we play today?", the device responds, "Shall we play ball in the park today?"

[0066] Step 11:

[0067] Users can provide feedback to the system through the application as needed, for example, by rating the system "the response was appropriate" or by inputting specific requests such as "I would like the system to respond more like this."

[0068] Step 12:

[0069] The server analyzes the feedback provided by the user and adjusts the AI ​​model, optimizing the system to generate responses that better suit the user's needs.

[0070] Step 13:

[0071] The server periodically collects new data, preprocesses it, and retrains the AI ​​model, ensuring that it always reflects the latest user thinking and educational policies.

[0072] Example 1

[0073] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0074] In today's child-rearing environment, it is difficult to alleviate the stress and burden on parents and achieve effective and consistent communication. Furthermore, in order for parents to provide appropriate education and advice through dialogue with their children, continuous learning and feedback are necessary, and achieving this requires advanced technology.

[0075] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0076] In this invention, the server includes a means for collecting user text data, a means for preprocessing the collected text data, and a means for training an AI model that learns the user's characteristic behavior and way of thinking using the preprocessed text data. This allows parents to use the generated AI model to provide appropriate responses to their children in real time. The server also includes a means for continuously updating the AI ​​model and retraining it based on the latest user text data, and a means for adjusting the AI ​​model based on feedback provided by the user, thereby enabling the server to generate optimal responses that always reflect the latest information.

[0077] "User text data" refers to the content of statements and messages that users input on a daily basis, including conversations, questions, opinions, and the like.

[0078] "Means of collection" refers to the function for saving the text data entered by the user in a certain format and transferring it to a server as necessary.

[0079] "Preprocessing" refers to the process of removing unnecessary information from collected text data and converting the data into a unified, easily analyzable format.

[0080] An "artificial intelligence model" refers to a system that is trained using machine learning algorithms to learn a user's characteristic behavior and way of thinking and generate responses based on that.

[0081] "Training" refers to the process of feeding preprocessed text data to an artificial intelligence model to allow the model to learn user characteristics.

[0082] A "real-time query" is a question or request entered by a user on the fly that requires an immediate response.

[0083] "Answer generation means" refers to the process of using an artificial intelligence model to generate an appropriate answer to a user's query.

[0084] "Generated answer" refers to a response to a user's query that is generated by an artificial intelligence model.

[0085] "Means for providing" refers to a function or interface for displaying the generated response to the user.

[0086] "Continuously updating" refers to the process of periodically retraining an artificial intelligence model with new data to maintain or improve the model's accuracy and effectiveness.

[0087] "Feedback" refers to evaluations and opinions provided by users, which are used to improve and adjust the quality of the system.

[0088] "Adjustment means" refers to the process of adjusting the parameters and algorithms of an artificial intelligence model based on user feedback to improve the model's response quality.

[0089] This invention is a system that collects users' text data, analyzes it using an AI model, and generates and provides responses that reflect the user's characteristic behavior and way of thinking. This system functions in cooperation between a server, a terminal, and the user.

[0090] First, users install a dedicated application on their device. Through this application, users can record their daily statements and messages. This involves a device such as a smartphone or tablet, and software that connects to a server via internet communication.

[0091] The device sends the recorded text data to a server at a fixed interval. The security of the data is ensured by using secure communication protocols such as HTTPS. The server then preprocesses the received data. Specifically, it performs processes such as filtering unnecessary data, normalizing, and tokenizing. This converts the data into a format that is easy to analyze.

[0092] The server then uses the preprocessed data to train an AI model, which can be a generative AI model such as GPT-3. The model is designed to learn the user's characteristic behaviors and thoughts and is trained using thousands to millions of data points. This process can take hours or days.

[0093] Real-time interaction begins when a user inputs a question or query into the device. For example, if the user inputs a question such as "What shall we play today?", the device sends this information to the server. The server inputs the received question into an AI model and generates an optimal response. The generated response is provided to the user via the device. For example, a response such as "Shall we play ball in the park today?" is generated.

[0094] Furthermore, the present invention features continuous learning. By collecting daily updates from users, periodically preprocessing them, and retraining the AI ​​model, it is possible to always reflect the user's latest thinking and educational policies. Users can also provide feedback. Based on this feedback, the server adjusts the AI ​​model. Specifically, it can strengthen highly rated responses and provide additional training to improve poorly rated responses.

[0095] As a concrete example, consider the case where a user inputs, "I'm worried about how to get my child to develop a good study habit." In this case, the device sends the inquiry to the server. The server uses an AI model to generate advice such as, "Why don't you try creating a schedule together that determines study time?" and provides it to the user via the device. In this way, the present invention supports high-quality, consistent communication between parents and children, providing assistance for achieving more ideal parenting.

[0096] An example of a prompt sentence is, "The user inputs, 'I'm worried about how to help my child develop study habits.' Please generate the most appropriate advice based on the data collected from the user's statements and messages."

[0097] Through the above process, the present invention provides a new means for reducing stress and burden on parents in the modern child-rearing environment and for realizing effective and consistent education.

[0098] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0099] Step 1: The user installs the application and collects text data.

[0100] Input: User comments and messages

[0101] Output: Collected text data

[0102] The device records user comments and messages through a dedicated application. This application has a chat-style interface and saves the comments and questions that users enter on a daily basis as text data. It also uses a voice recognition function to convert voice input into text and record it.

[0103] Step 2: The device sends the collected data to the server.

[0104] Input: Collected text data

[0105] Output: Data sent to the server

[0106] The device periodically sends the collected text data to the server via the HTTPS protocol, which ensures secure data transfer.

[0107] Step 3: The server preprocesses the data.

[0108] Input: Transmitted text data

[0109] Output: Preprocessed data

[0110] The server filters the submitted text data to remove unnecessary information. Specifically, it uses regular expressions to remove noise and stop words. It also normalizes the data, converting uppercase and lowercase letters, numbers, and special characters into a unified format. Finally, it tokenizes the data, splitting it into units that are easier to analyze.

[0111] Step 4: The server trains the AI ​​model.

[0112] Input: Preprocessed data

[0113] Output: A trained AI model

[0114] The server then feeds the preprocessed data to an AI model (such as GPT-3) to learn the user's characteristic behaviors and thoughts. This training process uses thousands to millions of data points and can take hours or even days. As a result, the AI ​​model is able to generate responses that reflect the user's unique phrasing and habits of speech.

[0115] Step 5: The user enters a real-time question.

[0116] Input: User question or query

[0117] Output: Query sent to the terminal

[0118] The user inputs a question or query into the device, for example, "What should we play today?" This information is immediately transmitted to the server.

[0119] Step 6: The server uses the AI ​​model to generate a response.

[0120] Input: User query

[0121] Output: The generated response

[0122] The server inputs the received question into an AI model and generates the best possible response. The generated response is specific and reflects the user's characteristics. A response such as "Shall we play ball in the park today?" is generated.

[0123] Step 7: The terminal provides the generated response to the user.

[0124] Input: The response sent by the server

[0125] Output: The response provided to the user

[0126] The device displays the generated responses to the user in real time, and the user can provide feedback, for example by giving a thumbs up if the response was helpful or indicating if they would like more suggestions.

[0127] Step 8: The server continues to learn and update the model.

[0128] Input: New data and feedback from users

[0129] Output: Updated AI model

[0130] The server collects daily updates and feedback from users, preprocesses them, and retrains the AI ​​model, ensuring that the model always reflects the latest information, improving the accuracy and effectiveness of its responses.

[0131] In this way, throughout the series of processing steps, the system can continue to provide the best possible response tailored to the user's needs.

[0132] (Application example 1)

[0133] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0134] Conventional content delivery systems have had difficulty providing customized content that fully reflects the individual needs and characteristics of users. Therefore, improving user satisfaction and increasing usage time are key challenges.

[0135] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0136] In this invention, the server includes means for collecting user text data, means for preprocessing the collected text data, means for training an AI model that learns the user's characteristic speech and behavior and way of thinking using the preprocessed text data, means for generating responses that imitate the user's speech and behavior in real time using the AI ​​model, means for providing the generated responses to the user, and means for generating and delivering content customized based on the user's characteristics, thereby enabling delivery of specialized content tailored to the user.

[0137] "User text data" refers to statements and messages that users input on a daily basis.

[0138] "Preprocessing" refers to converting collected text data into an analyzable format by filtering, normalizing, tokenizing, and other processes.

[0139] An "artificial intelligence model" is a collection of machine learning algorithms that learn a user's characteristic behavior and way of thinking and generate responses based on that.

[0140] "Real time" means that processing from data input to output is done instantaneously, with almost no delay.

[0141] "Customized content" refers to information and media that is specifically created based on the characteristics and preferences of an individual user.

[0142] "Feedback" refers to information such as user ratings and opinions, which are used to adjust and improve the system.

[0143] This invention is a customized content delivery system that uses an artificial intelligence model that collects user text data and learns user characteristics based on that data. This system is composed of three entities: a server, a terminal, and a user.

[0144] First, users install a dedicated application on their device. Through this application, users can enter their own comments and messages on a daily basis. The device collects this text data and sends it to a server at regular intervals.

[0145] The server first preprocesses the collected data. This involves filtering out unnecessary data, normalizing it, and tokenizing it. The preprocessed data is then used as training data for the artificial intelligence model. During preprocessing, the server analyzes the data using a natural language processing library (e.g., nltk).

[0146] The server then trains an artificial intelligence model on the preprocessed data. The model uses machine learning algorithms (such as sklearn's Ridge model) to learn the user's characteristic behaviors and thoughts, allowing the model to generate responses that reflect the user's unique phrasing and habits of speech.

[0147] The device interacts with the user in real time. For example, when the user inputs a question such as "What shall we play today?", the information is immediately sent to the server. The server inputs the received question into an artificial intelligence model and generates the most appropriate response. The response is then provided to the user via the device. For example, the response generated is "Shall we play ball in the park today?" and conveyed to the user.

[0148] Furthermore, the present invention also has a continuous learning function. The server periodically collects daily updates from users, preprocesses them, and retrains the AI ​​model to always reflect the latest user thinking and characteristics. Users can provide feedback, and the server will adjust the AI ​​model based on this feedback.

[0149] To generate and deliver customized content based on the user's characteristics, the server analyzes the collected data and provides videos and articles that match the user's preferences. For example, if a user frequently mentions a particular topic, content related to that topic will be generated and delivered preferentially.

[0150] An example of a prompt sentence is "What shall we play today?" In this way, the present invention can provide users with consistent, high-quality responses and customized content.

[0151] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0152] Step 1:

[0153] Users install a dedicated application on their devices, and through this application, they begin to input their own comments and messages on a daily basis. This input data is collected in text format.

[0154] Step 2:

[0155] The device sends the collected text data to the server at a fixed frequency. The input is the user's speech or message, and the output is the data sent to the server.

[0156] Step 3:

[0157] The server preprocesses the received text data by filtering, normalizing, tokenizing, and removing unnecessary data. The input is the user's raw data, and the output is preprocessed, well-formed data. Here, a natural language processing library (e.g., nltk) is used.

[0158] Step 4:

[0159] The server trains an AI model based on the preprocessed data. The input is the preprocessed text data, and the output is an AI model that has learned the user's characteristics. Here, the model is trained using a machine learning algorithm (e.g., sklearn's Ridge model).

[0160] Step 5:

[0161] The user types a question or request into the terminal. For example, the user types a prompt such as "What shall we play today?" The input is the user's question.

[0162] Step 6:

[0163] The terminal sends this question to the server. The input is the user's question, and the output is the data sent to the server.

[0164] Step 7:

[0165] The server inputs the received question into an artificial intelligence model to generate the most appropriate response. The input is the user's question, and the output is the generated response.

[0166] Step 8:

[0167] The generated response is provided to the user from the server via the terminal. The input is the response sent from the server, and the output is what is displayed to the user. For example, the response "Shall we play ball in the park today?" is displayed on the terminal.

[0168] Step 9:

[0169] The terminal collects the user's daily updated information and periodically sends it to the server. The input is newly collected text data, and the output is the transmission of updated data to the server.

[0170] Step 10:

[0171] The server preprocesses the update data using the same method as preprocessing and retrains the AI ​​model. The input is the preprocessed update data, and the output is an improved artificial intelligence model.

[0172] Step 11:

[0173] The terminal collects the feedback provided by the user and sends it to the server. The input is the user's feedback and the output is the feedback sent to the server.

[0174] Step 12:

[0175] The server adjusts the AI ​​model based on the feedback. The input is the user's feedback, and the output is the adjusted artificial intelligence model. For example, the model parameters are fine-tuned based on the feedback that the advice was good.

[0176] Through the above processing steps, the system can provide customized content that reflects the unique characteristics of the user.

[0177] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0178] This invention is a system that collects user text data, analyzes it using an artificial intelligence model and an emotion engine, and generates and provides responses that reflect the user's characteristic words, actions, thoughts, and emotions. This system functions in cooperation with a server, a terminal, and a user.

[0179] First, the user installs a dedicated application on their device and uses it on a daily basis. The device records the user's comments and messages and collects this text data at regular intervals. The device encrypts the collected text data and securely sends it to a server. The server stores the received text data in a database. The stored text data is first filtered to remove unnecessary information and spam.

[0180] The server then normalizes the stored text data, specifically by standardizing full-width and half-width characters, removing unnecessary spaces and special characters, and formatting the data. The normalized text data is then tokenized and used as training data for the AI ​​model.

[0181] The server uses the tokenized data to train the AI ​​model, which learns the user's characteristic behaviors and thoughts. This training process allows the AI ​​model to generate responses that reflect the user's phrasing, catchphrases, and educational principles.

[0182] A distinctive feature of the present invention is the incorporation of an emotion engine. The emotion engine is located in the server and analyzes emotions from the user's text data. The emotion information analyzed by the emotion engine is used as an important element in generating responses from the AI ​​model. For example, if the user is feeling stressed, a response that alleviates the user's emotions will be generated.

[0183] As a concrete example, suppose a child types a question into a device, such as "Why is Mommy angry?" When this information is sent to the server, the server tokenizes the question and inputs it into the emotion engine. The emotion engine analyzes the user's emotion based on past and current data. The analysis result determines that the emotion is "anger."

[0184] The AI ​​model then generates a response based on the emotion analysis, such as "Mommy is just tired, so let her get some rest," and sends it to the device via the server. The device then provides this response to the child via voice or text.

[0185] Furthermore, the present invention features continuous learning. By collecting daily updates from users and periodically preprocessing them to retrain the AI ​​model and emotion engine, it is possible to always reflect the latest user thoughts and emotions. Users can also provide feedback. Based on this feedback, the server adjusts the AI ​​model and emotion engine. In this way, the system is continuously optimized to meet the user's needs.

[0186] Through the above process, this invention provides a new means to reduce stress and burden on parents in the modern child-rearing environment and to realize effective and consistent education. In particular, by analyzing emotions and generating responses based on them, more humane and empathetic communication becomes possible.

[0187] The processing flow will be explained below.

[0188] Step 1:

[0189] Users install a dedicated application on their devices and use it on a daily basis. The devices record the user's comments and messages and collect this text data at regular intervals.

[0190] Step 2:

[0191] The device encrypts the collected text data and sends it securely to the server.

[0192] Step 3:

[0193] The server stores the received text data in a database, which is then filtered to remove unnecessary information and spam.

[0194] Step 4:

[0195] The server normalizes the stored text data, specifically by standardizing full-width and half-width characters, removing unnecessary spaces and special characters, and formatting the data.

[0196] Step 5:

[0197] The server tokenizes the normalized text data, splitting it into words and converting it into a format that is easy for the AI ​​model to learn.

[0198] Step 6:

[0199] The server uses the tokenized data to train an AI model, which learns the user's characteristic behaviors and thoughts. Specifically, it uses natural language processing algorithms and optimizes the model through a multi-layer neural network.

[0200] Step 7:

[0201] The server uses a trained emotion engine to analyze emotions from the user's text data, based on past and current data.

[0202] Step 8:

[0203] The device is responsible for real-time dialogue between the user and the child. When the child speaks to the device and types a question such as "Why is Mommy angry?", the response is sent to the server in text format.

[0204] Step 9:

[0205] The server tokenizes the received text data and inputs it into a trained emotion engine, which analyzes the user's emotions and extracts the emotion "anger."

[0206] Step 10:

[0207] The server uses the AI ​​model to generate the most appropriate response based on the analysis results of the emotion engine. In this case, the response generated is, "Mom is just tired, so let her get some rest."

[0208] Step 11:

[0209] The server sends the generated response to the terminal, which provides the response to the child in voice or text format.

[0210] Step 12:

[0211] Users can provide feedback to the system through the application as needed, for example, by rating the system "the response was appropriate" or by inputting specific requests such as "I would like the system to respond more like this."

[0212] Step 13:

[0213] The server analyzes the feedback provided by the user and adjusts the AI ​​model and emotion engine, optimizing the system to generate responses that better suit the user's needs.

[0214] Step 14:

[0215] The server periodically collects new data, preprocesses it, and retrains the AI ​​model and emotion engine, ensuring that the latest user thoughts and emotions are always reflected.

[0216] Through the above processing steps, the present invention supports high-quality, consistent communication between parents and children, and provides assistance for achieving more ideal child-rearing. In particular, by analyzing emotions and generating responses based on those emotions, more humane and empathetic communication becomes possible.

[0217] Example 2

[0218] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0219] Conventional text data analysis systems have difficulty generating responses that take into account the user's characteristic behavior and emotions, resulting in a decline in the quality of communication. Furthermore, given the need for continuous learning and real-time responses, conventional systems were not flexible enough. They also lacked a mechanism for optimizing the system using user feedback.

