system

Abstract

We provide the system. [Solution] A means for collecting user behavior data, A means for identifying user interests based on the aforementioned behavioral data, A means for selecting information relevant to the user based on the aforementioned interests, A means of aggregating selected information and generating a customized document, Means for providing the generated documents electronically, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds 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 comprehensive catalogs cover information, it has been difficult for users to quickly find the necessary information due to the large number of pages. In addition, the timing for users to consider new products and services is limited, which has been an obstacle to promoting utilization. Furthermore, the amount of paper resources used is large, and there is room for improvement in terms of cost.

Means for Solving the Problems

[0005] This invention provides a means for collecting user behavior data and identifying user interests based on that data. Based on these identified interests, relevant information is selected and documents optimized for each user are generated. Furthermore, by providing these generated documents electronically and also making printed versions available upon request, necessary information can be provided to users quickly and efficiently, facilitating the consideration of new products. This also reduces the use of paper resources and improves cost efficiency.

[0006] "User behavior data" refers to data such as a user's past search history, purchase history, and contract information, and is used to understand users' interests and purchasing behavior.

[0007] "Methods for identifying interests" refer to the processes and technologies used to analyze collected behavioral data and identify products and services that users are interested in.

[0008] "Means of selecting information" refers to methods or tools for selecting highly relevant product and service information based on the interests of identified users.

[0009] A "customized document" refers to a document that is individually created and contains information tailored to each user's interests, concerns, and needs.

[0010] "Means of providing electronically" refers to methods and technologies for delivering documents generated in digital formats, such as the internet or email, to users. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3]This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface that includes a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] This invention is a system that utilizes user behavior data to enable personalized information delivery tailored to each user. The following forms are possible for implementing this system.

[0033] The server first collects user behavior data. This data includes the user's past internet search history, purchase history, and subscriber information. This makes it possible to understand what products and services the user is interested in.

[0034] Next, the server analyzes the collected behavioral data to identify the user's interests. This may involve using technologies such as machine learning and data mining. Based on the analysis results, the server selects the most relevant information for each user, aggregates that information, and generates customized documents.

[0035] The generated document is provided electronically to the user's device via the server. The user can view this document in digital format. If the user requests a printed copy, the server will print it on demand and initiate the process of mailing the physical document.

[0036] As a concrete example, suppose a user frequently searches for information about high-performance cameras on the network. The server analyzes this data and identifies that the user is interested in new smartphones with superior camera capabilities. Next, based on this information, the server selects information on smartphones with high camera performance and related pricing plans, and generates this as a customized "My Catalog." This catalog is then delivered to the user's device, and a printed version is also provided if needed. In this way, the user can quickly obtain the information that is most suitable for them, enabling them to efficiently purchase products or review their plans.

[0037] The following describes the processing flow.

[0038] Step 1:

[0039] The server collects user behavior data. Specifically, it obtains search history, purchase history, and subscriber information from affiliated databases and cookies, and stores this information in a central data storage.

[0040] Step 2:

[0041] The server preprocesses the collected data. This includes imputing missing values ​​and normalizing the data to prepare it for easy analysis. If data anonymization is necessary, it is performed at this stage.

[0042] Step 3:

[0043] The server uses pre-processed data to identify user interests. Machine learning algorithms are then used to analyze search and purchase patterns and identify categories of products and services that the user is interested in.

[0044] Step 4:

[0045] The server selects information based on the user's interests. Based on the identified categories, it extracts relevant products, services, and pricing plans from the database and prioritizes them.

[0046] Step 5:

[0047] The server generates customized documents based on the selected information. Using a template engine, the documents are built as a user-optimized "My Catalog".

[0048] Step 6:

[0049] The server distributes generated documents electronically. Users can access their "My Catalog" via email or notifications on their devices, and they can view it in digital format.

[0050] Step 7:

[0051] If a user requests a printed copy, the server will arrange for printing on demand. The document will be physically mailed to the specified delivery address and delivered to the user.

[0052] (Example 1)

[0053] 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."

[0054] In today's world, the sheer volume of information makes it difficult for users to quickly obtain the information best suited to their needs. Solving this problem and providing appropriate information based on individual user interests is essential. Furthermore, in addition to digital formats, physical means of information delivery are also required as needed.

[0055] 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.

[0056] In this invention, the server includes means for collecting information about user behavior, means for analyzing the information to identify the user's interests, and means for integrating the selected information to generate personalized documents. This enables users to quickly and accurately receive information based on their interests.

[0057] "Information about user behavior" refers to data such as a user's search history, browsing history, purchase history, and contract information on the internet, and is data that indicates the user's interests and behavioral patterns.

[0058] "Methods for analyzing and identifying user interests" refers to the process of identifying user preferences and interests using machine learning models or data mining techniques on collected behavioral data.

[0059] "Means of selecting relevant information" refers to the process of extracting highly relevant information from an information base based on the user's identified interests and selecting the information necessary to provide to the user.

[0060] "Means of generating personalized documents" refers to a function that uses selected information, integrates it in a format suitable for each individual user, and creates documents that meet the user's interests.

[0061] "Means of providing to users in digital format" refers to a function that provides users with generated personalized documents in electronic format, enabling them to view them on their devices.

[0062] This invention is a system in which a server, a terminal, and a user work together to provide personalized information to the user. First, the server collects information about the user's behavior. This information includes the user's internet search history, purchase history, and contract information, which allows the server to infer the user's preferences and interests. For information collection, a streaming platform such as Apache® Kafka is used to receive and store data in real time.

[0063] Next, in the process of analyzing the collected data, the server builds machine learning models using Python's scikit-learn and TENSORFLOW® to identify user interests. This analysis makes it possible to extract products and services of interest based on user behavior patterns.

[0064] Next, the server selects relevant information based on the identified interests. This selected information is then integrated and generated as a personalized document for the user. The document is generated using LaTeX or HTML, providing a clear and well-organized format.

[0065] The generated documents are then sent digitally to the terminal, allowing the user to view the information on their device. If the user prefers a physical document, the server places a print order on demand and arranges for postal delivery. This process allows users to quickly receive customized information based on their interests, which can be helpful in product selection and contract review.

[0066] As a concrete example, if a user is interested in high-performance cameras, the server analyzes their history and generates a "My Catalog" that aggregates information on smartphones and related plans that match the user's interests. This catalog is then delivered to the user's device. An example of a prompt to the generating AI model would be, "Use the user's search history and purchase history to generate the most suitable product recommendation."

[0067] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0068] Step 1:

[0069] The server collects information about user behavior. At this stage, it gathers data from the internet, such as search history, purchase history, and visited websites. Using a streaming platform like Apache Kafka, it stores this data in a database in real time. The input to this process is user activity logs from the internet, and the output is user activity data recorded in the database.

[0070] Step 2:

[0071] The server analyzes collected behavioral data to identify user interests. It applies machine learning models using Python libraries such as scikit-learn and TensorFlow to generate user profiles based on the data. The input to this process is behavioral data retrieved from a database, and the output is profile information that details the user's interests.

[0072] Step 3:

[0073] The server selects relevant information based on the user's interests. Here, it uses the user's profile information to select relevant products and services from its information database. By calculating the degree of relevance between the database information and the profile, it extracts the most optimal recommendations. The input to this process is the generated user profile, and the output is a list of information relevant to the user.

[0074] Step 4:

[0075] The server integrates the selected information and generates personalized documents. Using LaTeX or HTML formatting, it formats the documents as user-specific catalogs. The input to this process is a list of selected information, and the output is a completed digital document.

[0076] Step 5:

[0077] The server delivers the generated document to the terminal. The document is transferred digitally using the HTTP protocol, and the user can view it through an application on the terminal. The input to this process is a personalized document, and the output is the information displayed on the user's terminal.

[0078] Step 6:

[0079] The server arranges on-demand printing in case a user requests a printed copy. Print jobs are sent to the printing facility via API, and the physical document is prepared for mailing to the user. The inputs to this process are a flag indicating the user wants to print and the personalized document; the output is the delivery of the printed physical document.

[0080] (Application Example 1)

[0081] 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."

[0082] Modern consumers are required to quickly acquire information that aligns with their interests and make appropriate purchasing decisions in a market offering a wide variety of goods and services. However, many consumers face the challenge of spending a lot of time searching for and filtering relevant information, making it difficult to have an efficient purchasing experience. Furthermore, insufficient information tailored to individual preferences can lead to decreased satisfaction after purchase.

[0083] 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.

[0084] In this invention, the server includes means for collecting user behavior data, means for identifying the user's interests based on the behavior data, means for selecting information relevant to the user based on the interests, means for aggregating the selected information and generating a customized data set, means for electronically providing the generated data set, and means for presenting the provided data set within a virtual store environment to support the user's purchasing activities. This enables consumers to obtain optimal information based on their interests and preferences, making efficient and satisfying purchasing decisions.

[0085] "User behavior data" is a general term for information that indicates consumer behavior, such as search history, purchase history, and browsing history performed by users on the internet and digital platforms.

[0086] "Means of identifying interests" refers to methods and technologies for analyzing collected user behavior data to infer specific categories or products that users are interested in.

[0087] "Means for selecting relevant information" refers to technologies that enable a process of selecting the most relevant product and service information for a user based on their identified interests.

[0088] "Means for generating data sets" refers to technologies that aggregate user-optimized information and compile it into a format that can be viewed as a digital format or visual media.

[0089] "Means of providing electronically" refers to technologies and methods for transmitting and displaying a generated data set on a user's device via the internet or digital communication means.

[0090] A "virtual store environment" refers to a digital platform that provides users with the experience of browsing and purchasing products in a virtual store space built online.

[0091] "Means of supporting purchasing activities" refer to methods and technologies that provide relevant information and suggestions to support users' decision-making during the process of considering a purchase.

