system

Abstract

We provide the system. [Solution] Means of collecting user behavior information anonymously, The means for preprocessing and standardizing the collected behavioral information, A means of integrating standardized information and extracting user characteristics, A means for generating personalized suggestion information based on extracted features, A means of notifying the user of the generated suggestion information, A means of receiving user feedback and improving suggested information, 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 method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Although conventional artificial intelligence (AI) systems have the ability to optimize the whole statistically, they have limitations in providing services optimized for individual users. Therefore, it is an issue to realize a system that can propose more personalized services and products for individual users. In particular, it is an important issue how to integrate various data obtained from different platforms, accurately grasp the characteristics of individual users, and make proposals based on them.

Means for Solving the Problems

[0005] This invention provides means for collecting user behavior information anonymously and means for preprocessing and standardizing the collected information. Next, it provides means for integrating the standardized data and extracting user characteristics to generate personalized profiles for individual users. Furthermore, it provides means for generating personalized suggestion information for a specific user based on this profile and notifying the user. This enables a highly accurate personalized service that could not be achieved with conventional systems by continuously receiving feedback from users and forming a cycle to improve the suggestion information.

[0006] "User behavior information" refers to data about a user's online and offline activities, including, for example, website browsing history, purchase history, and records of various service usage.

[0007] "Anonymous format" refers to a method that excludes personally identifiable information, meaning that data has been processed or modified in a way that does not identify individual users.

[0008] "Preprocessing" refers to the steps taken to make data analyzable, and includes processes such as filling in missing data and standardizing data formats.

[0009] Standardization refers to the process of converting data expressed in different formats into a consistent format, thereby improving data consistency and comparability.

[0010] "Integration" refers to the process of combining multiple datasets to generate a single, consistent dataset.

[0011] "User characteristics" refer to information that identifies or characterizes a user, such as their past behavior and preferences.

[0012] A "profile" refers to a dataset that organizes user characteristics and compiles them as individual information, forming the basis for providing personalized services.

[0013] "Personalized suggestion information" refers to information generated based on a user's profile, tailored to the specific needs and preferences of that user.

[0014] "Feedback" refers to the reactions and evaluations that users provide to a system, with the aim of using them to improve the system. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of 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, the numbered 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, the numbered 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 for providing personalized services to users, and is implemented in a form that includes a server, a terminal, and user interaction. The server collects anonymized user behavior information from group companies and other business partners via a pre-configured API. This information is diverse, including the user's website browsing history and purchase history.

[0037] On the terminal, the collected data is first preprocessed, with missing data points being filled in and noise being removed. This standardizes the data, making it available for subsequent processing by the server.

[0038] Next, the server runs a machine learning model based on the integrated data to generate individual user profiles. These profiles systematically organize the user's behavioral tendencies and interests. This enables the provision of personalized services to each user.

[0039] For example, if a user makes purchases on multiple e-commerce platforms through their device and frequently buys electronic devices, this user's profile will be described as having a "strong interest in technology products." Based on this profile, the server selects information about the latest gadgets and electronic devices and notifies the user via their device.

[0040] Users can receive suggestions and, if interested, directly view the information. Furthermore, they can send feedback about the suggestions to the server. The server analyzes the received feedback to improve the user profile and the accuracy of the suggestion algorithm.

[0041] In this way, it becomes possible to provide users with more highly personalized services and to offer suggestions that meet their individual needs. The invention is characterized by its ability to achieve high-quality personalization while ensuring the protection of personal information through thorough anonymization and preprocessing of collected data.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server collects user behavior information in an anonymized format using APIs provided by group companies and other companies. This information includes browsing history, purchase history, and other service usage data.

[0045] Step 2:

[0046] The terminal preprocesses the raw data received from the server. Specifically, it fills in missing data, standardizes the format, and removes noise, ensuring the data is organized in a consistent format.

[0047] Step 3:

[0048] The server integrates pre-processed data, associating it with each user. This brings together data from different platforms into a single user profile.

[0049] Step 4:

[0050] The server uses machine learning techniques on the integrated dataset. It applies data mining methods and algorithms to generate profiles that visualize user behavioral characteristics and interests.

[0051] Step 5:

[0052] The server analyzes the generated profile and produces personalized recommendations for the user. For example, it selects highly relevant products and content based on past purchase trends.

[0053] Step 6:

[0054] The device will notify the user of the generated suggestions. These will be delivered to the user's device as push notifications or in-app messages.

[0055] Step 7:

[0056] Users review the received proposals and access related information if they are interested. If the proposal does not meet their expectations, they send feedback to the server via their device.

[0057] Step 8:

[0058] The server collects and analyzes feedback received from users. Based on this information, it adjusts and improves the proposed algorithm and user profile.

[0059] In this way, the entire system continuously evolves, enabling more precise personalization for individual users.

[0060] (Example 1)

[0061] 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."

[0062] In today's information society, users are exposed to vast amounts of information, but much of it is provided uniformly. Therefore, there is a need for personalized information tailored to individual user interests and preferences. However, current systems struggle to efficiently and safely collect and utilize individual behavioral information, and the accuracy and relevance of the obtained information are often insufficient. Furthermore, there is a lack of mechanisms to effectively utilize user feedback to improve information provision.

[0063] 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.

[0064] In this invention, the server includes means for anonymizing and aggregating individual data received from multiple information sources by an information processing device, means for preprocessing the aggregated data with an analysis device to fill in data gaps, remove noise, and standardize the data, and means for inputting the standardized information into a machine learning model to generate individual user profiles. This makes it possible to provide information tailored to each user with high accuracy and to continuously improve the relevance of the information through feedback.

[0065] An "information processing device" is a device that has the function of receiving, processing, storing, or transmitting digital data.

[0066] "Individual data" refers to a collection of data that includes information such as the behavior and transaction history of a specific user.

[0067] "Anonymization" is a process that removes personally identifiable information from individual data in order to protect individual privacy.

[0068] "Aggregation" is a method of organizing multiple data sets into a single unit for efficient management.

[0069] An "analysis device" is a piece of equipment or software used to analyze data content and extract specific patterns or information.

[0070] "Preprocessing" refers to the steps taken to improve the quality of data before performing data analysis or model creation, such as processing or transforming it.

[0071] "Data loss" refers to a state in which incomplete or missing information exists within a dataset.

[0072] "Noise reduction" is the process of removing irrelevant or incorrect information from data to maintain its accuracy.

[0073] "Standardization" is the process of transforming different data formats and scales to unify them and make them comparable.

[0074] A "machine learning model" is an algorithm or program that learns patterns from data to make specific predictions or decisions.

[0075] A "user profile" is a collection of information that summarizes a user's behavioral tendencies and interests, based on analysis of individual data.

[0076] "Means of delivery" refers to the technologies and devices used to distribute generated information to users.

[0077] "Feedback" refers to users' reactions and opinions to the information and services provided, and is used for subsequent improvements.

[0078] This invention is a system for providing users with highly accurate and personalized information. This system consists of a server, a terminal, and user interaction.

[0079] The server acts as an information processing device, anonymizing and aggregating individual data from multiple sources. These sources include various online platforms and digital services, and data is retrieved via APIs. This data includes website browsing history and purchase history. The server stores the received data in a database, preparing it for subsequent processing.

[0080] Next, the terminal functions as an analysis device for preprocessing. The terminal receives aggregated data sent from the server and uses libraries such as Python's Pandas library to fill in any missing data. Furthermore, it performs noise reduction and data standardization. This ensures data integrity and consistency, allowing for more effective subsequent analysis.

[0081] The server then uses a machine learning model to analyze standardized data and generate user profiles. To do this, it utilizes libraries such as Scikit-learn to learn patterns from the data and make predictions. The generated user profiles reflect individual behavioral tendencies and interests.

[0082] For example, if a user frequently purchases electronic devices from multiple e-commerce sites, the server might profile that user as "interested in technology products" and select information on new gadgets for them.

[0083] This selection information is notified to the user's device. Users can review the information displayed on their device and provide feedback indicating their interest. The server analyzes this feedback to improve the accuracy of profiles and suggestions.

[0084] An example of a prompt might be: "Instruct me on how to create a profile for users interested in technology-related products based on their purchase history data, and how to recommend relevant products to them."

[0085] In this way, the system ensures data anonymization and standardization while efficiently providing users with the most relevant information.

[0086] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0087] Step 1:

[0088] The server collects user behavior data from multiple sources in an anonymized form. The input consists of user browsing and purchase history provided by various online platforms. The server retrieves this data via APIs and performs an anonymization process to remove user-specific information. The output is an anonymized and aggregated dataset.

[0089] Step 2:

[0090] The terminal preprocesses the anonymized data received from the server. The input is the raw data provided by the server. The terminal uses the Python Pandas library to statistically impute missing data points and denoise the data. Specific operations include interpolation using the mean of numerical data and filtering outliers. The output is preprocessed and standardized data.

[0091] Step 3:

[0092] The server runs a machine learning model based on preprocessed data. The input is standardized data from the terminal. The server uses the Scikit-learn library to perform clustering and regression analysis to generate user profiles. Specifically, this involves identifying patterns using clustering algorithms, such as K-means. The output is a profile that reflects the user's behavioral tendencies and interests.

[0093] Step 4:

[0094] The server generates personalized recommendations based on the generated user profile. The input is the generated user profile. The server filters relevant information based on the profile information and selects specific information. This may include selecting news about technology products or the latest gadget information. The output is personalized recommendation information.

[0095] Step 5:

[0096] The user receives suggestion information from the server via their terminal. The input is the suggestion information notified by the server. The information sent from the server is displayed on the user's terminal through the application. The output is the suggestion information received by the user.

[0097] Step 6:

[0098] Users submit feedback on the provided suggestion information. The input consists of the user's own opinions and evaluations. Users use a function to send feedback from their device to the server. The output is the user's feedback information.

[0099] Step 7:

[0100] The server analyzes user feedback to improve user profiles and suggestion algorithms. The input is user feedback. The server uses natural language processing techniques to analyze the feedback and incorporate new information into the profile. Specific operations include keyword extraction and frequency analysis of the feedback content. The output is a more accurate profile and suggestions.

[0101] (Application Example 1)

[0102] 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."

[0103] To meet the diverse needs of today's consumers, there is a demand for highly personalized services based on user behavior data. However, conventional technologies make it difficult to efficiently and accurately implement the entire process, from data collection to the generation of suggested information and the utilization of user feedback. Furthermore, insufficient protection of personal information and ensuring anonymity remain problematic.

[0104] 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.

[0105] In this invention, the server includes means for collecting user behavior information in an anonymous form, means for pre-processing and standardizing the collected behavior information, and means for integrating the standardized information and extracting user characteristics. This makes it possible to propose products and services optimized for the user.

[0106] "User behavior information" refers to information about a user's digital actions and activities, such as purchase history and website browsing history.

[0107] "Means of collecting information anonymously" refers to methods for carrying out a process of processing and collecting information in a way that prevents the identification of individual users.

[0108] "Preprocessing and standardization methods" refer to methods that prepare data for use in machine learning models and other applications by imputing missing values, removing noise, and so on.

[0109] "Means for integrating and extracting user characteristics" refers to methods for integrating collected standardized data and extracting specific characteristics that identify user behavior patterns and interests.

[0110] "Means for generating personalized suggestion information" refers to methods for creating information about products and services that are suitable for individual users, based on extracted user characteristics.

[0111] "Means for notifying users of generated suggestion information" refers to means for electronically transmitting personalized information to users.

[0112] "Means of receiving user feedback and improving suggested information" refers to methods of receiving and evaluating responses and reactions from users in order to improve the accuracy of suggestions.

[0113] A "user profile" is digital personal information that summarizes a user's behavior, preferences, interests, and other characteristics.

[0114] "Means for selecting and presenting relevant products" refers to methods for selecting appropriate products based on the user profile and displaying them to the user.

[0115] "Methods for updating purchase information and achieving further personalization" refer to methods for improving the accuracy of personalization by reflecting the user's new purchasing activities in the data and incorporating them into future recommendations.

[0116] To implement this invention, a system is first required to collect user behavior information anonymously. This information is collected by a server from multiple information provision platforms via an API. Specifically, it includes website browsing history and purchase history, and care is taken to ensure that individuals cannot be identified.

[0117] Next, the server preprocesses the collected data, standardizing it by imputing missing data and removing noise. This standardized data is then processed using machine learning models to extract and integrate user features. Recommended software for this process includes machine learning libraries such as TENSORFLOW® and PyTorch.

[0118] Based on the extracted features, personalized recommendation information is generated. This is because the server uses a generated AI model to recommend products based on the trends and interests of the user profile acquired so far. The generated information is notified to the user's information processing device, such as a smartphone or tablet. Since the notification is made via a dedicated application, the user can directly check the recommendations and make a purchase.

[0119] User feedback is sent back to the server for further analysis to improve the accuracy of the profile. This feedback process improves the accuracy of recommendations and provides users with more optimized product information.

[0120] For example, if a user has previously shown interest in and purchased "outdoor equipment," the app might notify them of new products suitable for the next season, such as "camping tents" or "hiking boots." An example of a prompt might be, "Based on the list of items User A has purchased in the past six months, please suggest three outdoor items to recommend for the next summer sale." This prompt would likely generate more sophisticated suggestions.