[0220] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0221] In this invention, the server includes means for encrypting and transmitting user text data, means for storing, filtering, and normalizing the transmitted text data, means for training an AI model that learns the user's characteristic behavior and way of thinking using the tokenized data, and means for generating a response that takes the user's emotions into consideration using the AI ​​model based on the emotion analysis results, thereby making it possible to provide high-quality responses that reflect the user's behavior and emotions in real time.

[0222] "User text data" refers to sentences or messages that a user inputs or generates through a terminal.

[0223] "Encryption" is the process of transforming data using a specific algorithm to make it unreadable to third parties in order to transmit it securely.

[0224] "Transmitting" refers to moving data from one point to another, and in this case means moving data from a terminal to a server.

[0225] "Storage" means storing data on an electronic recording medium in order to keep it safe for a long period of time.

[0226] "Filtering" is the process of removing unnecessary information and spam from data and extracting only useful information.

[0227] "Normalization" is the process of converting data into a unified format and making it consistent.

[0228] "Tokenization" is the process of dividing text data into small units such as words or sentences based on certain rules.

[0229] An "artificial intelligence model" is an algorithm or system that can learn and make inferences or predictions based on specific data.

[0230] "Training" is the process by which an artificial intelligence model learns from given data and improves its accuracy.

[0231] "Sentiment analysis" is the process of identifying emotions from a user's text data and quantitatively assessing the type and intensity of those emotions.

[0232] "Generation" means that the artificial intelligence model creates new data or responses based on the data and analysis results obtained.

[0233] "Feedback" refers to user evaluations and opinions on the system's performance and results.

[0234] "Tuning" refers to optimizing system parameters and settings based on feedback to improve performance and results.

[0235] MODE FOR CARRYING OUT THE INVENTION

[0236] This invention is a system that collects user text data, analyzes it using an artificial intelligence model and an emotion engine, and generates and provides responses that reflect the user's characteristic words, actions, thoughts, and emotions. This system functions in cooperation with a server, a terminal, and a user.

[0237] Terminal

[0238] First, the user installs a dedicated application on the device and uses it on a daily basis. The device records the user's statements and messages and collects this text data at a certain frequency. For example, a child might type "Why is Mommy angry?" into the device. The device encrypts the collected text data and securely transmits it to the server.

[0239] server

[0240] The server stores the received text data in a database. The stored text data is first filtered to remove unnecessary information and spam. The server then normalizes the stored text data. Specifically, it standardizes full-width and half-width characters, removes unnecessary spaces and special characters, and formats the data. This ensures that the data is processed in a consistent format.

[0241] The normalized text data is tokenized and used as training data for the AI ​​model. The server trains the AI ​​model using the tokenized data. For example, using a deep learning framework (e.g., TensorFlow, PyTorch), the AI ​​model learns the user's words, behaviors, and thoughts. This training process enables the AI ​​model to generate responses that reflect the user's phrasing, catchphrases, and educational principles.

[0242] A distinctive feature of the present invention is the incorporation of an emotion engine. The emotion engine is located in the server and analyzes emotions from the user's text data. The emotion information analyzed by the emotion engine is used as an important element in generating responses from the AI ​​model. For example, if the user is feeling stressed, a response that alleviates the user's emotions will be generated.

[0243] Specific examples

[0244] For example, a child might type a question into their device, such as "Why is Mommy angry?" When this information is sent to the server, the server tokenizes the question and inputs it into the emotion engine. The emotion engine analyzes the user's emotion based on past and current data. The analysis result determines that the emotion is "anger." The AI ​​model then generates a response based on the emotion analysis result. For example, a response such as "Mommy is just tired, so let her get some rest" is generated and sent to the device via the server. The device then provides this response to the child as voice or text.

[0245] Furthermore, the present invention features continuous learning. By collecting daily updates from users and periodically preprocessing them to retrain the AI ​​model and emotion engine, it is possible to always reflect the latest user thoughts and emotions. Users can also provide feedback. Based on this feedback, the server adjusts the AI ​​model and emotion engine. In this way, the system is continuously optimized to meet the user's needs.

[0246] Through the above process, the present invention provides a new means for reducing stress and strain on users in modern communication environments and generating effective and consistent responses. In particular, analyzing emotions and generating responses based on those emotions enables more human and empathetic communication.

[0247] keyword

[0248] Generative AI Models

[0249] An artificial intelligence model that learns a user's characteristic behavior and way of thinking and generates appropriate responses.

[0250] Prompt statement

[0251] Specific examples of text to input into the system, such as the question "Why is Mom mad?"

[0252] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0253] Program processing steps

[0254] Step 1:

[0255] Text data collection and encryption

[0256] input

[0257] Text data that a user enters into a device, such as a statement like "Why is Mom angry?"

[0258] operation

[0259] Users use a dedicated application to input comments and messages on a daily basis.

[0260] The terminal collects this input text data.

[0261] The collected text data is encrypted using an encryption algorithm such as AES.

[0262] output

[0263] Encrypted text data is generated.

[0264] Step 2:

[0265] Encrypted data transmission and storage

[0266] input

[0267] Encrypted text data.

[0268] operation

[0269] The device sends encrypted data securely to the server, typically using the SSL / TLS protocol.

[0270] The server stores the received encrypted data in a database.

[0271] Perform an integrity check to ensure the data was saved correctly.

[0272] output

[0273] The stored encrypted data is placed in a database.

[0274] Step 3:

[0275] Filtering and normalizing text data

[0276] input

[0277] Text data stored in a database.

[0278] operation

[0279] The server retrieves text data from a database and filters it for spam and unwanted information.

[0280] The server normalizes the filtered data, specifically by unifying full-width and half-width characters and removing unnecessary spaces and special characters.

[0281] output

[0282] Filtered and normalized text data is generated.

[0283] Step 4:

[0284] Tokenization of text data

[0285] input

[0286] Filtered and normalized text data.

[0287] operation

[0288] The server tokenizes the normalized text data, for example splitting the text "Why is Mom mad?" into individual words.

[0289] output

[0290] Tokenized data is generated.

[0291] Step 5:

[0292] Training an AI model

[0293] input

[0294] Tokenized text data.

[0295] operation

[0296] The server uses the tokenized data to train an AI model, which uses a deep learning framework (e.g., TensorFlow, PyTorch) to learn the user's characteristic behaviors and thoughts.

[0297] output

[0298] A trained AI model is generated.

[0299] Step 6:

[0300] Conducting sentiment analysis

[0301] input

[0302] Text data sent by the user.

[0303] operation

[0304] The server inputs the text data into the emotion engine and performs emotion analysis. For example, a question such as "Why is Mom angry?" is classified as the emotion "anger."

[0305] output

[0306] Emotional information is analyzed.

[0307] Step 7:

[0308] Response Generation

[0309] input

[0310] Sentiment analysis results and trained AI model.

[0311] operation

[0312] The server uses an AI model based on the results of the emotion analysis to generate an appropriate response, such as "Mom is just tired, so let her get some rest."

[0313] output

[0314] A generated response is created.

[0315] Step 8:

[0316] Sending and serving responses

[0317] input

[0318] The generated response.

[0319] operation

[0320] The server sends the generated response to the terminal.

[0321] The terminal provides the received response to the user, for example, the response is communicated to the user in text or audio format.

[0322] output

[0323] The response provided to the user is complete.

[0324] Step 9:

[0325] Continuous learning and feedback

[0326] input

[0327] User's daily text data and feedback.

[0328] operation

[0329] The user provides feedback on the generated response, for example, "This response was appropriate" or "I would have liked more specific information."

[0330] The server adjusts the parameters of the AI ​​model and emotion engine based on user feedback and performs retraining.

[0331] output

[0332] The optimized AI model and emotion engine are updated.

[0333] (Application example 2)

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

[0335] In conventional security services, communication between operators and customers is primarily manual, making it difficult to respond flexibly to customer emotions. Furthermore, there are no systems that can analyze emotions and generate appropriate responses in emergencies that require real-time response. This can lead to reduced customer satisfaction and delayed responses.

[0336] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user text data, means for encrypting the collected text data and securely transmitting it to the server, means for preprocessing the text data received by the server, means for tokenizing the preprocessed text data, means for training an artificial intelligence model that learns the user's characteristic words and actions and way of thinking using the tokenized data, means for analyzing emotions from the user's text data using an emotion engine, means for generating responses that imitate the user's words and actions in real time based on the analysis results of the emotion engine using the artificial intelligence model, and means for providing the generated responses to the user. This enables flexible and appropriate real-time responses according to emotions.

[0337] "Means for collecting user text data" refers to devices and software mechanisms for collecting messages and comments made by users.

[0338] "Means for encrypting collected text data and securely transmitting it to a server" refers to technologies and protocols that encrypt text data so that it cannot be deciphered by third parties and transmit it to a server over a secure channel.

[0339] The "means for preprocessing the text data received by the server" is a process for removing unnecessary information from the text data sent to the server and arranging the data in a proper format.

[0340] The "means for tokenizing preprocessed text data" refers to a process of segmenting preprocessed text data for natural language processing.

[0341] "Means for training an artificial intelligence model that learns a user's characteristic behaviors and ways of thinking using tokenized data" refers to the process of optimizing an artificial intelligence model to learn a user's characteristic behaviors and ways of thinking based on tokenized data.

[0342] "Means for analyzing emotions from user text data using an emotion engine" refers to an algorithm or system for identifying and analyzing emotions from user statements and messages.

[0343] "Means of using an artificial intelligence model to generate responses that mimic the user's words and actions in real time based on the analysis results of an emotion engine" refers to the ability of an artificial intelligence to mimic the user's tone of voice and terminology based on the results of emotion analysis and instantly generate responses.

[0344] "Means for providing the generated response to the user" refers to a mechanism for transmitting the response generated by the artificial intelligence through the device or application used by the user.

[0345]

[0346] The present invention is a system that analyzes a user's text data in real time and generates appropriate responses based on their emotions. This system enhances the effectiveness of security services by generating and providing responses that reflect the user's characteristic behavior and emotions. The following describes in detail an embodiment of the present invention.

[0347] A system for implementing the present invention functions primarily through cooperation between three parties: a server, a terminal, and a user. First, a user installs a specific application on a terminal (such as a smartphone or head-mounted display) and uses it on a daily basis. The terminal collects the user's comments and messages, encrypts them (using AES encryption, for example), and securely transmits them to a server.

[0348] The server stores the received text data in a database (e.g., MySQL, PostgreSQL). The stored text data is filtered to remove unnecessary information and spam. The filtered text data is then normalized to unify full-width and half-width characters and remove unnecessary spaces and special characters. The normalized text data is tokenized and used as training data for an artificial intelligence model (e.g., TensorFlow, PyTorch).

[0349] The server uses the tokenized data to train an AI model. The AI ​​model learns the user's characteristic behaviors and thoughts, and then analyzes the user's text data for emotions using an emotion engine (e.g., TextBlob, VaderSentiment). The analysis results are used as an important element in the AI ​​model's response generation.

[0350] The generated response is sent from the server to the device and provided to the user. For example, when a security operator receives an inquiry from a customer, this system is activated, analyzes the customer's emotions, and generates the optimal response. The hardware used includes iOS and Android smartphones and head-mounted displays such as the Oculus Quest 2.

[0351] As a concrete example, the following is an example of a prompt sentence for a generative AI model:

[0352] "A customer asks, 'My home security alarm is going off. What should I do?' I sense a sense of urgency in their recent conversations. How should I respond?"

[0353] Based on this prompt, the artificial intelligence model generates a response like this:

[0354] "Please stay calm. First, check all your doors and windows to make sure they're safe. Call the police if necessary."

[0355] The system of the present invention enables flexible and appropriate real-time responses according to emotions, thereby improving customer satisfaction with security services.

[0356] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0357] Step 1:

[0358] The device collects text data (utterances and messages) from the user. The input is the user's text data, and the output is the collected raw data. Specifically, data is acquired via the device's microphone or text input interface.

[0359] Step 2:

[0360] The terminal encrypts the collected text data and securely transmits it to the server. The input is the collected raw data, and the output is the encrypted data. Specifically, the data is encrypted using the AES encryption algorithm and transmitted to the server using the HTTPS protocol.

[0361] Step 3:

[0362] The server decrypts the received encrypted data and stores it in the database. The input is the encrypted data, and the output is the raw data stored in the database. Specifically, the data is decrypted using the AES decryption algorithm and stored in the MySQL or PostgreSQL database.

[0363] Step 4:

[0364] The server retrieves raw data from the database and performs preprocessing. The input is the raw data stored in the database, and the output is the preprocessed data. Specific operations include filtering (removing unnecessary information and spam data) and normalization (unifying full-width and half-width characters, deleting unnecessary spaces and special characters).

[0365] Step 5:

[0366] The server tokenizes the preprocessed data and uses it as training data for the AI ​​model. The input is the preprocessed data, and the output is the tokenized data. Specifically, it uses a natural language processing toolkit to split the text into tokens.

[0367] Step 6:

[0368] The server trains an AI model using the tokenized data. The input is the tokenized data, and the output is the trained AI model. Specifically, the model is trained using TensorFlow or PyTorch.

[0369] Step 7:

[0370] The server uses an emotion engine to analyze emotions from the user's text data. The input is preprocessed data, and the output is the emotion analysis result. Specifically, emotion analysis is performed using TextBlob and VaderSentiment.

[0371] Step 8:

[0372] The server uses an AI model based on the analysis results of the emotion engine to generate a response that mimics the user's words and actions in real time. The input is the emotion analysis result and the trained AI model, and the output is the generated response. Specifically, the server uses the generation function of the AI ​​model to generate a response to the prompt sentence.

[0373] Step 9:

[0374] The server sends the generated response to the terminal. The input is the generated response, and the output is the response sent to the terminal. As a specific operation, data is sent to the terminal using the HTTPS protocol.

[0375] Step 10:

[0376] The device provides the response received from the server to the user. The input is the response received from the server, and the output is the response provided to the user. Specific actions include displaying the response on the screen of a smartphone or head-mounted display, or reading it aloud.

[0377] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0378] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search<url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0379] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0380] [Second embodiment]

[0381] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0382] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0383] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0384] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0385] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0386] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0387] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0388] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0389] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0390] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0391] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0392] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0393] This invention is a system that collects users' text data, analyzes it using an AI model, and generates and provides responses that reflect the user's characteristic behavior and way of thinking. This system functions in cooperation between a server, a terminal, and the user.

[0394] First, users install a dedicated application on their devices. Through this application, users record their own speech and messages on a daily basis. The device collects this text data and sends it to a server at regular intervals. The collected data is first preprocessed. The server performs data preprocessing, including filtering unnecessary data, normalizing, and tokenizing. The preprocessed data is used as training data for the AI ​​model.

[0395] The server then uses the preprocessed data to train an AI model that learns the user's characteristic behaviors and thoughts. This training process enables the AI ​​model to generate responses that reflect the user's phrasing, catchphrases, and educational principles.

[0396] The device is responsible for real-time dialogue with the child. For example, when a child types a question into the device, such as "What shall we play today?", that information is sent to the server. The server inputs the received question into an AI model and generates the most appropriate response. That response is then provided to the child via the device. For example, a response such as "Shall we play ball in the park today?" is generated and conveyed to the child.

[0397] Furthermore, the present invention features continuous learning. By collecting daily updates from users, periodically preprocessing them, and retraining the AI ​​model, it is possible to always reflect the user's latest thinking and educational policies. Users can also provide feedback, which the server uses to adjust the AI ​​model. In this way, the system is continuously optimized to meet the user's needs.

[0398] As a specific example, suppose a user asks, "I'm worried about how to get my child to develop a good study habit." In this case, the device sends the consultation to the server. The server uses an AI model to generate advice such as, "Why don't you try creating a schedule together that determines study time?" and provides this advice to the user via the device. In this way, the present invention supports high-quality, consistent communication between parents and children, providing assistance for achieving more ideal parenting.

[0399] Through the above process, the present invention provides a new means for reducing stress and burden on parents in the modern child-rearing environment and for realizing effective and consistent education.

[0400] The processing flow will be explained below.

[0401] Step 1:

[0402] Users install a dedicated application on their devices and use it on a daily basis. The devices record the user's comments and messages and collect this text data at regular intervals.

[0403] Step 2:

[0404] The device encrypts the collected text data and sends it securely to the server.

[0405] Step 3:

[0406] The server stores the received text data in a database, which is then filtered to remove unnecessary information and spam.

[0407] Step 4:

[0408] The server normalizes the stored text data, specifically by standardizing full-width and half-width characters, removing unnecessary spaces and special characters, and formatting the data.

[0409] Step 5:

[0410] The server tokenizes the normalized text data, splitting it into words and converting it into a format that is easy for the AI ​​model to learn.

[0411] Step 6:

[0412] The server uses the tokenized data to train an AI model, which learns the user's characteristic behaviors and thoughts. Specifically, it uses natural language processing algorithms and optimizes the model through a multi-layer neural network.

[0413] Step 7:

[0414] The server stores the trained AI model and distributes it to devices as needed, while the AI ​​model is continuously updated to reflect the user's latest information.

[0415] Step 8:

[0416] The device is responsible for real-time interaction with the user and the child. When the child speaks to the device, the speech is sent to the server in text format.

[0417] Step 9:

[0418] The server tokenizes the received text data and feeds it into a trained AI model, which mimics the user's behavior and thoughts to generate appropriate responses.

[0419] Step 10:

[0420] The server sends the generated response to the device, which then provides the response to the child as voice or text. For example, if the child asks, "What shall we play today?", the device responds, "Shall we play ball in the park today?"

[0421] Step 11:

[0422] Users can provide feedback to the system through the application as needed, for example, by rating the system "the response was appropriate" or by inputting specific requests such as "I would like the system to respond more like this."

