system

Abstract

We provide the system. [Solution] A method that uses a generative model to analyze user data and select information of interest in order to predict user interests, A means of transmitting the selected information to the user's terminal, A means of displaying selected information on the user's terminal, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the modern information environment, users are exposed to a large amount of advertisements and information every day. Not only does it take time and effort to check all the less relevant information, but there is also a possibility of missing important information. In such an information overload situation, it is required to provide an environment where users can accurately obtain the information they need and reduce the burden of information selection.

Means for Solving the Problems

[0005] This invention provides a generative model that analyzes user data and selects information of interest in order to predict user interests. Furthermore, it constructs a system that uses this generative model to transmit the selected information to the user's terminal, making it visually accessible on the terminal. This allows users to efficiently access the information they need and mitigates the problem of information overload.

[0006] A "user" refers to an individual or organization that utilizes an information system, and is the target of information that is customized based on their behavior and interests.

[0007] "Predicting interests" means analyzing past data to infer what a user might be interested in in the future.

[0008] "User data" refers to a collection of information that indicates a user's characteristics, such as their behavioral history, interests, and purchase history.

[0009] "Analysis" refers to the process of verifying data and extracting trends in user behavior and interests.

[0010] "Information of interest" refers to advertisements and content that users are likely to find interesting and use.

[0011] A "generative model" refers to an algorithm that predicts user interests based on collected data and selects relevant information.

[0012] "Transmission" refers to the process of transferring information from a server to a user's terminal.

[0013] A "terminal" refers to a device that a user can use to receive and display information, and includes smartphones and personal computers.

[0014] "Display" refers to the action of visually presenting information on the user's device screen. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0018] In the following embodiments, a tagged processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a tagged RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a tagged storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

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

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention is a system that analyzes user behavior data and effectively provides information of interest based on the results. This system is mainly implemented using a server, a user terminal, and a generative model.

[0037] The server receives various types of data sent by users and stores them in a database. Specifically, this includes users' browsing history, purchase data, and email newsletter subscription history. The received data is input into a generative model and analyzed to predict user interests.

[0038] The generative model incorporates algorithms that utilize machine learning and data mining techniques to predict future interests based on a user's past behavior and select relevant information. The selection criteria dynamically change according to each user's behavioral history, ensuring the provision of up-to-date information.

[0039] The user's device receives the selection results sent from the server and displays the information through an intuitive interface. Specifically, information on products and services that the user is likely to be interested in, as well as event details, are presented in tab or list format.

[0040] For example, by analyzing user behavior data from when they purchased a new smartphone, the system can predict when they will upgrade again and display relevant advertisements and price comparison information at that time. Similarly, new music releases and live event information are suggested based on the user's past browsing and purchase history.

[0041] In this way, users can automatically obtain information of interest on their devices without having to actively search for it, significantly reducing the time and effort required to select information. This system reduces the user's information burden while providing highly relevant information.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The user's device automatically collects data such as their browsing history, app usage logs, and the subject lines of received emails. This creates a database that reflects the user's interests.

[0045] Step 2:

[0046] The device sends the collected data to the server at regular intervals. This transmission is carried out through an encrypted channel to ensure privacy.

[0047] Step 3:

[0048] The server organizes the received data and stores it in a database. This data is then prepared for analysis by a generative model.

[0049] Step 4:

[0050] A generative model runs on the server, inferring user interests and preferences from stored user data. For example, it analyzes frequency and time records related to a specific product category to predict the next information needed.

[0051] Step 5:

[0052] The generative model selects information that is likely to attract user interest based on prediction results. The selected information is customized for each user and organized on the server.

[0053] Step 6:

[0054] The server sends the selected information to the user's terminal. This information is presented in a format that is easily accessible to the user on the terminal.

[0055] Step 7:

[0056] The user's device displays the received information in an intuitive interface suited to it. The user can check the necessary information and click links to obtain more details if needed.

[0057] (Example 1)

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

[0059] Conventional information provision systems have struggled to accurately predict user interests and provide relevant information in a timely manner. Furthermore, the time and effort required for users to find useful information has been excessive.

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

[0061] In this invention, the server includes means for collecting user information and storing it in a database, means for using a generative memory model that predicts user interests and selects relevant information based on a machine learning algorithm using the stored information, and means for transmitting the selected information to the user's terminal and displaying it with an intuitive interface. This makes it possible to effectively predict user interests and quickly provide necessary information.

[0062] "User information" refers to all data related to the actions and choices generated by the user.

[0063] A "database" is a storage device used to systematically organize and store large amounts of information, and to efficiently manage and retrieve it.

[0064] A "machine learning algorithm" is a computational method that allows computers to recognize patterns based on past data and make predictions and decisions about the future.

[0065] A "generative memory model" is a model that uses machine learning to infer a user's future interests from their past information and select relevant information based on those inferences.

[0066] A "central processing unit" is a device that plays a central role in processing and analyzing information and managing the operation of the entire system.

[0067] An "intuitive interface" refers to an operating screen or method that users can use intuitively, providing usability that does not require special knowledge or training.

[0068] This system aims to provide relevant information by effectively utilizing the user's behavioral history. It consists of a server, a user terminal, and a generative memory model.

[0069] The server collects behavioral data submitted by users and stores it in the system's database. Using web server technology, the server efficiently collects information such as user browsing history, purchase history, and newsletter subscription history. Furthermore, by employing relational database technology, it enables rapid searching and retrieval of necessary data. This allows the server to manage large amounts of data while respecting user privacy.

[0070] Generative models predict user interests based on stored data, utilizing machine learning algorithms. Specifically, they analyze users' past behavioral patterns using data mining and deep learning models to predict future interests. Generative AI models can select information based on each user's interests, always providing the most up-to-date and relevant information.

[0071] The user's device receives selection information sent from the server and displays it through the user interface. The device consists of various types of devices, such as smartphones and personal computers, and presents the received information to the user in tab or list format. This allows the user to efficiently access information of interest.

[0072] For example, if a user has frequently searched online for travel-related information in the past, the generative model will predict travel destinations and travel packages that they might be interested in next. As a result, the server sends this information to the user's terminal, and the user can easily view it. An example of a prompt message would be, "Predict future interests based on the user's past behavior data, and present relevant information based on the results."

[0073] In this way, the system streamlines the acquisition of user information and enables the provision of information tailored to the user's interests.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The server collects user behavior data and stores it in a database. It receives data such as user browsing history and purchase information as input, converts it into a digital format, and stores it in the database. This process involves data cleansing and organization to build a highly accurate dataset.

[0077] Step 2:

[0078] The server inputs the collected data into the generative model. Cleansed user behavior data is provided as input to the generative model. At this stage, the data is preprocessed and formatted for machine learning algorithms. The output is a dataset ready for analysis.

[0079] Step 3:

[0080] Generative models analyze data using machine learning algorithms. This process predicts each user's interests based on input user behavior data. By extracting data features and analyzing behavioral patterns, the model generates personalized recommendations as output.

[0081] Step 4:

[0082] The server receives the analysis results from the generative model and selects information of interest. It analyzes the outputted recommendation information and filters it to the most relevant information for the user. The selected information is sent to the user's terminal in an optimized format.

[0083] Step 5:

[0084] The user's device receives and displays information sent from the server. It receives information optimized for input and displays it intuitively on the device's interface. Information is presented in tabs or lists to facilitate user access and support quick access to related content.

[0085] (Application Example 1)

[0086] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0087] In modern times, it is difficult for users to efficiently obtain information that matches their interests from a vast amount of information. Furthermore, especially in online shopping, product recommendations based on individual user interests are often not effectively implemented, compromising convenience. As a result, users are forced to spend time sifting through information. Therefore, this invention aims to automatically provide information of high interest based on user behavior data and realize product recommendations tailored to individual needs.

[0088] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0089] In this invention, the server includes means for using a predictive device that analyzes user information to predict user interests and selects information of interest; a device for transmitting the selected information to the user's terminal; and a device for displaying the selected information on the user's device. This enables users to effectively obtain highly relevant information and products based on their past behavior.

[0090] "Predicting user interests" means analyzing users' past behavioral data to estimate their future interests and the things they are likely to be interested in.

[0091] "User information" refers to all data provided by the user, such as purchase history, browsing history, and email newsletter subscription history.

[0092] A "predictive device" is a device that analyzes user behavior data to determine their interests and preferences, and then executes an algorithm to select information based on that analysis.

[0093] "Selected information" refers to information chosen by the prediction device as matching the user's interests.

[0094] "User devices" refer to information terminals that users use on a daily basis, such as smartphones, tablets, and personal computers.

[0095] "Special offer information" refers to information that provides users with special value or discounts, such as coupons and campaign information.

[0096] A "storage device" is a system that stores data transmitted by users and allows for analysis and retrieval as needed.

[0097] The system that realizes this invention consists of a server, a user terminal, and a prediction device. The server is responsible for receiving behavioral data transmitted from the user and storing it in a database. In doing so, the server uses security software to safely manage the data while considering privacy.

[0098] The prediction system utilizes generative AI models to analyze user behavior data and identify their interests and preferences. This analysis employs data mining techniques, with specific examples of software used including Python's pandas library and scikit-learn. This allows for real-time estimation of products and information that users are likely to be interested in.

[0099] The user's device receives selection results sent from the server and displays them through an intuitive interface. Specifically, it is designed to provide information on estimated products and services in list or recommendation format, and also displays special offers based on the user's purchase and browsing history. This makes it easy for users to obtain information that matches their interests.

[0100] For example, when a user purchases a new smart TV, recommendations for related accessories and services are displayed on the device based on their past purchase and browsing history. Related sales information and coupons are also presented, which can increase the user's desire to purchase.

[0101] An example of a prompt would be, "Considering the user's past purchase and browsing history, please list products that the user might be interested in." Using this prompt, the predictive tool can leverage its generative AI model to provide information optimized for the user.

[0102] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0103] Step 1:

[0104] The server receives user information from the user's device. This information includes the user's browsing history, purchase history, etc. The input data is stored in a database and encrypted to ensure privacy.

[0105] Step 2:

[0106] The server passes the stored data to the prediction device. The prediction device uses a generative AI model to analyze the data and predict the user's interests. At this stage, the generative AI model uses the prompt "Consider the user's past purchase and browsing history, and list products that the user might be interested in." As a result of the analysis, a list of products and services that may be of interest is output.

[0107] Step 3:

[0108] The server receives the information list generated by the prediction device and sends it to the user's terminal. This transmission uses network infrastructure and includes error checking to prevent information loss.

[0109] Step 4:

[0110] The user's device displays information via an interface based on the received data. The display format is either a list or a recommended products format, making it easy for the user to access. Based on the entered information, customized benefits (coupons and sales information) are also displayed, combined with the user's past behavioral data.

[0111] Step 5:

[0112] Users can select products they are interested in and view detailed information as needed. This action is sent from the device to the server as feedback, and the data is further updated and used to make future predictions.