[0121] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0122] Step 1:

[0123] The server collects user behavior information anonymously from multiple information sources via APIs. Inputs include website browsing history and purchase history, while output is anonymized behavioral data. During this process, all personally identifiable information is deleted or encrypted.

[0124] Step 2:

[0125] The server preprocesses the collected data. The input is the anonymized behavioral data obtained in step 1. Here, missing values ​​are imputed and noise is removed to obtain standardized data. The output is clean, standardized data. This standardization increases data consistency and improves the accuracy of the analysis.

[0126] Step 3:

[0127] The server integrates the pre-processed data and extracts user characteristics. The input is the standardized data generated in step 2. Here, a machine learning model is used to extract features that identify user behavior patterns and interests. The output is user profile data. Specifically, behavior patterns are extracted using a clustering algorithm.

[0128] Step 4:

[0129] The server generates personalized recommendation information using the extracted user characteristics. The input is the user profile data obtained in step 3. It utilizes a generative AI model to create product and service information based on the user's interests. The output is personalized recommendation information for each user. Natural language generation and recommendation technologies are operated by the generative AI model.

[0130] Step 5:

[0131] The server notifies the user's device of the generated suggestion information. The input is the personalized suggestion information generated in step 4. The output is the suggestion information message displayed on the device. Specifically, the information is delivered to the user via a notification API or push notification function.

[0132] Step 6:

[0133] The user reviews the suggested information and provides feedback as needed. The input is the suggested information received by the user. The output is the user's feedback data. The appropriateness of the suggestions is evaluated through the feedback.

[0134] Step 7:

[0135] The server improves the proposed algorithm based on the feedback it receives. The input is the feedback data obtained in step 6. The output is the updated proposed algorithm. Here, the model is retrained and the algorithm's parameters are adjusted based on the feedback, aiming to improve accuracy.

[0136] 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.

[0137] This invention provides a system for highly accurate, personalized responses to users, incorporating an emotion engine to realize services that take into account the user's emotional state. The server collects user behavior information in an anonymized form through APIs provided by group companies and other partners. This behavior information includes the user's website browsing history, purchase history, and service usage records.

[0138] The terminal preprocesses the collected data and organizes it in a standardized format. Based on this data, the server uses an emotion engine to identify the user's current emotional state. The emotion engine monitors the user's emotions in real time, referencing behavioral data and user feedback. This allows for the generation of the user's long-term emotional patterns.

[0139] The generated emotional information is integrated with the user profile, and the server constructs personalized recommendations. For example, if a user is using an online music streaming service and often listens to calming music on weekend nights, this behavioral pattern suggests an emotion of "wanting to relax." The server then incorporates the information from the emotional engine and can suggest a newly released relaxation music playlist to that user.

[0140] Users can review the suggested information through their device and either accept it or request alternative options. User feedback is sent through the device and stored on a server. The server analyzes the feedback and continuously improves the performance of the suggestion algorithm and sentiment engine.

[0141] In this way, a system incorporating an emotion engine can provide personalized services tailored to the user's emotions, thereby contributing to an improved user experience. The embodiment of the invention is configured to achieve advanced emotion-based personalization while ensuring the protection of personal information.

[0142] The following describes the processing flow.

[0143] Step 1:

[0144] The server collects user behavior information in an anonymized form from different service platforms. The information collected includes website visit timing, product viewing frequency, purchase history, and types of services used.

[0145] Step 2:

[0146] The terminal receives behavioral information sent from the server and performs preprocessing to impute missing values ​​and ensure data consistency. This process also standardizes the data format and detects and corrects outliers.

[0147] Step 3:

[0148] The server uses pre-processed data to drive the emotion engine. The emotion engine utilizes machine learning algorithms to estimate the user's emotional state from the data. For example, it recognizes that the user is seeking "calmness" from their music selection habits.

[0149] Step 4:

[0150] The server integrates the estimated emotional state into the user profile. It comprehensively evaluates the user's behavioral tendencies and emotional information to generate personalized suggestions.

[0151] Step 5:

[0152] The server prepares the generated suggestion information for specific users. It builds a selection of content, products, and services tailored to the user's emotions and selects the information to provide.

[0153] Step 6:

[0154] The device notifies the user of the generated suggestion information. This information is delivered to the user via in-app message display or push notification to the device.

[0155] Step 7:

[0156] Users can review the provided suggestions and determine whether they are favorable. They can then accept the suggestions or submit feedback to the system.

[0157] Step 8:

[0158] The server receives user feedback in real time and uses it to improve the performance of the emotion engine and the algorithms it provides. This improves the overall accuracy of the system's personalization and enhances the user experience.

[0159] (Example 2)

[0160] 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".

[0161] In today's information society, user needs are becoming increasingly diverse and individualized, making it difficult to meet user expectations with conventional, general information provision. Furthermore, the lack of technology to provide personalized services based on user emotions limits the potential for improving the user experience. There is also a need for methods to precisely analyze user behavior and emotions and provide effective suggestions while protecting user privacy.

[0162] 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.

[0163] In this invention, the server includes means for collecting user behavior information in an anonymous form, means for pre-processing and standardizing the collected behavior information, and means for identifying the user's emotional state based on the standardized information. This makes it possible to accurately grasp the user's emotional state and propose services tailored to their individual needs.

[0164] "User behavior information" refers to data about a series of activities performed by a user online or offline, and includes browsing history, purchase history, service usage records, etc.

[0165] "Collecting data anonymously" refers to the process of removing or transforming personally identifiable information so that the data does not belong to any specific individual.

[0166] "Preprocessing and standardizing" means applying processes such as data cleaning and normalization to transform data into an analyzable format, and organizing it into a consistent format.

[0167] "Identifying a user's emotional state" is the process of estimating and classifying the emotions a user is currently experiencing based on their behavioral data.

[0168] "Long-term emotional patterns" refer to data that shows the sustained trends in user emotions, obtained by analyzing a user's emotional state over time and revealing regular fluctuations and trends.

[0169] "Personalized suggestion information" refers to suggestions of information and services that are specially customized to address the user's characteristics and emotional state.

[0170] "Notifying a user" means presenting information or suggestions to the target user to draw their attention or encourage them to take action.

[0171] "Receiving feedback and making improvements" is the process of collecting responses and opinions from users and analyzing them to improve the functionality and quality of the system and services.

[0172] This invention realizes a system incorporating an emotion engine to provide personalized services to users. Its main function is to collect user behavior information, analyze the user's emotional state based on that data, and generate personalized suggestions. Specific embodiments are shown below.

[0173] 1. Information gathering and preprocessing

[0174] The server anonymously acquires user behavior information from multiple information dissemination platforms via APIs. The terminal preprocesses the collected data, removing noise and standardizing it, and organizing it into a format suitable for analysis. This ensures data consistency and improves the accuracy of the analysis.

[0175] 2. Analysis of emotional state

[0176] The server operates an emotion engine using standardized data from the terminal. This emotion engine utilizes machine learning and natural language processing techniques to identify the user's emotional state in real time and create long-term emotional patterns. This process makes it possible to accurately recognize the diverse emotions of various users.

[0177] 3. Proposal generation and feedback

[0178] Using a generative AI model, personalized suggestion information is created based on the user's emotional state and patterns. Users can receive and review these suggestions through an application program on their device. For example, if a user feels like relaxing, a playlist of newly released relaxation music will be suggested. Feedback on the suggestions is sent to a server via the device, which analyzes it to improve the emotion engine and suggestion algorithm.

[0179] In this way, systems that utilize emotion engines provide personalized services tailored to the user's emotions, contributing to an improved user experience. An example of a relevant prompt is as follows: "Suggest a music playlist that would be best suited for a user who has recently felt like relaxing."

[0180] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0181] Step 1:

[0182] The server uses APIs to collect user behavior information from multiple information dissemination platforms. Input data includes user web activity and purchase history, which is retrieved in an anonymized state. Output data generates an anonymized behavioral information dataset.

[0183] Step 2:

[0184] The terminal preprocesses the collected behavioral information. Specifically, it performs data noise reduction, imputation of missing values, and formatting standardization. The input is the anonymized dataset obtained in step 1, and the output is a standardized dataset suitable for analysis.

[0185] Step 3:

[0186] The server inputs standardized data into the emotion engine to identify the user's emotional state. Specifically, it uses natural language processing and machine learning algorithms to analyze patterns in the data. The input is standardized data, and the output is information indicating the user's current emotional state.

[0187] Step 4:

[0188] The server generates long-term emotional patterns of the user based on identified emotional states. Through data analysis, it identifies emotional trends and fluctuations, and constructs predictable emotional patterns. The input is current emotional state information, and the output is long-term emotional pattern data of the user.

[0189] Step 5:

[0190] The server generates personalized suggestion information using a generative AI model based on emotional states and patterns. Prompts are used to instruct the AI ​​model, which then outputs the most optimal suggestions. The input is emotional pattern data, and the output is personalized suggestion information.

[0191] Step 6:

[0192] The user receives suggestion information through an application program on their device. The device displays the suggestion information to the user and prompts them to confirm. The input is personalized suggestion information, and the output is displayed as a notification to the user.

[0193] Step 7:

[0194] Users send feedback on suggestions to the server via their device. The server receives the feedback and uses the analysis results to improve the algorithm and sentiment engine. The input is the user's feedback information, and the output is the feedback analysis results.

[0195] (Application Example 2)

[0196] 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".

[0197] Modern content delivery services are required to efficiently provide personalized content recommendations that respond to the diverse emotional states of users. However, existing technologies do not adequately address the need to understand users' emotional states in real time, resulting in a challenge in the accuracy of personalized recommendations necessary to improve the user experience.

[0198] 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.

[0199] In this invention, the server includes means for monitoring the user's emotional state in real time, means for collecting user behavior information anonymously, and means for pre-processing and standardizing the collected behavior information. This enables personalized content recommendations that take the user's emotions into consideration.

[0200] "Monitoring users' emotional states in real time" means using emotion analysis technology to instantly detect a user's emotions and psychological state as they engage in their daily activities and interactions.

[0201] "Collecting behavioral information anonymously" refers to a method of securely collecting user activity history and interaction records in a way that prevents the identification of individuals.

[0202] "Preprocessing and standardizing behavioral information" is the process of organizing collected data into an analyzable format and ensuring consistency among data in different formats.

[0203] "Extracting user characteristics" is the process of identifying the individual user's characteristics and preferences from standardized behavioral data and clarifying those characteristics.

[0204] "Generating personalized suggestion information" means creating data to provide information and services optimized for a user, based on their emotional state and characteristics.

[0205] "Notifying the user of the generated suggestion information" means informing the user of the constructed personalized information at the appropriate time.

[0206] "Receiving feedback and improving suggested information" is the process of collecting user reactions and opinions and using them to improve the accuracy and usefulness of the suggested algorithm.

[0207] "Collected from multiple platforms" means gathering data through various different services and media to aggregate comprehensive information.

[0208] "Performed through a program on the user's device" means using an application installed on the user's electronic device to provide information or perform interactions.

[0209] This invention is a system for providing personalized content in real time, taking into account the user's emotional state. The server anonymously collects user behavior information, preprocesses and standardizes this information, extracts user characteristics from the standardized data, and generates personalized suggestion information based on these characteristics. Furthermore, the suggestion information is further refined by monitoring the user's emotional state in real time.

[0210] The hardware includes server-centric infrastructure and user devices such as smartphones and smart glasses. Data processing is performed using sentiment analysis engines and generative AI models. This analysis utilizes Python and purpose-specific APIs (e.g., Google® Cloud Natural Language API).

[0211] Smart devices used daily by users anonymously collect their website browsing history, purchase history, and service usage records, and send this data to a server. The server uses an emotion analysis engine to infer the user's emotional state from this data and recommend personalized content.

[0212] For example, if the system detects that the user wants to relax on the weekend, it will recommend a newly released playlist of music with relaxation effects.

[0213] Furthermore, when using generative AI models, prompts like the following are used: "The user's current emotional state is relaxed / stressed. Please recommend relevant content."

[0214] In this way, we can provide services that are deeply committed to the user's emotions and improve the user experience.

[0215] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0216] Step 1:

[0217] The user's device collects their website browsing history, purchase history, and service usage records in an anonymized form. This information is used as input data. The device collects this data and sends it to the server.

[0218] Step 2:

[0219] The server preprocesses the received data, cleaning it and imputing missing values. It then converts the data into a standardized format. The input is user behavior information, and the output is standardized data.

[0220] Step 3:

[0221] The server uses a generative AI model based on standardized data to extract user characteristics. This process reveals user preferences and behavioral patterns through data analysis. The input is standardized data, and the output is user characteristic information.

[0222] Step 4:

[0223] The server uses an emotion analysis engine to monitor the user's emotional state in real time. This process integrates user characteristic information and feedback. The input is the user's characteristic information, and the output is the current emotional state.

[0224] Step 5:

[0225] The server generates personalized suggestion information based on the user's emotional state and characteristics. This process selects content that meets the user's needs. The input is the user's emotional state, and the output is the suggestion information.

[0226] Step 6:

[0227] The server notifies the user's terminal of the generated suggestion information. The user receives the notification and reviews the suggested content. The input is the suggestion information, and the output is the content notified to the user.