[0423] Step 12:

[0424] The server analyzes the feedback provided by the user and adjusts the AI ​​model, optimizing the system to generate responses that better suit the user's needs.

[0425] Step 13:

[0426] The server periodically collects new data, preprocesses it, and retrains the AI ​​model, ensuring that it always reflects the latest user thinking and educational policies.

[0427] Example 1

[0428] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0429] In today's child-rearing environment, it is difficult to alleviate the stress and burden on parents and achieve effective and consistent communication. Furthermore, in order for parents to provide appropriate education and advice through dialogue with their children, continuous learning and feedback are necessary, and achieving this requires advanced technology.

[0430] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0431] In this invention, the server includes a means for collecting user text data, a means for preprocessing the collected text data, and a means for training an AI model that learns the user's characteristic behavior and way of thinking using the preprocessed text data. This allows parents to use the generated AI model to provide appropriate responses to their children in real time. The server also includes a means for continuously updating the AI ​​model and retraining it based on the latest user text data, and a means for adjusting the AI ​​model based on feedback provided by the user, thereby enabling the server to generate optimal responses that always reflect the latest information.

[0432] "User text data" refers to the content of statements and messages that users input on a daily basis, including conversations, questions, opinions, and the like.

[0433] "Means of collection" refers to the function for saving the text data entered by the user in a certain format and transferring it to a server as necessary.

[0434] "Preprocessing" refers to the process of removing unnecessary information from collected text data and converting the data into a unified, easily analyzable format.

[0435] An "artificial intelligence model" refers to a system that is trained using machine learning algorithms to learn a user's characteristic behavior and way of thinking and generate responses based on that.

[0436] "Training" refers to the process of feeding preprocessed text data to an artificial intelligence model to allow the model to learn user characteristics.

[0437] A "real-time query" is a question or request entered by a user on the fly that requires an immediate response.

[0438] "Answer generation means" refers to the process of using an artificial intelligence model to generate an appropriate answer to a user's query.

[0439] "Generated answer" refers to a response to a user's query that is generated by an artificial intelligence model.

[0440] "Means for providing" refers to a function or interface for displaying the generated response to the user.

[0441] "Continuously updating" refers to the process of periodically retraining an artificial intelligence model with new data to maintain or improve the model's accuracy and effectiveness.

[0442] "Feedback" refers to evaluations and opinions provided by users, which are used to improve and adjust the quality of the system.

[0443] "Adjustment means" refers to the process of adjusting the parameters and algorithms of an artificial intelligence model based on user feedback to improve the model's response quality.

[0444] This invention is a system that collects users' text data, analyzes it using an AI model, and generates and provides responses that reflect the user's characteristic behavior and way of thinking. This system functions in cooperation between a server, a terminal, and the user.

[0445] First, users install a dedicated application on their device. Through this application, users can record their daily statements and messages. This involves a device such as a smartphone or tablet, and software that connects to a server via internet communication.

[0446] The device sends the recorded text data to a server at a fixed interval. The security of the data is ensured by using secure communication protocols such as HTTPS. The server then preprocesses the received data. Specifically, it performs processes such as filtering unnecessary data, normalizing, and tokenizing. This converts the data into a format that is easy to analyze.

[0447] The server then uses the preprocessed data to train an AI model, which can be a generative AI model such as GPT-3. The model is designed to learn the user's characteristic behaviors and thoughts and is trained using thousands to millions of data points. This process can take hours or days.

[0448] Real-time interaction begins when a user inputs a question or query into the device. For example, if the user inputs a question such as "What shall we play today?", the device sends this information to the server. The server inputs the received question into an AI model and generates an optimal response. The generated response is provided to the user via the device. For example, a response such as "Shall we play ball in the park today?" is generated.

[0449] Furthermore, the present invention features continuous learning. By collecting daily updates from users, periodically preprocessing them, and retraining the AI ​​model, it is possible to always reflect the user's latest thinking and educational policies. Users can also provide feedback. Based on this feedback, the server adjusts the AI ​​model. Specifically, it can strengthen highly rated responses and provide additional training to improve poorly rated responses.

[0450] As a concrete example, consider the case where a user inputs, "I'm worried about how to get my child to develop a good study habit." In this case, the device sends the inquiry to the server. The server uses an AI model to generate advice such as, "Why don't you try creating a schedule together that determines study time?" and provides it to the user via the device. In this way, the present invention supports high-quality, consistent communication between parents and children, providing assistance for achieving more ideal parenting.

[0451] An example of a prompt sentence is, "The user inputs, 'I'm worried about how to help my child develop study habits.' Please generate the most appropriate advice based on the data collected from the user's statements and messages."

[0452] Through the above process, the present invention provides a new means for reducing stress and burden on parents in the modern child-rearing environment and for realizing effective and consistent education.

[0453] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0454] Step 1: The user installs the application and collects text data.

[0455] Input: User comments and messages

[0456] Output: Collected text data

[0457] The device records user comments and messages through a dedicated application. This application has a chat-style interface and saves the comments and questions that users enter on a daily basis as text data. It also uses a voice recognition function to convert voice input into text and record it.

[0458] Step 2: The device sends the collected data to the server.

[0459] Input: Collected text data

[0460] Output: Data sent to the server

[0461] The device periodically sends the collected text data to the server via the HTTPS protocol, which ensures secure data transfer.

[0462] Step 3: The server preprocesses the data.

[0463] Input: Transmitted text data

[0464] Output: Preprocessed data

[0465] The server filters the submitted text data to remove unnecessary information. Specifically, it uses regular expressions to remove noise and stop words. It also normalizes the data, converting uppercase and lowercase letters, numbers, and special characters into a unified format. Finally, it tokenizes the data, splitting it into units that are easier to analyze.

[0466] Step 4: The server trains the AI ​​model.

[0467] Input: Preprocessed data

[0468] Output: A trained AI model

[0469] The server then feeds the preprocessed data to an AI model (such as GPT-3) to learn the user's characteristic behaviors and thoughts. This training process uses thousands to millions of data points and can take hours or even days. As a result, the AI ​​model is able to generate responses that reflect the user's unique phrasing and habits of speech.

[0470] Step 5: The user enters a real-time question.

[0471] Input: User question or query

[0472] Output: Query sent to the terminal

[0473] The user inputs a question or query into the device, for example, "What should we play today?" This information is immediately transmitted to the server.

[0474] Step 6: The server uses the AI ​​model to generate a response.

[0475] Input: User query

[0476] Output: The generated response

[0477] The server inputs the received question into an AI model and generates the best possible response. The generated response is specific and reflects the user's characteristics. A response such as "Shall we play ball in the park today?" is generated.

[0478] Step 7: The terminal provides the generated response to the user.

[0479] Input: The response sent by the server

[0480] Output: The response provided to the user

[0481] The device displays the generated responses to the user in real time, and the user can provide feedback, for example by giving a thumbs up if the response was helpful or indicating if they would like more suggestions.

[0482] Step 8: The server continues to learn and update the model.

[0483] Input: New data and feedback from users

[0484] Output: Updated AI model

[0485] The server collects daily updates and feedback from users, preprocesses them, and retrains the AI ​​model, ensuring that the model always reflects the latest information, improving the accuracy and effectiveness of its responses.

[0486] In this way, throughout the series of processing steps, the system can continue to provide the best possible response tailored to the user's needs.

[0487] (Application example 1)

[0488] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0489] Conventional content delivery systems have had difficulty providing customized content that fully reflects the individual needs and characteristics of users. Therefore, improving user satisfaction and increasing usage time are key challenges.

[0490] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0491] In this invention, the server includes means for collecting user text data, means for preprocessing the collected text data, means for training an AI model that learns the user's characteristic speech and behavior and way of thinking using the preprocessed text data, means for generating responses that imitate the user's speech and behavior in real time using the AI ​​model, means for providing the generated responses to the user, and means for generating and delivering content customized based on the user's characteristics, thereby enabling delivery of specialized content tailored to the user.

[0492] "User text data" refers to statements and messages that users input on a daily basis.

[0493] "Preprocessing" refers to converting collected text data into an analyzable format by filtering, normalizing, tokenizing, and other processes.

[0494] An "artificial intelligence model" is a collection of machine learning algorithms that learn a user's characteristic behavior and way of thinking and generate responses based on that.

[0495] "Real time" means that processing from data input to output is done instantaneously, with almost no delay.

[0496] "Customized content" refers to information and media that is specifically created based on the characteristics and preferences of an individual user.

[0497] "Feedback" refers to information such as user ratings and opinions, which are used to adjust and improve the system.

[0498] This invention is a customized content delivery system that uses an artificial intelligence model that collects user text data and learns user characteristics based on that data. This system is composed of three entities: a server, a terminal, and a user.

[0499] First, users install a dedicated application on their device. Through this application, users can enter their own comments and messages on a daily basis. The device collects this text data and sends it to a server at regular intervals.

[0500] The server first preprocesses the collected data. This involves filtering out unnecessary data, normalizing it, and tokenizing it. The preprocessed data is then used as training data for the artificial intelligence model. During preprocessing, the server analyzes the data using a natural language processing library (e.g., nltk).

[0501] The server then trains an artificial intelligence model on the preprocessed data. The model uses machine learning algorithms (such as sklearn's Ridge model) to learn the user's characteristic behaviors and thoughts, allowing the model to generate responses that reflect the user's unique phrasing and habits of speech.

[0502] The device interacts with the user in real time. For example, when the user inputs a question such as "What shall we play today?", the information is immediately sent to the server. The server inputs the received question into an artificial intelligence model and generates the most appropriate response. The response is then provided to the user via the device. For example, the response generated is "Shall we play ball in the park today?" and conveyed to the user.

[0503] Furthermore, the present invention also has a continuous learning function. The server periodically collects daily updates from users, preprocesses them, and retrains the AI ​​model to always reflect the latest user thinking and characteristics. Users can provide feedback, and the server will adjust the AI ​​model based on this feedback.

[0504] To generate and deliver customized content based on the user's characteristics, the server analyzes the collected data and provides videos and articles that match the user's preferences. For example, if a user frequently mentions a particular topic, content related to that topic will be generated and delivered preferentially.

[0505] An example of a prompt sentence is "What shall we play today?" In this way, the present invention can provide users with consistent, high-quality responses and customized content.

[0506] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0507] Step 1:

[0508] Users install a dedicated application on their devices, and through this application, they begin to input their own comments and messages on a daily basis. This input data is collected in text format.

[0509] Step 2:

[0510] The device sends the collected text data to the server at a fixed frequency. The input is the user's speech or message, and the output is the data sent to the server.

[0511] Step 3:

[0512] The server preprocesses the received text data by filtering, normalizing, tokenizing, and removing unnecessary data. The input is the user's raw data, and the output is preprocessed, well-formed data. Here, a natural language processing library (e.g., nltk) is used.

[0513] Step 4:

[0514] The server trains an AI model based on the preprocessed data. The input is the preprocessed text data, and the output is an AI model that has learned the user's characteristics. Here, the model is trained using a machine learning algorithm (e.g., sklearn's Ridge model).

[0515] Step 5:

[0516] The user types a question or request into the terminal. For example, the user types a prompt such as "What shall we play today?" The input is the user's question.

[0517] Step 6:

[0518] The terminal sends this question to the server. The input is the user's question, and the output is the data sent to the server.

[0519] Step 7:

[0520] The server inputs the received question into an artificial intelligence model to generate the most appropriate response. The input is the user's question, and the output is the generated response.

[0521] Step 8:

[0522] The generated response is provided to the user from the server via the terminal. The input is the response sent from the server, and the output is what is displayed to the user. For example, the response "Shall we play ball in the park today?" is displayed on the terminal.

[0523] Step 9:

[0524] The terminal collects the user's daily updated information and periodically sends it to the server. The input is newly collected text data, and the output is the transmission of updated data to the server.

[0525] Step 10:

[0526] The server preprocesses the update data using the same method as preprocessing and retrains the AI ​​model. The input is the preprocessed update data, and the output is an improved artificial intelligence model.

[0527] Step 11:

[0528] The terminal collects the feedback provided by the user and sends it to the server. The input is the user's feedback and the output is the feedback sent to the server.

[0529] Step 12:

[0530] The server adjusts the AI ​​model based on the feedback. The input is the user's feedback, and the output is the adjusted artificial intelligence model. For example, the model parameters are fine-tuned based on the feedback that the advice was good.

[0531] Through the above processing steps, the system can provide customized content that reflects the unique characteristics of the user.

[0532] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0533] This invention is a system that collects user text data, analyzes it using an artificial intelligence model and an emotion engine, and generates and provides responses that reflect the user's characteristic words, actions, thoughts, and emotions. This system functions in cooperation with a server, a terminal, and a user.

[0534] First, the user installs a dedicated application on their device and uses it on a daily basis. The device records the user's comments and messages and collects this text data at regular intervals. The device encrypts the collected text data and securely sends it to a server. The server stores the received text data in a database. The stored text data is first filtered to remove unnecessary information and spam.

[0535] The server then normalizes the stored text data, specifically by standardizing full-width and half-width characters, removing unnecessary spaces and special characters, and formatting the data. The normalized text data is then tokenized and used as training data for the AI ​​model.

[0536] The server uses the tokenized data to train the AI ​​model, which learns the user's characteristic behaviors and thoughts. This training process allows the AI ​​model to generate responses that reflect the user's phrasing, catchphrases, and educational principles.

[0537] A distinctive feature of the present invention is the incorporation of an emotion engine. The emotion engine is located in the server and analyzes emotions from the user's text data. The emotion information analyzed by the emotion engine is used as an important element in generating responses from the AI ​​model. For example, if the user is feeling stressed, a response that alleviates the user's emotions will be generated.

[0538] As a concrete example, suppose a child types a question into a device, such as "Why is Mommy angry?" When this information is sent to the server, the server tokenizes the question and inputs it into the emotion engine. The emotion engine analyzes the user's emotion based on past and current data. The analysis result determines that the emotion is "anger."

[0539] The AI ​​model then generates a response based on the emotion analysis, such as "Mommy is just tired, so let her get some rest," and sends it to the device via the server. The device then provides this response to the child via voice or text.

[0540] Furthermore, the present invention features continuous learning. By collecting daily updates from users and periodically preprocessing them to retrain the AI ​​model and emotion engine, it is possible to always reflect the latest user thoughts and emotions. Users can also provide feedback. Based on this feedback, the server adjusts the AI ​​model and emotion engine. In this way, the system is continuously optimized to meet the user's needs.

[0541] Through the above process, this invention provides a new means to reduce stress and burden on parents in the modern child-rearing environment and to realize effective and consistent education. In particular, by analyzing emotions and generating responses based on them, more humane and empathetic communication becomes possible.

[0542] The processing flow will be explained below.

[0543] Step 1:

[0544] Users install a dedicated application on their devices and use it on a daily basis. The devices record the user's comments and messages and collect this text data at regular intervals.

[0545] Step 2:

[0546] The device encrypts the collected text data and sends it securely to the server.

[0547] Step 3:

[0548] The server stores the received text data in a database, which is then filtered to remove unnecessary information and spam.

[0549] Step 4:

[0550] The server normalizes the stored text data, specifically by standardizing full-width and half-width characters, removing unnecessary spaces and special characters, and formatting the data.

[0551] Step 5:

[0552] The server tokenizes the normalized text data, splitting it into words and converting it into a format that is easy for the AI ​​model to learn.

[0553] Step 6:

[0554] The server uses the tokenized data to train an AI model, which learns the user's characteristic behaviors and thoughts. Specifically, it uses natural language processing algorithms and optimizes the model through a multi-layer neural network.

[0555] Step 7:

[0556] The server uses a trained emotion engine to analyze emotions from the user's text data, based on past and current data.

[0557] Step 8:

[0558] The device is responsible for real-time dialogue between the user and the child. When the child speaks to the device and types a question such as "Why is Mommy angry?", the response is sent to the server in text format.

[0559] Step 9:

[0560] The server tokenizes the received text data and inputs it into a trained emotion engine, which analyzes the user's emotions and extracts the emotion "anger."

[0561] Step 10:

[0562] The server uses the AI ​​model to generate the most appropriate response based on the analysis results of the emotion engine. In this case, the response generated is, "Mom is just tired, so let her get some rest."

[0563] Step 11:

[0564] The server sends the generated response to the terminal, which provides the response to the child in voice or text format.

[0565] Step 12:

[0566] Users can provide feedback to the system through the application as needed, for example, by rating the system "the response was appropriate" or by inputting specific requests such as "I would like the system to respond more like this."

[0567] Step 13:

[0568] The server analyzes the feedback provided by the user and adjusts the AI ​​model and emotion engine, optimizing the system to generate responses that better suit the user's needs.

[0569] Step 14:

[0570] The server periodically collects new data, preprocesses it, and retrains the AI ​​model and emotion engine, ensuring that the latest user thoughts and emotions are always reflected.

[0571] Through the above processing steps, the present invention supports high-quality, consistent communication between parents and children, and provides assistance for achieving more ideal child-rearing. In particular, by analyzing emotions and generating responses based on those emotions, more humane and empathetic communication becomes possible.

[0572] Example 2

[0573] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0574] Conventional text data analysis systems have difficulty generating responses that take into account the user's characteristic behavior and emotions, resulting in a decline in the quality of communication. Furthermore, given the need for continuous learning and real-time responses, conventional systems were not flexible enough. They also lacked a mechanism for optimizing the system using user feedback.

[0575] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0576] In this invention, the server includes means for encrypting and transmitting user text data, means for storing, filtering, and normalizing the transmitted text data, means for training an AI model that learns the user's characteristic behavior and way of thinking using the tokenized data, and means for generating a response that takes the user's emotions into consideration using the AI ​​model based on the emotion analysis results, thereby making it possible to provide high-quality responses that reflect the user's behavior and emotions in real time.