[0092] The system for realizing this invention consists of a server, a user terminal, and a digital platform for building a virtual store environment. First, the server uses a Python program to collect user behavior data. This behavior data includes the user's online search history and purchase history. This allows the system to identify the user's interests.

[0093] Next, the server uses machine learning models such as TensorFlow to analyze the collected behavioral data and predict specific categories or products that the user might be interested in. Based on the analyzed data, it selects the information most relevant to the user. The selected information is compiled into a customized data set generated using Unity and provided to the user's device.

[0094] The user's device, particularly smartphones and VR headsets, receives the generated data set and presents it visually within the virtual store environment. This presentation allows users to intuitively browse products and make purchases. By utilizing Unity, the virtual store environment is updated in real time, providing information tailored to the products the user is interested in.

[0095] As a concrete example, an instruction such as "Create the most relevant suggestions based on the product categories the user has shown interest in. Example: Summer bags." can be input into the AI ​​model to present information tailored to the user. This allows the user to quickly obtain the information that is most suitable for them.

[0096] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0097] Step 1:

[0098] The server uses a Python program to collect user behavior data. The input is the user's activity log on digital platforms, and the output is the collected raw data. This process uses the Google® Analytics API to obtain the pages the user viewed and the keywords they searched for.

[0099] Step 2:

[0100] The server analyzes the collected behavioral data using a machine learning model. The input is the raw data obtained in step 1, and the output is labeled data indicating the user's interests. TensorFlow is used to find hidden patterns in the data and infer the product categories that the user is interested in.

[0101] Step 3:

[0102] The server selects relevant information based on the analyzed data. The input is the labeled data from step 2, and the output is a list of product information that is highly relevant to the user. It retrieves information on the relevant products from the database and lists those that match the user's interests.

[0103] Step 4:

[0104] The server uses Unity to generate selected information as a customized data set. The input is a list of information from step 3, and the output is a visualized data set. Product information is built as 3D models and interactive content and packaged for the user.

[0105] Step 5:

[0106] The terminal receives the generated data set and presents it within the virtual store environment. The input is the visualized data set generated in step 4, and the output is an interactive shopping screen that the user can experience in real time. The terminal accepts user input for exploring products within the virtual store rendered by Unity.

[0107] Step 6:

[0108] Users select items of interest within a virtual store and prepare to make a purchase. Input is the product information displayed on the terminal, and output is data reflecting the user's purchase intention. Users then navigate the interface to view detailed product information and proceed with the purchase process.

[0109] Step 7:

[0110] The server inputs prompt text into the generative AI model and retrieves information that complements the user experience. The input is the instruction, "Create the most relevant suggestions based on the product categories the user has shown interest in," and the output is a customized suggestion text created by the generative AI model. This provides added value for the user and supports their purchasing decision.

[0111] 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.

[0112] This invention is a system that achieves more accurate and customized information delivery by combining user behavior data with an emotion engine. The following forms are possible for implementing this system.

[0113] The server first collects user behavior data and simultaneously obtains user emotional data using an emotion engine. This emotional data is obtained using methods such as text analysis, voice analysis, or facial expression analysis. This makes it possible to understand the user's current emotional state in detail.

[0114] Next, the server integrates this data to identify the user's interests. By combining emotional data with regular behavioral data, it is possible to capture the user's intentions more accurately. For example, past search history is compared with the user's current emotional state to select products and services that are predicted to be of genuine interest to the user.

[0115] The server then generates a customized document based on the selected information. This document takes into account the user's emotional state and incorporates expressions and suggestions that match that emotion. For example, if a positive emotion is detected, product suggestions may be presented in a more proactive tone.

[0116] The generated documents are delivered electronically from the server to the user's terminal. Users can access this information in digital format and, if necessary, receive physical copies via on-demand printing.

[0117] As a concrete example, consider a scenario where a user is entering a product review on a smartphone app, and sentiment analysis reveals that the review is very positive. In this case, the server determines that the user has a strong interest in the product and includes information on related accessories and services in "My Catalog," suggesting them to the user. This process enables the provision of information closely linked to the user's interests and emotions.

[0118] The following describes the processing flow.

[0119] Step 1:

[0120] The server collects user behavior data. This includes the process of obtaining and storing in a database the pages the user has viewed on a website, their online search history, and their past purchase history.

[0121] Step 2:

[0122] The server uses an emotion engine to acquire user emotion data. The emotion engine performs text and voice analysis to collect user reviews, feedback, or voice recordings, and analyzes their emotional state. For example, if there are many positive words in the reviews, it will be judged as having a positive emotion.

[0123] Step 3:

[0124] The server integrates and analyzes collected behavioral and emotional data. Machine learning models are used to clarify which products and services users are interested in and what suggestions align with their current emotions. These analysis results are used to identify user interests.

[0125] Step 4:

[0126] The server selects personalized information based on the user's identified interests and emotional state. This includes not only product features but also promotional messages and related products tailored to their emotions. For example, if a user leaves an enthusiastic review of a travel-related product, information including new travel products and special offers will be selected.

[0127] Step 5:

[0128] The server generates customized documents based on the selected information. This process utilizes templates and incorporates content and expressions appropriate to the emotions expressed. Positive emotions are conveyed through a cheerful writing style and encouraging language.

[0129] Step 6:

[0130] The server provides the generated documents electronically to the user's device. Users can view this catalog on their device and, if necessary, request a printed copy. The server then processes the on-demand printing and mails the printed copy.

[0131] (Example 2)

[0132] 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".

[0133] Modern information delivery systems often rely solely on user behavioral data to present information, making it difficult to accurately capture users' true interests and needs. Furthermore, the lack of appropriate information tailored to users' emotional states limits the user experience and reduces information receptivity.

[0134] 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.

[0135] In this invention, the server includes means for collecting user behavior information, means for acquiring user emotional information using emotion analysis technology, and means for generating customized documents that include expressions corresponding to the user's emotional state using a generative AI model. This makes it possible to provide personalized information that more accurately reflects the user's interests and emotions.

[0136] "User behavior information" refers to information such as operation history, search history, and purchase history that is generated when a user uses a device or service.

[0137] "Methods for identifying user interests" refer to technologies that analyze user behavior data to find topics and products that are likely to interest that user.

[0138] "Emotional analysis technology" is a technology that estimates a user's emotional state by analyzing data such as text, voice, or facial expressions obtained from the user.

[0139] "User emotional information" refers to information about the user's emotional state obtained using emotion analysis technology.

[0140] "Methods for selecting information" refer to technologies that select information deemed relevant to the user based on the user's behavioral and emotional information.

[0141] A "generative AI model" is an algorithm or framework that uses natural language processing technology to generate text and content that is tailored to the user's emotional state and interests.

[0142] "Means for generating customized documents" refers to technologies that create documents optimized for individual users by taking into account user behavioral and emotional information.

[0143] This invention relates to a system that provides personalized information using user behavioral and emotional information. Specifically, it is implemented using a server, a terminal, and a generative AI model.

[0144] The server's primary role is to collect user behavior information. This information includes web browsing history, application usage history, and purchase history, and is stored in a database. The server also uses sentiment analysis technology to obtain user emotional information. This emotional information is obtained using technologies such as text analysis, voice analysis, and facial expression analysis.

[0145] Next, the server integrates behavioral and emotional information and uses data analysis techniques to identify the user's interests. Based on the results of this analysis, the server utilizes a generative AI model to generate a customized document that includes expressions tailored to the user's emotional state. This document includes suggestions for products and services that match the user's interests and emotions.

[0146] The generated documents are provided electronically from the server to the user's terminal, allowing the user to view the information on their device. Physical printing is also possible if needed.

[0147] As a concrete example, consider a case where sentiment analysis reveals that a user's review on a smartphone app is very positive. In this case, the server determines that the user has a high level of interest in related products and suggests that information on related services and accessories be included in "My Catalog" for the user.

[0148] An example of a prompt generated by the AI ​​model is, "Consider the user's behavioral data and emotional state, and create a list of customized product suggestions related to electronic devices." In this way, valuable information is provided to the user.

[0149] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0150] Step 1:

[0151] The server collects user behavior information. The main inputs at this stage are operation history, search history, and purchase history obtained from the user's device. The server organizes this raw data, converts it into a unified format, and stores it in the database. This process prepares the basic information necessary for subsequent analysis.

[0152] Step 2:

[0153] The server uses sentiment analysis technology to acquire user emotional information. Inputs include text data, audio data, and image data generated by the user. The sentiment analysis algorithm analyzes this data to identify the user's emotional state. The output generates metadata about the emotional state (e.g., positive, negative, neutral).

[0154] Step 3:

[0155] The server integrates collected behavioral and emotional information and uses a data analysis engine to identify user interests. It performs correlation analysis and pattern recognition using behavioral and emotional information as input. The output is a list of topics and products that are presumed to be of interest to the user.

[0156] Step 4:

[0157] The server uses a generative AI model based on the user's interests identified in the previous step to generate a customized document. The input to this process includes metadata about identified interests and emotional states. Based on these inputs, the generative AI model automatically creates a document containing expressions and suggestions relevant to the user's situation. The output is a document containing content that matches the user's interests and emotions.

[0158] Step 5:

[0159] The server electronically delivers the generated customized document to the user's terminal. The input for this step is the generated and saved document. The server securely transmits the document to the user's terminal, where the user views this information. The output is a document accessible to the user, allowing them to obtain personalized information.

[0160] This series of steps allows users to receive personalized information tailored to their emotional state and enjoy a richer experience.

[0161] (Application Example 2)

[0162] 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".

[0163] Modern information delivery systems rely solely on user behavior data for customization, which limits their accuracy. Furthermore, the information provided often doesn't reflect the user's current emotional state, making it difficult to obtain information that truly interests them. This is particularly true in the advertising field, where there's a demand for optimal suggestions that respond to the user's immediate emotions.

[0164] 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.