[0113] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0114] This invention is a system that uses user behavioral data and emotional data to predict and appropriately provide information that users are interested in. This system is mainly implemented using a server, a user terminal, and an emotional engine.

[0115] In addition to recording the user's behavior history, the device incorporates an emotion engine that recognizes the user's emotions in real time. This engine analyzes emotional patterns from the user's facial expressions, tone of voice, and speed of operation. The collected emotional data is combined with behavioral data to create a dataset that more comprehensively reflects the user's characteristics.

[0116] The server stores received user data in a database, retrieves emotional data sent from the emotion engine, and analyzes it using a generative model. The generative model specifically evaluates how emotional trends influence users' purchase intent and information interests, and predicts user interests.

[0117] The sentiment data identified by the sentiment engine reveals what users are responding to positively or negatively, improving the predictive accuracy of generative models. For example, it can record a user's emotional changes when they see an advertisement for a product, allowing us to measure the user's level of interest in that product.

[0118] The server selects information relevant to the user based on the prediction results and sends that information to the user's terminal. The selected information is displayed on the user's terminal through an intuitive and easy-to-use interface. This allows users to easily obtain the latest information that interests them and reduces the burden of information selection.

[0119] For example, if a user frequently searches for information about a particular music artist, and the emotion engine detects a high level of positive emotion, the server can prioritize providing that user with information about the artist's new songs and tours. In this way, the present invention makes it possible to significantly personalize the user experience and improve user satisfaction.

[0120] The following describes the processing flow.

[0121] Step 1:

[0122] The user's device records their behavioral history and, simultaneously, uses its built-in emotion engine to record the user's emotional data in real time. This emotional data is collected by evaluating the user's emotional state based on their facial expressions, voice, input patterns, and other factors.

[0123] Step 2:

[0124] The device periodically or in real time transmits collected behavioral and emotional data to the server. A secure protocol is used for this transmission to protect the confidentiality of the data.

[0125] Step 3:

[0126] The server organizes the received data and stores it in a database. During this process, information that does not require user identification is anonymized to protect privacy.

[0127] Step 4:

[0128] A generative model runs on the server, comprehensively analyzing accumulated behavioral and emotional data. This analysis allows for a specific evaluation of user interests and emotional preferences.

[0129] Step 5:

[0130] The generative model selects information that is likely to be of interest to the user based on analysis. In this selection process, information related to the subject in which the user has shown positive emotions is often prioritized.

[0131] Step 6:

[0132] The server organizes the selected information and sends it to the user's terminal. The transmission employs an optimized communication method to ensure quick access for the user.

[0133] Step 7:

[0134] The user's device displays received information in a visually easy-to-understand user interface. Through this interface, users can easily access detailed information, which helps them make purchasing and event participation decisions.

[0135] (Example 2)

[0136] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0137] It is difficult for users to efficiently find information highly relevant to them from a vast amount of data. Furthermore, conventional systems have not been able to adequately reflect changes in users' interests and emotions, resulting in issues with the accuracy of information provision. This invention aims to achieve highly accurate information selection and personalized information provision based on users' behavioral history and emotional data.

[0138] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0139] In this invention, the server includes means for collecting user behavior history and emotional data and analyzing it using a generative AI model, means for predicting user interests based on the analyzed data and selecting relevant information, and means for transmitting the selected information to the user terminal. This makes it possible to provide highly accurate information based on the interests of individual users.

[0140] "User activity history" refers to historical information about the actions a user has taken and the content they have viewed on their digital devices.

[0141] "Emotional data" refers to data that quantifies or patterns the user's emotional state, and includes elements such as facial expressions, tone of voice, and speed of operation.

[0142] A "generative AI model" refers to an artificial intelligence model used to analyze collected data and predict user interests and behavioral patterns.

[0143] "Means of selecting information" refers to the process or mechanism of selecting appropriate information to provide to users based on analyzed data.

[0144] A "user terminal" is an electronic device that a user can directly operate, and includes smartphones, tablets, and personal computers.

[0145] An "emotion engine" refers to a digital system that analyzes user emotional data in real time to identify the user's emotional state.

[0146] This invention is implemented as a system combining an electronic terminal used by the user and a server that processes user data. The user's terminal is equipped with software that records behavioral history and also has a built-in emotion engine. The emotion engine acquires the user's facial expressions from a camera, their voice tone from a microphone, and their operation speed from a touch interface, and performs analysis in real time.

[0147] The user's device sends collected behavioral history and emotional data to the server. The server receives this data and analyzes it using a generative AI model. The generative AI model utilizes various data processing techniques to predict user interests, particularly analyzing how emotional changes affect interest and purchase intent. Based on the results of this model, the server selects information that the user is likely to be interested in and sends that information to the user's device.

[0148] The user's device displays selected information through a user-friendly interface. The user views the presented information, and their evaluation and feedback are collected again via the device as behavioral data. This data is sent to the server for the next cycle, contributing to improved analysis accuracy.

[0149] As a concrete example, let's assume a user frequently plays songs by a specific artist while using a music app, and the emotion engine detects positive emotions during this time. In this case, the server prioritizes selecting and notifying the user of new songs and concert information by that artist. The generative AI model supporting this process learns using prompts such as "Select information to provide preferentially based on the user's emotions and behavioral history," thereby improving the accuracy of information selection.

[0150] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0151] Step 1:

[0152] The device begins collecting user behavior history and emotional data. This includes information such as which applications the user is using and which websites they are browsing. It also uses an emotion engine to acquire real-time emotional data from the facial camera and microphone. At this point, the input is the user's actions and real-time biometric data, and the output is an initial set of behavior history and emotional data.

[0153] Step 2:

[0154] The device packages the collected behavioral history and emotional data, encrypts it, and then sends it to the server. This protects user privacy. The input is the data collected in step 1, and the output is the packaged data securely sent to the server.

[0155] Step 3:

[0156] The server receives data sent from the terminal and stores it in the database. This data is ready to be analyzed by the generative AI model. The input is the packaged data obtained in step 2, and the output is the raw data in the database before data analysis.

[0157] Step 4:

[0158] The server performs data analysis using a generative AI model. It predicts potential user interests using template prompts. The model analyzes the correlation between behavior and emotion to identify user areas of interest. The input is user data stored in a database, and the output is the interest prediction result.

[0159] Step 5:

[0160] The server selects information relevant to the user based on the analysis results. This information selection uses the interest prediction results as prompts. For example, new advertisements for a specific product or news articles in a genre of interest might be selected. The input is the interest prediction results from step 4, and the output is the selected set of information.

[0161] Step 6:

[0162] The server sends the selected information to the user's terminal. The input is the set of information selected in step 5, and the output is the information sent to the terminal.

[0163] Step 7:

[0164] The user's device displays the received information in an intuitive interface. Based on this information, the user can take further action. The input is the information sent from the server, and the output is the information displayed to the user.

[0165] Step 8:

[0166] The user reviews and uses the displayed information, thereby building further behavioral history and sentiment data. The input is the information displayed in step 7, and the output is new behavioral and sentiment data for the next cycle.

[0167] (Application Example 2)

[0168] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0169] In today's information society, users find it difficult to find information that is useful to them from the vast amount of information available. Furthermore, conventional information provision systems provide information without considering the user's emotions, so there is a need for greater personalization. This invention aims to achieve more accurate information provision by utilizing user behavior and emotion data.

[0170] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0171] In this invention, the server includes means for using a generative model that analyzes user data to predict user interests and selects information of interest; means for transmitting the selected information to the user's terminal; means for displaying the selected information on the user's terminal; means for using an emotion engine that analyzes user emotion data and recognizes emotions in real time; and means for selecting information relevant to the user based on the emotion data detected by the emotion engine. This makes it possible to efficiently provide information that is more of interest to the user.

[0172] "User data" refers to information that includes a user's behavioral history and emotional data, and is used to analyze user interests and behavior.

[0173] A "generative model" is an algorithm or computational method that analyzes user data and predicts user interests.

[0174] A "terminal" is a device that displays information and interacts with the user, and includes smartphones and computers.

[0175] An "emotion engine" is a system that analyzes the user's facial expressions, voice, etc., to recognize the user's emotions in real time.

[0176] "Methods for predicting interests" refer to methods that use generative models to identify in advance the information that users will be interested in.

[0177] "Relevant information" refers to information and content that is selected and provided to the user based on the user's current interests and feelings.

[0178] "Purchase intent" refers to the likelihood or level of desire a user has for purchasing a particular product or service.

[0179] The system that realizes this invention mainly consists of a server, a user terminal, and an emotion engine. The server predicts user interests using a generative model by comprehensively analyzing user behavior data and emotion data. The generative model learns from user data and executes algorithms to identify information and products that the user is interested in.

[0180] The user's device has a built-in emotion engine that analyzes the user's facial expressions and tone of voice in real time. This data, along with behavioral data, is sent to a server and analyzed by a generative model. The results of the analysis are selected as information predicted to be of interest to the user and sent to the device. The device then presents the selected information to the user through an intuitive and easy-to-use interface. This allows the user to efficiently obtain the latest information they need.

[0181] As a concrete example of its use, if a user is using an e-commerce app, and they express a positive sentiment towards product information presented based on their browsing and purchase history, the server can analyze that data and prioritize notifying them of promotional information for related products. This entire process is expected to make the user experience more personalized and improve satisfaction.

[0182] An example of a prompt message is: "User category name: Fashion, Item viewed: Jacket, Sentiment data: Positive, Product category to recommend: Related brand items". Based on this example, the generative AI model generates recommendations that are appropriate for the user.

[0183] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0184] Step 1:

[0185] The user's device uses an emotion engine to collect user emotion data in real time. This involves analyzing the user's facial expressions and voice tone, converting emotions (positive, negative, etc.) into data, and storing it as temporary data. The input to this process is the user's facial expressions and voice signals, and the output is emotion data.

[0186] Step 2:

[0187] The user's device collects behavioral data such as purchase history and browsing history. This data is temporarily stored on the user's device in preparation for subsequent analysis. The input to this process is the user's operation history and behavioral trajectory, and the output is behavioral data.

[0188] Step 3:

[0189] The user's device sends the collected emotional and behavioral data to the server. During this process, the data is encrypted and securely transferred to the server while ensuring privacy. In this step, the input data consists of emotional and behavioral data, and the output is encrypted data packets.

[0190] Step 4:

[0191] The server receives sentiment and behavioral data sent from the terminal and analyzes the data using a generative model. This model evaluates the data using various algorithms to predict user interests. The input is the received data, and the output is a list of information predicting interests.

[0192] Step 5:

[0193] Based on the analysis results of the generative model, the server selects relevant information and products and sends them to the user's terminal. This selection prioritizes information likely to be of interest based on the user's preferences. The input is the analysis results, and the output is the selected set of information.

[0194] Step 6:

[0195] The user's device receives selection information sent from the server and displays it through a visually intuitive interface. The user can interact with this interface and view information of interest. The input is the selection information, and the output is the information content displayed to the user.