[0228] Step 7:

[0229] The device receives user feedback and sends it to the server. The server uses this feedback to improve the performance of its suggestion algorithms and emotion engine. The input is user feedback, and the output is the improved algorithm.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] [Second Embodiment]

[0234] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0235] 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.

[0236] 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).

[0237] 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.

[0238] 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.

[0239] 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).

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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.

[0244] 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.

[0245] 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".

[0246] This invention is a system for providing personalized services to users, and is implemented in a form that includes a server, a terminal, and user interaction. The server collects anonymized user behavior information from group companies and other business partners via a pre-configured API. This information is diverse, including the user's website browsing history and purchase history.

[0247] On the terminal, the collected data is first preprocessed, with missing data points being filled in and noise being removed. This standardizes the data, making it available for subsequent processing by the server.

[0248] Next, the server runs a machine learning model based on the integrated data to generate individual user profiles. These profiles systematically organize the user's behavioral tendencies and interests. This enables the provision of personalized services to each user.

[0249] For example, if a user makes purchases on multiple e-commerce platforms through their device and frequently buys electronic devices, this user's profile will be described as having a "strong interest in technology products." Based on this profile, the server selects information about the latest gadgets and electronic devices and notifies the user via their device.

[0250] Users can receive suggestions and, if interested, directly view the information. Furthermore, they can send feedback about the suggestions to the server. The server analyzes the received feedback to improve the user profile and the accuracy of the suggestion algorithm.

[0251] In this way, it becomes possible to provide users with more highly personalized services and to offer suggestions that meet their individual needs. The invention is characterized by its ability to achieve high-quality personalization while ensuring the protection of personal information through thorough anonymization and preprocessing of collected data.

[0252] The following describes the processing flow.

[0253] Step 1:

[0254] The server collects user behavior information in an anonymized format using APIs provided by group companies and other companies. This information includes browsing history, purchase history, and other service usage data.

[0255] Step 2:

[0256] The terminal preprocesses the raw data received from the server. Specifically, it fills in missing data, standardizes the format, and removes noise, ensuring the data is organized in a consistent format.

[0257] Step 3:

[0258] The server integrates pre-processed data, associating it with each user. This brings together data from different platforms into a single user profile.

[0259] Step 4:

[0260] The server uses machine learning techniques on the integrated dataset. It applies data mining methods and algorithms to generate profiles that visualize user behavioral characteristics and interests.

[0261] Step 5:

[0262] The server analyzes the generated profile and produces personalized recommendations for the user. For example, it selects highly relevant products and content based on past purchase trends.

[0263] Step 6:

[0264] The device will notify the user of the generated suggestions. These will be delivered to the user's device as push notifications or in-app messages.

[0265] Step 7:

[0266] Users review the received proposals and access related information if they are interested. If the proposal does not meet their expectations, they send feedback to the server via their device.

[0267] Step 8:

[0268] The server collects and analyzes feedback received from users. Based on this information, it adjusts and improves the proposed algorithm and user profile.

[0269] In this way, the entire system continuously evolves, enabling more precise personalization for individual users.

[0270] (Example 1)

[0271] 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."

[0272] In today's information society, users are exposed to vast amounts of information, but much of it is provided uniformly. Therefore, there is a need for personalized information tailored to individual user interests and preferences. However, current systems struggle to efficiently and safely collect and utilize individual behavioral information, and the accuracy and relevance of the obtained information are often insufficient. Furthermore, there is a lack of mechanisms to effectively utilize user feedback to improve information provision.

[0273] 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.

[0274] In this invention, the server includes means for anonymizing and aggregating individual data received from multiple information sources by an information processing device, means for preprocessing the aggregated data with an analysis device to fill in data gaps, remove noise, and standardize the data, and means for inputting the standardized information into a machine learning model to generate individual user profiles. This makes it possible to provide information tailored to each user with high accuracy and to continuously improve the relevance of the information through feedback.

[0275] An "information processing device" is a device that has the function of receiving, processing, storing, or transmitting digital data.

[0276] "Individual data" refers to a data set that includes information such as the actions and transaction histories related to a specific user.

[0277] "Anonymization" is a process of removing information that identifies an individual from individual data to protect the privacy of the individual.

[0278] "Aggregation" is a method of organizing multiple data into one unit for efficient management.

[0279] "Analysis device" refers to a device or software for analyzing the content of data and extracting specific patterns and information.

[0280] "Preprocessing" is a procedure for improving the quality of data by performing processing and conversion before data analysis and model creation.

[0281] "Data deficiency" refers to a state where incomplete or missing information exists within a data set.

[0282] "Noise removal" is a process of removing irrelevant or incorrect information contained in data to maintain accurate data.

[0283] "Standardization" is a conversion operation for unifying different data formats and scales to make them comparable.

[0284] "Machine learning model" refers to an algorithm or program for learning patterns from data to make specific predictions and decisions.

[0285] "User profile" is an accumulation of information summarizing the behavior trends and interests of users analyzed based on individual data.

[0286] "Provision means" refers to the technology and devices for distributing the generated information to users.

[0287] "Feedback" refers to users' reactions and opinions to the information and services provided, and is used for subsequent improvements.

[0288] This invention is a system for providing users with highly accurate and personalized information. This system consists of a server, a terminal, and user interaction.

[0289] The server acts as an information processing device, anonymizing and aggregating individual data from multiple sources. These sources include various online platforms and digital services, and data is retrieved via APIs. This data includes website browsing history and purchase history. The server stores the received data in a database, preparing it for subsequent processing.

[0290] Next, the terminal functions as an analysis device for preprocessing. The terminal receives aggregated data sent from the server and uses libraries such as Python's Pandas library to fill in any missing data. Furthermore, it performs noise reduction and data standardization. This ensures data integrity and consistency, allowing for more effective subsequent analysis.

[0291] The server then uses a machine learning model to analyze standardized data and generate user profiles. To do this, it utilizes libraries such as Scikit-learn to learn patterns from the data and make predictions. The generated user profiles reflect individual behavioral tendencies and interests.

[0292] For example, if a user frequently purchases electronic devices from multiple e-commerce sites, the server might profile that user as "interested in technology products" and select information on new gadgets for them.

[0293] This selection information is notified to the user's device. Users can review the information displayed on their device and provide feedback indicating their interest. The server analyzes this feedback to improve the accuracy of profiles and suggestions.

[0294] An example of a prompt might be: "Instruct me on how to create a profile for users interested in technology-related products based on their purchase history data, and how to recommend relevant products to them."

[0295] In this way, the system ensures data anonymization and standardization while efficiently providing users with the most relevant information.

[0296] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0297] Step 1:

[0298] The server collects user behavior data from multiple sources in an anonymized form. The input consists of user browsing and purchase history provided by various online platforms. The server retrieves this data via APIs and performs an anonymization process to remove user-specific information. The output is an anonymized and aggregated dataset.

[0299] Step 2:

[0300] The terminal preprocesses the anonymized data received from the server. The input is the raw data provided by the server. The terminal uses the Python Pandas library to statistically impute missing data points and denoise the data. Specific operations include interpolation using the mean of numerical data and filtering outliers. The output is preprocessed and standardized data.

[0301] Step 3:

[0302] The server executes a machine learning model based on the preprocessed data. The input is the data standardized by the terminal. The server uses the Scikit-learn library to perform clustering and regression analysis to generate a user profile. Specifically, it includes the operation of identifying patterns using a clustering algorithm, such as K-means. As output, a profile reflecting the user's behavior trends and interests is obtained.

[0303] Step 4:

[0304] Based on the generated user profile, the server generates personalized recommendations. The input is the generated user profile. The server filters relevant information and selects specific information by referring to the profile information. For example, it includes the operation of selecting news about technology products and the latest gadget information. As output, personalized recommendation information is obtained.

[0305] Step 5:

[0306] The user receives the recommendation information from the server via the terminal. The input is the recommendation information notified by the server. On the user terminal, the information sent from the server is displayed through an application. The output is the recommendation information itself received by the user.

[0307] Step 6:

[0308] The user sends feedback on the provided recommendation information. The input is the user's own opinions and evaluations. The user uses the function to send feedback from the terminal to the server. As output, feedback information from the user is obtained.

[0309] Step 7:

[0310] The server analyzes user feedback to improve user profiles and suggestion algorithms. The input is user feedback. The server uses natural language processing techniques to analyze the feedback and incorporate new information into the profile. Specific operations include keyword extraction and frequency analysis of the feedback content. The output is a more accurate profile and suggestions.

[0311] (Application Example 1)

[0312] 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."

[0313] To meet the diverse needs of today's consumers, there is a demand for highly personalized services based on user behavior data. However, conventional technologies make it difficult to efficiently and accurately implement the entire process, from data collection to the generation of suggested information and the utilization of user feedback. Furthermore, insufficient protection of personal information and ensuring anonymity remain problematic.

[0314] 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.

[0315] In this invention, the server includes means for collecting user behavior information in an anonymous form, means for pre-processing and standardizing the collected behavior information, and means for integrating the standardized information and extracting user characteristics. This makes it possible to propose products and services optimized for the user.

[0316] "User behavior information" refers to information about a user's digital actions and activities, such as purchase history and website browsing history.

[0317] "Means of collecting information anonymously" refers to methods for carrying out a process of processing and collecting information in a way that prevents the identification of individual users.

[0318] "Preprocessing and standardization methods" refer to methods that prepare data for use in machine learning models and other applications by imputing missing values, removing noise, and so on.

[0319] "Means for integrating and extracting user characteristics" refers to methods for integrating collected standardized data and extracting specific characteristics that identify user behavior patterns and interests.

[0320] "Means for generating personalized suggestion information" refers to methods for creating information about products and services that are suitable for individual users, based on extracted user characteristics.

[0321] "Means for notifying users of generated suggestion information" refers to means for electronically transmitting personalized information to users.

[0322] "Means of receiving user feedback and improving suggested information" refers to methods of receiving and evaluating responses and reactions from users in order to improve the accuracy of suggestions.

[0323] A "user profile" is digital personal information that summarizes a user's behavior, preferences, interests, and other characteristics.

[0324] "Means for selecting and presenting relevant products" refers to methods for selecting appropriate products based on the user profile and displaying them to the user.

[0325] "Methods for updating purchase information and achieving further personalization" refer to methods for improving the accuracy of personalization by reflecting the user's new purchasing activities in the data and incorporating them into future recommendations.

[0326] To implement this invention, a system is first required to collect user behavior information anonymously. This information is collected by a server from multiple information provision platforms via an API. Specifically, it includes website browsing history and purchase history, and care is taken to ensure that individuals cannot be identified.

[0327] Next, the server preprocesses the collected data, standardizing it by imputing missing data and removing noise. This standardized data is then processed using machine learning models to extract and integrate user features. Machine learning libraries such as TensorFlow and PyTorch are recommended for this process.

[0328] Based on the extracted features, personalized recommendation information is generated. This is because the server uses a generated AI model to recommend products based on the trends and interests of the user profile acquired so far. The generated information is notified to the user's information processing device, such as a smartphone or tablet. Since the notification is made via a dedicated application, the user can directly check the recommendations and make a purchase.

[0329] User feedback is sent back to the server for further analysis to improve the accuracy of the profile. This feedback process improves the accuracy of recommendations and provides users with more optimized product information.

[0330] For example, if a user has previously shown interest in and purchased "outdoor equipment," the app might notify them of new products suitable for the next season, such as "camping tents" or "hiking boots." An example of a prompt might be, "Based on the list of items User A has purchased in the past six months, please suggest three outdoor items to recommend for the next summer sale." This prompt would likely generate more sophisticated suggestions.

[0331] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0332] Step 1:

[0333] The server collects user behavior information anonymously from multiple information sources via APIs. Inputs include website browsing history and purchase history, while output is anonymized behavioral data. During this process, all personally identifiable information is deleted or encrypted.

[0334] Step 2:

[0335] The server preprocesses the collected data. The input is the anonymized behavioral data obtained in step 1. Here, missing values ​​are imputed and noise is removed to obtain standardized data. The output is clean, standardized data. This standardization increases data consistency and improves the accuracy of the analysis.

[0336] Step 3:

[0337] The server integrates the pre-processed data and extracts user characteristics. The input is the standardized data generated in step 2. Here, a machine learning model is used to extract features that identify user behavior patterns and interests. The output is user profile data. Specifically, behavior patterns are extracted using a clustering algorithm.

[0338] Step 4:

[0339] The server generates personalized recommendation information using the extracted user characteristics. The input is the user profile data obtained in step 3. It utilizes a generative AI model to create product and service information based on the user's interests. The output is personalized recommendation information for each user. Natural language generation and recommendation technologies are operated by the generative AI model.

[0340] Step 5:

[0341] The server notifies the user's device of the generated suggestion information. The input is the personalized suggestion information generated in step 4. The output is the suggestion information message displayed on the device. Specifically, the information is delivered to the user via a notification API or push notification function.

[0342] Step 6:

[0343] The user reviews the suggested information and provides feedback as needed. The input is the suggested information received by the user. The output is the user's feedback data. The appropriateness of the suggestions is evaluated through the feedback.