[0165] In this invention, the server includes means for collecting user behavior data, means for analyzing user expressions to obtain emotional data, means for identifying the user's interests based on the behavior data and emotional data, means for selecting information relevant to the user based on the interests and emotional state, means for aggregating the selected information to generate customized expressions, and means for electronically providing the generated expressions. This enables the provision of more accurate and customized information by comprehensively considering the user's behavior and emotions.

[0166] "Users" refer to individuals or organizations targeted by this system, whose behavioral and emotional data are collected and analyzed by the system.

[0167] "Behavioral data" refers to information about a user's actions and habits, such as their application usage history, web browsing history, and location information.

[0168] "Expression" refers to the linguistic and non-linguistic elements that users exhibit, including voice, text, and facial expressions, and is a component used for emotion analysis.

[0169] "Emotional data" refers to data indicating emotional states obtained through user expressions, and is integrated with behavioral data using analytical methods.

[0170] "Interest" refers to events or information that the system estimates to be of interest to the user, based on behavioral and emotional data.

[0171] "Information" refers to the content of products, services, and other materials provided to users based on their interests and emotional states.

[0172] "Customized presentation" refers to information presentation and advertising formats that are tailored to the user's interests and emotional state, and are adapted to capture the user's attention.

[0173] "Means of providing information electronically" refers to technical methods that allow information to be transmitted to users via digital devices, and internet-based distribution is the most common method.

[0174] One possible embodiment of this invention is a system combining a server, a user terminal, and an analysis method. The server first collects behavioral data from the user's terminal. This data includes application usage history and web browsing history. In addition, a voice analysis system and facial recognition technology are used to analyze the user's expressions. Specific software options include "Google Cloud Speech-to-Text" and "Microsoft® Face API." These make it possible to obtain user emotion data.

[0175] The server uses machine learning platforms such as AWS® SageMaker to integrate collected behavioral and emotional data and identify user interests. Furthermore, it selects information based on these interests and emotional states. This selected information is then digitized and delivered to the user's device via the internet, often in the form of customized advertisements. For example, if a user is relaxing using a music app, advertisements for relaxation-related products and services will be appropriately suggested.

[0176] An example of a prompt statement is, "If the user's current emotional state is positive and they are watching content, what special suggestions should be made?" This prompt statement provides appropriate information to the generative AI model. Thus, this invention enables highly customized information provision that takes into account the user's behavior and emotions.

[0177] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0178] Step 1:

[0179] The server collects behavioral data from the user's device. Inputs include the user's app usage history and web browsing history, while output is the collected behavioral data. Specifically, it collects various operation logs from the user's device and sends them to the server in real time.

[0180] Step 2:

[0181] The server analyzes the user's expressions using a voice analysis system and facial recognition technology to acquire emotional data. The input is the user's voice and facial data, and the output is data indicating the user's emotional state. Specifically, it uses a microphone and camera to capture voice and video, and then analyzes this data to derive emotional data.

[0182] Step 3:

[0183] The server integrates collected behavioral and emotional data to identify interests. The input is behavioral and emotional data, and the output is the identified user interests. The server feeds this data into machine learning models such as AWS SageMaker to identify patterns of interest.

[0184] Step 4:

[0185] The server selects information relevant to the user based on identified interests and emotional states. The input is user interest and emotional data, and the output is the selected information. Prompt sentences are fed into an AI model to select appropriate advertisements and information.

[0186] Step 5:

[0187] The server generates a customized representation based on the selected information. The input is the selected information, and the output is the customized representation. Specifically, it personalizes the information appropriately and formats it into a display format.

[0188] Step 6:

[0189] The server electronically delivers the generated representation to the user's device via the internet. The input is the customized representation, and the output is the information displayed on the user's device. Specifically, information is delivered via email or in-app notifications.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] [Second Embodiment]

[0194] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0195] 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.

[0196] 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).

[0197] 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.

[0198] 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.

[0199] 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).

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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".

[0206] This invention is a system that utilizes user behavior data to enable personalized information delivery tailored to each user. The following forms are possible for implementing this system.

[0207] The server first collects user behavior data. This data includes the user's past internet search history, purchase history, and subscriber information. This makes it possible to understand what products and services the user is interested in.

[0208] Next, the server analyzes the collected behavioral data to identify the user's interests. This may involve using technologies such as machine learning and data mining. Based on the analysis results, the server selects the most relevant information for each user, aggregates that information, and generates customized documents.

[0209] The generated document is provided electronically to the user's device via the server. The user can view this document in digital format. If the user requests a printed copy, the server will print it on demand and initiate the process of mailing the physical document.

[0210] As a concrete example, suppose a user frequently searches for information about high-performance cameras on the network. The server analyzes this data and identifies that the user is interested in new smartphones with superior camera capabilities. Next, based on this information, the server selects information on smartphones with high camera performance and related pricing plans, and generates this as a customized "My Catalog." This catalog is then delivered to the user's device, and a printed version is also provided if needed. In this way, the user can quickly obtain the information that is most suitable for them, enabling them to efficiently purchase products or review their plans.

[0211] The following describes the processing flow.

[0212] Step 1:

[0213] The server collects user behavior data. Specifically, it obtains search history, purchase history, and subscriber information from affiliated databases and cookies, and stores this information in central data storage.

[0214] Step 2:

[0215] The server preprocesses the collected data. This includes imputing missing values ​​and normalizing the data to prepare it for easy analysis. If data anonymization is necessary, it is performed at this stage.

[0216] Step 3:

[0217] The server uses pre-processed data to identify user interests. Machine learning algorithms are then used to analyze search and purchase patterns and identify categories of products and services that the user is interested in.

[0218] Step 4:

[0219] The server selects information based on the user's interests. Based on the identified categories, it extracts relevant products, services, and pricing plans from the database and prioritizes them.

[0220] Step 5:

[0221] The server generates customized documents based on the selected information. Using a template engine, the documents are built as a user-optimized "My Catalog".

[0222] Step 6:

[0223] The server distributes generated documents electronically. Users can access their "My Catalog" via email or notifications on their devices, and they can view it in digital format.

[0224] Step 7:

[0225] If a user requests a printed copy, the server will arrange for printing on demand. The document will be physically mailed to the specified delivery address and delivered to the user.

[0226] (Example 1)

[0227] 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."

[0228] In today's world, the sheer volume of information makes it difficult for users to quickly obtain the information best suited to their needs. Solving this problem and providing appropriate information based on individual user interests is essential. Furthermore, in addition to digital formats, physical means of information delivery are also required as needed.

[0229] 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.

[0230] In this invention, the server includes means for collecting information about user behavior, means for analyzing the information to identify the user's interests, and means for integrating the selected information to generate personalized documents. This enables users to quickly and accurately receive information based on their interests.

[0231] "Information about user behavior" refers to data such as a user's search history, browsing history, purchase history, and contract information on the internet, and is data that indicates the user's interests and behavioral patterns.

[0232] "Methods for analyzing and identifying user interests" refers to the process of identifying user preferences and interests using machine learning models or data mining techniques on collected behavioral data.

[0233] "Means of selecting relevant information" refers to the process of extracting highly relevant information from an information base based on the user's identified interests and selecting the information necessary to provide to the user.

[0234] "Means of generating personalized documents" refers to a function that uses selected information, integrates it in a format suitable for each individual user, and creates documents that meet the user's interests.

[0235] "Means of providing to users in digital format" refers to a function that provides users with generated personalized documents in electronic format, enabling them to view them on their devices.

[0236] This invention is a system in which a server, a terminal, and a user work together to provide personalized information to the user. First, the server collects information about the user's behavior. This information includes the user's internet search history, purchase history, and contract information, which allows the server to infer the user's preferences and interests. A streaming platform such as Apache Kafka is used for information collection, receiving and storing data in real time.

[0237] Next, the server analyzes the collected data, building machine learning models using Python's scikit-learn and TensorFlow to identify user interests. This analysis makes it possible to extract products and services of interest based on user behavior patterns.

[0238] Next, the server selects relevant information based on the identified interests. This selected information is then integrated and generated as a personalized document for the user. The document is generated using LaTeX or HTML, providing a clear and well-organized format.

[0239] The generated documents are then sent digitally to the terminal, allowing the user to view the information on their device. If the user prefers a physical document, the server places a print order on demand and arranges for postal delivery. This process allows users to quickly receive customized information based on their interests, which can be helpful in product selection and contract review.

[0240] As a concrete example, if a user is interested in high-performance cameras, the server analyzes their history and generates a "My Catalog" that aggregates information on smartphones and related plans that match the user's interests. This catalog is then delivered to the user's device. An example of a prompt to the generating AI model would be, "Use the user's search history and purchase history to generate the most suitable product recommendation."

[0241] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0242] Step 1:

[0243] The server collects information about user behavior. At this stage, it gathers data from the internet, such as search history, purchase history, and visited websites. Using a streaming platform like Apache Kafka, it stores this data in a database in real time. The input to this process is user activity logs from the internet, and the output is user activity data recorded in the database.

[0244] Step 2:

[0245] The server analyzes collected behavioral data to identify user interests. It applies machine learning models using Python libraries such as scikit-learn and TensorFlow to generate user profiles based on the data. The input to this process is behavioral data retrieved from a database, and the output is profile information that details the user's interests.

[0246] Step 3:

[0247] The server selects relevant information based on the user's interests. Here, it uses the user's profile information to select relevant products and services from its information database. By calculating the degree of relevance between the database information and the profile, it extracts the most optimal recommendations. The input to this process is the generated user profile, and the output is a list of information relevant to the user.

[0248] Step 4:

[0249] The server integrates the selected information and generates personalized documents. Using LaTeX or HTML formatting, it formats the documents as user-specific catalogs. The input to this process is a list of selected information, and the output is a completed digital document.

[0250] Step 5:

[0251] The server delivers the generated document to the terminal. The document is transferred digitally using the HTTP protocol, and the user can view it through an application on the terminal. The input to this process is a personalized document, and the output is the information displayed on the user's terminal.