[0196] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0197] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0198] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0199] [Second Embodiment]

[0200] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0201] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0202] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0203] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0204] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0205] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0206] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0207] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0208] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0209] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0210] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0211] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0212] This invention is a system that analyzes user behavior data and effectively provides information of interest based on the results. This system is mainly implemented using a server, a user terminal, and a generative model.

[0213] The server receives various types of data sent by users and stores them in a database. Specifically, this includes users' browsing history, purchase data, and email newsletter subscription history. The received data is input into a generative model and analyzed to predict user interests.

[0214] The generative model incorporates algorithms that utilize machine learning and data mining techniques to predict future interests based on a user's past behavior and select relevant information. The selection criteria dynamically change according to each user's behavioral history, ensuring the provision of up-to-date information.

[0215] The user's device receives the selection results sent from the server and displays the information through an intuitive interface. Specifically, information on products and services that the user is likely to be interested in, as well as event details, are presented in tab or list format.

[0216] For example, by analyzing user behavior data from when they purchased a new smartphone, the system can predict when they will upgrade again and display relevant advertisements and price comparison information at that time. Similarly, new music releases and live event information are suggested based on the user's past browsing and purchase history.

[0217] In this way, users can automatically obtain information of interest on their devices without having to actively search for it, significantly reducing the time and effort required to select information. This system reduces the user's information burden while providing highly relevant information.

[0218] The following describes the processing flow.

[0219] Step 1:

[0220] The user's device automatically collects data such as their browsing history, app usage logs, and the subject lines of received emails. This creates a database that reflects the user's interests.

[0221] Step 2:

[0222] The device sends the collected data to the server at regular intervals. This transmission is carried out through an encrypted channel to ensure privacy.

[0223] Step 3:

[0224] The server organizes the received data and stores it in a database. This data is then prepared for analysis by a generative model.

[0225] Step 4:

[0226] A generative model runs on the server, inferring user interests and preferences from stored user data. For example, it analyzes frequency and time records related to a specific product category to predict the next information needed.

[0227] Step 5:

[0228] The generative model selects information that is likely to attract user interest based on prediction results. The selected information is customized for each user and organized on the server.

[0229] Step 6:

[0230] The server sends the selected information to the user's terminal. This information is presented in a format that is easily accessible to the user on the terminal.

[0231] Step 7:

[0232] The user's device displays the received information in an intuitive interface suited to it. The user can check the necessary information and click links to obtain more details if needed.

[0233] (Example 1)

[0234] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0235] Conventional information provision systems have struggled to accurately predict user interests and provide relevant information in a timely manner. Furthermore, the time and effort required for users to find useful information has been excessive.

[0236] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0237] In this invention, the server includes means for collecting user information and storing it in a database, means for using a generative memory model that predicts user interests and selects relevant information based on a machine learning algorithm using the stored information, and means for transmitting the selected information to the user's terminal and displaying it with an intuitive interface. This makes it possible to effectively predict user interests and quickly provide necessary information.

[0238] "User information" refers to all data related to the actions and choices generated by the user.

[0239] A "database" is a storage device used to systematically organize and store large amounts of information, and to efficiently manage and retrieve it.

[0240] A "machine learning algorithm" is a computational method that allows computers to recognize patterns based on past data and make predictions and decisions about the future.

[0241] A "generative memory model" is a model that uses machine learning to infer a user's future interests from their past information and select relevant information based on those inferences.

[0242] A "central processing unit" is a device that plays a central role in processing and analyzing information and managing the operation of the entire system.

[0243] An "intuitive interface" refers to an operating screen or method that users can use intuitively, providing usability that does not require special knowledge or training.

[0244] This system aims to provide relevant information by effectively utilizing the user's behavioral history. It consists of a server, a user terminal, and a generative memory model.

[0245] The server collects behavioral data submitted by users and stores it in the system's database. Using web server technology, the server efficiently collects information such as user browsing history, purchase history, and newsletter subscription history. Furthermore, by employing relational database technology, it enables rapid searching and retrieval of necessary data. This allows the server to manage large amounts of data while respecting user privacy.

[0246] Generative models predict user interests based on stored data, utilizing machine learning algorithms. Specifically, they analyze users' past behavioral patterns using data mining and deep learning models to predict future interests. Generative AI models can select information based on each user's interests, always providing the most up-to-date and relevant information.

[0247] The user's device receives selection information sent from the server and displays it through the user interface. The device consists of various types of devices, such as smartphones and personal computers, and presents the received information to the user in tab or list format. This allows the user to efficiently access information of interest.

[0248] For example, if a user has frequently searched online for travel-related information in the past, the generative model will predict travel destinations and travel packages that they might be interested in next. As a result, the server sends this information to the user's terminal, and the user can easily view it. An example of a prompt message would be, "Predict future interests based on the user's past behavior data, and present relevant information based on the results."

[0249] In this way, the system streamlines the acquisition of user information and enables the provision of information tailored to the user's interests.

[0250] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0251] Step 1:

[0252] The server collects user behavior data and stores it in a database. It receives data such as user browsing history and purchase information as input, converts it into a digital format, and stores it in the database. This process involves data cleansing and organization to build a highly accurate dataset.

[0253] Step 2:

[0254] The server inputs the collected data into the generative model. Cleansed user behavior data is provided as input to the generative model. At this stage, the data is preprocessed and formatted for machine learning algorithms. The output is a dataset ready for analysis.

[0255] Step 3:

[0256] Generative models analyze data using machine learning algorithms. This process predicts each user's interests based on input user behavior data. By extracting data features and analyzing behavioral patterns, the model generates personalized recommendations as output.

[0257] Step 4:

[0258] The server receives the analysis results from the generative model and selects information of interest. It analyzes the outputted recommendation information and filters it to the most relevant information for the user. The selected information is sent to the user's terminal in an optimized format.

[0259] Step 5:

[0260] The user's device receives and displays information sent from the server. It receives information optimized for input and displays it intuitively on the device's interface. Information is presented in tabs or lists to facilitate user access and support quick access to related content.

[0261] (Application Example 1)

[0262] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0263] In modern times, it is difficult for users to efficiently obtain information that matches their interests from a vast amount of information. Furthermore, especially in online shopping, product recommendations based on individual user interests are often not effectively implemented, compromising convenience. As a result, users are forced to spend time sifting through information. Therefore, this invention aims to automatically provide information of high interest based on user behavior data and realize product recommendations tailored to individual needs.

[0264] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0265] In this invention, the server includes means for using a predictive device that analyzes user information to predict user interests and selects information of interest; a device for transmitting the selected information to the user's terminal; and a device for displaying the selected information on the user's device. This enables users to effectively obtain highly relevant information and products based on their past behavior.

[0266] "Predicting user interests" means analyzing users' past behavioral data to estimate their future interests and the things they are likely to be interested in.

[0267] "User information" refers to all data provided by the user, such as purchase history, browsing history, and email newsletter subscription history.

[0268] A "predictive device" is a device that analyzes user behavior data to determine their interests and preferences, and then executes an algorithm to select information based on that analysis.

[0269] "Selected information" refers to information chosen by the prediction device as matching the user's interests.

[0270] "User devices" refer to information terminals that users use on a daily basis, such as smartphones, tablets, and personal computers.

[0271] "Special offer information" refers to information that provides users with special value or discounts, such as coupons and campaign information.

[0272] A "storage device" is a system that stores data transmitted by users and allows for analysis and retrieval as needed.

[0273] The system that realizes this invention consists of a server, a user terminal, and a prediction device. The server is responsible for receiving behavioral data transmitted from the user and storing it in a database. In doing so, the server uses security software to safely manage the data while considering privacy.

[0274] The prediction system utilizes generative AI models to analyze user behavior data and identify their interests and preferences. This analysis employs data mining techniques, with specific examples of software used including Python's pandas library and scikit-learn. This allows for real-time estimation of products and information that users are likely to be interested in.

[0275] The user's device receives selection results sent from the server and displays them through an intuitive interface. Specifically, it is designed to provide information on estimated products and services in list or recommendation format, and also displays special offers based on the user's purchase and browsing history. This makes it easy for users to obtain information that matches their interests.

[0276] For example, when a user purchases a new smart TV, recommendations for related accessories and services are displayed on the device based on their past purchase and browsing history. Related sales information and coupons are also presented, which can increase the user's desire to purchase.

[0277] An example of a prompt would be, "Considering the user's past purchase and browsing history, please list products that the user might be interested in." Using this prompt, the predictive tool can leverage its generative AI model to provide information optimized for the user.

[0278] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0279] Step 1:

[0280] The server receives user information from the user's device. This information includes the user's browsing history, purchase history, etc. The input data is stored in a database and encrypted to ensure privacy.

[0281] Step 2:

[0282] The server passes the stored data to the prediction device. The prediction device analyzes the data using a generative AI model and predicts the user's interests. At this stage, the generative AI model uses the prompt sentence "Please list the products that the user is likely to be interested in considering the user's past purchase history and browsing history." As an analysis result, a list of products and services that may attract interest is output.

[0283] Step 3:

[0284] The server receives the information list generated by the prediction device again and transmits it to the user's terminal. This transmission uses the network infrastructure and performs error checking to prevent information loss.

[0285] Step 4:

[0286] Based on the received information, the user's terminal displays the information via an interface. The display format is a list format or a recommended product format to make it easily accessible to the user. Customized benefits (coupons and sale information) compared with the user's past behavior data based on the input information are also displayed together.

[0287] Step 5:

[0288] The user can select the products of interest as needed and view the detailed information. This action is transmitted from the terminal to the server as feedback, and the data is further updated and utilized for the next prediction.

[0289] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion identification model 59 and perform specific processing using the user's emotions.

[0290] This invention is a system that uses user behavioral data and emotional data to predict and appropriately provide information that users are interested in. This system is mainly implemented using a server, a user terminal, and an emotional engine.

[0291] In addition to recording the user's behavior history, the device incorporates an emotion engine that recognizes the user's emotions in real time. This engine analyzes emotional patterns from the user's facial expressions, tone of voice, and speed of operation. The collected emotional data is combined with behavioral data to create a dataset that more comprehensively reflects the user's characteristics.

[0292] The server stores received user data in a database, retrieves emotional data sent from the emotion engine, and analyzes it using a generative model. The generative model specifically evaluates how emotional trends influence users' purchase intent and information interests, and predicts user interests.

[0293] The sentiment data identified by the sentiment engine reveals what users are responding to positively or negatively, improving the predictive accuracy of generative models. For example, it can record a user's emotional changes when they see an advertisement for a product, allowing us to measure the user's level of interest in that product.

[0294] The server selects information relevant to the user based on the prediction results and sends that information to the user's terminal. The selected information is displayed on the user's terminal through an intuitive and easy-to-use interface. This allows users to easily obtain the latest information that interests them and reduces the burden of information selection.