[0577] "User text data" refers to sentences or messages that a user inputs or generates through a terminal.

[0578] "Encryption" is the process of transforming data using a specific algorithm to make it unreadable to third parties in order to transmit it securely.

[0579] "Transmitting" refers to moving data from one point to another, and in this case means moving data from a terminal to a server.

[0580] "Storage" means storing data on an electronic recording medium in order to keep it safe for a long period of time.

[0581] "Filtering" is the process of removing unnecessary information and spam from data and extracting only useful information.

[0582] "Normalization" is the process of converting data into a unified format and making it consistent.

[0583] "Tokenization" is the process of dividing text data into small units such as words or sentences based on certain rules.

[0584] An "artificial intelligence model" is an algorithm or system that can learn and make inferences or predictions based on specific data.

[0585] "Training" is the process by which an artificial intelligence model learns from given data and improves its accuracy.

[0586] "Sentiment analysis" is the process of identifying emotions from a user's text data and quantitatively assessing the type and intensity of those emotions.

[0587] "Generation" means that the artificial intelligence model creates new data or responses based on the data and analysis results obtained.

[0588] "Feedback" refers to user evaluations and opinions on the system's performance and results.

[0589] "Tuning" refers to optimizing system parameters and settings based on feedback to improve performance and results.

[0590] MODE FOR CARRYING OUT THE INVENTION

[0591] This invention is a system that collects user text data, analyzes it using an artificial intelligence model and an emotion engine, and generates and provides responses that reflect the user's characteristic words, actions, thoughts, and emotions. This system functions in cooperation with a server, a terminal, and a user.

[0592] Terminal

[0593] First, the user installs a dedicated application on the device and uses it on a daily basis. The device records the user's statements and messages and collects this text data at a certain frequency. For example, a child might type "Why is Mommy angry?" into the device. The device encrypts the collected text data and securely transmits it to the server.

[0594] server

[0595] The server stores the received text data in a database. The stored text data is first filtered to remove unnecessary information and spam. The server then normalizes the stored text data. Specifically, it standardizes full-width and half-width characters, removes unnecessary spaces and special characters, and formats the data. This ensures that the data is processed in a consistent format.

[0596] The normalized text data is tokenized and used as training data for the AI ​​model. The server trains the AI ​​model using the tokenized data. For example, using a deep learning framework (e.g., TensorFlow, PyTorch), the AI ​​model learns the user's words, behaviors, and thoughts. This training process enables the AI ​​model to generate responses that reflect the user's phrasing, catchphrases, and educational principles.

[0597] A distinctive feature of the present invention is the incorporation of an emotion engine. The emotion engine is located in the server and analyzes emotions from the user's text data. The emotion information analyzed by the emotion engine is used as an important element in generating responses from the AI ​​model. For example, if the user is feeling stressed, a response that alleviates the user's emotions will be generated.

[0598] Specific examples

[0599] For example, a child might type a question into their device, such as "Why is Mommy angry?" When this information is sent to the server, the server tokenizes the question and inputs it into the emotion engine. The emotion engine analyzes the user's emotion based on past and current data. The analysis result determines that the emotion is "anger." The AI ​​model then generates a response based on the emotion analysis result. For example, a response such as "Mommy is just tired, so let her get some rest" is generated and sent to the device via the server. The device then provides this response to the child as voice or text.

[0600] Furthermore, the present invention features continuous learning. By collecting daily updates from users and periodically preprocessing them to retrain the AI ​​model and emotion engine, it is possible to always reflect the latest user thoughts and emotions. Users can also provide feedback. Based on this feedback, the server adjusts the AI ​​model and emotion engine. In this way, the system is continuously optimized to meet the user's needs.

[0601] Through the above process, the present invention provides a new means for reducing stress and strain on users in modern communication environments and generating effective and consistent responses. In particular, analyzing emotions and generating responses based on those emotions enables more human and empathetic communication.

[0602] keyword

[0603] Generative AI Models

[0604] An artificial intelligence model that learns a user's characteristic behavior and way of thinking and generates appropriate responses.

[0605] Prompt statement

[0606] Specific examples of text to input into the system, such as the question "Why is Mom mad?"

[0607] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0608] Program processing steps

[0609] Step 1:

[0610] Text data collection and encryption

[0611] input

[0612] Text data that a user enters into a device, such as a statement like "Why is Mom angry?"

[0613] operation

[0614] Users use a dedicated application to input comments and messages on a daily basis.

[0615] The terminal collects this input text data.

[0616] The collected text data is encrypted using an encryption algorithm such as AES.

[0617] output

[0618] Encrypted text data is generated.

[0619] Step 2:

[0620] Encrypted data transmission and storage

[0621] input

[0622] Encrypted text data.

[0623] operation

[0624] The device sends encrypted data securely to the server, typically using the SSL / TLS protocol.

[0625] The server stores the received encrypted data in a database.

[0626] Perform an integrity check to ensure the data was saved correctly.

[0627] output

[0628] The stored encrypted data is placed in a database.

[0629] Step 3:

[0630] Filtering and normalizing text data

[0631] input

[0632] Text data stored in a database.

[0633] operation

[0634] The server retrieves text data from a database and filters it for spam and unwanted information.

[0635] The server normalizes the filtered data, specifically by unifying full-width and half-width characters and removing unnecessary spaces and special characters.

[0636] output

[0637] Filtered and normalized text data is generated.

[0638] Step 4:

[0639] Tokenization of text data

[0640] input

[0641] Filtered and normalized text data.

[0642] operation

[0643] The server tokenizes the normalized text data, for example splitting the text "Why is Mom mad?" into individual words.

[0644] output

[0645] Tokenized data is generated.

[0646] Step 5:

[0647] Training an AI model

[0648] input

[0649] Tokenized text data.

[0650] operation

[0651] The server uses the tokenized data to train an AI model, which uses a deep learning framework (e.g., TensorFlow, PyTorch) to learn the user's characteristic behaviors and thoughts.

[0652] output

[0653] A trained AI model is generated.

[0654] Step 6:

[0655] Conducting sentiment analysis

[0656] input

[0657] Text data sent by the user.

[0658] operation

[0659] The server inputs the text data into the emotion engine and performs emotion analysis. For example, a question such as "Why is Mom angry?" is classified as the emotion "anger."

[0660] output

[0661] Emotional information is analyzed.

[0662] Step 7:

[0663] Response Generation

[0664] input

[0665] Sentiment analysis results and trained AI model.

[0666] operation

[0667] The server uses an AI model based on the results of the emotion analysis to generate an appropriate response, such as "Mom is just tired, so let her get some rest."

[0668] output

[0669] A generated response is created.

[0670] Step 8:

[0671] Sending and serving responses

[0672] input

[0673] The generated response.

[0674] operation

[0675] The server sends the generated response to the terminal.

[0676] The terminal provides the received response to the user, for example, the response is communicated to the user in text or audio format.

[0677] output

[0678] The response provided to the user is complete.

[0679] Step 9:

[0680] Continuous learning and feedback

[0681] input

[0682] User's daily text data and feedback.

[0683] operation

[0684] The user provides feedback on the generated response, for example, "This response was appropriate" or "I would have liked more specific information."

[0685] The server adjusts the parameters of the AI ​​model and emotion engine based on user feedback and performs retraining.

[0686] output

[0687] The optimized AI model and emotion engine are updated.

[0688] (Application example 2)

[0689] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0690] In conventional security services, communication between operators and customers is primarily manual, making it difficult to respond flexibly to customer emotions. Furthermore, there are no systems that can analyze emotions and generate appropriate responses in emergencies that require real-time response. This can lead to reduced customer satisfaction and delayed responses.

[0691] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user text data, means for encrypting the collected text data and securely transmitting it to the server, means for preprocessing the text data received by the server, means for tokenizing the preprocessed text data, means for training an artificial intelligence model that learns the user's characteristic words and actions and way of thinking using the tokenized data, means for analyzing emotions from the user's text data using an emotion engine, means for generating responses that imitate the user's words and actions in real time based on the analysis results of the emotion engine using the artificial intelligence model, and means for providing the generated responses to the user. This enables flexible and appropriate real-time responses according to emotions.

[0692] "Means for collecting user text data" refers to devices and software mechanisms for collecting messages and comments made by users.

[0693] "Means for encrypting collected text data and securely transmitting it to a server" refers to technologies and protocols that encrypt text data so that it cannot be deciphered by third parties and transmit it to a server over a secure channel.

[0694] The "means for preprocessing the text data received by the server" is a process for removing unnecessary information from the text data sent to the server and arranging the data in a proper format.

[0695] The "means for tokenizing preprocessed text data" refers to a process of segmenting preprocessed text data for natural language processing.

[0696] "Means for training an artificial intelligence model that learns a user's characteristic behaviors and ways of thinking using tokenized data" refers to the process of optimizing an artificial intelligence model to learn a user's characteristic behaviors and ways of thinking based on tokenized data.

[0697] "Means for analyzing emotions from user text data using an emotion engine" refers to an algorithm or system for identifying and analyzing emotions from user statements and messages.

[0698] "Means of using an artificial intelligence model to generate responses that mimic the user's words and actions in real time based on the analysis results of an emotion engine" refers to the ability of an artificial intelligence to mimic the user's tone of voice and terminology based on the results of emotion analysis and instantly generate responses.

[0699] "Means for providing the generated response to the user" refers to a mechanism for transmitting the response generated by the artificial intelligence through the device or application used by the user.

[0700]

[0701] The present invention is a system that analyzes a user's text data in real time and generates appropriate responses based on their emotions. This system enhances the effectiveness of security services by generating and providing responses that reflect the user's characteristic behavior and emotions. The following describes in detail an embodiment of the present invention.

[0702] A system for implementing the present invention functions primarily through cooperation between three parties: a server, a terminal, and a user. First, a user installs a specific application on a terminal (such as a smartphone or head-mounted display) and uses it on a daily basis. The terminal collects the user's comments and messages, encrypts them (using AES encryption, for example), and securely transmits them to a server.

[0703] The server stores the received text data in a database (e.g., MySQL, PostgreSQL). The stored text data is filtered to remove unnecessary information and spam. The filtered text data is then normalized to unify full-width and half-width characters and remove unnecessary spaces and special characters. The normalized text data is tokenized and used as training data for an artificial intelligence model (e.g., TensorFlow, PyTorch).

[0704] The server uses the tokenized data to train an AI model. The AI ​​model learns the user's characteristic behaviors and thoughts, and then analyzes the user's text data for emotions using an emotion engine (e.g., TextBlob, VaderSentiment). The analysis results are used as an important element in the AI ​​model's response generation.

[0705] The generated response is sent from the server to the device and provided to the user. For example, when a security operator receives an inquiry from a customer, this system is activated, analyzes the customer's emotions, and generates the optimal response. The hardware used includes iOS and Android smartphones and head-mounted displays such as the Oculus Quest 2.

[0706] As a concrete example, the following is an example of a prompt sentence for a generative AI model:

[0707] "A customer asks, 'My home security alarm is going off. What should I do?' I sense a sense of urgency in their recent conversations. How should I respond?"

[0708] Based on this prompt, the artificial intelligence model generates a response like this:

[0709] "Please stay calm. First, check all your doors and windows to make sure they're safe. Call the police if necessary."

[0710] The system of the present invention enables flexible and appropriate real-time responses according to emotions, thereby improving customer satisfaction with security services.

[0711] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0712] Step 1:

[0713] The device collects text data (utterances and messages) from the user. The input is the user's text data, and the output is the collected raw data. Specifically, data is acquired via the device's microphone or text input interface.

[0714] Step 2:

[0715] The terminal encrypts the collected text data and securely transmits it to the server. The input is the collected raw data, and the output is the encrypted data. Specifically, the data is encrypted using the AES encryption algorithm and transmitted to the server using the HTTPS protocol.

[0716] Step 3:

[0717] The server decrypts the received encrypted data and stores it in the database. The input is the encrypted data, and the output is the raw data stored in the database. Specifically, the data is decrypted using the AES decryption algorithm and stored in the MySQL or PostgreSQL database.

[0718] Step 4:

[0719] The server retrieves raw data from the database and performs preprocessing. The input is the raw data stored in the database, and the output is the preprocessed data. Specific operations include filtering (removing unnecessary information and spam data) and normalization (unifying full-width and half-width characters, deleting unnecessary spaces and special characters).

[0720] Step 5:

[0721] The server tokenizes the preprocessed data and uses it as training data for the AI ​​model. The input is the preprocessed data, and the output is the tokenized data. Specifically, it uses a natural language processing toolkit to split the text into tokens.

[0722] Step 6:

[0723] The server trains an AI model using the tokenized data. The input is the tokenized data, and the output is the trained AI model. Specifically, the model is trained using TensorFlow or PyTorch.

[0724] Step 7:

[0725] The server uses an emotion engine to analyze emotions from the user's text data. The input is preprocessed data, and the output is the emotion analysis result. Specifically, emotion analysis is performed using TextBlob and VaderSentiment.

[0726] Step 8:

[0727] The server uses an AI model based on the analysis results of the emotion engine to generate a response that mimics the user's words and actions in real time. The input is the emotion analysis result and the trained AI model, and the output is the generated response. Specifically, the server uses the generation function of the AI ​​model to generate a response to the prompt sentence.

[0728] Step 9:

[0729] The server sends the generated response to the terminal. The input is the generated response, and the output is the response sent to the terminal. As a specific operation, data is sent to the terminal using the HTTPS protocol.

[0730] Step 10:

[0731] The device provides the response received from the server to the user. The input is the response received from the server, and the output is the response provided to the user. Specific actions include displaying the response on the screen of a smartphone or head-mounted display, or reading it aloud.

[0732] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0733] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0734] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0735] [Third embodiment]

[0736] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0737] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0738] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0739] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0740] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0741] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0742] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0743] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0744] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0745] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0746] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0747] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0748] This invention is a system that collects users' text data, analyzes it using an AI model, and generates and provides responses that reflect the user's characteristic behavior and way of thinking. This system functions in cooperation between a server, a terminal, and the user.

[0749] First, users install a dedicated application on their devices. Through this application, users record their own speech and messages on a daily basis. The device collects this text data and sends it to a server at regular intervals. The collected data is first preprocessed. The server performs data preprocessing, including filtering unnecessary data, normalizing, and tokenizing. The preprocessed data is used as training data for the AI ​​model.

[0750] The server then uses the preprocessed data to train an AI model that learns the user's characteristic behaviors and thoughts. This training process enables the AI ​​model to generate responses that reflect the user's phrasing, catchphrases, and educational principles.

[0751] The device is responsible for real-time dialogue with the child. For example, when a child types a question into the device, such as "What shall we play today?", that information is sent to the server. The server inputs the received question into an AI model and generates the most appropriate response. That response is then provided to the child via the device. For example, a response such as "Shall we play ball in the park today?" is generated and conveyed to the child.

[0752] Furthermore, the present invention features continuous learning. By collecting daily updates from users, periodically preprocessing them, and retraining the AI ​​model, it is possible to always reflect the user's latest thinking and educational policies. Users can also provide feedback, which the server uses to adjust the AI ​​model. In this way, the system is continuously optimized to meet the user's needs.

[0753] As a specific example, suppose a user asks, "I'm worried about how to get my child to develop a good study habit." In this case, the device sends the consultation to the server. The server uses an AI model to generate advice such as, "Why don't you try creating a schedule together that determines study time?" and provides this advice to the user via the device. In this way, the present invention supports high-quality, consistent communication between parents and children, providing assistance for achieving more ideal parenting.

[0754] Through the above process, the present invention provides a new means for reducing stress and burden on parents in the modern child-rearing environment and for realizing effective and consistent education.

[0755] The processing flow will be explained below.

[0756] Step 1:

[0757] Users install a dedicated application on their devices and use it on a daily basis. The devices record the user's comments and messages and collect this text data at regular intervals.

[0758] Step 2:

[0759] The device encrypts the collected text data and sends it securely to the server.

[0760] Step 3:

[0761] The server stores the received text data in a database, which is then filtered to remove unnecessary information and spam.

[0762] Step 4:

[0763] The server normalizes the stored text data, specifically by standardizing full-width and half-width characters, removing unnecessary spaces and special characters, and formatting the data.

[0764] Step 5:

[0765] The server tokenizes the normalized text data, splitting it into words and converting it into a format that is easy for the AI ​​model to learn.

[0766] Step 6:

[0767] The server uses the tokenized data to train an AI model, which learns the user's characteristic behaviors and thoughts. Specifically, it uses natural language processing algorithms and optimizes the model through a multi-layer neural network.

[0768] Step 7:

[0769] The server stores the trained AI model and distributes it to devices as needed, while the AI ​​model is continuously updated to reflect the user's latest information.

[0770] Step 8:

[0771] The device is responsible for real-time interaction with the user and the child. When the child speaks to the device, the speech is sent to the server in text format.

[0772] Step 9:

[0773] The server tokenizes the received text data and feeds it into a trained AI model, which mimics the user's behavior and thoughts to generate appropriate responses.

[0774] Step 10:

[0775] The server sends the generated response to the device, which then provides the response to the child as voice or text. For example, if the child asks, "What shall we play today?", the device responds, "Shall we play ball in the park today?"

[0776] Step 11:

[0777] Users can provide feedback to the system through the application as needed, for example, by rating the system "the response was appropriate" or by inputting specific requests such as "I would like the system to respond more like this."

[0778] Step 12:

[0779] The server analyzes the feedback provided by the user and adjusts the AI ​​model, optimizing the system to generate responses that better suit the user's needs.

[0780] Step 13:

[0781] The server periodically collects new data, preprocesses it, and retrains the AI ​​model, ensuring that it always reflects the latest user thinking and educational policies.