[0252] Step 6:

[0253] The server arranges on-demand printing in case a user requests a printed copy. Print jobs are sent to the printing facility via API, and the physical document is prepared for mailing to the user. The inputs to this process are a flag indicating the user wants to print and the personalized document; the output is the delivery of the printed physical document.

[0254] (Application Example 1)

[0255] 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."

[0256] Modern consumers are required to quickly acquire information that aligns with their interests and make appropriate purchasing decisions in a market offering a wide variety of goods and services. However, many consumers face the challenge of spending a lot of time searching for and filtering relevant information, making it difficult to have an efficient purchasing experience. Furthermore, insufficient information tailored to individual preferences can lead to decreased satisfaction after purchase.

[0257] 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.

[0258] In this invention, the server includes means for collecting user behavior data, means for identifying the user's interests based on the behavior data, means for selecting information relevant to the user based on the interests, means for aggregating the selected information and generating a customized data set, means for electronically providing the generated data set, and means for presenting the provided data set within a virtual store environment to support the user's purchasing activities. This enables consumers to obtain optimal information based on their interests and preferences, making efficient and satisfying purchasing decisions.

[0259] "User behavior data" is a general term for information that indicates consumer behavior, such as search history, purchase history, and browsing history performed by users on the internet and digital platforms.

[0260] "Means of identifying interests" refers to methods and technologies for analyzing collected user behavior data to infer specific categories or products that users are interested in.

[0261] "Means for selecting relevant information" refers to technologies that enable a process of selecting the most relevant product and service information for a user based on their identified interests.

[0262] "Means for generating data sets" refers to technologies that aggregate user-optimized information and compile it into a format that can be viewed as a digital format or visual media.

[0263] "Means of providing electronically" refers to technologies and methods for transmitting and displaying a generated data set on a user's device via the internet or digital communication means.

[0264] A "virtual store environment" refers to a digital platform that provides users with the experience of browsing and purchasing products in a virtual store space built online.

[0265] "Means of supporting purchasing activities" refer to methods and technologies that provide relevant information and suggestions to support users' decision-making during the process of considering a purchase.

[0266] The system for realizing this invention consists of a server, a user terminal, and a digital platform for building a virtual store environment. First, the server uses a Python program to collect user behavior data. This behavior data includes the user's online search history and purchase history. This allows the system to identify the user's interests.

[0267] Next, the server uses machine learning models such as TensorFlow to analyze the collected behavioral data and predict specific categories or products that the user might be interested in. Based on the analyzed data, it selects the information most relevant to the user. The selected information is compiled into a customized data set generated using Unity and provided to the user's device.

[0268] The user's device, particularly smartphones and VR headsets, receives the generated data set and presents it visually within the virtual store environment. This presentation allows users to intuitively browse products and make purchases. By utilizing Unity, the virtual store environment is updated in real time, providing information tailored to the products the user is interested in.

[0269] As a concrete example, an instruction such as "Create the most relevant suggestions based on the product categories the user has shown interest in. Example: Summer bags." can be input into the AI ​​model to present information tailored to the user. This allows the user to quickly obtain the information that is most suitable for them.

[0270] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0271] Step 1:

[0272] The server uses a Python program to collect user behavior data. The input is the user's activity log on digital platforms, and the output is the collected raw data. This process uses the Google Analytics API to obtain the pages the user viewed and the keywords they searched for.

[0273] Step 2:

[0274] The server analyzes the collected behavioral data using a machine learning model. The input is the raw data obtained in step 1, and the output is labeled data indicating the user's interests. TensorFlow is used to find hidden patterns in the data and infer the product categories that the user is interested in.

[0275] Step 3:

[0276] The server selects relevant information based on the analyzed data. The input is the labeled data from step 2, and the output is a list of product information that is highly relevant to the user. It retrieves information on the relevant products from the database and lists those that match the user's interests.

[0277] Step 4:

[0278] The server uses Unity to generate selected information as a customized data set. The input is a list of information from step 3, and the output is a visualized data set. Product information is built as 3D models and interactive content and packaged for the user.

[0279] Step 5:

[0280] The terminal receives the generated data set and presents it within the virtual store environment. The input is the visualized data set generated in step 4, and the output is an interactive shopping screen that the user can experience in real time. The terminal accepts user input for exploring products within the virtual store rendered by Unity.

[0281] Step 6:

[0282] Users select items of interest within a virtual store and prepare to make a purchase. Input is the product information displayed on the terminal, and output is data reflecting the user's purchase intention. Users then navigate the interface to view detailed product information and proceed with the purchase process.

[0283] Step 7:

[0284] The server inputs a prompt sentence into the generative AI model to obtain information that complements the user experience. The input is an instruction "Please create the most relevant proposal based on the product category that the user has shown interest in.", and the output is a customized proposal sentence created by the generative AI model. It provides added value to the user and assists in the purchase decision.

[0285] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0286] The present invention is a system that realizes more accurate customized information provision by combining an emotion engine in addition to the user's behavior data. In order to implement this system, the following forms are conceivable.

[0287] First, the server collects the user's behavior data and also obtains the user's emotion data by means of an emotion engine. This emotion data can be obtained by using methods such as text analysis, voice analysis, or facial expression analysis. As a result, it becomes possible to specifically grasp the user's current emotional state.

[0288] Next, the server integrates these data to identify the user's interests. By combining emotion data compared to ordinary behavior data, the user's intention can be captured more accurately. For example, by comparing the past search history with the current emotional state, products and services that are predicted to be of real interest to the user are selected.

[0289] After that, the server generates a customized document based on the selected information. This document takes into account the user's emotional state and incorporates expressions and proposals that match the emotion. For example, when a positive emotion is detected, product proposals may be made in a more positive tone.

[0290] The generated documents are delivered electronically from the server to the user's terminal. Users can access this information in digital format and, if necessary, receive physical copies via on-demand printing.

[0291] As a concrete example, consider a scenario where a user is entering a product review on a smartphone app, and sentiment analysis reveals that the review is very positive. In this case, the server determines that the user has a strong interest in the product and includes information on related accessories and services in "My Catalog," suggesting them to the user. This process enables the provision of information closely linked to the user's interests and emotions.

[0292] The following describes the processing flow.

[0293] Step 1:

[0294] The server collects user behavior data. This includes the process of obtaining and storing in a database the pages the user has viewed on a website, their online search history, and their past purchase history.

[0295] Step 2:

[0296] The server uses an emotion engine to acquire user emotion data. The emotion engine performs text and voice analysis to collect user reviews, feedback, or voice recordings, and analyzes their emotional state. For example, if there are many positive words in the reviews, it will be judged as having a positive emotion.

[0297] Step 3:

[0298] The server integrates and analyzes collected behavioral and emotional data. Machine learning models are used to clarify which products and services the user is interested in and what suggestions align with their current emotions. These analysis results are used to identify user interests.

[0299] Step 4:

[0300] The server selects personalized information based on the identified interests and emotional state of the user. This includes not only product features but also sales promotion messages and related products according to emotions. For example, if the user leaves an excited review for travel-related products, information including new travel products and special offers will be selected.

[0301] Step 5:

[0302] The server generates a customized document based on the selected information. In this process, a template is utilized and content and expressions according to emotions are incorporated. For positive emotions, a bright writing style and promotional expressions are used.

[0303] Step 6:

[0304] The server electronically provides the generated document to the user's terminal. The user can view this catalog on their device and, if necessary, request the issuance of a printed version. The server will carry out the on-demand printing procedure upon receiving this request and mail it.

[0305] (Example 2)

[0306] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0307] Modern information provision systems only present information based on the mere behavior data of users, so it is difficult to accurately capture the true interests and needs of users. Also, there is a problem that the user experience is restricted and the receptivity of information decreases because appropriate information provision according to the emotional state of the user is not carried out.

[0308] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following respective means.

[0309] In this invention, the server includes means for collecting user behavior information, means for acquiring user emotional information using emotion analysis technology, and means for generating customized documents that include expressions corresponding to the user's emotional state using a generative AI model. This makes it possible to provide personalized information that more accurately reflects the user's interests and emotions.

[0310] "User behavior information" refers to information such as operation history, search history, and purchase history that is generated when a user uses a device or service.

[0311] "Methods for identifying user interests" refer to technologies that analyze user behavior data to find topics and products that are likely to interest that user.

[0312] "Emotional analysis technology" is a technology that estimates a user's emotional state by analyzing data such as text, voice, or facial expressions obtained from the user.

[0313] "User emotional information" refers to information about the user's emotional state obtained using emotion analysis technology.

[0314] "Methods for selecting information" refer to technologies that select information deemed relevant to the user based on the user's behavioral and emotional information.

[0315] A "generative AI model" is an algorithm or framework that uses natural language processing technology to generate text and content that is tailored to the user's emotional state and interests.

[0316] "Means for generating customized documents" refers to technologies that create documents optimized for individual users by taking into account user behavioral and emotional information.

[0317] This invention relates to a system that provides personalized information using user behavioral and emotional information. Specifically, it is implemented using a server, a terminal, and a generative AI model.

[0318] The server's primary role is to collect user behavior information. This information includes web browsing history, application usage history, and purchase history, and is stored in a database. The server also uses sentiment analysis technology to obtain user emotional information. This emotional information is obtained using technologies such as text analysis, voice analysis, and facial expression analysis.

[0319] Next, the server integrates behavioral and emotional information and uses data analysis techniques to identify the user's interests. Based on the results of this analysis, the server utilizes a generative AI model to generate a customized document that includes expressions tailored to the user's emotional state. This document includes suggestions for products and services that match the user's interests and emotions.

[0320] The generated documents are provided electronically from the server to the user's terminal, allowing the user to view the information on their device. Physical printing is also possible if needed.

[0321] As a concrete example, consider a case where sentiment analysis reveals that a user's review on a smartphone app is very positive. In this case, the server determines that the user has a high level of interest in related products and suggests that information on related services and accessories be included in "My Catalog" for the user.