[0295] For example, if a user frequently searches for information about a particular music artist, and the emotion engine detects a high level of positive emotion, the server can prioritize providing that user with information about the artist's new songs and tours. In this way, the present invention makes it possible to significantly personalize the user experience and improve user satisfaction.

[0296] The processing flow will be described below.

[0297] Step 1:

[0298] The user's terminal records the user's emotion data in real time using the built-in emotion engine in the terminal, along with the action history. The emotion data evaluates and collects the emotional state based on the user's expression, voice, input pattern, etc.

[0299] Step 2:

[0300] The terminal sends the collected action data and emotion data to the server periodically or in real time. A secure protocol is used for this transmission to protect the confidentiality of the data.

[0301] Step 3:

[0302] The server organizes the received data and stores it in the database. At this time, the information that does not require user identification is anonymized to protect privacy.

[0303] Step 4:

[0304] The generation model operates on the server and comprehensively analyzes the accumulated action and emotion data. Through the analysis, the interests based on the user's interest tendency and emotion are specifically evaluated.

[0305] Step 5:

[0306] Based on the analysis, the generation model selects the information that the user is likely to be interested in. In the selection, the information related to the object that the user shows positive emotions is often prioritized.

[0307] Step 6:

[0308] The server organizes the selected information and sends it to the user's terminal. The transmission employs an optimized communication method to ensure quick access for the user.

[0309] Step 7:

[0310] The user's device displays received information in a visually easy-to-understand user interface. Through this interface, users can easily access detailed information, which helps them make purchasing and event participation decisions.

[0311] (Example 2)

[0312] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0313] It is difficult for users to efficiently find information highly relevant to them from a vast amount of data. Furthermore, conventional systems have not been able to adequately reflect changes in users' interests and emotions, resulting in issues with the accuracy of information provision. This invention aims to achieve highly accurate information selection and personalized information provision based on users' behavioral history and emotional data.

[0314] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0315] In this invention, the server includes means for collecting user behavior history and emotional data and analyzing it using a generative AI model, means for predicting user interests based on the analyzed data and selecting relevant information, and means for transmitting the selected information to the user terminal. This makes it possible to provide highly accurate information based on the interests of individual users.

[0316] "User activity history" refers to historical information about the actions a user has taken and the content they have viewed on their digital devices.

[0317] "Emotional data" refers to data that quantifies or patterns the user's emotional state, and includes elements such as facial expressions, tone of voice, and speed of operation.

[0318] A "generative AI model" refers to an artificial intelligence model used to analyze collected data and predict user interests and behavioral patterns.

[0319] "Means of selecting information" refers to the process or mechanism of selecting appropriate information to provide to users based on analyzed data.

[0320] A "user terminal" is an electronic device that a user can directly operate, and includes smartphones, tablets, and personal computers.

[0321] An "emotion engine" refers to a digital system that analyzes user emotional data in real time to identify the user's emotional state.

[0322] This invention is implemented as a system combining an electronic terminal used by the user and a server that processes user data. The user's terminal is equipped with software that records behavioral history and also has a built-in emotion engine. The emotion engine acquires the user's facial expressions from a camera, their voice tone from a microphone, and their operation speed from a touch interface, and performs analysis in real time.

[0323] The user's device sends collected behavioral history and emotional data to the server. The server receives this data and analyzes it using a generative AI model. The generative AI model utilizes various data processing techniques to predict user interests, particularly analyzing how emotional changes affect interest and purchase intent. Based on the results of this model, the server selects information that the user is likely to be interested in and sends that information to the user's device.

[0324] The user's device displays selected information through a user-friendly interface. The user views the presented information, and their evaluation and feedback are collected again via the device as behavioral data. This data is sent to the server for the next cycle, contributing to improved analysis accuracy.

[0325] As a concrete example, let's assume a user frequently plays songs by a specific artist while using a music app, and the emotion engine detects positive emotions during this time. In this case, the server prioritizes selecting and notifying the user of new songs and concert information by that artist. The generative AI model supporting this process learns using prompts such as "Select information to provide preferentially based on the user's emotions and behavioral history," thereby improving the accuracy of information selection.

[0326] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0327] Step 1:

[0328] The device begins collecting user behavior history and emotional data. This includes information such as which applications the user is using and which websites they are browsing. It also uses an emotion engine to acquire real-time emotional data from the facial camera and microphone. At this point, the input is the user's actions and real-time biometric data, and the output is an initial set of behavior history and emotional data.

[0329] Step 2:

[0330] The device packages the collected behavioral history and emotional data, encrypts it, and then sends it to the server. This protects user privacy. The input is the data collected in step 1, and the output is the packaged data securely sent to the server.

[0331] Step 3:

[0332] The server receives data sent from the terminal and stores it in the database. This data is ready to be analyzed by the generative AI model. The input is the packaged data obtained in step 2, and the output is the raw data in the database before data analysis.

[0333] Step 4:

[0334] The server performs data analysis using a generative AI model. It predicts potential user interests using template prompts. The model analyzes the correlation between behavior and emotion to identify user areas of interest. The input is user data stored in a database, and the output is the interest prediction result.

[0335] Step 5:

[0336] The server selects information relevant to the user based on the analysis results. This information selection uses the interest prediction results as prompts. For example, new advertisements for a specific product or news articles in a genre of interest might be selected. The input is the interest prediction results from step 4, and the output is the selected set of information.

[0337] Step 6:

[0338] The server sends the selected information to the user's terminal. The input is the set of information selected in step 5, and the output is the information sent to the terminal.

[0339] Step 7:

[0340] The user's device displays the received information in an intuitive interface. Based on this information, the user can take further action. The input is the information sent from the server, and the output is the information displayed to the user.

[0341] Step 8:

[0342] The user reviews and uses the displayed information, thereby building further behavioral history and sentiment data. The input is the information displayed in step 7, and the output is new behavioral and sentiment data for the next cycle.

[0343] (Application Example 2)

[0344] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0345] In today's information society, users find it difficult to find information that is useful to them from the vast amount of information available. Furthermore, conventional information provision systems provide information without considering the user's emotions, so there is a need for greater personalization. This invention aims to achieve more accurate information provision by utilizing user behavior and emotion data.

[0346] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0347] In this invention, the server includes means for using a generative model that analyzes user data to predict user interests and selects information of interest; means for transmitting the selected information to the user's terminal; means for displaying the selected information on the user's terminal; means for using an emotion engine that analyzes user emotion data and recognizes emotions in real time; and means for selecting information relevant to the user based on the emotion data detected by the emotion engine. This makes it possible to efficiently provide information that is more of interest to the user.

[0348] "User data" refers to information that includes a user's behavioral history and emotional data, and is used to analyze user interests and behavior.

[0349] A "generative model" is an algorithm or computational method that analyzes user data and predicts user interests.

[0350] A "terminal" is a device that displays information and interacts with the user, and includes smartphones and computers.

[0351] An "emotion engine" is a system that analyzes the user's facial expressions, voice, etc., to recognize the user's emotions in real time.

[0352] "Methods for predicting interests" refer to methods that use generative models to identify in advance the information that users will be interested in.

[0353] "Relevant information" refers to information and content that is selected and provided to the user based on the user's current interests and feelings.

[0354] "Purchase intent" refers to the likelihood or level of desire a user has for purchasing a particular product or service.

[0355] The system that realizes this invention mainly consists of a server, a user terminal, and an emotion engine. The server predicts user interests using a generative model by comprehensively analyzing user behavior data and emotion data. The generative model learns from user data and executes algorithms to identify information and products that the user is interested in.

[0356] The user's device has a built-in emotion engine that analyzes the user's facial expressions and tone of voice in real time. This data, along with behavioral data, is sent to a server and analyzed by a generative model. The results of the analysis are selected as information predicted to be of interest to the user and sent to the device. The device then presents the selected information to the user through an intuitive and easy-to-use interface. This allows the user to efficiently obtain the latest information they need.

[0357] As a concrete example of its use, if a user is using an e-commerce app, and they express a positive sentiment towards product information presented based on their browsing and purchase history, the server can analyze that data and prioritize notifying them of promotional information for related products. This entire process is expected to make the user experience more personalized and improve satisfaction.

[0358] An example of a prompt message is: "User category name: Fashion, Item viewed: Jacket, Sentiment data: Positive, Product category to recommend: Related brand items". Based on this example, the generative AI model generates recommendations that are appropriate for the user.

[0359] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0360] Step 1:

[0361] The user's device uses an emotion engine to collect user emotion data in real time. This involves analyzing the user's facial expressions and voice tone, converting emotions (positive, negative, etc.) into data, and storing it as temporary data. The input to this process is the user's facial expressions and voice signals, and the output is emotion data.

[0362] Step 2:

[0363] The user's device collects behavioral data such as purchase history and browsing history. This data is temporarily stored on the user's device in preparation for subsequent analysis. The input to this process is the user's operation history and behavioral trajectory, and the output is behavioral data.

[0364] Step 3:

[0365] The user's device sends the collected emotional and behavioral data to the server. During this process, the data is encrypted and securely transferred to the server while ensuring privacy. In this step, the input data consists of emotional and behavioral data, and the output is encrypted data packets.

[0366] Step 4:

[0367] The server receives sentiment and behavioral data sent from the terminal and analyzes the data using a generative model. This model evaluates the data using various algorithms to predict user interests. The input is the received data, and the output is a list of information predicting interests.

[0368] Step 5:

[0369] Based on the analysis results of the generative model, the server selects relevant information and products and sends them to the user's terminal. This selection prioritizes information likely to be of interest based on the user's preferences. The input is the analysis results, and the output is the selected set of information.

[0370] Step 6:

[0371] The user's device receives selection information sent from the server and displays it through a visually intuitive interface. The user can interact with this interface and view information of interest. The input is the selection information, and the output is the information content displayed to the user.

[0372] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0373] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0374] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0375] [Third Embodiment]

[0376] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0377] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0378] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0379] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0380] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0381] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0382] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0383] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0384] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0385] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0386] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0387] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0388] This invention is a system that analyzes user behavior data and effectively provides information of interest based on the results. This system is mainly implemented using a server, a user terminal, and a generative model.

[0389] The server receives various types of data sent by users and stores them in a database. Specifically, this includes users' browsing history, purchase data, and email newsletter subscription history. The received data is input into a generative model and analyzed to predict user interests.

[0390] The generative model incorporates algorithms that utilize machine learning and data mining techniques to predict future interests based on a user's past behavior and select relevant information. The selection criteria dynamically change according to each user's behavioral history, ensuring the provision of up-to-date information.

[0391] The user's device receives the selection results sent from the server and displays the information through an intuitive interface. Specifically, information on products and services that the user is likely to be interested in, as well as event details, are presented in tab or list format.

[0392] For example, by analyzing user behavior data from when they purchased a new smartphone, the system can predict when they will upgrade again and display relevant advertisements and price comparison information at that time. Similarly, new music releases and live event information are suggested based on the user's past browsing and purchase history.

[0393] In this way, users can automatically obtain information of interest on their devices without having to actively search for it, significantly reducing the time and effort required to select information. This system reduces the user's information burden while providing highly relevant information.