[0344] Step 7:

[0345] The server improves the proposed algorithm based on the feedback it receives. The input is the feedback data obtained in step 6. The output is the updated proposed algorithm. Here, the model is retrained and the algorithm's parameters are adjusted based on the feedback, aiming to improve accuracy.

[0346] 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.

[0347] This invention provides a system for highly accurate, personalized responses to users, incorporating an emotion engine to realize services that take into account the user's emotional state. The server collects user behavior information in an anonymized form through APIs provided by group companies and other partners. This behavior information includes the user's website browsing history, purchase history, and service usage records.

[0348] The terminal preprocesses the collected data and organizes it in a standardized format. Based on this data, the server uses an emotion engine to identify the user's current emotional state. The emotion engine monitors the user's emotions in real time, referencing behavioral data and user feedback. This allows for the generation of the user's long-term emotional patterns.

[0349] The generated emotional information is integrated with the user profile, and the server constructs personalized recommendations. For example, if a user is using an online music streaming service and often listens to calming music on weekend nights, this behavioral pattern suggests an emotion of "wanting to relax." The server then incorporates the information from the emotional engine and can suggest a newly released relaxation music playlist to that user.

[0350] Users can review the suggested information through their device and either accept it or request alternative options. User feedback is sent through the device and stored on a server. The server analyzes the feedback and continuously improves the performance of the suggestion algorithm and sentiment engine.

[0351] In this way, a system incorporating an emotion engine can provide personalized services tailored to the user's emotions, thereby contributing to an improved user experience. The embodiment of the invention is configured to achieve advanced emotion-based personalization while ensuring the protection of personal information.

[0352] The following describes the processing flow.

[0353] Step 1:

[0354] The server collects user behavior information in an anonymized form from different service platforms. The information collected includes website visit timing, product viewing frequency, purchase history, and types of services used.

[0355] Step 2:

[0356] The terminal receives behavioral information sent from the server and performs preprocessing to impute missing values ​​and ensure data consistency. This process also standardizes the data format and detects and corrects outliers.

[0357] Step 3:

[0358] The server uses pre-processed data to drive the emotion engine. The emotion engine utilizes machine learning algorithms to estimate the user's emotional state from the data. For example, it recognizes that the user is seeking "calmness" from their music selection habits.

[0359] Step 4:

[0360] The server integrates the estimated emotional state into the user profile. It comprehensively evaluates the user's behavioral tendencies and emotional information to generate personalized suggestions.

[0361] Step 5:

[0362] The server prepares the generated suggestion information for specific users. It builds a selection of content, products, and services tailored to the user's emotions and selects the information to provide.

[0363] Step 6:

[0364] The device notifies the user of the generated suggestion information. This information is delivered to the user via in-app message display or push notification to the device.

[0365] Step 7:

[0366] Users can review the provided suggestions and determine whether they are favorable. They can then accept the suggestions or submit feedback to the system.

[0367] Step 8:

[0368] The server receives user feedback in real time and uses it to improve the performance of the emotion engine and the algorithms it provides. This improves the overall accuracy of the system's personalization and enhances the user experience.

[0369] (Example 2)

[0370] 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".

[0371] In today's information society, user needs are becoming increasingly diverse and individualized, making it difficult to meet user expectations with conventional, general information provision. Furthermore, the lack of technology to provide personalized services based on user emotions limits the potential for improving the user experience. There is also a need for methods to precisely analyze user behavior and emotions and provide effective suggestions while protecting user privacy.

[0372] 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.

[0373] In this invention, the server includes means for collecting user behavior information in an anonymous form, means for pre-processing and standardizing the collected behavior information, and means for identifying the user's emotional state based on the standardized information. This makes it possible to accurately grasp the user's emotional state and propose services tailored to their individual needs.

[0374] "User behavior information" refers to data about a series of activities performed by a user online or offline, and includes browsing history, purchase history, service usage records, etc.

[0375] "Collecting data anonymously" refers to the process of removing or transforming personally identifiable information so that the data does not belong to any specific individual.

[0376] "Preprocessing and standardizing" means applying processes such as data cleaning and normalization to transform data into an analyzable format, and organizing it into a consistent format.

[0377] "Identifying a user's emotional state" is the process of estimating and classifying the emotions a user is currently experiencing based on their behavioral data.

[0378] "Long-term emotional patterns" refer to data that shows the sustained trends in user emotions, obtained by analyzing a user's emotional state over time and revealing regular fluctuations and trends.

[0379] "Personalized suggestion information" refers to suggestions of information and services that are specially customized to address the user's characteristics and emotional state.

[0380] "Notifying a user" means presenting information or suggestions to the target user to draw their attention or encourage them to take action.

[0381] "Receiving feedback and making improvements" is the process of collecting responses and opinions from users and analyzing them to improve the functionality and quality of the system and services.

[0382] This invention realizes a system incorporating an emotion engine to provide personalized services to users. Its main function is to collect user behavior information, analyze the user's emotional state based on that data, and generate personalized suggestions. Specific embodiments are shown below.

[0383] 1. Information gathering and preprocessing

[0384] The server anonymously acquires user behavior information from multiple information dissemination platforms via APIs. The terminal preprocesses the collected data, removing noise and standardizing it, and organizing it into a format suitable for analysis. This ensures data consistency and improves the accuracy of the analysis.

[0385] 2. Analysis of emotional state

[0386] The server operates an emotion engine using standardized data from the terminal. This emotion engine utilizes machine learning and natural language processing techniques to identify the user's emotional state in real time and create long-term emotional patterns. This process makes it possible to accurately recognize the diverse emotions of various users.

[0387] 3. Proposal generation and feedback

[0388] Using a generative AI model, personalized suggestion information is created based on the user's emotional state and patterns. Users can receive and review these suggestions through an application program on their device. For example, if a user feels like relaxing, a playlist of newly released relaxation music will be suggested. Feedback on the suggestions is sent to a server via the device, which analyzes it to improve the emotion engine and suggestion algorithm.

[0389] In this way, systems that utilize emotion engines provide personalized services tailored to the user's emotions, contributing to an improved user experience. An example of a relevant prompt is as follows: "Suggest a music playlist that would be best suited for a user who has recently felt like relaxing."

[0390] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0391] Step 1:

[0392] The server uses APIs to collect user behavior information from multiple information dissemination platforms. Input data includes user web activity and purchase history, which is retrieved in an anonymized state. Output data generates an anonymized behavioral information dataset.

[0393] Step 2:

[0394] The terminal preprocesses the collected behavioral information. Specifically, it performs data noise reduction, imputation of missing values, and formatting standardization. The input is the anonymized dataset obtained in step 1, and the output is a standardized dataset suitable for analysis.

[0395] Step 3:

[0396] The server inputs standardized data into the emotion engine to identify the user's emotional state. Specifically, it uses natural language processing and machine learning algorithms to analyze patterns in the data. The input is standardized data, and the output is information indicating the user's current emotional state.

[0397] Step 4:

[0398] The server generates long-term emotional patterns of the user based on identified emotional states. Through data analysis, it identifies emotional trends and fluctuations, and constructs predictable emotional patterns. The input is current emotional state information, and the output is long-term emotional pattern data of the user.

[0399] Step 5:

[0400] The server generates personalized suggestion information using a generative AI model based on emotional states and patterns. Prompts are used to instruct the AI ​​model, which then outputs the most optimal suggestions. The input is emotional pattern data, and the output is personalized suggestion information.

[0401] Step 6:

[0402] The user receives suggestion information through an application program on their device. The device displays the suggestion information to the user and prompts them to confirm. The input is personalized suggestion information, and the output is displayed as a notification to the user.

[0403] Step 7:

[0404] Users send feedback on suggestions to the server via their device. The server receives the feedback and uses the analysis results to improve the algorithm and sentiment engine. The input is the user's feedback information, and the output is the feedback analysis results.

[0405] (Application Example 2)

[0406] 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."

[0407] Modern content delivery services are required to efficiently provide personalized content recommendations that respond to the diverse emotional states of users. However, existing technologies do not adequately address the need to understand users' emotional states in real time, resulting in a challenge in the accuracy of personalized recommendations necessary to improve the user experience.

[0408] 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.

[0409] In this invention, the server includes means for monitoring the user's emotional state in real time, means for collecting user behavior information anonymously, and means for pre-processing and standardizing the collected behavior information. This enables personalized content recommendations that take the user's emotions into consideration.

[0410] "Monitoring users' emotional states in real time" means using emotion analysis technology to instantly detect a user's emotions and psychological state as they engage in their daily activities and interactions.

[0411] "Collecting behavioral information anonymously" refers to a method of securely collecting user activity history and interaction records in a way that prevents the identification of individuals.

[0412] "Preprocessing and standardizing behavioral information" is the process of organizing collected data into an analyzable format and ensuring consistency among data in different formats.

[0413] "Extracting user characteristics" is the process of identifying the individual user's characteristics and preferences from standardized behavioral data and clarifying those characteristics.

[0414] "Generating personalized suggestion information" means creating data to provide information and services optimized for a user, based on their emotional state and characteristics.

[0415] "Notifying the user of the generated suggestion information" means informing the user of the constructed personalized information at the appropriate time.

[0416] "Receiving feedback and improving suggested information" is the process of collecting user reactions and opinions and using them to improve the accuracy and usefulness of the suggested algorithm.

[0417] "Collected from multiple platforms" means gathering data through various different services and media to aggregate comprehensive information.

[0418] "Performed through a program on the user's device" means using an application installed on the user's electronic device to provide information or perform interactions.

[0419] This invention is a system for providing personalized content in real time, taking into account the user's emotional state. The server anonymously collects user behavior information, preprocesses and standardizes this information, extracts user characteristics from the standardized data, and generates personalized suggestion information based on these characteristics. Furthermore, the suggestion information is further refined by monitoring the user's emotional state in real time.

[0420] The hardware includes server-centric infrastructure and user devices such as smartphones and smart glasses. Data processing is performed using sentiment analysis engines and generative AI models. This analysis utilizes Python and purpose-specific APIs (e.g., Google Cloud Natural Language API).

[0421] Smart devices used daily by users anonymously collect their website browsing history, purchase history, and service usage records, and send this data to a server. The server uses an emotion analysis engine to infer the user's emotional state from this data and recommend personalized content.

[0422] For example, if the system detects that the user wants to relax on the weekend, it will recommend a newly released playlist of music with relaxation effects.

[0423] Furthermore, when using generative AI models, prompts like the following are used: "The user's current emotional state is relaxed / stressed. Please recommend relevant content."

[0424] In this way, we can provide services that are deeply committed to the user's emotions and improve the user experience.

[0425] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0426] Step 1:

[0427] The user's device collects their website browsing history, purchase history, and service usage records in an anonymized form. This information is used as input data. The device collects this data and sends it to the server.

[0428] Step 2:

[0429] The server preprocesses the received data, cleaning it and imputing missing values. It then converts the data into a standardized format. The input is user behavior information, and the output is standardized data.

[0430] Step 3:

[0431] The server uses a generative AI model based on standardized data to extract user characteristics. This process reveals user preferences and behavioral patterns through data analysis. The input is standardized data, and the output is user characteristic information.

[0432] Step 4:

[0433] The server uses an emotion analysis engine to monitor the user's emotional state in real time. This process integrates user characteristic information and feedback. The input is the user's characteristic information, and the output is the current emotional state.

[0434] Step 5:

[0435] The server generates personalized suggestion information based on the user's emotional state and characteristics. This process selects content that meets the user's needs. The input is the user's emotional state, and the output is the suggestion information.

[0436] Step 6:

[0437] The server notifies the user's terminal of the generated suggestion information. The user receives the notification and reviews the suggested content. The input is the suggestion information, and the output is the content notified to the user.

[0438] Step 7:

[0439] The device receives user feedback and sends it to the server. The server uses this feedback to improve the performance of its suggestion algorithms and emotion engine. The input is user feedback, and the output is the improved algorithm.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] [Third Embodiment]

[0444] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0445] 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.

[0446] 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).

[0447] 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.

[0448] 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.

[0449] 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).

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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.

[0454] 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.

[0455] 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".

[0456] This invention is a system for providing personalized services to users, and is implemented in a form that includes a server, a terminal, and user interaction. The server collects anonymized user behavior information from group companies and other business partners via a pre-configured API. This information is diverse, including the user's website browsing history and purchase history.

[0457] On the terminal, the collected data is first preprocessed, with missing data points being filled in and noise being removed. This standardizes the data, making it available for subsequent processing by the server.

[0458] Next, the server runs a machine learning model based on the integrated data to generate individual user profiles. These profiles systematically organize the user's behavioral tendencies and interests. This enables the provision of personalized services to each user.

[0459] For example, if a user makes purchases on multiple e-commerce platforms through their device and frequently buys electronic devices, this user's profile will be described as having a "strong interest in technology products." Based on this profile, the server selects information about the latest gadgets and electronic devices and notifies the user via their device.

[0460] Users can receive suggestions and, if interested, directly view the information. Furthermore, they can send feedback about the suggestions to the server. The server analyzes the received feedback to improve the user profile and the accuracy of the suggestion algorithm.

[0461] In this way, it becomes possible to provide users with more highly personalized services and to offer suggestions that meet their individual needs. The invention is characterized by its ability to achieve high-quality personalization while ensuring the protection of personal information through thorough anonymization and preprocessing of collected data.