[0322] An example of a prompt generated by the AI ​​model is, "Consider the user's behavioral data and emotional state, and create a list of customized product suggestions related to electronic devices." In this way, valuable information is provided to the user.

[0323] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0324] Step 1:

[0325] The server collects user behavior information. The main inputs at this stage are operation history, search history, and purchase history obtained from the user's device. The server organizes this raw data, converts it into a unified format, and stores it in the database. This process prepares the basic information necessary for subsequent analysis.

[0326] Step 2:

[0327] The server uses sentiment analysis technology to acquire user emotional information. Inputs include text data, audio data, and image data generated by the user. The sentiment analysis algorithm analyzes this data to identify the user's emotional state. The output generates metadata about the emotional state (e.g., positive, negative, neutral).

[0328] Step 3:

[0329] The server integrates collected behavioral and emotional information and uses a data analysis engine to identify user interests. It performs correlation analysis and pattern recognition using behavioral and emotional information as input. The output is a list of topics and products that are presumed to be of interest to the user.

[0330] Step 4:

[0331] The server uses a generative AI model based on the user's interests identified in the previous step to generate a customized document. The input to this process includes metadata about identified interests and emotional states. Based on these inputs, the generative AI model automatically creates a document containing expressions and suggestions relevant to the user's situation. The output is a document containing content that matches the user's interests and emotions.

[0332] Step 5:

[0333] The server electronically delivers the generated customized document to the user's terminal. The input for this step is the generated and saved document. The server securely transmits the document to the user's terminal, where the user views this information. The output is a document accessible to the user, allowing them to obtain personalized information.

[0334] This series of steps allows users to receive personalized information tailored to their emotional state and enjoy a richer experience.

[0335] (Application Example 2)

[0336] 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."

[0337] Modern information delivery systems rely solely on user behavior data for customization, which limits their accuracy. Furthermore, the information provided often doesn't reflect the user's current emotional state, making it difficult to obtain information that truly interests them. This is particularly true in the advertising field, where there's a demand for optimal suggestions that respond to the user's immediate emotions.

[0338] 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.

[0339] In this invention, the server includes means for collecting user behavior data, means for analyzing user expressions to obtain emotional data, means for identifying the user's interests based on the behavior data and emotional data, means for selecting information relevant to the user based on the interests and emotional state, means for aggregating the selected information to generate customized expressions, and means for electronically providing the generated expressions. This enables the provision of more accurate and customized information by comprehensively considering the user's behavior and emotions.

[0340] "Users" refer to individuals or organizations targeted by this system, whose behavioral and emotional data are collected and analyzed by the system.

[0341] "Behavioral data" refers to information about a user's actions and habits, such as their application usage history, web browsing history, and location information.

[0342] "Expression" refers to the linguistic and non-linguistic elements that users exhibit, including voice, text, and facial expressions, and is a component used for emotion analysis.

[0343] "Emotional data" refers to data indicating emotional states obtained through user expressions, and is integrated with behavioral data using analytical methods.

[0344] "Interest" refers to events or information that the system estimates to be of interest to the user, based on behavioral and emotional data.

[0345] "Information" refers to the content of products, services, and other materials provided to users based on their interests and emotional states.

[0346] "Customized presentation" refers to information presentation and advertising formats that are tailored to the user's interests and emotional state, and are adapted to capture the user's attention.

[0347] "Means of providing information electronically" refers to technical methods that allow information to be transmitted to users via digital devices, and internet-based distribution is the most common method.

[0348] One possible embodiment of this invention is a system combining a server, a user terminal, and an analysis method. The server first collects behavioral data from the user's terminal. This data includes application usage history and web browsing history. In addition, a speech analysis system and facial recognition technology are used to analyze the user's expressions. Specific software options include "Google Cloud Speech-to-Text" and "Microsoft Face API." These make it possible to obtain user emotion data.

[0349] The server uses machine learning platforms such as AWS SageMaker to integrate collected behavioral and emotional data and identify user interests. Furthermore, it selects information based on these interests and emotional states. This selected information is then digitized and delivered to the user's device via the internet, in the form of customized advertisements. For example, if a user is relaxing using a music app, advertisements for relaxation-related products and services will be appropriately suggested.

[0350] An example of a prompt statement is, "If the user's current emotional state is positive and they are watching content, what special suggestions should be made?" This prompt statement provides appropriate information to the generative AI model. Thus, this invention enables highly customized information provision that takes into account the user's behavior and emotions.

[0351] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0352] Step 1:

[0353] The server collects behavioral data from the user's device. Inputs include the user's app usage history and web browsing history, while output is the collected behavioral data. Specifically, it collects various operation logs from the user's device and sends them to the server in real time.

[0354] Step 2:

[0355] The server analyzes the user's expressions using a voice analysis system and facial recognition technology to acquire emotional data. The input is the user's voice and facial data, and the output is data indicating the user's emotional state. Specifically, it uses a microphone and camera to capture voice and video, and then analyzes this data to derive emotional data.

[0356] Step 3:

[0357] The server integrates collected behavioral and emotional data to identify interests. The input is behavioral and emotional data, and the output is the identified user interests. The server feeds this data into machine learning models such as AWS SageMaker to identify patterns of interest.

[0358] Step 4:

[0359] The server selects information relevant to the user based on identified interests and emotional states. The input is user interest and emotional data, and the output is the selected information. Prompt sentences are fed into an AI model to select appropriate advertisements and information.

[0360] Step 5:

[0361] The server generates a customized representation based on the selected information. The input is the selected information, and the output is the customized representation. Specifically, it personalizes the information appropriately and formats it into a display format.

[0362] Step 6:

[0363] The server electronically delivers the generated representation to the user's device via the internet. The input is a customized representation, and the output is information displayed on the user's device. Specifically, information is delivered via email or in-app notifications.

[0364] 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.

[0365] 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.

[0366] 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.

[0367] [Third Embodiment]

[0368] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0369] 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.

[0370] 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).

[0371] 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.

[0372] 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.

[0373] 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).

[0374] 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.

[0375] 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.

[0376] 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.

[0377] 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.

[0378] 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.

[0379] 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".

[0380] This invention is a system that utilizes user behavior data to enable personalized information delivery tailored to each user. The following forms are possible for implementing this system.

[0381] The server first collects user behavior data. This data includes the user's past internet search history, purchase history, and subscriber information. This makes it possible to understand what products and services the user is interested in.

[0382] Next, the server analyzes the collected behavioral data to identify the user's interests. This may involve using technologies such as machine learning and data mining. Based on the analysis results, the server selects the most relevant information for each user, aggregates that information, and generates customized documents.

[0383] The generated document is provided electronically to the user's device via the server. The user can view this document in digital format. If the user requests a printed copy, the server will print it on demand and initiate the process of mailing the physical document.

[0384] As a concrete example, suppose a user frequently searches for information about high-performance cameras on the network. The server analyzes this data and identifies that the user is interested in new smartphones with superior camera capabilities. Next, based on this information, the server selects information on smartphones with high camera performance and related pricing plans, and generates this as a customized "My Catalog." This catalog is then delivered to the user's device, and a printed version is also provided if needed. In this way, the user can quickly obtain the information that is most suitable for them, enabling them to efficiently purchase products or review their plans.

[0385] The following describes the processing flow.

[0386] Step 1:

[0387] The server collects user behavior data. Specifically, it obtains search history, purchase history, and subscriber information from affiliated databases and cookies, and stores this information in central data storage.

[0388] Step 2:

[0389] The server preprocesses the collected data. This includes imputing missing values ​​and normalizing the data to prepare it for easy analysis. If data anonymization is necessary, it is performed at this stage.

[0390] Step 3:

[0391] The server uses pre-processed data to identify user interests. Machine learning algorithms are then used to analyze search and purchase patterns and identify categories of products and services that the user is interested in.

[0392] Step 4:

[0393] The server selects information based on the user's interests. Based on the identified categories, it extracts relevant products, services, and pricing plans from the database and prioritizes them.

[0394] Step 5:

[0395] The server generates customized documents based on the selected information. Using a template engine, the documents are built as a user-optimized "My Catalog".

[0396] Step 6:

[0397] The server distributes generated documents electronically. Users can access their "My Catalog" via email or notifications on their devices, and they can view it in digital format.

[0398] Step 7:

[0399] If a user requests a printed copy, the server will arrange for printing on demand. The document will be physically mailed to the specified delivery address and delivered to the user.

[0400] (Example 1)

[0401] 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."

[0402] In today's world, the sheer volume of information makes it difficult for users to quickly obtain the information best suited to their needs. Solving this problem and providing appropriate information based on individual user interests is essential. Furthermore, in addition to digital formats, physical means of information delivery are also required as needed.

[0403] 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.

[0404] In this invention, the server includes means for collecting information about user behavior, means for analyzing the information to identify the user's interests, and means for integrating the selected information to generate personalized documents. This enables users to quickly and accurately receive information based on their interests.

[0405] "Information about user behavior" refers to data such as a user's search history, browsing history, purchase history, and contract information on the internet, and is data that indicates the user's interests and behavioral patterns.

[0406] "Methods for analyzing and identifying user interests" refers to the process of identifying user preferences and interests using machine learning models or data mining techniques on collected behavioral data.

[0407] "Means of selecting relevant information" refers to the process of extracting highly relevant information from an information base based on the user's identified interests and selecting the information necessary to provide to the user.

[0408] "Means of generating personalized documents" refers to a function that uses selected information, integrates it in a format suitable for each individual user, and creates documents that meet the user's interests.

[0409] "Means of providing to users in digital format" refers to a function that provides users with generated personalized documents in electronic format, enabling them to view them on their devices.

[0410] This invention is a system in which a server, a terminal, and a user work together to provide personalized information to the user. First, the server collects information about the user's behavior. This information includes the user's internet search history, purchase history, and contract information, which allows the server to infer the user's preferences and interests. A streaming platform such as Apache Kafka is used for information collection, receiving and storing data in real time.