[0394] The following describes the processing flow.

[0395] Step 1:

[0396] The user's device automatically collects data such as their browsing history, app usage logs, and the subject lines of received emails. This creates a database that reflects the user's interests.

[0397] Step 2:

[0398] The device sends the collected data to the server at regular intervals. This transmission is carried out through an encrypted channel to ensure privacy.

[0399] Step 3:

[0400] The server organizes the received data and stores it in a database. This data is then prepared for analysis by a generative model.

[0401] Step 4:

[0402] A generative model runs on the server, inferring user interests and preferences from stored user data. For example, it analyzes frequency and time records related to a specific product category to predict the next information needed.

[0403] Step 5:

[0404] The generative model selects information that is likely to attract user interest based on prediction results. The selected information is customized for each user and organized on the server.

[0405] Step 6:

[0406] The server sends the selected information to the user's terminal. This information is presented in a format that is easily accessible to the user on the terminal.

[0407] Step 7:

[0408] The user's device displays the received information in an intuitive interface suited to it. The user can check the necessary information and click links to obtain more details if needed.

[0409] (Example 1)

[0410] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0411] Conventional information provision systems have struggled to accurately predict user interests and provide relevant information in a timely manner. Furthermore, the time and effort required for users to find useful information has been excessive.

[0412] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0413] In this invention, the server includes means for collecting user information and storing it in a database, means for using a generative memory model that predicts user interests and selects relevant information based on a machine learning algorithm using the stored information, and means for transmitting the selected information to the user's terminal and displaying it with an intuitive interface. This makes it possible to effectively predict user interests and quickly provide necessary information.

[0414] "User information" refers to all data related to the actions and choices generated by the user.

[0415] A "database" is a storage device used to systematically organize and store large amounts of information, and to efficiently manage and retrieve it.

[0416] A "machine learning algorithm" is a computational method that allows computers to recognize patterns based on past data and make predictions and decisions about the future.

[0417] A "generative memory model" is a model that uses machine learning to infer a user's future interests from their past information and select relevant information based on those inferences.

[0418] A "central processing unit" is a device that plays a central role in processing and analyzing information and managing the operation of the entire system.

[0419] An "intuitive interface" refers to an operating screen or method that users can use intuitively, providing usability that does not require special knowledge or training.

[0420] This system aims to provide relevant information by effectively utilizing the user's behavioral history. It consists of a server, a user terminal, and a generative memory model.

[0421] The server collects behavioral data submitted by users and stores it in the system's database. Using web server technology, the server efficiently collects information such as user browsing history, purchase history, and newsletter subscription history. Furthermore, by employing relational database technology, it enables rapid searching and retrieval of necessary data. This allows the server to manage large amounts of data while respecting user privacy.

[0422] Generative models predict user interests based on stored data, utilizing machine learning algorithms. Specifically, they analyze users' past behavioral patterns using data mining and deep learning models to predict future interests. Generative AI models can select information based on each user's interests, always providing the most up-to-date and relevant information.

[0423] The user's device receives selection information sent from the server and displays it through the user interface. The device consists of various types of devices, such as smartphones and personal computers, and presents the received information to the user in tab or list format. This allows the user to efficiently access information of interest.

[0424] For example, if a user has frequently searched online for travel-related information in the past, the generative model will predict travel destinations and travel packages that they might be interested in next. As a result, the server sends this information to the user's terminal, and the user can easily view it. An example of a prompt message would be, "Predict future interests based on the user's past behavior data, and present relevant information based on the results."

[0425] In this way, the system streamlines the acquisition of user information and enables the provision of information tailored to the user's interests.

[0426] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0427] Step 1:

[0428] The server collects user behavior data and stores it in a database. It receives data such as user browsing history and purchase information as input, converts it into a digital format, and stores it in the database. This process involves data cleansing and organization to build a highly accurate dataset.

[0429] Step 2:

[0430] The server inputs the collected data into the generative model. Cleansed user behavior data is provided as input to the generative model. At this stage, the data is preprocessed and formatted for machine learning algorithms. The output is a dataset ready for analysis.

[0431] Step 3:

[0432] Generative models analyze data using machine learning algorithms. This process predicts each user's interests based on input user behavior data. By extracting data features and analyzing behavioral patterns, the model generates personalized recommendations as output.

[0433] Step 4:

[0434] The server receives the analysis results from the generative model and selects information of interest. It analyzes the outputted recommendation information and filters it to the most relevant information for the user. The selected information is sent to the user's terminal in an optimized format.

[0435] Step 5:

[0436] The user's device receives and displays information sent from the server. It receives information optimized for input and displays it intuitively on the device's interface. Information is presented in tabs or lists to facilitate user access and support quick access to related content.

[0437] (Application Example 1)

[0438] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0439] In modern times, it is difficult for users to efficiently obtain information that matches their interests from a vast amount of information. Furthermore, especially in online shopping, product recommendations based on individual user interests are often not effectively implemented, compromising convenience. As a result, users are forced to spend time sifting through information. Therefore, this invention aims to automatically provide information of high interest based on user behavior data and realize product recommendations tailored to individual needs.

[0440] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0441] In this invention, the server includes means for using a predictive device that analyzes user information to predict user interests and selects information of interest; a device for transmitting the selected information to the user's terminal; and a device for displaying the selected information on the user's device. This enables users to effectively obtain highly relevant information and products based on their past behavior.

[0442] "Predicting user interests" means analyzing users' past behavioral data to estimate their future interests and the things they are likely to be interested in.

[0443] "User information" refers to all data provided by the user, such as purchase history, browsing history, and email newsletter subscription history.

[0444] A "predictive device" is a device that analyzes user behavior data to determine their interests and preferences, and then executes an algorithm to select information based on that analysis.

[0445] "Selected information" refers to information chosen by the prediction device as matching the user's interests.

[0446] "User devices" refer to information terminals that users use on a daily basis, such as smartphones, tablets, and personal computers.

[0447] "Special offer information" refers to information that provides users with special value or discounts, such as coupons and campaign information.

[0448] A "storage device" is a system that stores data transmitted by users and allows for analysis and retrieval as needed.

[0449] The system that realizes this invention consists of a server, a user terminal, and a prediction device. The server is responsible for receiving behavioral data transmitted from the user and storing it in a database. In doing so, the server uses security software to safely manage the data while considering privacy.

[0450] The prediction system utilizes generative AI models to analyze user behavior data and identify their interests and preferences. This analysis employs data mining techniques, with specific examples of software used including Python's pandas library and scikit-learn. This allows for real-time estimation of products and information that users are likely to be interested in.

[0451] The user's device receives selection results sent from the server and displays them through an intuitive interface. Specifically, it is designed to provide information on estimated products and services in list or recommendation format, and also displays special offers based on the user's purchase and browsing history. This makes it easy for users to obtain information that matches their interests.

[0452] For example, when a user purchases a new smart TV, recommendations for related accessories and services are displayed on the device based on their past purchase and browsing history. Related sales information and coupons are also presented, which can increase the user's desire to purchase.

[0453] An example of a prompt would be, "Considering the user's past purchase and browsing history, please list products that the user might be interested in." Using this prompt, the predictive tool can leverage its generative AI model to provide information optimized for the user.

[0454] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0455] Step 1:

[0456] The server receives user information from the user's device. This information includes the user's browsing history, purchase history, etc. The input data is stored in a database and encrypted to ensure privacy.

[0457] Step 2:

[0458] The server passes the stored data to the prediction device. The prediction device uses a generative AI model to analyze the data and predict the user's interests. At this stage, the generative AI model uses the prompt "Consider the user's past purchase and browsing history, and list products that the user might be interested in." As a result of the analysis, a list of products and services that may be of interest is output.

[0459] Step 3:

[0460] The server receives the information list generated by the prediction device and sends it to the user's terminal. This transmission uses network infrastructure and includes error checking to prevent information loss.

[0461] Step 4:

[0462] The user's device displays information via an interface based on the received data. The display format is either a list or a recommended products format, making it easy for the user to access. Based on the entered information, customized benefits (coupons and sales information) are also displayed, combined with the user's past behavioral data.

[0463] Step 5:

[0464] Users can select products they are interested in and view detailed information as needed. This action is sent from the device to the server as feedback, and the data is further updated and used to make future predictions.

[0465] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0466] This invention is a system that uses user behavioral data and emotional data to predict and appropriately provide information that users are interested in. This system is mainly implemented using a server, a user terminal, and an emotional engine.

[0467] In addition to recording the user's behavior history, the device incorporates an emotion engine that recognizes the user's emotions in real time. This engine analyzes emotional patterns from the user's facial expressions, tone of voice, and speed of operation. The collected emotional data is combined with behavioral data to create a dataset that more comprehensively reflects the user's characteristics.

[0468] The server stores received user data in a database, retrieves emotional data sent from the emotion engine, and analyzes it using a generative model. The generative model specifically evaluates how emotional trends influence users' purchase intent and information interests, and predicts user interests.

[0469] The sentiment data identified by the sentiment engine reveals what users are responding to positively or negatively, improving the predictive accuracy of generative models. For example, it can record a user's emotional changes when they see an advertisement for a product, allowing us to measure the user's level of interest in that product.

[0470] The server selects information relevant to the user based on the prediction results and sends that information to the user's terminal. The selected information is displayed on the user's terminal through an intuitive and easy-to-use interface. This allows users to easily obtain the latest information that interests them and reduces the burden of information selection.

[0471] For example, if a user frequently searches for information about a particular music artist, and the emotion engine detects a high level of positive emotion, the server can prioritize providing that user with information about the artist's new songs and tours. In this way, the present invention makes it possible to significantly personalize the user experience and improve user satisfaction.

[0472] The following describes the processing flow.

[0473] Step 1:

[0474] The user's device records their behavioral history and, simultaneously, uses its built-in emotion engine to record the user's emotional data in real time. This emotional data is collected by evaluating the user's emotional state based on their facial expressions, voice, input patterns, and other factors.

[0475] Step 2:

[0476] The device periodically or in real time transmits collected behavioral and emotional data to the server. A secure protocol is used for this transmission to protect the confidentiality of the data.

[0477] Step 3:

[0478] The server organizes the received data and stores it in a database. During this process, information that does not require user identification is anonymized to protect privacy.

[0479] Step 4:

[0480] A generative model runs on the server, comprehensively analyzing accumulated behavioral and emotional data. This analysis allows for a specific evaluation of user interests and emotional preferences.

[0481] Step 5:

[0482] The generative model selects information that is likely to be of interest to the user based on analysis. In this selection process, information related to the subject in which the user has shown positive emotions is often prioritized.

[0483] Step 6:

[0484] The server organizes the selected information and sends it to the user's terminal. The transmission employs an optimized communication method to ensure quick access for the user.

[0485] Step 7:

[0486] The user's device displays received information in a visually easy-to-understand user interface. Through this interface, users can easily access detailed information, which helps them make purchasing and event participation decisions.