[0782] Example 1

[0783] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0784] In today's child-rearing environment, it is difficult to alleviate the stress and burden on parents and achieve effective and consistent communication. Furthermore, in order for parents to provide appropriate education and advice through dialogue with their children, continuous learning and feedback are necessary, and achieving this requires advanced technology.

[0785] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0786] In this invention, the server includes a means for collecting user text data, a means for preprocessing the collected text data, and a means for training an AI model that learns the user's characteristic behavior and way of thinking using the preprocessed text data. This allows parents to use the generated AI model to provide appropriate responses to their children in real time. The server also includes a means for continuously updating the AI ​​model and retraining it based on the latest user text data, and a means for adjusting the AI ​​model based on feedback provided by the user, thereby enabling the server to generate optimal responses that always reflect the latest information.

[0787] "User text data" refers to the content of statements and messages that users input on a daily basis, including conversations, questions, opinions, and the like.

[0788] "Means of collection" refers to the function for saving the text data entered by the user in a certain format and transferring it to a server as necessary.

[0789] "Preprocessing" refers to the process of removing unnecessary information from collected text data and converting the data into a unified, easily analyzable format.

[0790] An "artificial intelligence model" refers to a system that is trained using machine learning algorithms to learn a user's characteristic behavior and way of thinking and generate responses based on that.

[0791] "Training" refers to the process of feeding preprocessed text data to an artificial intelligence model to allow the model to learn user characteristics.

[0792] A "real-time query" is a question or request entered by a user on the fly that requires an immediate response.

[0793] "Answer generation means" refers to the process of using an artificial intelligence model to generate an appropriate answer to a user's query.

[0794] "Generated answer" refers to a response to a user's query that is generated by an artificial intelligence model.

[0795] "Means for providing" refers to a function or interface for displaying the generated response to the user.

[0796] "Continuously updating" refers to the process of periodically retraining an artificial intelligence model with new data to maintain or improve the model's accuracy and effectiveness.

[0797] "Feedback" refers to evaluations and opinions provided by users, which are used to improve and adjust the quality of the system.

[0798] "Adjustment means" refers to the process of adjusting the parameters and algorithms of an artificial intelligence model based on user feedback to improve the model's response quality.

[0799] This invention is a system that collects users' text data, analyzes it using an AI model, and generates and provides responses that reflect the user's characteristic behavior and way of thinking. This system functions in cooperation between a server, a terminal, and the user.

[0800] First, users install a dedicated application on their device. Through this application, users can record their daily statements and messages. This involves a device such as a smartphone or tablet, and software that connects to a server via internet communication.

[0801] The device sends the recorded text data to a server at a fixed interval. The security of the data is ensured by using secure communication protocols such as HTTPS. The server then preprocesses the received data. Specifically, it performs processes such as filtering unnecessary data, normalizing, and tokenizing. This converts the data into a format that is easy to analyze.

[0802] The server then uses the preprocessed data to train an AI model, which can be a generative AI model such as GPT-3. The model is designed to learn the user's characteristic behaviors and thoughts and is trained using thousands to millions of data points. This process can take hours or days.

[0803] Real-time interaction begins when a user inputs a question or query into the device. For example, if the user inputs a question such as "What shall we play today?", the device sends this information to the server. The server inputs the received question into an AI model and generates an optimal response. The generated response is provided to the user via the device. For example, a response such as "Shall we play ball in the park today?" is generated.

[0804] Furthermore, the present invention features continuous learning. By collecting daily updates from users, periodically preprocessing them, and retraining the AI ​​model, it is possible to always reflect the user's latest thinking and educational policies. Users can also provide feedback. Based on this feedback, the server adjusts the AI ​​model. Specifically, it can strengthen highly rated responses and provide additional training to improve poorly rated responses.

[0805] As a concrete example, consider the case where a user inputs, "I'm worried about how to get my child to develop a good study habit." In this case, the device sends the inquiry to the server. The server uses an AI model to generate advice such as, "Why don't you try creating a schedule together that determines study time?" and provides it to the user via the device. In this way, the present invention supports high-quality, consistent communication between parents and children, providing assistance for achieving more ideal parenting.

[0806] An example of a prompt sentence is, "The user inputs, 'I'm worried about how to help my child develop study habits.' Please generate the most appropriate advice based on the data collected from the user's statements and messages."

[0807] Through the above process, the present invention provides a new means for reducing stress and burden on parents in the modern child-rearing environment and for realizing effective and consistent education.

[0808] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0809] Step 1: The user installs the application and collects text data.

[0810] Input: User comments and messages

[0811] Output: Collected text data

[0812] The device records user comments and messages through a dedicated application. This application has a chat-style interface and saves the comments and questions that users enter on a daily basis as text data. It also uses a voice recognition function to convert voice input into text and record it.

[0813] Step 2: The device sends the collected data to the server.

[0814] Input: Collected text data

[0815] Output: Data sent to the server

[0816] The device periodically sends the collected text data to the server via the HTTPS protocol, which ensures secure data transfer.

[0817] Step 3: The server preprocesses the data.

[0818] Input: Transmitted text data

[0819] Output: Preprocessed data

[0820] The server filters the submitted text data to remove unnecessary information. Specifically, it uses regular expressions to remove noise and stop words. It also normalizes the data, converting uppercase and lowercase letters, numbers, and special characters into a unified format. Finally, it tokenizes the data, splitting it into units that are easier to analyze.

[0821] Step 4: The server trains the AI ​​model.

[0822] Input: Preprocessed data

[0823] Output: A trained AI model

[0824] The server then feeds the preprocessed data to an AI model (such as GPT-3) to learn the user's characteristic behaviors and thoughts. This training process uses thousands to millions of data points and can take hours or even days. As a result, the AI ​​model is able to generate responses that reflect the user's unique phrasing and habits of speech.

[0825] Step 5: The user enters a real-time question.

[0826] Input: User question or query

[0827] Output: Query sent to the terminal

[0828] The user inputs a question or query into the device, for example, "What should we play today?" This information is immediately transmitted to the server.

[0829] Step 6: The server uses the AI ​​model to generate a response.

[0830] Input: User query

[0831] Output: The generated response

[0832] The server inputs the received question into an AI model and generates the best possible response. The generated response is specific and reflects the user's characteristics. A response such as "Shall we play ball in the park today?" is generated.

[0833] Step 7: The terminal provides the generated response to the user.

[0834] Input: The response sent by the server

[0835] Output: The response provided to the user

[0836] The device displays the generated responses to the user in real time, and the user can provide feedback, for example by giving a thumbs up if the response was helpful or indicating if they would like more suggestions.

[0837] Step 8: The server continues to learn and update the model.

[0838] Input: New data and feedback from users

[0839] Output: Updated AI model

[0840] The server collects daily updates and feedback from users, preprocesses them, and retrains the AI ​​model, ensuring that the model always reflects the latest information, improving the accuracy and effectiveness of its responses.

[0841] In this way, throughout the series of processing steps, the system can continue to provide the best possible response tailored to the user's needs.

[0842] (Application example 1)

[0843] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0844] Conventional content delivery systems have had difficulty providing customized content that fully reflects the individual needs and characteristics of users. Therefore, improving user satisfaction and increasing usage time are key challenges.

[0845] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0846] In this invention, the server includes means for collecting user text data, means for preprocessing the collected text data, means for training an AI model that learns the user's characteristic speech and behavior and way of thinking using the preprocessed text data, means for generating responses that imitate the user's speech and behavior in real time using the AI ​​model, means for providing the generated responses to the user, and means for generating and delivering content customized based on the user's characteristics, thereby enabling delivery of specialized content tailored to the user.

[0847] "User text data" refers to statements and messages that users input on a daily basis.

[0848] "Preprocessing" refers to converting collected text data into an analyzable format by filtering, normalizing, tokenizing, and other processes.

[0849] An "artificial intelligence model" is a collection of machine learning algorithms that learn a user's characteristic behavior and way of thinking and generate responses based on that.

[0850] "Real time" means that processing from data input to output is done instantaneously, with almost no delay.

[0851] "Customized content" refers to information and media that is specifically created based on the characteristics and preferences of an individual user.

[0852] "Feedback" refers to information such as user ratings and opinions, which are used to adjust and improve the system.

[0853] This invention is a customized content delivery system that uses an artificial intelligence model that collects user text data and learns user characteristics based on that data. This system is composed of three entities: a server, a terminal, and a user.

[0854] First, users install a dedicated application on their device. Through this application, users can enter their own comments and messages on a daily basis. The device collects this text data and sends it to a server at regular intervals.

[0855] The server first preprocesses the collected data. This involves filtering out unnecessary data, normalizing it, and tokenizing it. The preprocessed data is then used as training data for the artificial intelligence model. During preprocessing, the server analyzes the data using a natural language processing library (e.g., nltk).

[0856] The server then trains an artificial intelligence model on the preprocessed data. The model uses machine learning algorithms (such as sklearn's Ridge model) to learn the user's characteristic behaviors and thoughts, allowing the model to generate responses that reflect the user's unique phrasing and habits of speech.

[0857] The device interacts with the user in real time. For example, when the user inputs a question such as "What shall we play today?", the information is immediately sent to the server. The server inputs the received question into an artificial intelligence model and generates the most appropriate response. The response is then provided to the user via the device. For example, the response generated is "Shall we play ball in the park today?" and conveyed to the user.

[0858] Furthermore, the present invention also has a continuous learning function. The server periodically collects daily updates from users, preprocesses them, and retrains the AI ​​model to always reflect the latest user thinking and characteristics. Users can provide feedback, and the server will adjust the AI ​​model based on this feedback.

[0859] To generate and deliver customized content based on the user's characteristics, the server analyzes the collected data and provides videos and articles that match the user's preferences. For example, if a user frequently mentions a particular topic, content related to that topic will be generated and delivered preferentially.

[0860] An example of a prompt sentence is "What shall we play today?" In this way, the present invention can provide users with consistent, high-quality responses and customized content.

[0861] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0862] Step 1:

[0863] Users install a dedicated application on their devices, and through this application, they begin to input their own comments and messages on a daily basis. This input data is collected in text format.

[0864] Step 2:

[0865] The device sends the collected text data to the server at a fixed frequency. The input is the user's speech or message, and the output is the data sent to the server.

[0866] Step 3:

[0867] The server preprocesses the received text data by filtering, normalizing, tokenizing, and removing unnecessary data. The input is the user's raw data, and the output is preprocessed, well-formed data. Here, a natural language processing library (e.g., nltk) is used.

[0868] Step 4:

[0869] The server trains an AI model based on the preprocessed data. The input is the preprocessed text data, and the output is an AI model that has learned the user's characteristics. Here, the model is trained using a machine learning algorithm (e.g., sklearn's Ridge model).

[0870] Step 5:

[0871] The user types a question or request into the terminal. For example, the user types a prompt such as "What shall we play today?" The input is the user's question.

[0872] Step 6:

[0873] The terminal sends this question to the server. The input is the user's question, and the output is the data sent to the server.

[0874] Step 7:

[0875] The server inputs the received question into an artificial intelligence model to generate the most appropriate response. The input is the user's question, and the output is the generated response.

[0876] Step 8:

[0877] The generated response is provided to the user from the server via the terminal. The input is the response sent from the server, and the output is what is displayed to the user. For example, the response "Shall we play ball in the park today?" is displayed on the terminal.

[0878] Step 9:

[0879] The terminal collects the user's daily updated information and periodically sends it to the server. The input is newly collected text data, and the output is the transmission of updated data to the server.

[0880] Step 10:

[0881] The server preprocesses the update data using the same method as preprocessing and retrains the AI ​​model. The input is the preprocessed update data, and the output is an improved artificial intelligence model.

[0882] Step 11:

[0883] The terminal collects the feedback provided by the user and sends it to the server. The input is the user's feedback and the output is the feedback sent to the server.

[0884] Step 12:

[0885] The server adjusts the AI ​​model based on the feedback. The input is the user's feedback, and the output is the adjusted artificial intelligence model. For example, the model parameters are fine-tuned based on the feedback that the advice was good.

[0886] Through the above processing steps, the system can provide customized content that reflects the unique characteristics of the user.

[0887] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0888] This invention is a system that collects user text data, analyzes it using an artificial intelligence model and an emotion engine, and generates and provides responses that reflect the user's characteristic words, actions, thoughts, and emotions. This system functions in cooperation with a server, a terminal, and a user.

[0889] First, the user installs a dedicated application on their device and uses it on a daily basis. The device records the user's comments and messages and collects this text data at regular intervals. The device encrypts the collected text data and securely sends it to a server. The server stores the received text data in a database. The stored text data is first filtered to remove unnecessary information and spam.

[0890] The server then normalizes the stored text data, specifically by standardizing full-width and half-width characters, removing unnecessary spaces and special characters, and formatting the data. The normalized text data is then tokenized and used as training data for the AI ​​model.

[0891] The server uses the tokenized data to train the AI ​​model, which learns the user's characteristic behaviors and thoughts. This training process allows the AI ​​model to generate responses that reflect the user's phrasing, catchphrases, and educational principles.

[0892] A distinctive feature of the present invention is the incorporation of an emotion engine. The emotion engine is located in the server and analyzes emotions from the user's text data. The emotion information analyzed by the emotion engine is used as an important element in generating responses from the AI ​​model. For example, if the user is feeling stressed, a response that alleviates the user's emotions will be generated.

[0893] As a concrete example, suppose a child types a question into a device, such as "Why is Mommy angry?" When this information is sent to the server, the server tokenizes the question and inputs it into the emotion engine. The emotion engine analyzes the user's emotion based on past and current data. The analysis result determines that the emotion is "anger."

[0894] The AI ​​model then generates a response based on the emotion analysis, such as "Mommy is just tired, so let her get some rest," and sends it to the device via the server. The device then provides this response to the child via voice or text.

[0895] Furthermore, the present invention features continuous learning. By collecting daily updates from users and periodically preprocessing them to retrain the AI ​​model and emotion engine, it is possible to always reflect the latest user thoughts and emotions. Users can also provide feedback. Based on this feedback, the server adjusts the AI ​​model and emotion engine. In this way, the system is continuously optimized to meet the user's needs.

[0896] Through the above process, this invention provides a new means to reduce stress and burden on parents in the modern child-rearing environment and to realize effective and consistent education. In particular, by analyzing emotions and generating responses based on them, more humane and empathetic communication becomes possible.

[0897] The processing flow will be explained below.

[0898] Step 1:

[0899] Users install a dedicated application on their devices and use it on a daily basis. The devices record the user's comments and messages and collect this text data at regular intervals.

[0900] Step 2:

[0901] The device encrypts the collected text data and sends it securely to the server.

[0902] Step 3:

[0903] The server stores the received text data in a database, which is then filtered to remove unnecessary information and spam.

[0904] Step 4:

[0905] The server normalizes the stored text data, specifically by standardizing full-width and half-width characters, removing unnecessary spaces and special characters, and formatting the data.

[0906] Step 5:

[0907] The server tokenizes the normalized text data, splitting it into words and converting it into a format that is easy for the AI ​​model to learn.

[0908] Step 6:

[0909] The server uses the tokenized data to train an AI model, which learns the user's characteristic behaviors and thoughts. Specifically, it uses natural language processing algorithms and optimizes the model through a multi-layer neural network.

[0910] Step 7:

[0911] The server uses a trained emotion engine to analyze emotions from the user's text data, based on past and current data.

[0912] Step 8:

[0913] The device is responsible for real-time dialogue between the user and the child. When the child speaks to the device and types a question such as "Why is Mommy angry?", the response is sent to the server in text format.

[0914] Step 9:

[0915] The server tokenizes the received text data and inputs it into a trained emotion engine, which analyzes the user's emotions and extracts the emotion "anger."

[0916] Step 10:

[0917] The server uses the AI ​​model to generate the most appropriate response based on the analysis results of the emotion engine. In this case, the response generated is, "Mom is just tired, so let her get some rest."

[0918] Step 11:

[0919] The server sends the generated response to the terminal, which provides the response to the child in voice or text format.

[0920] Step 12:

[0921] Users can provide feedback to the system through the application as needed, for example, by rating the system "the response was appropriate" or by inputting specific requests such as "I would like the system to respond more like this."

[0922] Step 13:

[0923] The server analyzes the feedback provided by the user and adjusts the AI ​​model and emotion engine, optimizing the system to generate responses that better suit the user's needs.

[0924] Step 14:

[0925] The server periodically collects new data, preprocesses it, and retrains the AI ​​model and emotion engine, ensuring that the latest user thoughts and emotions are always reflected.

[0926] Through the above processing steps, the present invention supports high-quality, consistent communication between parents and children, and provides assistance for achieving more ideal child-rearing. In particular, by analyzing emotions and generating responses based on those emotions, more humane and empathetic communication becomes possible.

[0927] Example 2

[0928] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0929] Conventional text data analysis systems have difficulty generating responses that take into account the user's characteristic behavior and emotions, resulting in a decline in the quality of communication. Furthermore, given the need for continuous learning and real-time responses, conventional systems were not flexible enough. They also lacked a mechanism for optimizing the system using user feedback.

[0930] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0931] In this invention, the server includes means for encrypting and transmitting user text data, means for storing, filtering, and normalizing the transmitted text data, means for training an AI model that learns the user's characteristic behavior and way of thinking using the tokenized data, and means for generating a response that takes the user's emotions into consideration using the AI ​​model based on the emotion analysis results, thereby making it possible to provide high-quality responses that reflect the user's behavior and emotions in real time.

[0932] "User text data" refers to sentences or messages that a user inputs or generates through a terminal.

[0933] "Encryption" is the process of transforming data using a specific algorithm to make it unreadable to third parties in order to transmit it securely.

[0934] "Transmitting" refers to moving data from one point to another, and in this case means moving data from a terminal to a server.