[0411] Next, the server analyzes the collected data, building machine learning models using Python's scikit-learn and TensorFlow to identify user interests. This analysis makes it possible to extract products and services of interest based on user behavior patterns.

[0412] Next, the server selects relevant information based on the identified interests. This selected information is then integrated and generated as a personalized document for the user. The document is generated using LaTeX or HTML, providing a clear and well-organized format.

[0413] The generated documents are then sent digitally to the terminal, allowing the user to view the information on their device. If the user prefers a physical document, the server places a print order on demand and arranges for postal delivery. This process allows users to quickly receive customized information based on their interests, which can be helpful in product selection and contract review.

[0414] As a concrete example, if a user is interested in high-performance cameras, the server analyzes their history and generates a "My Catalog" that aggregates information on smartphones and related plans that match the user's interests. This catalog is then delivered to the user's device. An example of a prompt to the generating AI model would be, "Use the user's search history and purchase history to generate the most suitable product recommendation."

[0415] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0416] Step 1:

[0417] The server collects information about user behavior. At this stage, it gathers data from the internet, such as search history, purchase history, and visited websites. Using a streaming platform like Apache Kafka, it stores this data in a database in real time. The input to this process is user activity logs from the internet, and the output is user activity data recorded in the database.

[0418] Step 2:

[0419] The server analyzes collected behavioral data to identify user interests. It applies machine learning models using Python libraries such as scikit-learn and TensorFlow to generate user profiles based on the data. The input to this process is behavioral data retrieved from a database, and the output is profile information that details the user's interests.

[0420] Step 3:

[0421] The server selects relevant information based on the user's interests. Here, it uses the user's profile information to select relevant products and services from its information database. By calculating the degree of relevance between the database information and the profile, it extracts the most optimal recommendations. The input to this process is the generated user profile, and the output is a list of information relevant to the user.

[0422] Step 4:

[0423] The server integrates the selected information and generates personalized documents. Using LaTeX or HTML formatting, it formats the documents as user-specific catalogs. The input to this process is a list of selected information, and the output is a completed digital document.

[0424] Step 5:

[0425] The server delivers the generated document to the terminal. The document is transferred digitally using the HTTP protocol, and the user can view it through an application on the terminal. The input to this process is a personalized document, and the output is the information displayed on the user's terminal.

[0426] Step 6:

[0427] The server arranges on-demand printing in case a user requests a printed copy. Print jobs are sent to the printing facility via API, and the physical document is prepared for mailing to the user. The inputs to this process are a flag indicating the user wants to print and the personalized document; the output is the delivery of the printed physical document.

[0428] (Application Example 1)

[0429] 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."

[0430] Modern consumers are required to quickly acquire information that aligns with their interests and make appropriate purchasing decisions in a market offering a wide variety of goods and services. However, many consumers face the challenge of spending a lot of time searching for and filtering relevant information, making it difficult to have an efficient purchasing experience. Furthermore, insufficient information tailored to individual preferences can lead to decreased satisfaction after purchase.

[0431] 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.

[0432] In this invention, the server includes means for collecting user behavior data, means for identifying the user's interests based on the behavior data, means for selecting information relevant to the user based on the interests, means for aggregating the selected information and generating a customized data set, means for electronically providing the generated data set, and means for presenting the provided data set within a virtual store environment to support the user's purchasing activities. This enables consumers to obtain optimal information based on their interests and preferences, making efficient and satisfying purchasing decisions.

[0433] "User behavior data" is a general term for information that indicates consumer behavior, such as search history, purchase history, and browsing history performed by users on the internet and digital platforms.

[0434] "Means of identifying interests" refers to methods and technologies for analyzing collected user behavior data to infer specific categories or products that users are interested in.

[0435] "Means for selecting relevant information" refers to technologies that enable a process of selecting the most relevant product and service information for a user based on their identified interests.

[0436] "Means for generating data sets" refers to technologies that aggregate user-optimized information and compile it into a format that can be viewed as a digital format or visual media.

[0437] "Means of providing electronically" refers to technologies and methods for transmitting and displaying a generated data set on a user's device via the internet or digital communication means.

[0438] A "virtual store environment" refers to a digital platform that provides users with the experience of browsing and purchasing products in a virtual store space built online.

[0439] "Means of supporting purchasing activities" refer to methods and technologies that provide relevant information and suggestions to support users' decision-making during the process of considering a purchase.

[0440] The system for realizing this invention consists of a server, a user terminal, and a digital platform for building a virtual store environment. First, the server uses a Python program to collect user behavior data. This behavior data includes the user's online search history and purchase history. This allows the system to identify the user's interests.

[0441] Next, the server uses machine learning models such as TensorFlow to analyze the collected behavioral data and predict specific categories or products that the user might be interested in. Based on the analyzed data, it selects the information most relevant to the user. The selected information is compiled into a customized data set generated using Unity and provided to the user's device.

[0442] The user's device, particularly smartphones and VR headsets, receives the generated data set and presents it visually within the virtual store environment. This presentation allows users to intuitively browse products and make purchases. By utilizing Unity, the virtual store environment is updated in real time, providing information tailored to the products the user is interested in.

[0443] As a concrete example, an instruction such as "Create the most relevant suggestions based on the product categories the user has shown interest in. Example: Summer bags." can be input into the AI ​​model to present information tailored to the user. This allows the user to quickly obtain the information that is most suitable for them.

[0444] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0445] Step 1:

[0446] The server uses a Python program to collect user behavior data. The input is the user's activity log on digital platforms, and the output is the collected raw data. This process uses the Google Analytics API to obtain the pages the user viewed and the keywords they searched for.

[0447] Step 2:

[0448] The server analyzes the collected behavioral data using a machine learning model. The input is the raw data obtained in step 1, and the output is labeled data indicating the user's interests. TensorFlow is used to find hidden patterns in the data and infer the product categories that the user is interested in.

[0449] Step 3:

[0450] The server selects relevant information based on the analyzed data. The input is the labeled data from step 2, and the output is a list of product information that is highly relevant to the user. It retrieves information on the relevant products from the database and lists those that match the user's interests.

[0451] Step 4:

[0452] The server uses Unity to generate selected information as a customized data set. The input is a list of information from step 3, and the output is a visualized data set. Product information is built as 3D models and interactive content and packaged for the user.

[0453] Step 5:

[0454] The terminal receives the generated data set and presents it within the virtual store environment. The input is the visualized data set generated in step 4, and the output is an interactive shopping screen that the user can experience in real time. The terminal accepts user input for exploring products within the virtual store rendered by Unity.

[0455] Step 6:

[0456] Users select items of interest within a virtual store and prepare to make a purchase. Input is the product information displayed on the terminal, and output is data reflecting the user's purchase intention. Users then navigate the interface to view detailed product information and proceed with the purchase process.

[0457] Step 7:

[0458] The server inputs prompt text into a generative AI model and retrieves information that complements the user experience. The input is an instruction to "create the most relevant suggestions based on the product categories the user has shown interest in," and the output is a customized suggestion text created by the generative AI model. This provides added value for the user and supports their purchasing decision.

[0459] 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.

[0460] This invention is a system that achieves more accurate and customized information delivery by combining user behavior data with an emotion engine. The following forms are possible for implementing this system.

[0461] The server first collects user behavior data and simultaneously obtains user emotional data using an emotion engine. This emotional data is obtained using methods such as text analysis, voice analysis, or facial expression analysis. This makes it possible to understand the user's current emotional state in detail.

[0462] Next, the server integrates this data to identify the user's interests. By combining emotional data with regular behavioral data, it is possible to capture the user's intentions more accurately. For example, past search history is compared with the current emotional state to select products and services that are predicted to truly interest the user.

[0463] The server then generates a customized document based on the selected information. This document takes into account the user's emotional state and incorporates expressions and suggestions that match that emotion. For example, if a positive emotion is detected, product suggestions may be presented in a more proactive tone.

[0464] The generated documents are delivered electronically from the server to the user's terminal. Users can access this information in digital format and, if necessary, receive physical copies via on-demand printing.

[0465] As a concrete example, consider a scenario where a user is entering a product review on a smartphone app, and sentiment analysis reveals that the review is very positive. In this case, the server determines that the user has a strong interest in the product and includes information on related accessories and services in "My Catalog," suggesting them to the user. This process enables the provision of information closely linked to the user's interests and emotions.

[0466] The following describes the processing flow.

[0467] Step 1:

[0468] The server collects user behavior data. This includes the process of obtaining and storing in a database the pages the user has viewed on a website, their online search history, and their past purchase history.

[0469] Step 2:

[0470] The server uses an emotion engine to acquire user emotion data. The emotion engine performs text and voice analysis to collect user reviews, feedback, or voice recordings, and analyzes their emotional state. For example, if there are many positive words in the reviews, it will be judged as having a positive emotion.

[0471] Step 3:

[0472] The server integrates and analyzes collected behavioral and emotional data. Machine learning models are used to clarify which products and services users are interested in and what suggestions align with their current emotions. These analysis results are used to identify user interests.

[0473] Step 4:

[0474] The server selects personalized information based on the user's identified interests and emotional state. This includes not only product features but also promotional messages and related products tailored to their emotions. For example, if a user leaves an enthusiastic review of a travel-related product, information including new travel products and special offers will be selected.

[0475] Step 5:

[0476] The server generates customized documents based on the selected information. This process utilizes templates and incorporates content and expressions tailored to specific emotions. Positive emotions are expressed using a cheerful writing style and encouraging language.

[0477] Step 6:

[0478] The server provides the generated documents electronically to the user's device. Users can view this catalog on their device and, if necessary, request a printed copy. The server then processes the on-demand printing and mails the printed copy.

[0479] (Example 2)

[0480] 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."