[0487] (Example 2)

[0488] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0489] It is difficult for users to efficiently find information highly relevant to them from a vast amount of data. Furthermore, conventional systems have not been able to adequately reflect changes in users' interests and emotions, resulting in issues with the accuracy of information provision. This invention aims to achieve highly accurate information selection and personalized information provision based on users' behavioral history and emotional data.

[0490] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0491] In this invention, the server includes means for collecting user behavior history and emotional data and analyzing it using a generative AI model, means for predicting user interests based on the analyzed data and selecting relevant information, and means for transmitting the selected information to the user terminal. This makes it possible to provide highly accurate information based on the interests of individual users.

[0492] "User activity history" refers to historical information about the actions a user has taken and the content they have viewed on their digital devices.

[0493] "Emotional data" refers to data that quantifies or patterns the user's emotional state, and includes elements such as facial expressions, tone of voice, and speed of operation.

[0494] A "generative AI model" refers to an artificial intelligence model used to analyze collected data and predict user interests and behavioral patterns.

[0495] "Means of selecting information" refers to the process or mechanism of selecting appropriate information to provide to users based on analyzed data.

[0496] A "user terminal" is an electronic device that a user can directly operate, and includes smartphones, tablets, and personal computers.

[0497] An "emotion engine" refers to a digital system that analyzes user emotional data in real time to identify the user's emotional state.

[0498] This invention is implemented as a system combining an electronic terminal used by the user and a server that processes user data. The user's terminal is equipped with software that records behavioral history and also has a built-in emotion engine. The emotion engine acquires the user's facial expressions from a camera, their voice tone from a microphone, and their operation speed from a touch interface, and performs analysis in real time.

[0499] The user's device sends collected behavioral history and emotional data to the server. The server receives this data and analyzes it using a generative AI model. The generative AI model utilizes various data processing techniques to predict user interests, particularly analyzing how emotional changes affect interest and purchase intent. Based on the results of this model, the server selects information that the user is likely to be interested in and sends that information to the user's device.

[0500] The user's device displays selected information through a user-friendly interface. The user views the presented information, and their evaluation and feedback are collected again via the device as behavioral data. This data is sent to the server for the next cycle, contributing to improved analysis accuracy.

[0501] As a concrete example, let's assume a user frequently plays songs by a specific artist while using a music app, and the emotion engine detects positive emotions during this time. In this case, the server prioritizes selecting and notifying the user of new songs and concert information by that artist. The generative AI model supporting this process learns using prompts such as "Select information to provide preferentially based on the user's emotions and behavioral history," thereby improving the accuracy of information selection.

[0502] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0503] Step 1:

[0504] The device begins collecting user behavior history and emotional data. This includes information such as which applications the user is using and which websites they are browsing. It also uses an emotion engine to acquire real-time emotional data from the facial camera and microphone. At this point, the input is the user's actions and real-time biometric data, and the output is an initial set of behavior history and emotional data.

[0505] Step 2:

[0506] The device packages the collected behavioral history and emotional data, encrypts it, and then sends it to the server. This protects user privacy. The input is the data collected in step 1, and the output is the packaged data securely sent to the server.

[0507] Step 3:

[0508] The server receives data sent from the terminal and stores it in the database. This data is ready to be analyzed by the generative AI model. The input is the packaged data obtained in step 2, and the output is the raw data in the database before data analysis.

[0509] Step 4:

[0510] The server performs data analysis using a generative AI model. It predicts potential user interests using template prompts. The model analyzes the correlation between behavior and emotion to identify user areas of interest. The input is user data stored in a database, and the output is the interest prediction result.

[0511] Step 5:

[0512] The server selects information relevant to the user based on the analysis results. This information selection uses the interest prediction results as prompts. For example, new advertisements for a specific product or news articles in a genre of interest might be selected. The input is the interest prediction results from step 4, and the output is the selected set of information.

[0513] Step 6:

[0514] The server sends the selected information to the user's terminal. The input is the set of information selected in step 5, and the output is the information sent to the terminal.

[0515] Step 7:

[0516] The user's device displays the received information in an intuitive interface. Based on this information, the user can take further action. The input is the information sent from the server, and the output is the information displayed to the user.

[0517] Step 8:

[0518] The user reviews and uses the displayed information, thereby building further behavioral history and sentiment data. The input is the information displayed in step 7, and the output is new behavioral and sentiment data for the next cycle.

[0519] (Application Example 2)

[0520] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0521] In today's information society, users find it difficult to find information that is useful to them from the vast amount of information available. Furthermore, conventional information provision systems provide information without considering the user's emotions, so there is a need for greater personalization. This invention aims to achieve more accurate information provision by utilizing user behavior and emotion data.

[0522] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0523] In this invention, the server includes means for using a generative model that analyzes user data to predict user interests and selects information of interest; means for transmitting the selected information to the user's terminal; means for displaying the selected information on the user's terminal; means for using an emotion engine that analyzes user emotion data and recognizes emotions in real time; and means for selecting information relevant to the user based on the emotion data detected by the emotion engine. This makes it possible to efficiently provide information that is more of interest to the user.

[0524] "User data" refers to information that includes a user's behavioral history and emotional data, and is used to analyze user interests and behavior.

[0525] A "generative model" is an algorithm or computational method that analyzes user data and predicts user interests.

[0526] A "terminal" is a device that displays information and interacts with the user, and includes smartphones and computers.

[0527] An "emotion engine" is a system that analyzes the user's facial expressions, voice, etc., to recognize the user's emotions in real time.

[0528] "Methods for predicting interests" refer to methods that use generative models to identify in advance the information that users will be interested in.

[0529] "Relevant information" refers to information and content that is selected and provided to the user based on the user's current interests and feelings.

[0530] "Purchase intent" refers to the likelihood or level of desire a user has for purchasing a particular product or service.

[0531] The system that realizes this invention mainly consists of a server, a user terminal, and an emotion engine. The server predicts user interests using a generative model by comprehensively analyzing user behavior data and emotion data. The generative model learns from user data and executes algorithms to identify information and products that the user is interested in.

[0532] The user's device has a built-in emotion engine that analyzes the user's facial expressions and tone of voice in real time. This data, along with behavioral data, is sent to a server and analyzed by a generative model. The results of the analysis are selected as information predicted to be of interest to the user and sent to the device. The device then presents the selected information to the user through an intuitive and easy-to-use interface. This allows the user to efficiently obtain the latest information they need.

[0533] As a concrete example of its use, if a user is using an e-commerce app, and they express a positive sentiment towards product information presented based on their browsing and purchase history, the server can analyze that data and prioritize notifying them of promotional information for related products. This entire process is expected to make the user experience more personalized and improve satisfaction.

[0534] An example of a prompt message is: "User category name: Fashion, Item viewed: Jacket, Sentiment data: Positive, Product category to recommend: Related brand items". Based on this example, the generative AI model generates recommendations that are appropriate for the user.

[0535] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0536] Step 1:

[0537] The user's device uses an emotion engine to collect user emotion data in real time. This involves analyzing the user's facial expressions and voice tone, converting emotions (positive, negative, etc.) into data, and storing it as temporary data. The input to this process is the user's facial expressions and voice signals, and the output is emotion data.

[0538] Step 2:

[0539] The user's device collects behavioral data such as purchase history and browsing history. This data is temporarily stored on the user's device in preparation for subsequent analysis. The input to this process is the user's operation history and behavioral trajectory, and the output is behavioral data.

[0540] Step 3:

[0541] The user's device sends the collected emotional and behavioral data to the server. During this process, the data is encrypted and securely transferred to the server while ensuring privacy. In this step, the input data consists of emotional and behavioral data, and the output is encrypted data packets.

[0542] Step 4:

[0543] The server receives sentiment and behavioral data sent from the terminal and analyzes the data using a generative model. This model evaluates the data using various algorithms to predict user interests. The input is the received data, and the output is a list of information predicting interests.

[0544] Step 5:

[0545] Based on the analysis results of the generative model, the server selects relevant information and products and sends them to the user's terminal. This selection prioritizes information likely to be of interest based on the user's preferences. The input is the analysis results, and the output is the selected set of information.

[0546] Step 6:

[0547] The user's device receives selection information sent from the server and displays it through a visually intuitive interface. The user can interact with this interface and view information of interest. The input is the selection information, and the output is the information content displayed to the user.

[0548] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0549] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0550] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0551] [Fourth Embodiment]

[0552] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0553] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0554] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0555] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0556] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0557] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0558] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0559] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0560] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0561] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0562] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0563] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0564] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0565] This invention is a system that analyzes user behavior data and effectively provides information of interest based on the results. This system is mainly implemented using a server, a user terminal, and a generative model.

[0566] The server receives various types of data sent by users and stores them in a database. Specifically, this includes users' browsing history, purchase data, and email newsletter subscription history. The received data is input into a generative model and analyzed to predict user interests.

[0567] The generative model incorporates algorithms that utilize machine learning and data mining techniques to predict future interests based on a user's past behavior and select relevant information. The selection criteria dynamically change according to each user's behavioral history, ensuring the provision of up-to-date information.

[0568] The user's device receives the selection results sent from the server and displays the information through an intuitive interface. Specifically, information on products and services that the user is likely to be interested in, as well as event details, are presented in tab or list format.

[0569] For example, by analyzing user behavior data from when they purchased a new smartphone, the system can predict when they will upgrade again and display relevant advertisements and price comparison information at that time. Similarly, new music releases and live event information are suggested based on the user's past browsing and purchase history.

[0570] In this way, users can automatically obtain information of interest on their devices without having to actively search for it, significantly reducing the time and effort required to select information. This system reduces the user's information burden while providing highly relevant information.

[0571] The following describes the processing flow.

[0572] Step 1:

[0573] The user's device automatically collects data such as their browsing history, app usage logs, and the subject lines of received emails. This creates a database that reflects the user's interests.

[0574] Step 2:

[0575] The device sends the collected data to the server at regular intervals. This transmission is carried out through an encrypted channel to ensure privacy.

[0576] Step 3:

[0577] The server organizes the received data and stores it in a database. This data is then prepared for analysis by a generative model.

[0578] Step 4:

[0579] A generative model runs on the server, inferring user interests and preferences from stored user data. For example, it analyzes frequency and time records related to a specific product category to predict the next information needed.

[0580] Step 5:

[0581] The generative model selects information that is likely to attract user interest based on prediction results. The selected information is customized for each user and organized on the server.

[0582] Step 6:

[0583] The server sends the selected information to the user's terminal. This information is presented in a format that is easily accessible to the user on the terminal.

[0584] Step 7:

[0585] The user's device displays the received information in an intuitive interface suited to it. The user can check the necessary information and click links to obtain more details if needed.

[0586] (Example 1)

[0587] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0588] Conventional information provision systems have struggled to accurately predict user interests and provide relevant information in a timely manner. Furthermore, the time and effort required for users to find useful information has been excessive.