[0935] "Storage" means storing data on an electronic recording medium in order to keep it safe for a long period of time.

[0936] "Filtering" is the process of removing unnecessary information and spam from data and extracting only useful information.

[0937] "Normalization" is the process of converting data into a unified format and making it consistent.

[0938] "Tokenization" is the process of dividing text data into small units such as words or sentences based on certain rules.

[0939] An "artificial intelligence model" is an algorithm or system that can learn and make inferences or predictions based on specific data.

[0940] "Training" is the process by which an artificial intelligence model learns from given data and improves its accuracy.

[0941] "Sentiment analysis" is the process of identifying emotions from a user's text data and quantitatively assessing the type and intensity of those emotions.

[0942] "Generation" means that the artificial intelligence model creates new data or responses based on the data and analysis results obtained.

[0943] "Feedback" refers to user evaluations and opinions on the system's performance and results.

[0944] "Tuning" refers to optimizing system parameters and settings based on feedback to improve performance and results.

[0945] MODE FOR CARRYING OUT THE INVENTION

[0946] This invention is a system that collects user text data, analyzes it using an artificial intelligence model and an emotion engine, and generates and provides responses that reflect the user's characteristic words, actions, thoughts, and emotions. This system functions in cooperation with a server, a terminal, and a user.

[0947] Terminal

[0948] First, the user installs a dedicated application on the device and uses it on a daily basis. The device records the user's statements and messages and collects this text data at a certain frequency. For example, a child might type "Why is Mommy angry?" into the device. The device encrypts the collected text data and securely transmits it to the server.

[0949] server

[0950] The server stores the received text data in a database. The stored text data is first filtered to remove unnecessary information and spam. The server then normalizes the stored text data. Specifically, it standardizes full-width and half-width characters, removes unnecessary spaces and special characters, and formats the data. This ensures that the data is processed in a consistent format.

[0951] The normalized text data is tokenized and used as training data for the AI ​​model. The server trains the AI ​​model using the tokenized data. For example, using a deep learning framework (e.g., TensorFlow, PyTorch), the AI ​​model learns the user's words, behaviors, and thoughts. This training process enables the AI ​​model to generate responses that reflect the user's phrasing, catchphrases, and educational principles.

[0952] A distinctive feature of the present invention is the incorporation of an emotion engine. The emotion engine is located in the server and analyzes emotions from the user's text data. The emotion information analyzed by the emotion engine is used as an important element in generating responses from the AI ​​model. For example, if the user is feeling stressed, a response that alleviates the user's emotions will be generated.

[0953] Specific examples

[0954] For example, a child might type a question into their device, such as "Why is Mommy angry?" When this information is sent to the server, the server tokenizes the question and inputs it into the emotion engine. The emotion engine analyzes the user's emotion based on past and current data. The analysis result determines that the emotion is "anger." The AI ​​model then generates a response based on the emotion analysis result. For example, a response such as "Mommy is just tired, so let her get some rest" is generated and sent to the device via the server. The device then provides this response to the child as voice or text.

[0955] Furthermore, the present invention features continuous learning. By collecting daily updates from users and periodically preprocessing them to retrain the AI ​​model and emotion engine, it is possible to always reflect the latest user thoughts and emotions. Users can also provide feedback. Based on this feedback, the server adjusts the AI ​​model and emotion engine. In this way, the system is continuously optimized to meet the user's needs.

[0956] Through the above process, the present invention provides a new means for reducing stress and strain on users in modern communication environments and generating effective and consistent responses. In particular, analyzing emotions and generating responses based on those emotions enables more human and empathetic communication.

[0957] keyword

[0958] Generative AI Models

[0959] An artificial intelligence model that learns a user's characteristic behavior and way of thinking and generates appropriate responses.

[0960] Prompt statement

[0961] Specific examples of text to input into the system, such as the question "Why is Mom mad?"

[0962] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0963] Program processing steps

[0964] Step 1:

[0965] Text data collection and encryption

[0966] input

[0967] Text data that a user enters into a device, such as a statement like "Why is Mom angry?"

[0968] operation

[0969] Users use a dedicated application to input comments and messages on a daily basis.

[0970] The terminal collects this input text data.

[0971] The collected text data is encrypted using an encryption algorithm such as AES.

[0972] output

[0973] Encrypted text data is generated.

[0974] Step 2:

[0975] Encrypted data transmission and storage

[0976] input

[0977] Encrypted text data.

[0978] operation

[0979] The device sends encrypted data securely to the server, typically using the SSL / TLS protocol.

[0980] The server stores the received encrypted data in a database.

[0981] Perform an integrity check to ensure the data was saved correctly.

[0982] output

[0983] The stored encrypted data is placed in a database.

[0984] Step 3:

[0985] Filtering and normalizing text data

[0986] input

[0987] Text data stored in a database.

[0988] operation

[0989] The server retrieves text data from a database and filters it for spam and unwanted information.

[0990] The server normalizes the filtered data, specifically by unifying full-width and half-width characters and removing unnecessary spaces and special characters.

[0991] output

[0992] Filtered and normalized text data is generated.

[0993] Step 4:

[0994] Tokenization of text data

[0995] input

[0996] Filtered and normalized text data.

[0997] operation

[0998] The server tokenizes the normalized text data, for example splitting the text "Why is Mom mad?" into individual words.

[0999] output

[1000] Tokenized data is generated.

[1001] Step 5:

[1002] Training an AI model

[1003] input

[1004] Tokenized text data.

[1005] operation

[1006] The server uses the tokenized data to train an AI model, which uses a deep learning framework (e.g., TensorFlow, PyTorch) to learn the user's characteristic behaviors and thoughts.

[1007] output

[1008] A trained AI model is generated.

[1009] Step 6:

[1010] Conducting sentiment analysis

[1011] input

[1012] Text data sent by the user.

[1013] operation

[1014] The server inputs the text data into the emotion engine and performs emotion analysis. For example, a question such as "Why is Mom angry?" is classified as the emotion "anger."

[1015] output

[1016] Emotional information is analyzed.

[1017] Step 7:

[1018] Response Generation

[1019] input

[1020] Sentiment analysis results and trained AI model.

[1021] operation

[1022] The server uses an AI model based on the results of the emotion analysis to generate an appropriate response, such as "Mom is just tired, so let her get some rest."

[1023] output

[1024] A generated response is created.

[1025] Step 8:

[1026] Sending and serving responses

[1027] input

[1028] The generated response.

[1029] operation

[1030] The server sends the generated response to the terminal.

[1031] The terminal provides the received response to the user, for example, the response is communicated to the user in text or audio format.

[1032] output

[1033] The response provided to the user is complete.

[1034] Step 9:

[1035] Continuous learning and feedback

[1036] input

[1037] User's daily text data and feedback.

[1038] operation

[1039] The user provides feedback on the generated response, for example, "This response was appropriate" or "I would have liked more specific information."

[1040] The server adjusts the parameters of the AI ​​model and emotion engine based on user feedback and performs retraining.

[1041] output

[1042] The optimized AI model and emotion engine are updated.

[1043] (Application example 2)

[1044] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1045] In conventional security services, communication between operators and customers is primarily manual, making it difficult to respond flexibly to customer emotions. Furthermore, there are no systems that can analyze emotions and generate appropriate responses in emergencies that require real-time response. This can lead to reduced customer satisfaction and delayed responses.

[1046] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user text data, means for encrypting the collected text data and securely transmitting it to the server, means for preprocessing the text data received by the server, means for tokenizing the preprocessed text data, means for training an artificial intelligence model that learns the user's characteristic words and actions and way of thinking using the tokenized data, means for analyzing emotions from the user's text data using an emotion engine, means for generating responses that imitate the user's words and actions in real time based on the analysis results of the emotion engine using the artificial intelligence model, and means for providing the generated responses to the user. This enables flexible and appropriate real-time responses according to emotions.

[1047] "Means for collecting user text data" refers to devices and software mechanisms for collecting messages and comments made by users.

[1048] "Means for encrypting collected text data and securely transmitting it to a server" refers to technologies and protocols that encrypt text data so that it cannot be deciphered by third parties and transmit it to a server over a secure channel.

[1049] The "means for preprocessing the text data received by the server" is a process for removing unnecessary information from the text data sent to the server and arranging the data in a proper format.

[1050] The "means for tokenizing preprocessed text data" refers to a process of segmenting preprocessed text data for natural language processing.

[1051] "Means for training an artificial intelligence model that learns a user's characteristic behaviors and ways of thinking using tokenized data" refers to the process of optimizing an artificial intelligence model to learn a user's characteristic behaviors and ways of thinking based on tokenized data.

[1052] "Means for analyzing emotions from user text data using an emotion engine" refers to an algorithm or system for identifying and analyzing emotions from user statements and messages.

[1053] "Means of using an artificial intelligence model to generate responses that mimic the user's words and actions in real time based on the analysis results of an emotion engine" refers to the ability of an artificial intelligence to mimic the user's tone of voice and terminology based on the results of emotion analysis and instantly generate responses.

[1054] "Means for providing the generated response to the user" refers to a mechanism for transmitting the response generated by the artificial intelligence through the device or application used by the user.

[1055]

[1056] The present invention is a system that analyzes a user's text data in real time and generates appropriate responses based on their emotions. This system enhances the effectiveness of security services by generating and providing responses that reflect the user's characteristic behavior and emotions. The following describes in detail an embodiment of the present invention.

[1057] A system for implementing the present invention functions primarily through cooperation between three parties: a server, a terminal, and a user. First, a user installs a specific application on a terminal (such as a smartphone or head-mounted display) and uses it on a daily basis. The terminal collects the user's comments and messages, encrypts them (using AES encryption, for example), and securely transmits them to a server.

[1058] The server stores the received text data in a database (e.g., MySQL, PostgreSQL). The stored text data is filtered to remove unnecessary information and spam. The filtered text data is then normalized to unify full-width and half-width characters and remove unnecessary spaces and special characters. The normalized text data is tokenized and used as training data for an artificial intelligence model (e.g., TensorFlow, PyTorch).

[1059] The server uses the tokenized data to train an AI model. The AI ​​model learns the user's characteristic behaviors and thoughts, and then analyzes the user's text data for emotions using an emotion engine (e.g., TextBlob, VaderSentiment). The analysis results are used as an important element in the AI ​​model's response generation.

[1060] The generated response is sent from the server to the device and provided to the user. For example, when a security operator receives an inquiry from a customer, this system is activated, analyzes the customer's emotions, and generates the optimal response. The hardware used includes iOS and Android smartphones and head-mounted displays such as the Oculus Quest 2.

[1061] As a concrete example, the following is an example of a prompt sentence for a generative AI model:

[1062] "A customer asks, 'My home security alarm is going off. What should I do?' I sense a sense of urgency in their recent conversations. How should I respond?"

[1063] Based on this prompt, the artificial intelligence model generates a response like this:

[1064] "Please stay calm. First, check all your doors and windows to make sure they're safe. Call the police if necessary."

[1065] The system of the present invention enables flexible and appropriate real-time responses according to emotions, thereby improving customer satisfaction with security services.

[1066] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1067] Step 1:

[1068] The device collects text data (utterances and messages) from the user. The input is the user's text data, and the output is the collected raw data. Specifically, data is acquired via the device's microphone or text input interface.

[1069] Step 2:

[1070] The terminal encrypts the collected text data and securely transmits it to the server. The input is the collected raw data, and the output is the encrypted data. Specifically, the data is encrypted using the AES encryption algorithm and transmitted to the server using the HTTPS protocol.

[1071] Step 3:

[1072] The server decrypts the received encrypted data and stores it in the database. The input is the encrypted data, and the output is the raw data stored in the database. Specifically, the data is decrypted using the AES decryption algorithm and stored in the MySQL or PostgreSQL database.

[1073] Step 4:

[1074] The server retrieves raw data from the database and performs preprocessing. The input is the raw data stored in the database, and the output is the preprocessed data. Specific operations include filtering (removing unnecessary information and spam data) and normalization (unifying full-width and half-width characters, deleting unnecessary spaces and special characters).

[1075] Step 5:

[1076] The server tokenizes the preprocessed data and uses it as training data for the AI ​​model. The input is the preprocessed data, and the output is the tokenized data. Specifically, it uses a natural language processing toolkit to split the text into tokens.

[1077] Step 6:

[1078] The server trains an AI model using the tokenized data. The input is the tokenized data, and the output is the trained AI model. Specifically, the model is trained using TensorFlow or PyTorch.

[1079] Step 7:

[1080] The server uses an emotion engine to analyze emotions from the user's text data. The input is preprocessed data, and the output is the emotion analysis result. Specifically, emotion analysis is performed using TextBlob and VaderSentiment.

[1081] Step 8:

[1082] The server uses an AI model based on the analysis results of the emotion engine to generate a response that mimics the user's words and actions in real time. The input is the emotion analysis result and the trained AI model, and the output is the generated response. Specifically, the server uses the generation function of the AI ​​model to generate a response to the prompt sentence.

[1083] Step 9:

[1084] The server sends the generated response to the terminal. The input is the generated response, and the output is the response sent to the terminal. As a specific operation, data is sent to the terminal using the HTTPS protocol.

[1085] Step 10:

[1086] The device provides the response received from the server to the user. The input is the response received from the server, and the output is the response provided to the user. Specific actions include displaying the response on the screen of a smartphone or head-mounted display, or reading it aloud.

[1087] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1088] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1089] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1090] [Fourth embodiment]

[1091] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1092] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1093] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1094] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1095] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1096] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1097] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1098] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1099] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1100] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1101] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1102] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1103] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1104] This invention is a system that collects users' text data, analyzes it using an AI model, and generates and provides responses that reflect the user's characteristic behavior and way of thinking. This system functions in cooperation between a server, a terminal, and the user.

[1105] First, users install a dedicated application on their devices. Through this application, users record their own speech and messages on a daily basis. The device collects this text data and sends it to a server at regular intervals. The collected data is first preprocessed. The server performs data preprocessing, including filtering unnecessary data, normalizing, and tokenizing. The preprocessed data is used as training data for the AI ​​model.

[1106] The server then uses the preprocessed data to train an AI model that learns the user's characteristic behaviors and thoughts. This training process enables the AI ​​model to generate responses that reflect the user's phrasing, catchphrases, and educational principles.

[1107] The device is responsible for real-time dialogue with the child. For example, when a child types a question into the device, such as "What shall we play today?", that information is sent to the server. The server inputs the received question into an AI model and generates the most appropriate response. That response is then provided to the child via the device. For example, a response such as "Shall we play ball in the park today?" is generated and conveyed to the child.

[1108] Furthermore, the present invention features continuous learning. By collecting daily updates from users, periodically preprocessing them, and retraining the AI ​​model, it is possible to always reflect the user's latest thinking and educational policies. Users can also provide feedback, which the server uses to adjust the AI ​​model. In this way, the system is continuously optimized to meet the user's needs.

[1109] As a specific example, suppose a user asks, "I'm worried about how to get my child to develop a good study habit." In this case, the device sends the consultation to the server. The server uses an AI model to generate advice such as, "Why don't you try creating a schedule together that determines study time?" and provides this advice to the user via the device. In this way, the present invention supports high-quality, consistent communication between parents and children, providing assistance for achieving more ideal parenting.

[1110] Through the above process, the present invention provides a new means for reducing stress and burden on parents in the modern child-rearing environment and for realizing effective and consistent education.

[1111] The processing flow will be explained below.

[1112] Step 1:

[1113] Users install a dedicated application on their devices and use it on a daily basis. The devices record the user's comments and messages and collect this text data at regular intervals.

[1114] Step 2:

[1115] The device encrypts the collected text data and sends it securely to the server.

[1116] Step 3:

[1117] The server stores the received text data in a database, which is then filtered to remove unnecessary information and spam.

[1118] Step 4:

[1119] The server normalizes the stored text data, specifically by standardizing full-width and half-width characters, removing unnecessary spaces and special characters, and formatting the data.

[1120] Step 5:

[1121] The server tokenizes the normalized text data, splitting it into words and converting it into a format that is easy for the AI ​​model to learn.

[1122] Step 6:

[1123] The server uses the tokenized data to train an AI model, which learns the user's characteristic behaviors and thoughts. Specifically, it uses natural language processing algorithms and optimizes the model through a multi-layer neural network.

[1124] Step 7:

[1125] The server stores the trained AI model and distributes it to devices as needed, while the AI ​​model is continuously updated to reflect the user's latest information.

[1126] Step 8:

[1127] The device is responsible for real-time interaction with the user and the child. When the child speaks to the device, the speech is sent to the server in text format.

[1128] Step 9:

[1129] The server tokenizes the received text data and feeds it into a trained AI model, which mimics the user's behavior and thoughts to generate appropriate responses.

[1130] Step 10:

[1131] The server sends the generated response to the device, which then provides the response to the child as voice or text. For example, if the child asks, "What shall we play today?", the device responds, "Shall we play ball in the park today?"

[1132] Step 11:

[1133] Users can provide feedback to the system through the application as needed, for example, by rating the system "the response was appropriate" or by inputting specific requests such as "I would like the system to respond more like this."

[1134] Step 12:

[1135] The server analyzes the feedback provided by the user and adjusts the AI ​​model, optimizing the system to generate responses that better suit the user's needs.

[1136] Step 13:

[1137] The server periodically collects new data, preprocesses it, and retrains the AI ​​model, ensuring that it always reflects the latest user thinking and educational policies.

[1138] Example 1

[1139] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1140] In today's child-rearing environment, it is difficult to alleviate the stress and burden on parents and achieve effective and consistent communication. Furthermore, in order for parents to provide appropriate education and advice through dialogue with their children, continuous learning and feedback are necessary, and achieving this requires advanced technology.