[0481] Modern information delivery systems often rely solely on user behavioral data to present information, making it difficult to accurately capture users' true interests and needs. Furthermore, the lack of appropriate information tailored to users' emotional states limits the user experience and reduces information receptivity.

[0482] 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.

[0483] In this invention, the server includes means for collecting user behavior information, means for acquiring user emotional information using emotion analysis technology, and means for generating customized documents that include expressions corresponding to the user's emotional state using a generative AI model. This makes it possible to provide personalized information that more accurately reflects the user's interests and emotions.

[0484] "User behavior information" refers to information such as operation history, search history, and purchase history that is generated when a user uses a device or service.

[0485] "Methods for identifying user interests" refer to technologies that analyze user behavior data to find topics and products that are likely to interest that user.

[0486] "Emotional analysis technology" is a technology that estimates a user's emotional state by analyzing data such as text, voice, or facial expressions obtained from the user.

[0487] "User emotional information" refers to information about the user's emotional state obtained using emotion analysis technology.

[0488] "Methods for selecting information" refer to technologies that select information deemed relevant to the user based on the user's behavioral and emotional information.

[0489] A "generative AI model" is an algorithm or framework that uses natural language processing technology to generate text and content that is tailored to the user's emotional state and interests.

[0490] "Means for generating customized documents" refers to technologies that create documents optimized for individual users by taking into account user behavioral and emotional information.

[0491] This invention relates to a system that provides personalized information using user behavioral and emotional information. Specifically, it is implemented using a server, a terminal, and a generative AI model.

[0492] The server's primary role is to collect user behavior information. This information includes web browsing history, application usage history, and purchase history, and is stored in a database. The server also uses sentiment analysis technology to obtain user emotional information. This emotional information is obtained using technologies such as text analysis, voice analysis, and facial expression analysis.

[0493] Next, the server integrates behavioral and emotional information and uses data analysis techniques to identify the user's interests. Based on the results of this analysis, the server utilizes a generative AI model to generate a customized document that includes expressions tailored to the user's emotional state. This document includes suggestions for products and services that match the user's interests and emotions.

[0494] The generated documents are provided electronically from the server to the user's terminal, allowing the user to view the information on their device. Physical printing is also possible if needed.

[0495] As a concrete example, consider a case where sentiment analysis reveals that a user's review on a smartphone app is very positive. In this case, the server determines that the user has a high level of interest in related products and suggests that information on related services and accessories be included in "My Catalog" for the user.

[0496] An example of a prompt generated by the AI ​​model is, "Consider the user's behavioral data and emotional state, and create a list of customized product suggestions related to electronic devices." In this way, valuable information is provided to the user.

[0497] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0498] Step 1:

[0499] The server collects user behavior information. The main inputs at this stage are operation history, search history, and purchase history obtained from the user's device. The server organizes this raw data, converts it into a unified format, and stores it in the database. This process prepares the basic information necessary for subsequent analysis.

[0500] Step 2:

[0501] The server uses sentiment analysis technology to acquire user emotional information. Inputs include text data, audio data, and image data generated by the user. The sentiment analysis algorithm analyzes this data to identify the user's emotional state. The output generates metadata about the emotional state (e.g., positive, negative, neutral).

[0502] Step 3:

[0503] The server integrates collected behavioral and emotional information and uses a data analysis engine to identify user interests. It performs correlation analysis and pattern recognition using behavioral and emotional information as input. The output is a list of topics and products that are presumed to be of interest to the user.

[0504] Step 4:

[0505] The server uses a generative AI model based on the user's interests identified in the previous step to generate a customized document. The input to this process includes metadata about identified interests and emotional states. Based on these inputs, the generative AI model automatically creates a document containing expressions and suggestions relevant to the user's situation. The output is a document containing content that matches the user's interests and emotions.

[0506] Step 5:

[0507] The server electronically delivers the generated customized document to the user's terminal. The input for this step is the generated and saved document. The server securely transmits the document to the user's terminal, where the user views this information. The output is a document accessible to the user, allowing them to obtain personalized information.

[0508] This series of steps allows users to receive personalized information tailored to their emotional state and enjoy a richer experience.

[0509] (Application Example 2)

[0510] 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."

[0511] Modern information delivery systems rely solely on user behavior data for customization, which limits their accuracy. Furthermore, the information provided often doesn't reflect the user's current emotional state, making it difficult to obtain information that truly interests them. This is particularly true in the advertising field, where there's a demand for optimal suggestions that respond to the user's immediate emotions.

[0512] 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.

[0513] In this invention, the server includes means for collecting user behavior data, means for analyzing user expressions to obtain emotional data, means for identifying the user's interests based on the behavior data and emotional data, means for selecting information relevant to the user based on the interests and emotional state, means for aggregating the selected information to generate customized expressions, and means for electronically providing the generated expressions. This enables the provision of more accurate and customized information by comprehensively considering the user's behavior and emotions.

[0514] "Users" refer to individuals or organizations targeted by this system, whose behavioral and emotional data are collected and analyzed by the system.

[0515] "Behavioral data" refers to information about a user's actions and habits, such as their application usage history, web browsing history, and location information.

[0516] "Expression" refers to the linguistic and non-linguistic elements that users exhibit, including voice, text, and facial expressions, and is a component used for emotion analysis.

[0517] "Emotional data" refers to data indicating emotional states obtained through user expressions, and is integrated with behavioral data using analytical methods.

[0518] "Interest" refers to events or information that the system estimates to be of interest to the user, based on behavioral and emotional data.

[0519] "Information" refers to the content of products, services, and other materials provided to users based on their interests and emotional states.

[0520] "Customized presentation" refers to information presentation and advertising formats that are tailored to the user's interests and emotional state, and are adapted to capture the user's attention.

[0521] "Means of providing information electronically" refers to technical methods that allow information to be transmitted to users via digital devices, and internet-based distribution is the most common method.

[0522] One possible embodiment of this invention is a system combining a server, a user terminal, and an analysis method. The server first collects behavioral data from the user's terminal. This data includes application usage history and web browsing history. In addition, a speech analysis system and facial recognition technology are used to analyze the user's expressions. Specific software options include "Google Cloud Speech-to-Text" and "Microsoft Face API." These make it possible to obtain user emotion data.

[0523] The server uses machine learning platforms such as AWS SageMaker to integrate collected behavioral and emotional data and identify user interests. Furthermore, it selects information based on these interests and emotional states. This selected information is then digitized and delivered to the user's device via the internet, in the form of customized advertisements. For example, if a user is relaxing using a music app, advertisements for relaxation-related products and services will be appropriately suggested.

[0524] An example of a prompt statement is, "If the user's current emotional state is positive and they are watching content, what special suggestions should be made?" This prompt statement provides appropriate information to the generative AI model. Thus, this invention enables highly customized information provision that takes into account the user's behavior and emotions.

[0525] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0526] Step 1:

[0527] The server collects behavioral data from the user's device. Inputs include the user's app usage history and web browsing history, while output is the collected behavioral data. Specifically, it collects various operation logs from the user's device and sends them to the server in real time.

[0528] Step 2:

[0529] The server analyzes the user's expressions using a voice analysis system and facial recognition technology to acquire emotional data. The input is the user's voice and facial data, and the output is data indicating the user's emotional state. Specifically, it uses a microphone and camera to capture voice and video, and then analyzes this data to derive emotional data.

[0530] Step 3:

[0531] The server integrates collected behavioral and emotional data to identify interests. The input is behavioral and emotional data, and the output is the identified user interests. The server feeds this data into machine learning models such as AWS SageMaker to identify patterns of interest.

[0532] Step 4:

[0533] The server selects information relevant to the user based on identified interests and emotional states. The input is user interest and emotional data, and the output is the selected information. Prompt sentences are fed into an AI model to select appropriate advertisements and information.

[0534] Step 5:

[0535] The server generates a customized representation based on the selected information. The input is the selected information, and the output is the customized representation. Specifically, it personalizes the information appropriately and formats it into a display format.

[0536] Step 6:

[0537] The server electronically delivers the generated representation to the user's device via the internet. The input is a customized representation, and the output is information displayed on the user's device. Specifically, information is delivered via email or in-app notifications.

[0538] 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.

[0539] 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.

[0540] 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.

[0541] [Fourth Embodiment]

[0542] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0543] 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.

[0544] 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).

[0545] 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.

[0546] 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.

[0547] 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).

[0548] 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.

[0549] 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.

[0550] 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.

[0551] 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.

[0552] 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.

[0553] 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.

[0554] 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".

[0555] This invention is a system that utilizes user behavior data to enable personalized information delivery tailored to each user. The following forms are possible for implementing this system.

[0556] The server first collects user behavior data. This data includes the user's past internet search history, purchase history, and subscriber information. This makes it possible to understand what products and services the user is interested in.

[0557] Next, the server analyzes the collected behavioral data to identify the user's interests. This may involve using technologies such as machine learning and data mining. Based on the analysis results, the server selects the most relevant information for each user, aggregates that information, and generates customized documents.

[0558] The generated document is provided electronically to the user's device via the server. The user can view this document in digital format. If the user requests a printed copy, the server will print it on demand and initiate the process of mailing the physical document.

[0559] As a concrete example, suppose a user frequently searches for information about high-performance cameras on the network. The server analyzes this data and identifies that the user is interested in new smartphones with superior camera capabilities. Next, based on this information, the server selects information on smartphones with high camera performance and related pricing plans, and generates this as a customized "My Catalog." This catalog is then delivered to the user's device, and a printed version is also provided if needed. In this way, the user can quickly obtain the information that is most suitable for them, enabling them to efficiently purchase products or review their plans.

[0560] The following describes the processing flow.

[0561] Step 1:

[0562] The server collects user behavior data. Specifically, it obtains search history, purchase history, and subscriber information from affiliated databases and cookies, and stores this information in central data storage.

[0563] Step 2:

[0564] The server preprocesses the collected data. This includes imputing missing values ​​and normalizing the data to prepare it for easy analysis. If data anonymization is necessary, it is performed at this stage.