[0462] The following describes the processing flow.

[0463] Step 1:

[0464] The server collects user behavior information in an anonymized format using APIs provided by group companies and other companies. This information includes browsing history, purchase history, and other service usage data.

[0465] Step 2:

[0466] The terminal preprocesses the raw data received from the server. Specifically, it fills in missing data, standardizes the format, and removes noise, ensuring the data is organized in a consistent format.

[0467] Step 3:

[0468] The server integrates pre-processed data, associating it with each user. This brings together data from different platforms into a single user profile.

[0469] Step 4:

[0470] The server uses machine learning techniques on the integrated dataset. It applies data mining methods and algorithms to generate profiles that visualize user behavioral characteristics and interests.

[0471] Step 5:

[0472] The server analyzes the generated profile and produces personalized recommendations for the user. For example, it selects highly relevant products and content based on past purchase trends.

[0473] Step 6:

[0474] The device will notify the user of the generated suggestions. These will be delivered to the user's device as push notifications or in-app messages.

[0475] Step 7:

[0476] Users review the received proposals and access related information if they are interested. If the proposal does not meet their expectations, they send feedback to the server via their device.

[0477] Step 8:

[0478] The server collects and analyzes feedback received from users. Based on this information, it adjusts and improves the proposed algorithm and user profile.

[0479] In this way, the entire system continuously evolves, enabling more precise personalization for individual users.

[0480] (Example 1)

[0481] 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."

[0482] In today's information society, users are exposed to vast amounts of information, but much of it is provided uniformly. Therefore, there is a need for personalized information tailored to individual user interests and preferences. However, current systems struggle to efficiently and safely collect and utilize individual behavioral information, and the accuracy and relevance of the obtained information are often insufficient. Furthermore, there is a lack of mechanisms to effectively utilize user feedback to improve information provision.

[0483] 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.

[0484] In this invention, the server includes means for anonymizing and aggregating individual data received from multiple information sources by an information processing device, means for preprocessing the aggregated data with an analysis device to fill in data gaps, remove noise, and standardize the data, and means for inputting the standardized information into a machine learning model to generate individual user profiles. This makes it possible to provide information tailored to each user with high accuracy and to continuously improve the relevance of the information through feedback.

[0485] An "information processing device" is a device that has the function of receiving, processing, storing, or transmitting digital data.

[0486] "Individual data" refers to a collection of data that includes information such as the behavior and transaction history of a specific user.

[0487] "Anonymization" is a process that removes personally identifiable information from individual data in order to protect individual privacy.

[0488] "Aggregation" is a method of organizing multiple data sets into a single unit for efficient management.

[0489] An "analysis device" is a piece of equipment or software used to analyze data content and extract specific patterns or information.

[0490] "Preprocessing" refers to the steps taken to improve the quality of data before performing data analysis or model creation, such as processing or transforming it.

[0491] "Data loss" refers to a state in which incomplete or missing information exists within a dataset.

[0492] "Noise reduction" is the process of removing irrelevant or incorrect information from data to maintain its accuracy.

[0493] "Standardization" is the process of transforming different data formats and scales to unify them and make them comparable.

[0494] A "machine learning model" is an algorithm or program that learns patterns from data to make specific predictions or decisions.

[0495] A "user profile" is a collection of information that summarizes a user's behavioral tendencies and interests, based on analysis of individual data.

[0496] "Means of delivery" refers to the technologies and devices used to distribute generated information to users.

[0497] "Feedback" refers to users' reactions and opinions to the information and services provided, and is used for subsequent improvements.

[0498] This invention is a system for providing users with highly accurate and personalized information. This system consists of a server, a terminal, and user interaction.

[0499] The server acts as an information processing device, anonymizing and aggregating individual data from multiple sources. These sources include various online platforms and digital services, and data is retrieved via APIs. This data includes website browsing history and purchase history. The server stores the received data in a database, preparing it for subsequent processing.

[0500] Next, the terminal functions as an analysis device for preprocessing. The terminal receives aggregated data sent from the server and uses libraries such as Python's Pandas library to fill in any missing data. Furthermore, it performs noise reduction and data standardization. This ensures data integrity and consistency, allowing for more effective subsequent analysis.

[0501] The server then uses a machine learning model to analyze standardized data and generate user profiles. To do this, it utilizes libraries such as Scikit-learn to learn patterns from the data and make predictions. The generated user profiles reflect individual behavioral tendencies and interests.

[0502] For example, if a user frequently purchases electronic devices from multiple e-commerce sites, the server might profile that user as "interested in technology products" and select information on new gadgets for them.

[0503] This selection information is notified to the user's device. Users can review the information displayed on their device and provide feedback indicating their interest. The server analyzes this feedback to improve the accuracy of profiles and suggestions.

[0504] An example of a prompt might be: "Instruct me on how to create a profile for users interested in technology-related products based on their purchase history data, and how to recommend relevant products to them."

[0505] In this way, the system ensures data anonymization and standardization while efficiently providing users with the most relevant information.

[0506] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0507] Step 1:

[0508] The server collects user behavior data from multiple sources in an anonymized form. The input consists of user browsing and purchase history provided by various online platforms. The server retrieves this data via APIs and performs an anonymization process to remove user-specific information. The output is an anonymized and aggregated dataset.

[0509] Step 2:

[0510] The terminal preprocesses the anonymized data received from the server. The input is the raw data provided by the server. The terminal uses the Python Pandas library to statistically impute missing data points and denoise the data. Specific operations include interpolation using the mean of numerical data and filtering outliers. The output is preprocessed and standardized data.

[0511] Step 3:

[0512] The server runs a machine learning model based on preprocessed data. The input is standardized data from the terminal. The server uses the Scikit-learn library to perform clustering and regression analysis to generate user profiles. Specifically, this involves identifying patterns using clustering algorithms, such as K-means. The output is a profile that reflects the user's behavioral tendencies and interests.

[0513] Step 4:

[0514] The server generates personalized recommendations based on the generated user profile. The input is the generated user profile. The server filters relevant information based on the profile information and selects specific information. This may include selecting news about technology products or the latest gadget information. The output is personalized recommendation information.

[0515] Step 5:

[0516] The user receives suggestion information from the server via their terminal. The input is the suggestion information notified by the server. The information sent from the server is displayed on the user's terminal through the application. The output is the suggestion information received by the user.

[0517] Step 6:

[0518] Users submit feedback on the provided suggestion information. The input consists of the user's own opinions and evaluations. Users use a function to send feedback from their device to the server. The output is the user's feedback information.

[0519] Step 7:

[0520] The server analyzes user feedback to improve user profiles and suggestion algorithms. The input is user feedback. The server uses natural language processing techniques to analyze the feedback and incorporate new information into the profile. Specific operations include keyword extraction and frequency analysis of the feedback content. The output is a more accurate profile and suggestions.

[0521] (Application Example 1)

[0522] 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."

[0523] To meet the diverse needs of today's consumers, there is a demand for highly personalized services based on user behavior data. However, conventional technologies make it difficult to efficiently and accurately implement the entire process, from data collection to the generation of suggested information and the utilization of user feedback. Furthermore, insufficient protection of personal information and ensuring anonymity remain problematic.

[0524] 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.

[0525] In this invention, the server includes means for collecting user behavior information in an anonymous form, means for pre-processing and standardizing the collected behavior information, and means for integrating the standardized information and extracting user characteristics. This makes it possible to propose products and services optimized for the user.

[0526] "User behavior information" refers to information about a user's digital actions and activities, such as purchase history and website browsing history.

[0527] "Means of collecting information anonymously" refers to methods for carrying out a process of processing and collecting information in a way that prevents the identification of individual users.

[0528] "Preprocessing and standardization methods" refer to methods that prepare data for use in machine learning models and other applications by imputing missing values, removing noise, and so on.

[0529] "Means for integrating and extracting user characteristics" refers to methods for integrating collected standardized data and extracting specific characteristics that identify user behavior patterns and interests.

[0530] "Means for generating personalized suggestion information" refers to methods for creating information about products and services that are suitable for individual users, based on extracted user characteristics.

[0531] "Means for notifying users of generated suggestion information" refers to means for electronically transmitting personalized information to users.

[0532] "Means of receiving user feedback and improving suggested information" refers to methods of receiving and evaluating responses and reactions from users in order to improve the accuracy of suggestions.

[0533] A "user profile" is digital personal information that summarizes a user's behavior, preferences, interests, and other characteristics.

[0534] "Means for selecting and presenting relevant products" refers to methods for selecting appropriate products based on the user profile and displaying them to the user.

[0535] "Methods for updating purchase information and achieving further personalization" refer to methods for improving the accuracy of personalization by reflecting the user's new purchasing activities in the data and incorporating them into future recommendations.

[0536] To implement this invention, a system is first required to collect user behavior information anonymously. This information is collected by a server from multiple information provision platforms via an API. Specifically, it includes website browsing history and purchase history, and care is taken to ensure that individuals cannot be identified.

[0537] Next, the server preprocesses the collected data, standardizing it by imputing missing data and removing noise. This standardized data is then processed using machine learning models to extract and integrate user features. Machine learning libraries such as TensorFlow and PyTorch are recommended for this process.

[0538] Based on the extracted features, personalized recommendation information is generated. This is because the server uses a generated AI model to recommend products based on the trends and interests of the user profile acquired so far. The generated information is notified to the user's information processing device, such as a smartphone or tablet. Since the notification is made via a dedicated application, the user can directly check the recommendations and make a purchase.

[0539] User feedback is sent back to the server for further analysis to improve the accuracy of the profile. This feedback process improves the accuracy of recommendations and provides users with more optimized product information.

[0540] For example, if a user has previously shown interest in and purchased "outdoor equipment," the app might notify them of new products suitable for the next season, such as "camping tents" or "hiking boots." An example of a prompt might be, "Based on the list of items User A has purchased in the past six months, please suggest three outdoor items to recommend for the next summer sale." This prompt would likely generate more sophisticated suggestions.

[0541] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0542] Step 1:

[0543] The server collects user behavior information anonymously from multiple information sources via APIs. Inputs include website browsing history and purchase history, while output is anonymized behavioral data. During this process, all personally identifiable information is deleted or encrypted.

[0544] Step 2:

[0545] The server preprocesses the collected data. The input is the anonymized behavioral data obtained in step 1. Here, missing values ​​are imputed and noise is removed to obtain standardized data. The output is clean, standardized data. This standardization increases data consistency and improves the accuracy of the analysis.

[0546] Step 3:

[0547] The server integrates the pre-processed data and extracts user characteristics. The input is the standardized data generated in step 2. Here, a machine learning model is used to extract features that identify user behavior patterns and interests. The output is user profile data. Specifically, behavior patterns are extracted using a clustering algorithm.

[0548] Step 4:

[0549] The server generates personalized recommendation information using the extracted user characteristics. The input is the user profile data obtained in step 3. It utilizes a generative AI model to create product and service information based on the user's interests. The output is personalized recommendation information for each user. Natural language generation and recommendation technologies are operated by the generative AI model.

[0550] Step 5:

[0551] The server notifies the user's device of the generated suggestion information. The input is the personalized suggestion information generated in step 4. The output is the suggestion information message displayed on the device. Specifically, the information is delivered to the user via a notification API or push notification function.

[0552] Step 6:

[0553] The user reviews the suggested information and provides feedback as needed. The input is the suggested information received by the user. The output is the user's feedback data. The appropriateness of the suggestions is evaluated through the feedback.

[0554] Step 7:

[0555] The server improves the proposed algorithm based on the feedback it receives. The input is the feedback data obtained in step 6. The output is the updated proposed algorithm. Here, the model is retrained and the algorithm's parameters are adjusted based on the feedback, aiming to improve accuracy.

[0556] 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.

[0557] This invention provides a system for highly accurate, personalized responses to users, incorporating an emotion engine to realize services that take into account the user's emotional state. The server collects user behavior information in an anonymized form through APIs provided by group companies and other partners. This behavior information includes the user's website browsing history, purchase history, and service usage records.

[0558] The terminal preprocesses the collected data and organizes it in a standardized format. Based on this data, the server uses an emotion engine to identify the user's current emotional state. The emotion engine monitors the user's emotions in real time, referencing behavioral data and user feedback. This allows for the generation of the user's long-term emotional patterns.

[0559] The generated emotional information is integrated with the user profile, and the server constructs personalized recommendations. For example, if a user is using an online music streaming service and often listens to calming music on weekend nights, this behavioral pattern suggests an emotion of "wanting to relax." The server then incorporates the information from the emotional engine and can suggest a newly released relaxation music playlist to that user.

[0560] Users can review the suggested information through their device and either accept it or request alternative options. User feedback is sent through the device and stored on a server. The server analyzes the feedback and continuously improves the performance of the suggestion algorithm and sentiment engine.

[0561] In this way, a system incorporating an emotion engine can provide personalized services tailored to the user's emotions, thereby contributing to an improved user experience. The embodiment of the invention is configured to achieve advanced emotion-based personalization while ensuring the protection of personal information.

[0562] The following describes the processing flow.

[0563] Step 1:

[0564] The server collects user behavior information in an anonymized form from different service platforms. The information collected includes website visit timing, product viewing frequency, purchase history, and types of services used.