[1141] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1142] In this invention, the server includes a means for collecting user text data, a means for preprocessing the collected text data, and a means for training an AI model that learns the user's characteristic behavior and way of thinking using the preprocessed text data. This allows parents to use the generated AI model to provide appropriate responses to their children in real time. The server also includes a means for continuously updating the AI ​​model and retraining it based on the latest user text data, and a means for adjusting the AI ​​model based on feedback provided by the user, thereby enabling the server to generate optimal responses that always reflect the latest information.

[1143] "User text data" refers to the content of statements and messages that users input on a daily basis, including conversations, questions, opinions, and the like.

[1144] "Means of collection" refers to the function for saving the text data entered by the user in a certain format and transferring it to a server as necessary.

[1145] "Preprocessing" refers to the process of removing unnecessary information from collected text data and converting the data into a unified, easily analyzable format.

[1146] An "artificial intelligence model" refers to a system that is trained using machine learning algorithms to learn a user's characteristic behavior and way of thinking and generate responses based on that.

[1147] "Training" refers to the process of feeding preprocessed text data to an artificial intelligence model to allow the model to learn user characteristics.

[1148] A "real-time query" is a question or request entered by a user on the fly that requires an immediate response.

[1149] "Answer generation means" refers to the process of using an artificial intelligence model to generate an appropriate answer to a user's query.

[1150] "Generated answer" refers to a response to a user's query that is generated by an artificial intelligence model.

[1151] "Means for providing" refers to a function or interface for displaying the generated response to the user.

[1152] "Continuously updating" refers to the process of periodically retraining an artificial intelligence model with new data to maintain or improve the model's accuracy and effectiveness.

[1153] "Feedback" refers to evaluations and opinions provided by users, which are used to improve and adjust the quality of the system.

[1154] "Adjustment means" refers to the process of adjusting the parameters and algorithms of an artificial intelligence model based on user feedback to improve the model's response quality.

[1155] This invention is a system that collects users' text data, analyzes it using an AI model, and generates and provides responses that reflect the user's characteristic behavior and way of thinking. This system functions in cooperation between a server, a terminal, and the user.

[1156] First, users install a dedicated application on their device. Through this application, users can record their daily statements and messages. This involves a device such as a smartphone or tablet, and software that connects to a server via internet communication.

[1157] The device sends the recorded text data to a server at a fixed interval. The security of the data is ensured by using secure communication protocols such as HTTPS. The server then preprocesses the received data. Specifically, it performs processes such as filtering unnecessary data, normalizing, and tokenizing. This converts the data into a format that is easy to analyze.

[1158] The server then uses the preprocessed data to train an AI model, which can be a generative AI model such as GPT-3. The model is designed to learn the user's characteristic behaviors and thoughts and is trained using thousands to millions of data points. This process can take hours or days.

[1159] Real-time interaction begins when a user inputs a question or query into the device. For example, if the user inputs a question such as "What shall we play today?", the device sends this information to the server. The server inputs the received question into an AI model and generates an optimal response. The generated response is provided to the user via the device. For example, a response such as "Shall we play ball in the park today?" is generated.

[1160] Furthermore, the present invention features continuous learning. By collecting daily updates from users, periodically preprocessing them, and retraining the AI ​​model, it is possible to always reflect the user's latest thinking and educational policies. Users can also provide feedback. Based on this feedback, the server adjusts the AI ​​model. Specifically, it can strengthen highly rated responses and provide additional training to improve poorly rated responses.

[1161] As a concrete example, consider the case where a user inputs, "I'm worried about how to get my child to develop a good study habit." In this case, the device sends the inquiry to the server. The server uses an AI model to generate advice such as, "Why don't you try creating a schedule together that determines study time?" and provides it to the user via the device. In this way, the present invention supports high-quality, consistent communication between parents and children, providing assistance for achieving more ideal parenting.

[1162] An example of a prompt sentence is, "The user inputs, 'I'm worried about how to help my child develop study habits.' Please generate the most appropriate advice based on the data collected from the user's statements and messages."

[1163] Through the above process, the present invention provides a new means for reducing stress and burden on parents in the modern child-rearing environment and for realizing effective and consistent education.

[1164] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1165] Step 1: The user installs the application and collects text data.

[1166] Input: User comments and messages

[1167] Output: Collected text data

[1168] The device records user comments and messages through a dedicated application. This application has a chat-style interface and saves the comments and questions that users enter on a daily basis as text data. It also uses a voice recognition function to convert voice input into text and record it.

[1169] Step 2: The device sends the collected data to the server.

[1170] Input: Collected text data

[1171] Output: Data sent to the server

[1172] The device periodically sends the collected text data to the server via the HTTPS protocol, which ensures secure data transfer.

[1173] Step 3: The server preprocesses the data.

[1174] Input: Transmitted text data

[1175] Output: Preprocessed data

[1176] The server filters the submitted text data to remove unnecessary information. Specifically, it uses regular expressions to remove noise and stop words. It also normalizes the data, converting uppercase and lowercase letters, numbers, and special characters into a unified format. Finally, it tokenizes the data, splitting it into units that are easier to analyze.

[1177] Step 4: The server trains the AI ​​model.

[1178] Input: Preprocessed data

[1179] Output: A trained AI model

[1180] The server then feeds the preprocessed data to an AI model (such as GPT-3) to learn the user's characteristic behaviors and thoughts. This training process uses thousands to millions of data points and can take hours or even days. As a result, the AI ​​model is able to generate responses that reflect the user's unique phrasing and habits of speech.

[1181] Step 5: The user enters a real-time question.

[1182] Input: User question or query

[1183] Output: Query sent to the terminal

[1184] The user inputs a question or query into the device, for example, "What should we play today?" This information is immediately transmitted to the server.

[1185] Step 6: The server uses the AI ​​model to generate a response.

[1186] Input: User query

[1187] Output: The generated response

[1188] The server inputs the received question into an AI model and generates the best possible response. The generated response is specific and reflects the user's characteristics. A response such as "Shall we play ball in the park today?" is generated.

[1189] Step 7: The terminal provides the generated response to the user.

[1190] Input: The response sent by the server

[1191] Output: The response provided to the user

[1192] The device displays the generated responses to the user in real time, and the user can provide feedback, for example by giving a thumbs up if the response was helpful or indicating if they would like more suggestions.

[1193] Step 8: The server continues to learn and update the model.

[1194] Input: New data and feedback from users

[1195] Output: Updated AI model

[1196] The server collects daily updates and feedback from users, preprocesses them, and retrains the AI ​​model, ensuring that the model always reflects the latest information, improving the accuracy and effectiveness of its responses.

[1197] In this way, throughout the series of processing steps, the system can continue to provide the best possible response tailored to the user's needs.

[1198] (Application example 1)

[1199] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1200] Conventional content delivery systems have had difficulty providing customized content that fully reflects the individual needs and characteristics of users. Therefore, improving user satisfaction and increasing usage time are key challenges.

[1201] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1202] In this invention, the server includes means for collecting user text data, means for preprocessing the collected text data, means for training an AI model that learns the user's characteristic speech and behavior and way of thinking using the preprocessed text data, means for generating responses that imitate the user's speech and behavior in real time using the AI ​​model, means for providing the generated responses to the user, and means for generating and delivering content customized based on the user's characteristics, thereby enabling delivery of specialized content tailored to the user.

[1203] "User text data" refers to statements and messages that users input on a daily basis.

[1204] "Preprocessing" refers to converting collected text data into an analyzable format by filtering, normalizing, tokenizing, and other processes.

[1205] An "artificial intelligence model" is a collection of machine learning algorithms that learn a user's characteristic behavior and way of thinking and generate responses based on that.

[1206] "Real time" means that processing from data input to output is done instantaneously, with almost no delay.

[1207] "Customized content" refers to information and media that is specifically created based on the characteristics and preferences of an individual user.

[1208] "Feedback" refers to information such as user ratings and opinions, which are used to adjust and improve the system.

[1209] This invention is a customized content delivery system that uses an artificial intelligence model that collects user text data and learns user characteristics based on that data. This system is composed of three entities: a server, a terminal, and a user.

[1210] First, users install a dedicated application on their device. Through this application, users can enter their own comments and messages on a daily basis. The device collects this text data and sends it to a server at regular intervals.

[1211] The server first preprocesses the collected data. This involves filtering out unnecessary data, normalizing it, and tokenizing it. The preprocessed data is then used as training data for the artificial intelligence model. During preprocessing, the server analyzes the data using a natural language processing library (e.g., nltk).

[1212] The server then trains an artificial intelligence model on the preprocessed data. The model uses machine learning algorithms (such as sklearn's Ridge model) to learn the user's characteristic behaviors and thoughts, allowing the model to generate responses that reflect the user's unique phrasing and habits of speech.

[1213] The device interacts with the user in real time. For example, when the user inputs a question such as "What shall we play today?", the information is immediately sent to the server. The server inputs the received question into an artificial intelligence model and generates the most appropriate response. The response is then provided to the user via the device. For example, the response generated is "Shall we play ball in the park today?" and conveyed to the user.

[1214] Furthermore, the present invention also has a continuous learning function. The server periodically collects daily updates from users, preprocesses them, and retrains the AI ​​model to always reflect the latest user thinking and characteristics. Users can provide feedback, and the server will adjust the AI ​​model based on this feedback.

[1215] To generate and deliver customized content based on the user's characteristics, the server analyzes the collected data and provides videos and articles that match the user's preferences. For example, if a user frequently mentions a particular topic, content related to that topic will be generated and delivered preferentially.

[1216] An example of a prompt sentence is "What shall we play today?" In this way, the present invention can provide users with consistent, high-quality responses and customized content.

[1217] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1218] Step 1:

[1219] Users install a dedicated application on their devices, and through this application, they begin to input their own comments and messages on a daily basis. This input data is collected in text format.

[1220] Step 2:

[1221] The device sends the collected text data to the server at a fixed frequency. The input is the user's speech or message, and the output is the data sent to the server.

[1222] Step 3:

[1223] The server preprocesses the received text data by filtering, normalizing, tokenizing, and removing unnecessary data. The input is the user's raw data, and the output is preprocessed, well-formed data. Here, a natural language processing library (e.g., nltk) is used.

[1224] Step 4:

[1225] The server trains an AI model based on the preprocessed data. The input is the preprocessed text data, and the output is an AI model that has learned the user's characteristics. Here, the model is trained using a machine learning algorithm (e.g., sklearn's Ridge model).

[1226] Step 5:

[1227] The user types a question or request into the terminal. For example, the user types a prompt such as "What shall we play today?" The input is the user's question.

[1228] Step 6:

[1229] The terminal sends this question to the server. The input is the user's question, and the output is the data sent to the server.

[1230] Step 7:

[1231] The server inputs the received question into an artificial intelligence model to generate the most appropriate response. The input is the user's question, and the output is the generated response.

[1232] Step 8:

[1233] The generated response is provided to the user from the server via the terminal. The input is the response sent from the server, and the output is what is displayed to the user. For example, the response "Shall we play ball in the park today?" is displayed on the terminal.

[1234] Step 9:

[1235] The terminal collects the user's daily updated information and periodically sends it to the server. The input is newly collected text data, and the output is the transmission of updated data to the server.

[1236] Step 10:

[1237] The server preprocesses the update data using the same method as preprocessing and retrains the AI ​​model. The input is the preprocessed update data, and the output is an improved artificial intelligence model.

[1238] Step 11:

[1239] The terminal collects the feedback provided by the user and sends it to the server. The input is the user's feedback and the output is the feedback sent to the server.

[1240] Step 12:

[1241] The server adjusts the AI ​​model based on the feedback. The input is the user's feedback, and the output is the adjusted artificial intelligence model. For example, the model parameters are fine-tuned based on the feedback that the advice was good.

[1242] Through the above processing steps, the system can provide customized content that reflects the unique characteristics of the user.

[1243] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1244] This invention is a system that collects user text data, analyzes it using an artificial intelligence model and an emotion engine, and generates and provides responses that reflect the user's characteristic words, actions, thoughts, and emotions. This system functions in cooperation with a server, a terminal, and a user.

[1245] First, the user installs a dedicated application on their device and uses it on a daily basis. The device records the user's comments and messages and collects this text data at regular intervals. The device encrypts the collected text data and securely sends it to a server. The server stores the received text data in a database. The stored text data is first filtered to remove unnecessary information and spam.

[1246] The server then normalizes the stored text data, specifically by standardizing full-width and half-width characters, removing unnecessary spaces and special characters, and formatting the data. The normalized text data is then tokenized and used as training data for the AI ​​model.

[1247] The server uses the tokenized data to train the AI ​​model, which learns the user's characteristic behaviors and thoughts. This training process allows the AI ​​model to generate responses that reflect the user's phrasing, catchphrases, and educational principles.

[1248] A distinctive feature of the present invention is the incorporation of an emotion engine. The emotion engine is located in the server and analyzes emotions from the user's text data. The emotion information analyzed by the emotion engine is used as an important element in generating responses from the AI ​​model. For example, if the user is feeling stressed, a response that alleviates the user's emotions will be generated.

[1249] As a concrete example, suppose a child types a question into a device, such as "Why is Mommy angry?" When this information is sent to the server, the server tokenizes the question and inputs it into the emotion engine. The emotion engine analyzes the user's emotion based on past and current data. The analysis result determines that the emotion is "anger."

[1250] The AI ​​model then generates a response based on the emotion analysis, such as "Mommy is just tired, so let her get some rest," and sends it to the device via the server. The device then provides this response to the child via voice or text.

[1251] Furthermore, the present invention features continuous learning. By collecting daily updates from users and periodically preprocessing them to retrain the AI ​​model and emotion engine, it is possible to always reflect the latest user thoughts and emotions. Users can also provide feedback. Based on this feedback, the server adjusts the AI ​​model and emotion engine. In this way, the system is continuously optimized to meet the user's needs.

[1252] Through the above process, this invention provides a new means to reduce stress and burden on parents in the modern child-rearing environment and to realize effective and consistent education. In particular, by analyzing emotions and generating responses based on them, more humane and empathetic communication becomes possible.

[1253] The processing flow will be explained below.

[1254] Step 1:

[1255] Users install a dedicated application on their devices and use it on a daily basis. The devices record the user's comments and messages and collect this text data at regular intervals.

[1256] Step 2:

[1257] The device encrypts the collected text data and sends it securely to the server.

[1258] Step 3:

[1259] The server stores the received text data in a database, which is then filtered to remove unnecessary information and spam.

[1260] Step 4:

[1261] The server normalizes the stored text data, specifically by standardizing full-width and half-width characters, removing unnecessary spaces and special characters, and formatting the data.

[1262] Step 5:

[1263] The server tokenizes the normalized text data, splitting it into words and converting it into a format that is easy for the AI ​​model to learn.

[1264] Step 6:

[1265] The server uses the tokenized data to train an AI model, which learns the user's characteristic behaviors and thoughts. Specifically, it uses natural language processing algorithms and optimizes the model through a multi-layer neural network.

[1266] Step 7:

[1267] The server uses a trained emotion engine to analyze emotions from the user's text data, based on past and current data.

[1268] Step 8:

[1269] The device is responsible for real-time dialogue between the user and the child. When the child speaks to the device and types a question such as "Why is Mommy angry?", the response is sent to the server in text format.

[1270] Step 9:

[1271] The server tokenizes the received text data and inputs it into a trained emotion engine, which analyzes the user's emotions and extracts the emotion "anger."

[1272] Step 10:

[1273] The server uses the AI ​​model to generate the most appropriate response based on the analysis results of the emotion engine. In this case, the response generated is, "Mom is just tired, so let her get some rest."

[1274] Step 11:

[1275] The server sends the generated response to the terminal, which provides the response to the child in voice or text format.

[1276] Step 12:

[1277] Users can provide feedback to the system through the application as needed, for example, by rating the system "the response was appropriate" or by inputting specific requests such as "I would like the system to respond more like this."

[1278] Step 13:

[1279] The server analyzes the feedback provided by the user and adjusts the AI ​​model and emotion engine, optimizing the system to generate responses that better suit the user's needs.

[1280] Step 14:

[1281] The server periodically collects new data, preprocesses it, and retrains the AI ​​model and emotion engine, ensuring that the latest user thoughts and emotions are always reflected.

[1282] Through the above processing steps, the present invention supports high-quality, consistent communication between parents and children, and provides assistance for achieving more ideal child-rearing. In particular, by analyzing emotions and generating responses based on those emotions, more humane and empathetic communication becomes possible.

[1283] Example 2

[1284] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1285] Conventional text data analysis systems have difficulty generating responses that take into account the user's characteristic behavior and emotions, resulting in a decline in the quality of communication. Furthermore, given the need for continuous learning and real-time responses, conventional systems were not flexible enough. They also lacked a mechanism for optimizing the system using user feedback.

[1286] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1287] In this invention, the server includes means for encrypting and transmitting user text data, means for storing, filtering, and normalizing the transmitted text data, means for training an AI model that learns the user's characteristic behavior and way of thinking using the tokenized data, and means for generating a response that takes the user's emotions into consideration using the AI ​​model based on the emotion analysis results, thereby making it possible to provide high-quality responses that reflect the user's behavior and emotions in real time.

[1288] "User text data" refers to sentences or messages that a user inputs or generates through a terminal.

[1289] "Encryption" is the process of transforming data using a specific algorithm to make it unreadable to third parties in order to transmit it securely.

[1290] "Transmitting" refers to moving data from one point to another, and in this case means moving data from a terminal to a server.

[1291] "Storage" means storing data on an electronic recording medium in order to keep it safe for a long period of time.

[1292] "Filtering" is the process of removing unnecessary information and spam from data and extracting only useful information.

[1293] "Normalization" is the process of converting data into a unified format and making it consistent.

[1294] "Tokenization" is the process of dividing text data into small units such as words or sentences based on certain rules.