[0589] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0590] In this invention, the server includes means for collecting user information and storing it in a database, means for using a generative memory model that predicts user interests and selects relevant information based on a machine learning algorithm using the stored information, and means for transmitting the selected information to the user's terminal and displaying it with an intuitive interface. This makes it possible to effectively predict user interests and quickly provide necessary information.

[0591] "User information" refers to all data related to the actions and choices generated by the user.

[0592] A "database" is a storage device used to systematically organize and store large amounts of information, and to efficiently manage and retrieve it.

[0593] A "machine learning algorithm" is a computational method that allows computers to recognize patterns based on past data and make predictions and decisions about the future.

[0594] A "generative memory model" is a model that uses machine learning to infer a user's future interests from their past information and select relevant information based on those inferences.

[0595] A "central processing unit" is a device that plays a central role in processing and analyzing information and managing the operation of the entire system.

[0596] An "intuitive interface" refers to an operating screen or method that users can use intuitively, providing usability that does not require special knowledge or training.

[0597] This system aims to provide relevant information by effectively utilizing the user's behavioral history. It consists of a server, a user terminal, and a generative memory model.

[0598] The server collects behavioral data submitted by users and stores it in the system's database. Using web server technology, the server efficiently collects information such as user browsing history, purchase history, and newsletter subscription history. Furthermore, by employing relational database technology, it enables rapid searching and retrieval of necessary data. This allows the server to manage large amounts of data while respecting user privacy.

[0599] Generative models predict user interests based on stored data, utilizing machine learning algorithms. Specifically, they analyze users' past behavioral patterns using data mining and deep learning models to predict future interests. Generative AI models can select information based on each user's interests, always providing the most up-to-date and relevant information.

[0600] The user's device receives selection information sent from the server and displays it through the user interface. The device consists of various types of devices, such as smartphones and personal computers, and presents the received information to the user in tab or list format. This allows the user to efficiently access information of interest.

[0601] For example, if a user has frequently searched online for travel-related information in the past, the generative model will predict travel destinations and travel packages that they might be interested in next. As a result, the server sends this information to the user's terminal, and the user can easily view it. An example of a prompt message would be, "Predict future interests based on the user's past behavior data, and present relevant information based on the results."

[0602] In this way, the system streamlines the acquisition of user information and enables the provision of information tailored to the user's interests.

[0603] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0604] Step 1:

[0605] The server collects user behavior data and stores it in a database. It receives data such as user browsing history and purchase information as input, converts it into a digital format, and stores it in the database. This process involves data cleansing and organization to build a highly accurate dataset.

[0606] Step 2:

[0607] The server inputs the collected data into the generative model. Cleansed user behavior data is provided as input to the generative model. At this stage, the data is preprocessed and formatted for machine learning algorithms. The output is a dataset ready for analysis.

[0608] Step 3:

[0609] Generative models analyze data using machine learning algorithms. This process predicts each user's interests based on input user behavior data. By extracting data features and analyzing behavioral patterns, the model generates personalized recommendations as output.

[0610] Step 4:

[0611] The server receives the analysis results from the generative model and selects information of interest. It analyzes the outputted recommendation information and filters it to the most relevant information for the user. The selected information is sent to the user's terminal in an optimized format.

[0612] Step 5:

[0613] The user's device receives and displays information sent from the server. It receives information optimized for input and displays it intuitively on the device's interface. Information is presented in tabs or lists to facilitate user access and support quick access to related content.

[0614] (Application Example 1)

[0615] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0616] In modern times, it is difficult for users to efficiently obtain information that matches their interests from a vast amount of information. Furthermore, especially in online shopping, product recommendations based on individual user interests are often not effectively implemented, compromising convenience. As a result, users are forced to spend time sifting through information. Therefore, this invention aims to automatically provide information of high interest based on user behavior data and realize product recommendations tailored to individual needs.

[0617] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0618] In this invention, the server includes means for using a predictive device that analyzes user information to predict user interests and selects information of interest; a device for transmitting the selected information to the user's terminal; and a device for displaying the selected information on the user's device. This enables users to effectively obtain highly relevant information and products based on their past behavior.

[0619] "Predicting user interests" means analyzing users' past behavioral data to estimate their future interests and the things they are likely to be interested in.

[0620] "User information" refers to all data provided by the user, such as purchase history, browsing history, and email newsletter subscription history.

[0621] A "predictive device" is a device that analyzes user behavior data to determine their interests and preferences, and then executes an algorithm to select information based on that analysis.

[0622] "Selected information" refers to information chosen by the prediction device as matching the user's interests.

[0623] "User devices" refer to information terminals that users use on a daily basis, such as smartphones, tablets, and personal computers.

[0624] "Special offer information" refers to information that provides users with special value or discounts, such as coupons and campaign information.

[0625] A "storage device" is a system that stores data transmitted by users and allows for analysis and retrieval as needed.

[0626] The system that realizes this invention consists of a server, a user terminal, and a prediction device. The server is responsible for receiving behavioral data transmitted from the user and storing it in a database. In doing so, the server uses security software to safely manage the data while considering privacy.

[0627] The prediction system utilizes generative AI models to analyze user behavior data and identify their interests and preferences. This analysis employs data mining techniques, with specific examples of software used including Python's pandas library and scikit-learn. This allows for real-time estimation of products and information that users are likely to be interested in.

[0628] The user's device receives selection results sent from the server and displays them through an intuitive interface. Specifically, it is designed to provide information on estimated products and services in list or recommendation format, and also displays special offers based on the user's purchase and browsing history. This makes it easy for users to obtain information that matches their interests.

[0629] For example, when a user purchases a new smart TV, recommendations for related accessories and services are displayed on the device based on their past purchase and browsing history. Related sales information and coupons are also presented, which can increase the user's desire to purchase.

[0630] An example of a prompt would be, "Considering the user's past purchase and browsing history, please list products that the user might be interested in." Using this prompt, the predictive tool can leverage its generative AI model to provide information optimized for the user.

[0631] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0632] Step 1:

[0633] The server receives user information from the user's device. This information includes the user's browsing history, purchase history, etc. The input data is stored in a database and encrypted to ensure privacy.

[0634] Step 2:

[0635] The server passes the stored data to the prediction device. The prediction device uses a generative AI model to analyze the data and predict the user's interests. At this stage, the generative AI model uses the prompt "Consider the user's past purchase and browsing history, and list products that the user might be interested in." As a result of the analysis, a list of products and services that may be of interest is output.

[0636] Step 3:

[0637] The server receives the information list generated by the prediction device and sends it to the user's terminal. This transmission uses network infrastructure and includes error checking to prevent information loss.

[0638] Step 4:

[0639] The user's device displays information via an interface based on the received data. The display format is either a list or a recommended products format, making it easy for the user to access. Based on the entered information, customized benefits (coupons and sales information) are also displayed, combined with the user's past behavioral data.

[0640] Step 5:

[0641] Users can select products they are interested in and view detailed information as needed. This action is sent from the device to the server as feedback, and the data is further updated and used to make future predictions.

[0642] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0643] This invention is a system that uses user behavioral data and emotional data to predict and appropriately provide information that users are interested in. This system is mainly implemented using a server, a user terminal, and an emotional engine.

[0644] In addition to recording the user's behavior history, the device incorporates an emotion engine that recognizes the user's emotions in real time. This engine analyzes emotional patterns from the user's facial expressions, tone of voice, and speed of operation. The collected emotional data is combined with behavioral data to create a dataset that more comprehensively reflects the user's characteristics.

[0645] The server stores received user data in a database, retrieves emotional data sent from the emotion engine, and analyzes it using a generative model. The generative model specifically evaluates how emotional trends influence users' purchase intent and information interests, and predicts user interests.

[0646] The sentiment data identified by the sentiment engine reveals what users are responding to positively or negatively, improving the predictive accuracy of generative models. For example, it can record a user's emotional changes when they see an advertisement for a product, allowing us to measure the user's level of interest in that product.

[0647] The server selects information relevant to the user based on the prediction results and sends that information to the user's terminal. The selected information is displayed on the user's terminal through an intuitive and easy-to-use interface. This allows users to easily obtain the latest information that interests them and reduces the burden of information selection.

[0648] For example, if a user frequently searches for information about a particular music artist, and the emotion engine detects a high level of positive emotion, the server can prioritize providing that user with information about the artist's new songs and tours. In this way, the present invention makes it possible to significantly personalize the user experience and improve user satisfaction.

[0649] The following describes the processing flow.

[0650] Step 1:

[0651] The user's device records their behavioral history and, simultaneously, uses its built-in emotion engine to record the user's emotional data in real time. This emotional data is collected by evaluating the user's emotional state based on their facial expressions, voice, input patterns, and other factors.

[0652] Step 2:

[0653] The device periodically or in real time transmits collected behavioral and emotional data to the server. A secure protocol is used for this transmission to protect the confidentiality of the data.

[0654] Step 3:

[0655] The server organizes the received data and stores it in a database. During this process, information that does not require user identification is anonymized to protect privacy.

[0656] Step 4:

[0657] A generative model runs on the server, comprehensively analyzing accumulated behavioral and emotional data. This analysis allows for a specific evaluation of user interests and emotional preferences.

[0658] Step 5:

[0659] The generative model selects information that is likely to be of interest to the user based on analysis. In this selection process, information related to the subject in which the user has shown positive emotions is often prioritized.

[0660] Step 6:

[0661] The server organizes the selected information and sends it to the user's terminal. The transmission employs an optimized communication method to ensure quick access for the user.

[0662] Step 7:

[0663] The user's device displays received information in a visually easy-to-understand user interface. Through this interface, users can easily access detailed information, which helps them make purchasing and event participation decisions.

[0664] (Example 2)

[0665] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0666] It is difficult for users to efficiently find information highly relevant to them from a vast amount of data. Furthermore, conventional systems have not been able to adequately reflect changes in users' interests and emotions, resulting in issues with the accuracy of information provision. This invention aims to achieve highly accurate information selection and personalized information provision based on users' behavioral history and emotional data.

[0667] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0668] In this invention, the server includes means for collecting user behavior history and emotional data and analyzing it using a generative AI model, means for predicting user interests based on the analyzed data and selecting relevant information, and means for transmitting the selected information to the user terminal. This makes it possible to provide highly accurate information based on the interests of individual users.

[0669] "User activity history" refers to historical information about the actions a user has taken and the content they have viewed on their digital devices.

[0670] "Emotional data" refers to data that quantifies or patterns the user's emotional state, and includes elements such as facial expressions, tone of voice, and speed of operation.

[0671] A "generative AI model" refers to an artificial intelligence model used to analyze collected data and predict user interests and behavioral patterns.

[0672] "Means of selecting information" refers to the process or mechanism of selecting appropriate information to provide to users based on analyzed data.

[0673] A "user terminal" is an electronic device that a user can directly operate, and includes smartphones, tablets, and personal computers.

[0674] An "emotion engine" refers to a digital system that analyzes user emotional data in real time to identify the user's emotional state.