[0565] Step 2:

[0566] The terminal receives behavioral information sent from the server and performs preprocessing to impute missing values ​​and ensure data consistency. This process also standardizes the data format and detects and corrects outliers.

[0567] Step 3:

[0568] The server uses pre-processed data to drive the emotion engine. The emotion engine utilizes machine learning algorithms to estimate the user's emotional state from the data. For example, it recognizes that the user is seeking "calmness" from their music selection habits.

[0569] Step 4:

[0570] The server integrates the estimated emotional state into the user profile. It comprehensively evaluates the user's behavioral tendencies and emotional information to generate personalized suggestions.

[0571] Step 5:

[0572] The server prepares the generated suggestion information for specific users. It builds a selection of content, products, and services tailored to the user's emotions and selects the information to provide.

[0573] Step 6:

[0574] The device notifies the user of the generated suggestion information. This information is delivered to the user via in-app message display or push notification to the device.

[0575] Step 7:

[0576] Users can review the provided suggestions and determine whether they are favorable. They can then accept the suggestions or submit feedback to the system.

[0577] Step 8:

[0578] The server receives user feedback in real time and uses it to improve the performance of the emotion engine and the algorithms it provides. This improves the overall accuracy of the system's personalization and enhances the user experience.

[0579] (Example 2)

[0580] 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."

[0581] In today's information society, user needs are becoming increasingly diverse and individualized, making it difficult to meet user expectations with conventional, general information provision. Furthermore, the lack of technology to provide personalized services based on user emotions limits the potential for improving the user experience. There is also a need for methods to precisely analyze user behavior and emotions and provide effective suggestions while protecting user privacy.

[0582] 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.

[0583] In this invention, the server includes means for collecting user behavior information in an anonymous form, means for pre-processing and standardizing the collected behavior information, and means for identifying the user's emotional state based on the standardized information. This makes it possible to accurately grasp the user's emotional state and propose services tailored to their individual needs.

[0584] "User behavior information" refers to data about a series of activities performed by a user online or offline, and includes browsing history, purchase history, service usage records, etc.

[0585] "Collecting data anonymously" refers to the process of removing or transforming personally identifiable information so that the data does not belong to any specific individual.

[0586] "Preprocessing and standardizing" means applying processes such as data cleaning and normalization to transform data into an analyzable format, and organizing it into a consistent format.

[0587] "Identifying a user's emotional state" is the process of estimating and classifying the emotions a user is currently experiencing based on their behavioral data.

[0588] "Long-term emotional patterns" refer to data that shows the sustained trends in user emotions, obtained by analyzing a user's emotional state over time and revealing regular fluctuations and trends.

[0589] "Personalized suggestion information" refers to suggestions of information and services that are specially customized to address the user's characteristics and emotional state.

[0590] "Notifying a user" means presenting information or suggestions to the target user to draw their attention or encourage them to take action.

[0591] "Receiving feedback and making improvements" is the process of collecting responses and opinions from users and analyzing them to improve the functionality and quality of the system and services.

[0592] This invention realizes a system incorporating an emotion engine to provide personalized services to users. Its main function is to collect user behavior information, analyze the user's emotional state based on that data, and generate personalized suggestions. Specific embodiments are shown below.

[0593] 1. Information gathering and preprocessing

[0594] The server anonymously acquires user behavior information from multiple information dissemination platforms via APIs. The terminal preprocesses the collected data, removing noise and standardizing it, and organizing it into a format suitable for analysis. This ensures data consistency and improves the accuracy of the analysis.

[0595] 2. Analysis of emotional state

[0596] The server operates an emotion engine using standardized data from the terminal. This emotion engine utilizes machine learning and natural language processing techniques to identify the user's emotional state in real time and create long-term emotional patterns. This process makes it possible to accurately recognize the diverse emotions of various users.

[0597] 3. Proposal generation and feedback

[0598] Using a generative AI model, personalized suggestion information is created based on the user's emotional state and patterns. Users can receive and review these suggestions through an application program on their device. For example, if a user feels like relaxing, a playlist of newly released relaxation music will be suggested. Feedback on the suggestions is sent to a server via the device, which analyzes it to improve the emotion engine and suggestion algorithm.

[0599] In this way, systems that utilize emotion engines provide personalized services tailored to the user's emotions, contributing to an improved user experience. An example of a relevant prompt is as follows: "Suggest a music playlist that would be best suited for a user who has recently felt like relaxing."

[0600] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0601] Step 1:

[0602] The server uses APIs to collect user behavior information from multiple information dissemination platforms. Input data includes user web activity and purchase history, which is retrieved in an anonymized state. Output data generates an anonymized behavioral information dataset.

[0603] Step 2:

[0604] The terminal preprocesses the collected behavioral information. Specifically, it performs data noise reduction, imputation of missing values, and formatting standardization. The input is the anonymized dataset obtained in step 1, and the output is a standardized dataset suitable for analysis.

[0605] Step 3:

[0606] The server inputs standardized data into the emotion engine to identify the user's emotional state. Specifically, it uses natural language processing and machine learning algorithms to analyze patterns in the data. The input is standardized data, and the output is information indicating the user's current emotional state.

[0607] Step 4:

[0608] The server generates long-term emotional patterns of the user based on identified emotional states. Through data analysis, it identifies emotional trends and fluctuations, and constructs predictable emotional patterns. The input is current emotional state information, and the output is long-term emotional pattern data of the user.

[0609] Step 5:

[0610] The server generates personalized suggestion information using a generative AI model based on emotional states and patterns. Prompts are used to instruct the AI ​​model, which then outputs the most optimal suggestions. The input is emotional pattern data, and the output is personalized suggestion information.

[0611] Step 6:

[0612] The user receives suggestion information through an application program on their device. The device displays the suggestion information to the user and prompts them to confirm. The input is personalized suggestion information, and the output is displayed as a notification to the user.

[0613] Step 7:

[0614] Users send feedback on suggestions to the server via their device. The server receives the feedback and uses the analysis results to improve the algorithm and sentiment engine. The input is the user's feedback information, and the output is the feedback analysis results.

[0615] (Application Example 2)

[0616] 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."

[0617] Modern content delivery services are required to efficiently provide personalized content recommendations that respond to the diverse emotional states of users. However, existing technologies do not adequately address the need to understand users' emotional states in real time, resulting in a challenge in the accuracy of personalized recommendations necessary to improve the user experience.

[0618] 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.

[0619] In this invention, the server includes means for monitoring the user's emotional state in real time, means for collecting user behavior information anonymously, and means for pre-processing and standardizing the collected behavior information. This enables personalized content recommendations that take the user's emotions into consideration.

[0620] "Monitoring users' emotional states in real time" means using emotion analysis technology to instantly detect a user's emotions and psychological state as they engage in their daily activities and interactions.

[0621] "Collecting behavioral information anonymously" refers to a method of securely collecting user activity history and interaction records in a way that prevents the identification of individuals.

[0622] "Preprocessing and standardizing behavioral information" is the process of organizing collected data into an analyzable format and ensuring consistency among data in different formats.

[0623] "Extracting user characteristics" is the process of identifying the individual user's characteristics and preferences from standardized behavioral data and clarifying those characteristics.

[0624] "Generating personalized suggestion information" means creating data to provide information and services optimized for a user, based on their emotional state and characteristics.

[0625] "Notifying the user of the generated suggestion information" means informing the user of the constructed personalized information at the appropriate time.

[0626] "Receiving feedback and improving suggested information" is the process of collecting user reactions and opinions and using them to improve the accuracy and usefulness of the suggested algorithm.

[0627] "Collected from multiple platforms" means gathering data through various different services and media to aggregate comprehensive information.

[0628] "Performed through a program on the user's device" means using an application installed on the user's electronic device to provide information or perform interactions.

[0629] This invention is a system for providing personalized content in real time, taking into account the user's emotional state. The server anonymously collects user behavior information, preprocesses and standardizes this information, extracts user characteristics from the standardized data, and generates personalized suggestion information based on these characteristics. Furthermore, the suggestion information is further refined by monitoring the user's emotional state in real time.

[0630] The hardware includes server-centric infrastructure and user devices such as smartphones and smart glasses. Data processing is performed using sentiment analysis engines and generative AI models. This analysis utilizes Python and purpose-specific APIs (e.g., Google Cloud Natural Language API).

[0631] Smart devices used daily by users anonymously collect their website browsing history, purchase history, and service usage records, and send this data to a server. The server uses an emotion analysis engine to infer the user's emotional state from this data and recommend personalized content.

[0632] For example, if the system detects that the user wants to relax on the weekend, it will recommend a newly released playlist of music with relaxation effects.

[0633] Furthermore, when using generative AI models, prompts like the following are used: "The user's current emotional state is relaxed / stressed. Please recommend relevant content."

[0634] In this way, we can provide services that are deeply committed to the user's emotions and improve the user experience.

[0635] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0636] Step 1:

[0637] The user's device collects their website browsing history, purchase history, and service usage records in an anonymized form. This information is used as input data. The device collects this data and sends it to the server.

[0638] Step 2:

[0639] The server preprocesses the received data, cleaning it and imputing missing values. It then converts the data into a standardized format. The input is user behavior information, and the output is standardized data.

[0640] Step 3:

[0641] The server uses a generative AI model based on standardized data to extract user characteristics. This process reveals user preferences and behavioral patterns through data analysis. The input is standardized data, and the output is user characteristic information.

[0642] Step 4:

[0643] The server uses an emotion analysis engine to monitor the user's emotional state in real time. This process integrates user characteristic information and feedback. The input is the user's characteristic information, and the output is the current emotional state.

[0644] Step 5:

[0645] The server generates personalized suggestion information based on the user's emotional state and characteristics. This process selects content that meets the user's needs. The input is the user's emotional state, and the output is the suggestion information.

[0646] Step 6:

[0647] The server notifies the user's terminal of the generated suggestion information. The user receives the notification and reviews the suggested content. The input is the suggestion information, and the output is the content notified to the user.

[0648] Step 7:

[0649] The device receives user feedback and sends it to the server. The server uses this feedback to improve the performance of its suggestion algorithms and emotion engine. The input is user feedback, and the output is the improved algorithm.

[0650] 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.

[0651] 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.

[0652] 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.

[0653] [Fourth Embodiment]

[0654] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0655] 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.

[0656] 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).

[0657] 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.

[0658] 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.

[0659] 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).

[0660] 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.

[0661] 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.

[0662] 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.

[0663] 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.

[0664] 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.

[0665] 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.

[0666] 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".

[0667] This invention is a system for providing personalized services to users, and is implemented in a form that includes a server, a terminal, and user interaction. The server collects anonymized user behavior information from group companies and other business partners via a pre-configured API. This information is diverse, including the user's website browsing history and purchase history.

[0668] On the terminal, the collected data is first preprocessed, with missing data points being filled in and noise being removed. This standardizes the data, making it available for subsequent processing by the server.

[0669] Next, the server runs a machine learning model based on the integrated data to generate individual user profiles. These profiles systematically organize the user's behavioral tendencies and interests. This enables the provision of personalized services to each user.

[0670] For example, if a user makes purchases on multiple e-commerce platforms through their device and frequently buys electronic devices, this user's profile will be described as having a "strong interest in technology products." Based on this profile, the server selects information about the latest gadgets and electronic devices and notifies the user via their device.

[0671] Users can receive suggestions and, if interested, directly view the information. Furthermore, they can send feedback about the suggestions to the server. The server analyzes the received feedback to improve the user profile and the accuracy of the suggestion algorithm.

[0672] In this way, it becomes possible to provide users with more highly personalized services and to offer suggestions that meet their individual needs. The invention is characterized by its ability to achieve high-quality personalization while ensuring the protection of personal information through thorough anonymization and preprocessing of collected data.

[0673] The following describes the processing flow.

[0674] Step 1:

[0675] The server collects user behavior information in an anonymized format using APIs provided by group companies and other companies. This information includes browsing history, purchase history, and other service usage data.

[0676] Step 2:

[0677] The terminal preprocesses the raw data received from the server. Specifically, it fills in missing data, standardizes the format, and removes noise, ensuring the data is organized in a consistent format.

[0678] Step 3:

[0679] The server integrates pre-processed data, associating it with each user. This brings together data from different platforms into a single user profile.

[0680] Step 4:

[0681] The server uses machine learning techniques on the integrated dataset. It applies data mining methods and algorithms to generate profiles that visualize user behavioral characteristics and interests.

[0682] Step 5:

[0683] The server analyzes the generated profile and produces personalized recommendations for the user. For example, it selects highly relevant products and content based on past purchase trends.

[0684] Step 6:

[0685] The device will notify the user of the generated suggestions. These will be delivered to the user's device as push notifications or in-app messages.

[0686] Step 7:

[0687] Users review the received proposals and access related information if they are interested. If the proposal does not meet their expectations, they send feedback to the server via their device.

[0688] Step 8:

[0689] The server collects and analyzes feedback received from users. Based on this information, it adjusts and improves the proposed algorithm and user profile.

[0690] In this way, the entire system continuously evolves, enabling more precise personalization for individual users.

[0691] (Example 1)

[0692] 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".