[1295] An "artificial intelligence model" is an algorithm or system that can learn and make inferences or predictions based on specific data.

[1296] "Training" is the process by which an artificial intelligence model learns from given data and improves its accuracy.

[1297] "Sentiment analysis" is the process of identifying emotions from a user's text data and quantitatively assessing the type and intensity of those emotions.

[1298] "Generation" means that the artificial intelligence model creates new data or responses based on the data and analysis results obtained.

[1299] "Feedback" refers to user evaluations and opinions on the system's performance and results.

[1300] "Tuning" refers to optimizing system parameters and settings based on feedback to improve performance and results.

[1301] MODE FOR CARRYING OUT THE INVENTION

[1302] This invention is a system that collects user text data, analyzes it using an artificial intelligence model and an emotion engine, and generates and provides responses that reflect the user's characteristic words, actions, thoughts, and emotions. This system functions in cooperation with a server, a terminal, and a user.

[1303] Terminal

[1304] First, the user installs a dedicated application on the device and uses it on a daily basis. The device records the user's statements and messages and collects this text data at a certain frequency. For example, a child might type "Why is Mommy angry?" into the device. The device encrypts the collected text data and securely transmits it to the server.

[1305] server

[1306] The server stores the received text data in a database. The stored text data is first filtered to remove unnecessary information and spam. The server then normalizes the stored text data. Specifically, it standardizes full-width and half-width characters, removes unnecessary spaces and special characters, and formats the data. This ensures that the data is processed in a consistent format.

[1307] The normalized text data is tokenized and used as training data for the AI ​​model. The server trains the AI ​​model using the tokenized data. For example, using a deep learning framework (e.g., TensorFlow, PyTorch), the AI ​​model learns the user's words, behaviors, and thoughts. This training process enables the AI ​​model to generate responses that reflect the user's phrasing, catchphrases, and educational principles.

[1308] A distinctive feature of the present invention is the incorporation of an emotion engine. The emotion engine is located in the server and analyzes emotions from the user's text data. The emotion information analyzed by the emotion engine is used as an important element in generating responses from the AI ​​model. For example, if the user is feeling stressed, a response that alleviates the user's emotions will be generated.

[1309] Specific examples

[1310] For example, a child might type a question into their device, such as "Why is Mommy angry?" When this information is sent to the server, the server tokenizes the question and inputs it into the emotion engine. The emotion engine analyzes the user's emotion based on past and current data. The analysis result determines that the emotion is "anger." The AI ​​model then generates a response based on the emotion analysis result. For example, a response such as "Mommy is just tired, so let her get some rest" is generated and sent to the device via the server. The device then provides this response to the child as voice or text.

[1311] Furthermore, the present invention features continuous learning. By collecting daily updates from users and periodically preprocessing them to retrain the AI ​​model and emotion engine, it is possible to always reflect the latest user thoughts and emotions. Users can also provide feedback. Based on this feedback, the server adjusts the AI ​​model and emotion engine. In this way, the system is continuously optimized to meet the user's needs.

[1312] Through the above process, the present invention provides a new means for reducing stress and strain on users in modern communication environments and generating effective and consistent responses. In particular, analyzing emotions and generating responses based on those emotions enables more human and empathetic communication.

[1313] keyword

[1314] Generative AI Models

[1315] An artificial intelligence model that learns a user's characteristic behavior and way of thinking and generates appropriate responses.

[1316] Prompt statement

[1317] Specific examples of text to input into the system, such as the question "Why is Mom mad?"

[1318] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1319] Program processing steps

[1320] Step 1:

[1321] Text data collection and encryption

[1322] input

[1323] Text data that a user enters into a device, such as a statement like "Why is Mom angry?"

[1324] operation

[1325] Users use a dedicated application to input comments and messages on a daily basis.

[1326] The terminal collects this input text data.

[1327] The collected text data is encrypted using an encryption algorithm such as AES.

[1328] output

[1329] Encrypted text data is generated.

[1330] Step 2:

[1331] Encrypted data transmission and storage

[1332] input

[1333] Encrypted text data.

[1334] operation

[1335] The device sends encrypted data securely to the server, typically using the SSL / TLS protocol.

[1336] The server stores the received encrypted data in a database.

[1337] Perform an integrity check to ensure the data was saved correctly.

[1338] output

[1339] The stored encrypted data is placed in a database.

[1340] Step 3:

[1341] Filtering and normalizing text data

[1342] input

[1343] Text data stored in a database.

[1344] operation

[1345] The server retrieves text data from a database and filters it for spam and unwanted information.

[1346] The server normalizes the filtered data, specifically by unifying full-width and half-width characters and removing unnecessary spaces and special characters.

[1347] output

[1348] Filtered and normalized text data is generated.

[1349] Step 4:

[1350] Tokenization of text data

[1351] input

[1352] Filtered and normalized text data.

[1353] operation

[1354] The server tokenizes the normalized text data, for example splitting the text "Why is Mom mad?" into individual words.

[1355] output

[1356] Tokenized data is generated.

[1357] Step 5:

[1358] Training an AI model

[1359] input

[1360] Tokenized text data.

[1361] operation

[1362] The server uses the tokenized data to train an AI model, which uses a deep learning framework (e.g., TensorFlow, PyTorch) to learn the user's characteristic behaviors and thoughts.

[1363] output

[1364] A trained AI model is generated.

[1365] Step 6:

[1366] Conducting sentiment analysis

[1367] input

[1368] Text data sent by the user.

[1369] operation

[1370] The server inputs the text data into the emotion engine and performs emotion analysis. For example, a question such as "Why is Mom angry?" is classified as the emotion "anger."

[1371] output

[1372] Emotional information is analyzed.

[1373] Step 7:

[1374] Response Generation

[1375] input

[1376] Sentiment analysis results and trained AI model.

[1377] operation

[1378] The server uses an AI model based on the results of the emotion analysis to generate an appropriate response, such as "Mom is just tired, so let her get some rest."

[1379] output

[1380] A generated response is created.

[1381] Step 8:

[1382] Sending and serving responses

[1383] input

[1384] The generated response.

[1385] operation

[1386] The server sends the generated response to the terminal.

[1387] The terminal provides the received response to the user, for example, the response is communicated to the user in text or audio format.

[1388] output

[1389] The response provided to the user is complete.

[1390] Step 9:

[1391] Continuous learning and feedback

[1392] input

[1393] User's daily text data and feedback.

[1394] operation

[1395] The user provides feedback on the generated response, for example, "This response was appropriate" or "I would have liked more specific information."

[1396] The server adjusts the parameters of the AI ​​model and emotion engine based on user feedback and performs retraining.

[1397] output

[1398] The optimized AI model and emotion engine are updated.

[1399] (Application example 2)

[1400] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1401] In conventional security services, communication between operators and customers is primarily manual, making it difficult to respond flexibly to customer emotions. Furthermore, there are no systems that can analyze emotions and generate appropriate responses in emergencies that require real-time response. This can lead to reduced customer satisfaction and delayed responses.

[1402] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user text data, means for encrypting the collected text data and securely transmitting it to the server, means for preprocessing the text data received by the server, means for tokenizing the preprocessed text data, means for training an artificial intelligence model that learns the user's characteristic words and actions and way of thinking using the tokenized data, means for analyzing emotions from the user's text data using an emotion engine, means for generating responses that imitate the user's words and actions in real time based on the analysis results of the emotion engine using the artificial intelligence model, and means for providing the generated responses to the user. This enables flexible and appropriate real-time responses according to emotions.

[1403] "Means for collecting user text data" refers to devices and software mechanisms for collecting messages and comments made by users.

[1404] "Means for encrypting collected text data and securely transmitting it to a server" refers to technologies and protocols that encrypt text data so that it cannot be deciphered by third parties and transmit it to a server over a secure channel.

[1405] The "means for preprocessing the text data received by the server" is a process for removing unnecessary information from the text data sent to the server and arranging the data in a proper format.

[1406] The "means for tokenizing preprocessed text data" refers to a process of segmenting preprocessed text data for natural language processing.

[1407] "Means for training an artificial intelligence model that learns a user's characteristic behaviors and ways of thinking using tokenized data" refers to the process of optimizing an artificial intelligence model to learn a user's characteristic behaviors and ways of thinking based on tokenized data.

[1408] "Means for analyzing emotions from user text data using an emotion engine" refers to an algorithm or system for identifying and analyzing emotions from user statements and messages.

[1409] "Means of using an artificial intelligence model to generate responses that mimic the user's words and actions in real time based on the analysis results of an emotion engine" refers to the ability of an artificial intelligence to mimic the user's tone of voice and terminology based on the results of emotion analysis and instantly generate responses.

[1410] "Means for providing the generated response to the user" refers to a mechanism for transmitting the response generated by the artificial intelligence through the device or application used by the user.

[1411]

[1412] The present invention is a system that analyzes a user's text data in real time and generates appropriate responses based on their emotions. This system enhances the effectiveness of security services by generating and providing responses that reflect the user's characteristic behavior and emotions. The following describes in detail an embodiment of the present invention.

[1413] A system for implementing the present invention functions primarily through cooperation between three parties: a server, a terminal, and a user. First, a user installs a specific application on a terminal (such as a smartphone or head-mounted display) and uses it on a daily basis. The terminal collects the user's comments and messages, encrypts them (using AES encryption, for example), and securely transmits them to a server.

[1414] The server stores the received text data in a database (e.g., MySQL, PostgreSQL). The stored text data is filtered to remove unnecessary information and spam. The filtered text data is then normalized to unify full-width and half-width characters and remove unnecessary spaces and special characters. The normalized text data is tokenized and used as training data for an artificial intelligence model (e.g., TensorFlow, PyTorch).

[1415] The server uses the tokenized data to train an AI model. The AI ​​model learns the user's characteristic behaviors and thoughts, and then analyzes the user's text data for emotions using an emotion engine (e.g., TextBlob, VaderSentiment). The analysis results are used as an important element in the AI ​​model's response generation.

[1416] The generated response is sent from the server to the device and provided to the user. For example, when a security operator receives an inquiry from a customer, this system is activated, analyzes the customer's emotions, and generates the optimal response. The hardware used includes iOS and Android smartphones and head-mounted displays such as the Oculus Quest 2.

[1417] As a concrete example, the following is an example of a prompt sentence for a generative AI model:

[1418] "A customer asks, 'My home security alarm is going off. What should I do?' I sense a sense of urgency in their recent conversations. How should I respond?"

[1419] Based on this prompt, the artificial intelligence model generates a response like this:

[1420] "Please stay calm. First, check all your doors and windows to make sure they're safe. Call the police if necessary."

[1421] The system of the present invention enables flexible and appropriate real-time responses according to emotions, thereby improving customer satisfaction with security services.

[1422] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1423] Step 1:

[1424] The device collects text data (utterances and messages) from the user. The input is the user's text data, and the output is the collected raw data. Specifically, data is acquired via the device's microphone or text input interface.

[1425] Step 2:

[1426] The terminal encrypts the collected text data and securely transmits it to the server. The input is the collected raw data, and the output is the encrypted data. Specifically, the data is encrypted using the AES encryption algorithm and transmitted to the server using the HTTPS protocol.

[1427] Step 3:

[1428] The server decrypts the received encrypted data and stores it in the database. The input is the encrypted data, and the output is the raw data stored in the database. Specifically, the data is decrypted using the AES decryption algorithm and stored in the MySQL or PostgreSQL database.

[1429] Step 4:

[1430] The server retrieves raw data from the database and performs preprocessing. The input is the raw data stored in the database, and the output is the preprocessed data. Specific operations include filtering (removing unnecessary information and spam data) and normalization (unifying full-width and half-width characters, deleting unnecessary spaces and special characters).

[1431] Step 5:

[1432] The server tokenizes the preprocessed data and uses it as training data for the AI ​​model. The input is the preprocessed data, and the output is the tokenized data. Specifically, it uses a natural language processing toolkit to split the text into tokens.

[1433] Step 6:

[1434] The server trains an AI model using the tokenized data. The input is the tokenized data, and the output is the trained AI model. Specifically, the model is trained using TensorFlow or PyTorch.

[1435] Step 7:

[1436] The server uses an emotion engine to analyze emotions from the user's text data. The input is preprocessed data, and the output is the emotion analysis result. Specifically, emotion analysis is performed using TextBlob and VaderSentiment.

[1437] Step 8:

[1438] The server uses an AI model based on the analysis results of the emotion engine to generate a response that mimics the user's words and actions in real time. The input is the emotion analysis result and the trained AI model, and the output is the generated response. Specifically, the server uses the generation function of the AI ​​model to generate a response to the prompt sentence.

[1439] Step 9:

[1440] The server sends the generated response to the terminal. The input is the generated response, and the output is the response sent to the terminal. As a specific operation, data is sent to the terminal using the HTTPS protocol.

[1441] Step 10:

[1442] The device provides the response received from the server to the user. The input is the response received from the server, and the output is the response provided to the user. Specific actions include displaying the response on the screen of a smartphone or head-mounted display, or reading it aloud.

[1443] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1444] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1445] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1446] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1447] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1448] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1449] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1450] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1451] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1452] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1453] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1454] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1455] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1456] 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.

[1457] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1458] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1459] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1460] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1461] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1462] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1463] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1464] The following is further disclosed regarding the above embodiment.

[1465] (Claim 1)

[1466] means for collecting user text data;

[1467] A means for preprocessing the collected text data;

[1468] A means for training an artificial intelligence model that learns a user's characteristic behaviors and thoughts using the preprocessed text data;

[1469] means for generating responses that mimic the user's behavior in real time using an artificial intelligence model;

[1470] means for providing the generated response to a user;

[1471] A system including:

[1472] (Claim 2)

[1473] 10. The system of claim 1, further comprising means for continuously updating and retraining the artificial intelligence model based on the most recent user text data.

[1474] (Claim 3)

[1475] 10. The system of claim 1, further comprising means for adjusting the artificial intelligence model based on feedback provided by a user.

[1476] "Example 1"

[1477] (Claim 1)

[1478] means for collecting user text data;

[1479] A means for preprocessing the collected text data;

[1480] A means for training an artificial intelligence model that learns a user's characteristic behaviors and thoughts using the preprocessed text data;

[1481] means for transmitting user-entered real-time queries and generating responses;

[1482] means for providing the generated response to a user;

[1483] A system including:

[1484] (Claim 2)

[1485] 10. The system of claim 1, further comprising means for continuously updating and retraining the artificial intelligence model based on the most recent user text data.

[1486] (Claim 3)

[1487] 10. The system of claim 1, further comprising means for adjusting the artificial intelligence model based on feedback provided by a user.

[1488] "Application Example 1"

[1489] (Claim 1)

[1490] means for collecting user text data;

[1491] A means for preprocessing the collected text data;

[1492] A means for training an artificial intelligence model that learns a user's characteristic behaviors and thoughts using the preprocessed text data;

[1493] means for generating responses that mimic the user's behavior in real time using an artificial intelligence model;

[1494] means for providing the generated response to a user;

[1495] means for generating and delivering customized content based on user characteristics;

[1496] A system including:

[1497] (Claim 2)

[1498] 10. The system of claim 1, further comprising means for continuously updating and retraining the artificial intelligence model based on the most recent user text data.

[1499] (Claim 3)

[1500] 10. The system of claim 1, further comprising means for adjusting the artificial intelligence model based on feedback provided by a user.

[1501] "Example 2: Combining Emotion Engines"

[1502] (Claim 1)

[1503] means for collecting user text data;

[1504] A means for encrypting and transmitting the collected text data;

[1505] means for storing, filtering and normalizing the transmitted text data;

[1506] a means for tokenizing the normalized text data;

[1507] means for training an artificial intelligence model that uses the tokenized data to learn the user's characteristic behaviors and thoughts;

[1508] emotion analysis means for analyzing emotions from user text data;

[1509] A means for generating a response that takes into account the user's emotions using an artificial intelligence model based on the emotion analysis results;

[1510] means for providing the generated response to a user;

[1511] A system including:

[1512] (Claim 2)

[1513] 10. The system of claim 1, further comprising means for continuously updating and retraining the artificial intelligence model based on the most recent user text data.

[1514] (Claim 3)

[1515] 10. The system of claim 1, further comprising means for adjusting the artificial intelligence model and the sentiment analysis means based on feedback provided by a user.

[1516] "Application example 2 when combining emotion engines"

[1517] (Claim 1)

[1518] means for collecting user text data;

[1519] A means for encrypting the collected text data and sending it securely to a server;

[1520] means for preprocessing text data received at a server;

[1521] means for tokenizing the preprocessed text data;

[1522] a means for training an artificial intelligence model that uses the tokenized data to learn a user's characteristic behaviors and thoughts;

[1523] means for analyzing emotions from user text data using an emotion engine;

[1524] A means for generating responses that mimic the user's words and actions in real time based on the analysis results of the emotion engine using an artificial intelligence model;

[1525] means for providing the generated response to a user;

[1526] A system including:

[1527] (Claim 2)

[1528] 10. The system of claim 1, further comprising means for continuously updating and retraining the artificial intelligence model based on the most recent user text data.

[1529] (Claim 3)

[1530] 10. The system of claim 1, further comprising means for adjusting the artificial intelligence model based on feedback provided by a user. [Explanation of symbols]

[1531] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for collecting user text data; A means for preprocessing the collected text data; A means for training an artificial intelligence model that learns a user's characteristic behaviors and thoughts using the preprocessed text data; means for generating responses that mimic the user's behavior in real time using an artificial intelligence model; means for providing the generated response to a user; A system including:

2. The system of claim 1 , further comprising means for continually updating and retraining the artificial intelligence model based on current user text data.

3. The system of claim 1 , further comprising means for adjusting the artificial intelligence model based on user-provided feedback.

Images