[0675] This invention is implemented as a system combining an electronic terminal used by the user and a server that processes user data. The user's terminal is equipped with software that records behavioral history and also has a built-in emotion engine. The emotion engine acquires the user's facial expressions from a camera, their voice tone from a microphone, and their operation speed from a touch interface, and performs analysis in real time.

[0676] The user's device sends collected behavioral history and emotional data to the server. The server receives this data and analyzes it using a generative AI model. The generative AI model utilizes various data processing techniques to predict user interests, particularly analyzing how emotional changes affect interest and purchase intent. Based on the results of this model, the server selects information that the user is likely to be interested in and sends that information to the user's device.

[0677] The user's device displays selected information through a user-friendly interface. The user views the presented information, and their evaluation and feedback are collected again via the device as behavioral data. This data is sent to the server for the next cycle, contributing to improved analysis accuracy.

[0678] As a concrete example, let's assume a user frequently plays songs by a specific artist while using a music app, and the emotion engine detects positive emotions during this time. In this case, the server prioritizes selecting and notifying the user of new songs and concert information by that artist. The generative AI model supporting this process learns using prompts such as "Select information to provide preferentially based on the user's emotions and behavioral history," thereby improving the accuracy of information selection.

[0679] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0680] Step 1:

[0681] The device begins collecting user behavior history and emotional data. This includes information such as which applications the user is using and which websites they are browsing. It also uses an emotion engine to acquire real-time emotional data from the facial camera and microphone. At this point, the input is the user's actions and real-time biometric data, and the output is an initial set of behavior history and emotional data.

[0682] Step 2:

[0683] The device packages the collected behavioral history and emotional data, encrypts it, and then sends it to the server. This protects user privacy. The input is the data collected in step 1, and the output is the packaged data securely sent to the server.

[0684] Step 3:

[0685] The server receives data sent from the terminal and stores it in the database. This data is ready to be analyzed by the generative AI model. The input is the packaged data obtained in step 2, and the output is the raw data in the database before data analysis.

[0686] Step 4:

[0687] The server performs data analysis using a generative AI model. It predicts potential user interests using template prompts. The model analyzes the correlation between behavior and emotion to identify user areas of interest. The input is user data stored in a database, and the output is the interest prediction result.

[0688] Step 5:

[0689] The server selects information relevant to the user based on the analysis results. This information selection uses the interest prediction results as prompts. For example, new advertisements for a specific product or news articles in a genre of interest might be selected. The input is the interest prediction results from step 4, and the output is the selected set of information.

[0690] Step 6:

[0691] The server sends the selected information to the user's terminal. The input is the set of information selected in step 5, and the output is the information sent to the terminal.

[0692] Step 7:

[0693] The user's device displays the received information in an intuitive interface. Based on this information, the user can take further action. The input is the information sent from the server, and the output is the information displayed to the user.

[0694] Step 8:

[0695] The user reviews and uses the displayed information, thereby building further behavioral history and sentiment data. The input is the information displayed in step 7, and the output is new behavioral and sentiment data for the next cycle.

[0696] (Application Example 2)

[0697] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0698] In today's information society, users find it difficult to find information that is useful to them from the vast amount of information available. Furthermore, conventional information provision systems provide information without considering the user's emotions, so there is a need for greater personalization. This invention aims to achieve more accurate information provision by utilizing user behavior and emotion data.

[0699] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0700] In this invention, the server includes means for using a generative model that analyzes user data to predict user interests and selects information of interest; means for transmitting the selected information to the user's terminal; means for displaying the selected information on the user's terminal; means for using an emotion engine that analyzes user emotion data and recognizes emotions in real time; and means for selecting information relevant to the user based on the emotion data detected by the emotion engine. This makes it possible to efficiently provide information that is more of interest to the user.

[0701] "User data" refers to information that includes a user's behavioral history and emotional data, and is used to analyze user interests and behavior.

[0702] A "generative model" is an algorithm or computational method that analyzes user data and predicts user interests.

[0703] A "terminal" is a device that displays information and interacts with the user, and includes smartphones and computers.

[0704] An "emotion engine" is a system that analyzes the user's facial expressions, voice, etc., to recognize the user's emotions in real time.

[0705] "Methods for predicting interests" refer to methods that use generative models to identify in advance the information that users will be interested in.

[0706] "Relevant information" refers to information and content that is selected and provided to the user based on the user's current interests and feelings.

[0707] "Purchase intent" refers to the likelihood or level of desire a user has for purchasing a particular product or service.

[0708] The system that realizes this invention mainly consists of a server, a user terminal, and an emotion engine. The server predicts user interests using a generative model by comprehensively analyzing user behavior data and emotion data. The generative model learns from user data and executes algorithms to identify information and products that the user is interested in.

[0709] The user's device has a built-in emotion engine that analyzes the user's facial expressions and tone of voice in real time. This data, along with behavioral data, is sent to a server and analyzed by a generative model. The results of the analysis are selected as information predicted to be of interest to the user and sent to the device. The device then presents the selected information to the user through an intuitive and easy-to-use interface. This allows the user to efficiently obtain the latest information they need.

[0710] As a concrete example of its use, if a user is using an e-commerce app, and they express a positive sentiment towards product information presented based on their browsing and purchase history, the server can analyze that data and prioritize notifying them of promotional information for related products. This entire process is expected to make the user experience more personalized and improve satisfaction.

[0711] An example of a prompt message is: "User category name: Fashion, Item viewed: Jacket, Sentiment data: Positive, Product category to recommend: Related brand items". Based on this example, the generative AI model generates recommendations that are appropriate for the user.

[0712] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0713] Step 1:

[0714] The user's device uses an emotion engine to collect user emotion data in real time. This involves analyzing the user's facial expressions and voice tone, converting emotions (positive, negative, etc.) into data, and storing it as temporary data. The input to this process is the user's facial expressions and voice signals, and the output is emotion data.

[0715] Step 2:

[0716] The user's device collects behavioral data such as purchase history and browsing history. This data is temporarily stored on the user's device in preparation for subsequent analysis. The input to this process is the user's operation history and behavioral trajectory, and the output is behavioral data.

[0717] Step 3:

[0718] The user's device sends the collected emotional and behavioral data to the server. During this process, the data is encrypted and securely transferred to the server while ensuring privacy. In this step, the input data consists of emotional and behavioral data, and the output is encrypted data packets.

[0719] Step 4:

[0720] The server receives sentiment and behavioral data sent from the terminal and analyzes the data using a generative model. This model evaluates the data using various algorithms to predict user interests. The input is the received data, and the output is a list of information predicting interests.

[0721] Step 5:

[0722] Based on the analysis results of the generative model, the server selects relevant information and products and sends them to the user's terminal. This selection prioritizes information likely to be of interest based on the user's preferences. The input is the analysis results, and the output is the selected set of information.

[0723] Step 6:

[0724] The user's device receives selection information sent from the server and displays it through a visually intuitive interface. The user can interact with this interface and view information of interest. The input is the selection information, and the output is the information content displayed to the user.

[0725] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0726] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0727] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0728] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0729] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0730] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0731] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0732] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0733] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0734] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0735] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0736] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0737] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0738] 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.

[0739] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0740] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0741] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0742] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0743] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0744] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0745] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0746] The following is further disclosed regarding the embodiments described above.

[0747] (Claim 1)

[0748] A method that uses a generative model to analyze user data and select information of interest in order to predict user interests,

[0749] A means of transmitting the selected information to the user's terminal,

[0750] A means of displaying selected information on the user's terminal,

[0751] A system that includes this.

[0752] (Claim 2)

[0753] The system according to claim 1, which records the user's activity history and transmits it to a server with respect to privacy.

[0754] (Claim 3)

[0755] The system according to claim 1, which predicts the user's future behavior based on data analyzed by a generative model.

[0756] "Example 1"

[0757] (Claim 1)

[0758] Means for collecting user information and storing it in a database,

[0759] A method using a generative memory model that predicts user interests based on machine learning algorithms using stored information and selects relevant information,

[0760] A means of sending the selected information to the user's terminal and displaying it with an intuitive interface,

[0761] A system that includes this.

[0762] (Claim 2)

[0763] The system according to claim 1, which records the user's activity history and transmits it to a central processing unit with protective measures in place.

[0764] (Claim 3)

[0765] The system according to claim 1, wherein a generative memory model predicts the user's future behavior based on the analyzed information.

[0766] "Application Example 1"

[0767] (Claim 1)

[0768] A means of using a predictive device that analyzes user information to predict user interests and selects information of interest,

[0769] A device that transmits the selected information to the user's terminal,

[0770] A device that displays selected information on the user's device,

[0771] A means of displaying product recommendation information based on selected information,

[0772] A device that provides special offer information based on purchase history and browsing history,

[0773] A system that includes this.

[0774] (Claim 2)

[0775] The system according to claim 1, which records the user's behavior history and transmits it to a storage device with respect to privacy.

[0776] (Claim 3)

[0777] The system according to claim 1, which predicts the user's future behavior and recommends related products based on data analyzed by a prediction device.

[0778] "Example 2 of combining an emotion engine"

[0779] (Claim 1)

[0780] A means for collecting user behavior history and sentiment data and analyzing it using a generative AI model,

[0781] A means of predicting user interests based on analyzed data and selecting relevant information,

[0782] A means for transmitting the selected information to the user terminal,

[0783] A means of displaying selected information on the user's terminal and collecting feedback from the user,

[0784] A system that includes this.

[0785] (Claim 2)

[0786] The system according to claim 1, which incorporates an emotion engine that processes user emotion data in real time and analyzes the user's emotional state.

[0787] (Claim 3)

[0788] The system according to claim 1, which predicts future user behavior and interests based on analyzed user behavior and emotional data.

[0789] "Application example 2 when combining with an emotional engine"

[0790] (Claim 1)

[0791] A method that uses a generative model to analyze user data and select information of interest in order to predict user interests,

[0792] A means of transmitting the selected information to the user's terminal,

[0793] A means of displaying selected information on the user's terminal,

[0794] A method that uses an emotion engine to analyze user emotion data and recognize emotions in real time,

[0795] A means for selecting user-related information based on emotional data detected by the emotion engine,

[0796] A system that includes this.

[0797] (Claim 2)

[0798] The system according to claim 1, which records the user's activity history and transmits it to a server with respect to privacy.

[0799] (Claim 3)

[0800] A means of predicting the user's future behavior based on data analyzed by a generative model,

[0801] A means of selecting products and services that users are highly likely to purchase,

[0802] The system according to claim 1, including the following: [Explanation of Symbols]

[0803] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A method that uses a generative model to analyze user data and select information of interest in order to predict user interests, A means of transmitting the selected information to the user's terminal, A means of displaying selected information on the user's terminal, A system that includes this.

2. The system according to claim 1, which records the user's activity history and transmits it to a server with respect to privacy.

3. The system according to claim 1, which predicts the user's future behavior based on data analyzed by a generative model.

Images