[0693] In today's information society, users are exposed to vast amounts of information, but much of it is provided uniformly. Therefore, there is a need for personalized information tailored to individual user interests and preferences. However, current systems struggle to efficiently and safely collect and utilize individual behavioral information, and the accuracy and relevance of the obtained information are often insufficient. Furthermore, there is a lack of mechanisms to effectively utilize user feedback to improve information provision.

[0694] 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.

[0695] In this invention, the server includes means for anonymizing and aggregating individual data received from multiple information sources by an information processing device, means for preprocessing the aggregated data with an analysis device to fill in data gaps, remove noise, and standardize the data, and means for inputting the standardized information into a machine learning model to generate individual user profiles. This makes it possible to provide information tailored to each user with high accuracy and to continuously improve the relevance of the information through feedback.

[0696] An "information processing device" is a device that has the function of receiving, processing, storing, or transmitting digital data.

[0697] "Individual data" refers to a collection of data that includes information such as the behavior and transaction history of a specific user.

[0698] "Anonymization" is a process that removes personally identifiable information from individual data in order to protect individual privacy.

[0699] "Aggregation" is a method of organizing multiple data sets into a single unit for efficient management.

[0700] An "analysis device" is a piece of equipment or software used to analyze data content and extract specific patterns or information.

[0701] "Preprocessing" refers to the steps taken to improve the quality of data before performing data analysis or model creation, such as processing or transforming it.

[0702] "Data loss" refers to a state in which incomplete or missing information exists within a dataset.

[0703] "Noise reduction" is the process of removing irrelevant or incorrect information from data to maintain its accuracy.

[0704] "Standardization" is the process of transforming different data formats and scales to unify them and make them comparable.

[0705] A "machine learning model" is an algorithm or program that learns patterns from data to make specific predictions or decisions.

[0706] A "user profile" is a collection of information that summarizes a user's behavioral tendencies and interests, based on analysis of individual data.

[0707] "Means of delivery" refers to the technologies and devices used to distribute generated information to users.

[0708] "Feedback" refers to users' reactions and opinions to the information and services provided, and is used for subsequent improvements.

[0709] This invention is a system for providing users with highly accurate and personalized information. This system consists of a server, a terminal, and user interaction.

[0710] The server acts as an information processing device, anonymizing and aggregating individual data from multiple sources. These sources include various online platforms and digital services, and data is retrieved via APIs. This data includes website browsing history and purchase history. The server stores the received data in a database, preparing it for subsequent processing.

[0711] Next, the terminal functions as an analysis device for preprocessing. The terminal receives aggregated data sent from the server and uses libraries such as Python's Pandas library to fill in any missing data. Furthermore, it performs noise reduction and data standardization. This ensures data integrity and consistency, allowing for more effective subsequent analysis.

[0712] The server then uses a machine learning model to analyze standardized data and generate user profiles. To do this, it utilizes libraries such as Scikit-learn to learn patterns from the data and make predictions. The generated user profiles reflect individual behavioral tendencies and interests.

[0713] For example, if a user frequently purchases electronic devices from multiple e-commerce sites, the server might profile that user as "interested in technology products" and select information on new gadgets for them.

[0714] This selection information is notified to the user's device. Users can review the information displayed on their device and provide feedback indicating their interest. The server analyzes this feedback to improve the accuracy of profiles and suggestions.

[0715] An example of a prompt might be: "Instruct me on how to create a profile for users interested in technology-related products based on their purchase history data, and how to recommend relevant products to them."

[0716] In this way, the system ensures data anonymization and standardization while efficiently providing users with the most relevant information.

[0717] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0718] Step 1:

[0719] The server collects user behavior data from multiple sources in an anonymized form. The input consists of user browsing and purchase history provided by various online platforms. The server retrieves this data via APIs and performs an anonymization process to remove user-specific information. The output is an anonymized and aggregated dataset.

[0720] Step 2:

[0721] The terminal preprocesses the anonymized data received from the server. The input is the raw data provided by the server. The terminal uses the Python Pandas library to statistically impute missing data points and denoise the data. Specific operations include interpolation using the mean of numerical data and filtering outliers. The output is preprocessed and standardized data.

[0722] Step 3:

[0723] The server runs a machine learning model based on preprocessed data. The input is standardized data from the terminal. The server uses the Scikit-learn library to perform clustering and regression analysis to generate user profiles. Specifically, this involves identifying patterns using clustering algorithms, such as K-means. The output is a profile that reflects the user's behavioral tendencies and interests.

[0724] Step 4:

[0725] The server generates personalized recommendations based on the generated user profile. The input is the generated user profile. The server filters relevant information based on the profile information and selects specific information. This may include selecting news about technology products or the latest gadget information. The output is personalized recommendation information.

[0726] Step 5:

[0727] The user receives suggestion information from the server via their terminal. The input is the suggestion information notified by the server. The information sent from the server is displayed on the user's terminal through the application. The output is the suggestion information received by the user.

[0728] Step 6:

[0729] Users submit feedback on the provided suggestion information. The input consists of the user's own opinions and evaluations. Users use a function to send feedback from their device to the server. The output is the user's feedback information.

[0730] Step 7:

[0731] The server analyzes user feedback to improve user profiles and suggestion algorithms. The input is user feedback. The server uses natural language processing techniques to analyze the feedback and incorporate new information into the profile. Specific operations include keyword extraction and frequency analysis of the feedback content. The output is a more accurate profile and suggestions.

[0732] (Application Example 1)

[0733] 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".

[0734] To meet the diverse needs of today's consumers, there is a demand for highly personalized services based on user behavior data. However, conventional technologies make it difficult to efficiently and accurately implement the entire process, from data collection to the generation of suggested information and the utilization of user feedback. Furthermore, insufficient protection of personal information and ensuring anonymity remain problematic.

[0735] 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.

[0736] In this invention, the server includes means for collecting user behavior information in an anonymous form, means for pre-processing and standardizing the collected behavior information, and means for integrating the standardized information and extracting user characteristics. This makes it possible to propose products and services optimized for the user.

[0737] "User behavior information" refers to information about a user's digital actions and activities, such as purchase history and website browsing history.

[0738] "Means of collecting information anonymously" refers to methods for carrying out a process of processing and collecting information in a way that prevents the identification of individual users.

[0739] "Preprocessing and standardization methods" refer to methods that prepare data for use in machine learning models and other applications by imputing missing values, removing noise, and so on.

[0740] "Means for integrating and extracting user characteristics" refers to methods for integrating collected standardized data and extracting specific characteristics that identify user behavior patterns and interests.

[0741] "Means for generating personalized suggestion information" refers to methods for creating information about products and services that are suitable for individual users, based on extracted user characteristics.

[0742] "Means for notifying users of generated suggestion information" refers to means for electronically transmitting personalized information to users.

[0743] "Means of receiving user feedback and improving suggested information" refers to methods of receiving and evaluating responses and reactions from users in order to improve the accuracy of suggestions.

[0744] A "user profile" is digital personal information that summarizes a user's behavior, preferences, interests, and other characteristics.

[0745] "Means for selecting and presenting relevant products" refers to methods for selecting appropriate products based on the user profile and displaying them to the user.

[0746] "Methods for updating purchase information and achieving further personalization" refer to methods for improving the accuracy of personalization by reflecting the user's new purchasing activities in the data and incorporating them into future recommendations.

[0747] To implement this invention, a system is first required to collect user behavior information anonymously. This information is collected by a server from multiple information provision platforms via an API. Specifically, it includes website browsing history and purchase history, and care is taken to ensure that individuals cannot be identified.

[0748] Next, the server preprocesses the collected data, standardizing it by imputing missing data and removing noise. This standardized data is then processed using machine learning models to extract and integrate user features. Machine learning libraries such as TensorFlow and PyTorch are recommended for this process.

[0749] Based on the extracted features, personalized recommendation information is generated. This is because the server uses a generated AI model to recommend products based on the trends and interests of the user profile acquired so far. The generated information is notified to the user's information processing device, such as a smartphone or tablet. Since the notification is made via a dedicated application, the user can directly check the recommendations and make a purchase.

[0750] User feedback is sent back to the server for further analysis to improve the accuracy of the profile. This feedback process improves the accuracy of recommendations and provides users with more optimized product information.

[0751] For example, if a user has previously shown interest in and purchased "outdoor equipment," the app might notify them of new products suitable for the next season, such as "camping tents" or "hiking boots." An example of a prompt might be, "Based on the list of items User A has purchased in the past six months, please suggest three outdoor items to recommend for the next summer sale." This prompt would likely generate more sophisticated suggestions.

[0752] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0753] Step 1:

[0754] The server collects user behavior information anonymously from multiple information sources via APIs. Inputs include website browsing history and purchase history, while output is anonymized behavioral data. During this process, all personally identifiable information is deleted or encrypted.

[0755] Step 2:

[0756] The server preprocesses the collected data. The input is the anonymized behavioral data obtained in step 1. Here, missing values ​​are imputed and noise is removed to obtain standardized data. The output is clean, standardized data. This standardization increases data consistency and improves the accuracy of the analysis.

[0757] Step 3:

[0758] The server integrates the pre-processed data and extracts user characteristics. The input is the standardized data generated in step 2. Here, a machine learning model is used to extract features that identify user behavior patterns and interests. The output is user profile data. Specifically, behavior patterns are extracted using a clustering algorithm.

[0759] Step 4:

[0760] The server generates personalized recommendation information using the extracted user characteristics. The input is the user profile data obtained in step 3. It utilizes a generative AI model to create product and service information based on the user's interests. The output is personalized recommendation information for each user. Natural language generation and recommendation technologies are operated by the generative AI model.

[0761] Step 5:

[0762] The server notifies the user's device of the generated suggestion information. The input is the personalized suggestion information generated in step 4. The output is the suggestion information message displayed on the device. Specifically, the information is delivered to the user via a notification API or push notification function.

[0763] Step 6:

[0764] The user reviews the suggested information and provides feedback as needed. The input is the suggested information received by the user. The output is the user's feedback data. The appropriateness of the suggestions is evaluated through the feedback.

[0765] Step 7:

[0766] The server improves the proposed algorithm based on the feedback it receives. The input is the feedback data obtained in step 6. The output is the updated proposed algorithm. Here, the model is retrained and the algorithm's parameters are adjusted based on the feedback, aiming to improve accuracy.

[0767] 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.

[0768] This invention provides a system for highly accurate, personalized responses to users, incorporating an emotion engine to realize services that take into account the user's emotional state. The server collects user behavior information in an anonymized form through APIs provided by group companies and other partners. This behavior information includes the user's website browsing history, purchase history, and service usage records.

[0769] The terminal preprocesses the collected data and organizes it in a standardized format. Based on this data, the server uses an emotion engine to identify the user's current emotional state. The emotion engine monitors the user's emotions in real time, referencing behavioral data and user feedback. This allows for the generation of the user's long-term emotional patterns.

[0770] The generated emotional information is integrated with the user profile, and the server constructs personalized recommendations. For example, if a user is using an online music streaming service and often listens to calming music on weekend nights, this behavioral pattern suggests an emotion of "wanting to relax." The server then incorporates the information from the emotional engine and can suggest a newly released relaxation music playlist to that user.

[0771] Users can review the suggested information through their device and either accept it or request alternative options. User feedback is sent through the device and stored on a server. The server analyzes the feedback and continuously improves the performance of the suggestion algorithm and sentiment engine.

[0772] In this way, a system incorporating an emotion engine can provide personalized services tailored to the user's emotions, thereby contributing to an improved user experience. The embodiment of the invention is configured to achieve advanced emotion-based personalization while ensuring the protection of personal information.

[0773] The following describes the processing flow.

[0774] Step 1:

[0775] The server collects user behavior information in an anonymized form from different service platforms. The information collected includes website visit timing, product viewing frequency, purchase history, and types of services used.

[0776] Step 2:

[0777] The terminal receives behavioral information sent from the server and performs preprocessing to impute missing values ​​and ensure data consistency. This process also standardizes the data format and detects and corrects outliers.

[0778] Step 3:

[0779] The server uses pre-processed data to drive the emotion engine. The emotion engine utilizes machine learning algorithms to estimate the user's emotional state from the data. For example, it recognizes that the user is seeking "calmness" from their music selection habits.

[0780] Step 4:

[0781] The server integrates the estimated emotional state into the user profile. It comprehensively evaluates the user's behavioral tendencies and emotional information to generate personalized suggestions.

[0782] Step 5:

[0783] The server prepares the generated suggestion information for specific users. It builds a selection of content, products, and services tailored to the user's emotions and selects the information to provide.

[0784] Step 6:

[0785] The device notifies the user of the generated suggestion information. This information is delivered to the user via in-app message display or push notification to the device.

[0786] Step 7:

[0787] Users can review the provided suggestions and determine whether they are favorable. They can then accept the suggestions or submit feedback to the system.

[0788] Step 8:

[0789] The server receives user feedback in real time and uses it to improve the performance of the emotion engine and the algorithms it provides. This improves the overall accuracy of the system's personalization and enhances the user experience.

[0790] (Example 2)

[0791] 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".

[0792] In today's information society, user needs are becoming increasingly diverse and individualized, making it difficult to meet user expectations with conventional, general information provision. Furthermore, the lack of technology to provide personalized services based on user emotions limits the potential for improving the user experience. There is also a need for methods to precisely analyze user behavior and emotions and provide effective suggestions while protecting user privacy.

[0793] 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.

[0794] In this invention, the server includes means for collecting user behavior information in an anonymous form, means for pre-processing and standardizing the collected behavior information, and means for identifying the user's emotional state based on the standardized information. This makes it possible to accurately grasp the user's emotional state and propose services tailored to their individual needs.

[0795] "User behavior information" refers to data about a series of activities performed by a user online or offline, and includes browsing history, purchase history, service usage records, etc.

[0796] "Collecting data anonymously" refers to the process of removing or transforming personally identifiable information so that the data does not belong to any specific individual.

[0797] "Preprocessing and standardizing" means applying processes such as data cleaning and normalization to transform data into an analyzable format, and organizing it into a consistent format.

[0798] "Identifying a user's emotional state" is the process of estimating and classifying the emotions a user is currently experiencing based on their behavioral data.

[0799] "Long-term emotional patterns" refer to data that shows the sustained trends in user emotions, obtained by analyzing a user's emotional state over time and revealing regular fluctuations and trends.

[0800] "Personalized suggestion information" refers to suggestions of information and services that are specially customized to address the user's characteristics and emotional state.

[0801] "Notifying a user" means presenting information or suggestions to the target user to draw their attention or encourage them to take action.

[0802] "Receiving feedback and making improvements" is the process of collecting responses and opinions from users and analyzing them to improve the functionality and quality of the system and services.

[0803] This invention realizes a system incorporating an emotion engine to provide personalized services to users. Its main function is to collect user behavior information, analyze the user's emotional state based on that data, and generate personalized suggestions. Specific embodiments are shown below.

[0804] 1. Information gathering and preprocessing

[0805] The server anonymously acquires user behavior information from multiple information dissemination platforms via APIs. The terminal preprocesses the collected data, removing noise and standardizing it, and organizing it into a format suitable for analysis. This ensures data consistency and improves the accuracy of the analysis.

[0806] 2. Analysis of emotional state

[0807] The server operates an emotion engine using standardized data from the terminal. This emotion engine utilizes machine learning and natural language processing techniques to identify the user's emotional state in real time and create long-term emotional patterns. This process makes it possible to accurately recognize the diverse emotions of various users.

[0808] 3. Proposal generation and feedback

[0809] Using a generative AI model, personalized suggestion information is created based on the user's emotional state and patterns. Users can receive and review these suggestions through an application program on their device. For example, if a user feels like relaxing, a playlist of newly released relaxation music will be suggested. Feedback on the suggestions is sent to a server via the device, which analyzes it to improve the emotion engine and suggestion algorithm.

[0810] In this way, systems that utilize emotion engines provide personalized services tailored to the user's emotions, contributing to an improved user experience. An example of a relevant prompt is as follows: "Suggest a music playlist that would be best suited for a user who has recently felt like relaxing."

[0811] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0812] Step 1:

[0813] The server uses APIs to collect user behavior information from multiple information dissemination platforms. Input data includes user web activity and purchase history, which is retrieved in an anonymized state. Output data generates an anonymized behavioral information dataset.

[0814] Step 2:

[0815] The terminal preprocesses the collected behavioral information. Specifically, it performs data noise reduction, imputation of missing values, and formatting standardization. The input is the anonymized dataset obtained in step 1, and the output is a standardized dataset suitable for analysis.

[0816] Step 3:

[0817] The server inputs standardized data into the emotion engine to identify the user's emotional state. Specifically, it uses natural language processing and machine learning algorithms to analyze patterns in the data. The input is standardized data, and the output is information indicating the user's current emotional state.

[0818] Step 4:

[0819] The server generates long-term emotional patterns of the user based on identified emotional states. Through data analysis, it identifies emotional trends and fluctuations, and constructs predictable emotional patterns. The input is current emotional state information, and the output is long-term emotional pattern data of the user.

[0820] Step 5:

[0821] The server generates personalized suggestion information using a generative AI model based on emotional states and patterns. Prompts are used to instruct the AI ​​model, which then outputs the most optimal suggestions. The input is emotional pattern data, and the output is personalized suggestion information.

[0822] Step 6:

[0823] The user receives suggestion information through an application program on their device. The device displays the suggestion information to the user and prompts them to confirm. The input is personalized suggestion information, and the output is displayed as a notification to the user.

[0824] Step 7:

[0825] Users send feedback on suggestions to the server via their device. The server receives the feedback and uses the analysis results to improve the algorithm and sentiment engine. The input is the user's feedback information, and the output is the feedback analysis results.

[0826] (Application Example 2)

[0827] 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".

[0828] Modern content delivery services are required to efficiently provide personalized content recommendations that respond to the diverse emotional states of users. However, existing technologies do not adequately address the need to understand users' emotional states in real time, resulting in a challenge in the accuracy of personalized recommendations necessary to improve the user experience.

[0829] 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.

[0830] In this invention, the server includes means for monitoring the user's emotional state in real time, means for collecting user behavior information anonymously, and means for pre-processing and standardizing the collected behavior information. This enables personalized content recommendations that take the user's emotions into consideration.

[0831] "Monitoring users' emotional states in real time" means using emotion analysis technology to instantly detect a user's emotions and psychological state as they engage in their daily activities and interactions.

[0832] "Collecting behavioral information anonymously" refers to a method of securely collecting user activity history and interaction records in a way that prevents the identification of individuals.

[0833] "Preprocessing and standardizing behavioral information" is the process of organizing collected data into an analyzable format and ensuring consistency among data in different formats.

[0834] "Extracting user characteristics" is the process of identifying the individual user's characteristics and preferences from standardized behavioral data and clarifying those characteristics.

[0835] "Generating personalized suggestion information" means creating data to provide information and services optimized for a user, based on their emotional state and characteristics.

[0836] "Notifying the user of the generated suggestion information" means informing the user of the constructed personalized information at the appropriate time.

[0837] "Receiving feedback and improving suggested information" is the process of collecting user reactions and opinions and using them to improve the accuracy and usefulness of the suggested algorithm.

[0838] "Collected from multiple platforms" means gathering data through various different services and media to aggregate comprehensive information.

[0839] "Performed through a program on the user's device" means using an application installed on the user's electronic device to provide information or perform interactions.

[0840] This invention is a system for providing personalized content in real time, taking into account the user's emotional state. The server anonymously collects user behavior information, preprocesses and standardizes this information, extracts user characteristics from the standardized data, and generates personalized suggestion information based on these characteristics. Furthermore, the suggestion information is further refined by monitoring the user's emotional state in real time.

[0841] The hardware includes server-centric infrastructure and user devices such as smartphones and smart glasses. Data processing is performed using sentiment analysis engines and generative AI models. This analysis utilizes Python and purpose-specific APIs (e.g., Google Cloud Natural Language API).

[0842] Smart devices used daily by users anonymously collect their website browsing history, purchase history, and service usage records, and send this data to a server. The server uses an emotion analysis engine to infer the user's emotional state from this data and recommend personalized content.

[0843] For example, if the system detects that the user wants to relax on the weekend, it will recommend a newly released playlist of music with relaxation effects.

[0844] Furthermore, when using generative AI models, prompts like the following are used: "The user's current emotional state is relaxed / stressed. Please recommend relevant content."

[0845] In this way, we can provide services that are deeply committed to the user's emotions and improve the user experience.

[0846] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0847] Step 1:

[0848] The user's device collects their website browsing history, purchase history, and service usage records in an anonymized form. This information is used as input data. The device collects this data and sends it to the server.

[0849] Step 2:

[0850] The server preprocesses the received data, cleaning it and imputing missing values. It then converts the data into a standardized format. The input is user behavior information, and the output is standardized data.

[0851] Step 3:

[0852] The server uses a generative AI model based on standardized data to extract user characteristics. This process reveals user preferences and behavioral patterns through data analysis. The input is standardized data, and the output is user characteristic information.

[0853] Step 4:

[0854] The server uses an emotion analysis engine to monitor the user's emotional state in real time. This process integrates user characteristic information and feedback. The input is the user's characteristic information, and the output is the current emotional state.

[0855] Step 5:

[0856] The server generates personalized suggestion information based on the user's emotional state and characteristics. This process selects content that meets the user's needs. The input is the user's emotional state, and the output is the suggestion information.

[0857] Step 6:

[0858] The server notifies the user's terminal of the generated suggestion information. The user receives the notification and reviews the suggested content. The input is the suggestion information, and the output is the content notified to the user.

[0859] Step 7:

[0860] The device receives user feedback and sends it to the server. The server uses this feedback to improve the performance of its suggestion algorithms and emotion engine. The input is user feedback, and the output is the improved algorithm.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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."

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] 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 as being incorporated by reference.

[0882] The following is further disclosed regarding the embodiments described above.

[0883] (Claim 1)

[0884] Means of collecting user behavior information anonymously,

[0885] The means for preprocessing and standardizing the collected behavioral information,

[0886] A means of integrating standardized information and extracting user characteristics,

[0887] A means for generating personalized suggestion information based on extracted features,

[0888] A means of notifying the user of the generated suggestion information,

[0889] A means of receiving user feedback and improving suggested information,

[0890] A system that includes this.

[0891] (Claim 2)

[0892] The system according to claim 1, further comprising means for collecting user behavior information from multiple service platforms.

[0893] (Claim 3)

[0894] The system according to claim 1, further comprising means for notifying the proposed information through an application on the user's terminal.

[0895] "Example 1"

[0896] (Claim 1)

[0897] An information processing device provides means for anonymizing and aggregating individual data received from multiple information sources,

[0898] The aggregated data is preprocessed using an analysis device, and means are used to fill in data gaps, remove noise, and standardize the data.

[0899] A means of inputting standardized information into a machine learning model to generate individual user profiles,

[0900] A means for selecting information relevant to the user based on the generated profile and creating personalized suggestions through the means of provision,

[0901] A means for notifying the aforementioned proposal via the user's terminal,

[0902] A means of analyzing user feedback to improve machine learning models and enhance the accuracy of user profiles,

[0903] A system that includes this.

[0904] (Claim 2)

[0905] The system according to claim 1, characterized in that the aforementioned information is collected from multiple information exchange platforms.

[0906] (Claim 3)

[0907] The system according to claim 1, characterized in that the notification of the aforementioned proposal is made via a program on an information processing terminal.

[0908] "Application Example 1"

[0909] (Claim 1)

[0910] Means of collecting user behavior information anonymously,

[0911] The means for preprocessing and standardizing the collected behavioral information,

[0912] A means of integrating standardized information and extracting user characteristics,

[0913] A means for generating personalized suggestion information based on extracted features,

[0914] A means of notifying the user of the generated suggestion information,

[0915] A means of receiving user feedback and improving suggested information,

[0916] A means of selecting and presenting relevant products based on user profiles,

[0917] A means to update purchase information based on the suggested products and achieve further personalization,

[0918] A system that includes this.

[0919] (Claim 2)

[0920] The system according to claim 1, further comprising means for collecting user behavior information from multiple information provision platforms.

[0921] (Claim 3)

[0922] The system according to claim 1, further comprising means for notifying the proposed information through application software on the user's information processing device.

[0923] "Example 2 of combining an emotion engine"

[0924] (Claim 1)

[0925] Means of collecting user behavior information anonymously,

[0926] The means for preprocessing and standardizing the collected behavioral information,

[0927] A means of identifying a user's emotional state based on standardized information,

[0928] A means for generating a user's long-term emotional patterns from identified emotional states,

[0929] A means for generating personalized suggestion information based on extracted features,

[0930] A means of notifying the user of the generated suggestion information,

[0931] A means of receiving user feedback and improving suggestion information and sentiment engines,

[0932] A system that includes this.

[0933] (Claim 2)

[0934] The system according to claim 1, further comprising means for collecting user behavior information from multiple information dissemination platforms.

[0935] (Claim 3)

[0936] The system according to claim 1, further comprising means for notifying the proposed information through an application program on the user's information processing device.

[0937] "Application example 2 when combining with an emotional engine"

[0938] (Claim 1)

[0939] A means of monitoring the user's emotional state in real time,

[0940] Means of collecting user behavior information anonymously,

[0941] The means for preprocessing and standardizing the collected behavioral information,

[0942] A means of integrating standardized information and extracting user characteristics,

[0943] A means for generating personalized suggestion information based on extracted features and the user's emotional state,

[0944] A means of notifying the user of the generated suggestion information,

[0945] A means of receiving user feedback and improving suggested information,

[0946] A system that includes this.

[0947] (Claim 2)

[0948] The system according to claim 1, further comprising means for collecting user behavior information from multiple platforms.

[0949] (Claim 3)

[0950] The system according to claim 1, further comprising means for notifying the proposed information through a program on the user's device. [Explanation of symbols]

[0951] 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. Means of collecting user behavior information anonymously, The means for preprocessing and standardizing the collected behavioral information, A means of integrating standardized information and extracting user characteristics, A means for generating personalized suggestion information based on extracted features, A means of notifying the user of the generated suggestion information, A means of receiving user feedback and improving suggested information, A system that includes this.

2. The system according to claim 1, further comprising means for collecting user behavior information from multiple service platforms.

3. The system according to claim 1, further comprising means for notifying the proposed information through an application on the user's terminal.

Images