[0565] Step 3:

[0566] The server uses pre-processed data to identify user interests. Machine learning algorithms are then used to analyze search and purchase patterns and identify categories of products and services that the user is interested in.

[0567] Step 4:

[0568] The server selects information based on the user's interests. Based on the identified categories, it extracts relevant products, services, and pricing plans from the database and prioritizes them.

[0569] Step 5:

[0570] The server generates customized documents based on the selected information. Using a template engine, the documents are built as a user-optimized "My Catalog".

[0571] Step 6:

[0572] The server distributes generated documents electronically. Users can access their "My Catalog" via email or notifications on their devices, and they can view it in digital format.

[0573] Step 7:

[0574] If a user requests a printed copy, the server will arrange for printing on demand. The document will be physically mailed to the specified delivery address and delivered to the user.

[0575] (Example 1)

[0576] 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".

[0577] In today's world, the sheer volume of information makes it difficult for users to quickly obtain the information best suited to their needs. Solving this problem and providing appropriate information based on individual user interests is essential. Furthermore, in addition to digital formats, physical means of information delivery are also required as needed.

[0578] 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.

[0579] In this invention, the server includes means for collecting information about user behavior, means for analyzing the information to identify the user's interests, and means for integrating the selected information to generate personalized documents. This enables users to quickly and accurately receive information based on their interests.

[0580] "Information about user behavior" refers to data such as a user's search history, browsing history, purchase history, and contract information on the internet, and is data that indicates the user's interests and behavioral patterns.

[0581] "Methods for analyzing and identifying user interests" refers to the process of identifying user preferences and interests using machine learning models or data mining techniques on collected behavioral data.

[0582] "Means of selecting relevant information" refers to the process of extracting highly relevant information from an information base based on the user's identified interests and selecting the information necessary to provide to the user.

[0583] "Means of generating personalized documents" refers to a function that uses selected information, integrates it in a format suitable for each individual user, and creates documents that meet the user's interests.

[0584] "Means of providing to users in digital format" refers to a function that provides users with generated personalized documents in electronic format, enabling them to view them on their devices.

[0585] This invention is a system in which a server, a terminal, and a user work together to provide personalized information to the user. First, the server collects information about the user's behavior. This information includes the user's internet search history, purchase history, and contract information, which allows the server to infer the user's preferences and interests. A streaming platform such as Apache Kafka is used for information collection, receiving and storing data in real time.

[0586] Next, the server analyzes the collected data, building machine learning models using Python's scikit-learn and TensorFlow to identify user interests. This analysis makes it possible to extract products and services of interest based on user behavior patterns.

[0587] Next, the server selects relevant information based on the identified interests. This selected information is then integrated and generated as a personalized document for the user. The document is generated using LaTeX or HTML, providing a clear and well-organized format.

[0588] The generated documents are then sent digitally to the terminal, allowing the user to view the information on their device. If the user prefers a physical document, the server places a print order on demand and arranges for postal delivery. This process allows users to quickly receive customized information based on their interests, which can be helpful in product selection and contract review.

[0589] As a concrete example, if a user is interested in high-performance cameras, the server analyzes their history and generates a "My Catalog" that aggregates information on smartphones and related plans that match the user's interests. This catalog is then delivered to the user's device. An example of a prompt to the generating AI model would be, "Use the user's search history and purchase history to generate the most suitable product recommendation."

[0590] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0591] Step 1:

[0592] The server collects information about user behavior. At this stage, it gathers data from the internet, such as search history, purchase history, and visited websites. Using a streaming platform like Apache Kafka, it stores this data in a database in real time. The input to this process is user activity logs from the internet, and the output is user activity data recorded in the database.

[0593] Step 2:

[0594] The server analyzes collected behavioral data to identify user interests. It applies machine learning models using Python libraries such as scikit-learn and TensorFlow to generate user profiles based on the data. The input to this process is behavioral data retrieved from a database, and the output is profile information that details the user's interests.

[0595] Step 3:

[0596] The server selects relevant information based on the user's interests. Here, it uses the user's profile information to select relevant products and services from its information database. By calculating the degree of relevance between the database information and the profile, it extracts the most optimal recommendations. The input to this process is the generated user profile, and the output is a list of information relevant to the user.

[0597] Step 4:

[0598] The server integrates the selected information and generates personalized documents. Using LaTeX or HTML formatting, it formats the documents as user-specific catalogs. The input to this process is a list of selected information, and the output is a completed digital document.

[0599] Step 5:

[0600] The server delivers the generated document to the terminal. The document is transferred digitally using the HTTP protocol, and the user can view it through an application on the terminal. The input to this process is a personalized document, and the output is the information displayed on the user's terminal.

[0601] Step 6:

[0602] The server arranges on-demand printing in case a user requests a printed copy. Print jobs are sent to the printing facility via API, and the physical document is prepared for mailing to the user. The inputs to this process are a flag indicating the user wants to print and the personalized document; the output is the delivery of the printed physical document.

[0603] (Application Example 1)

[0604] 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".

[0605] Modern consumers are required to quickly acquire information that aligns with their interests and make appropriate purchasing decisions in a market offering a wide variety of goods and services. However, many consumers face the challenge of spending a lot of time searching for and filtering relevant information, making it difficult to have an efficient purchasing experience. Furthermore, insufficient information tailored to individual preferences can lead to decreased satisfaction after purchase.

[0606] 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.

[0607] In this invention, the server includes means for collecting user behavior data, means for identifying the user's interests based on the behavior data, means for selecting information relevant to the user based on the interests, means for aggregating the selected information and generating a customized data set, means for electronically providing the generated data set, and means for presenting the provided data set within a virtual store environment to support the user's purchasing activities. This enables consumers to obtain optimal information based on their interests and preferences, making efficient and satisfying purchasing decisions.

[0608] "User behavior data" is a general term for information that indicates consumer behavior, such as search history, purchase history, and browsing history performed by users on the internet and digital platforms.

[0609] "Means of identifying interests" refers to methods and technologies for analyzing collected user behavior data to infer specific categories or products that users are interested in.

[0610] "Means for selecting relevant information" refers to technologies that enable a process of selecting the most relevant product and service information for a user based on their identified interests.

[0611] "Means for generating data sets" refers to technologies that aggregate user-optimized information and compile it into a format that can be viewed as a digital format or visual media.

[0612] "Means of providing electronically" refers to technologies and methods for transmitting and displaying a generated data set on a user's device via the internet or digital communication means.

[0613] A "virtual store environment" refers to a digital platform that provides users with the experience of browsing and purchasing products in a virtual store space built online.

[0614] "Means of supporting purchasing activities" refer to methods and technologies that provide relevant information and suggestions to support users' decision-making during the process of considering a purchase.

[0615] The system for realizing this invention consists of a server, a user terminal, and a digital platform for building a virtual store environment. First, the server uses a Python program to collect user behavior data. This behavior data includes the user's online search history and purchase history. This allows the system to identify the user's interests.

[0616] Next, the server uses machine learning models such as TensorFlow to analyze the collected behavioral data and predict specific categories or products that the user might be interested in. Based on the analyzed data, it selects the information most relevant to the user. The selected information is compiled into a customized data set generated using Unity and provided to the user's device.

[0617] The user's device, particularly smartphones and VR headsets, receives the generated data set and presents it visually within the virtual store environment. This presentation allows users to intuitively browse products and make purchases. By utilizing Unity, the virtual store environment is updated in real time, providing information tailored to the products the user is interested in.

[0618] As a concrete example, an instruction such as "Create the most relevant suggestions based on the product categories the user has shown interest in. Example: Summer bags." can be input into the AI ​​model to present information tailored to the user. This allows the user to quickly obtain the information that is most suitable for them.

[0619] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0620] Step 1:

[0621] The server uses a Python program to collect user behavior data. The input is the user's activity log on digital platforms, and the output is the collected raw data. This process uses the Google Analytics API to obtain the pages the user viewed and the keywords they searched for.

[0622] Step 2:

[0623] The server analyzes the collected behavioral data using a machine learning model. The input is the raw data obtained in step 1, and the output is labeled data indicating the user's interests. TensorFlow is used to find hidden patterns in the data and infer the product categories that the user is interested in.

[0624] Step 3:

[0625] The server selects relevant information based on the analyzed data. The input is the labeled data from step 2, and the output is a list of product information that is highly relevant to the user. It retrieves information on the relevant products from the database and lists those that match the user's interests.

[0626] Step 4:

[0627] The server uses Unity to generate selected information as a customized data set. The input is a list of information from step 3, and the output is a visualized data set. Product information is built as 3D models and interactive content and packaged for the user.

[0628] Step 5:

[0629] The terminal receives the generated data set and presents it within the virtual store environment. The input is the visualized data set generated in step 4, and the output is an interactive shopping screen that the user can experience in real time. The terminal accepts user input for exploring products within the virtual store rendered by Unity.

[0630] Step 6:

[0631] Users select items of interest within a virtual store and prepare to make a purchase. Input is the product information displayed on the terminal, and output is data reflecting the user's purchase intention. Users then navigate the interface to view detailed product information and proceed with the purchase process.

[0632] Step 7:

[0633] The server inputs prompt text into a generative AI model and retrieves information that complements the user experience. The input is an instruction to "create the most relevant suggestions based on the product categories the user has shown interest in," and the output is a customized suggestion text created by the generative AI model. This provides added value for the user and supports their purchasing decision.

[0634] 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.

[0635] This invention is a system that achieves more accurate and customized information delivery by combining user behavior data with an emotion engine. The following forms are possible for implementing this system.

[0636] The server first collects user behavior data and simultaneously obtains user emotional data using an emotion engine. This emotional data is obtained using methods such as text analysis, voice analysis, or facial expression analysis. This makes it possible to understand the user's current emotional state in detail.

[0637] Next, the server integrates this data to identify the user's interests. By combining emotional data with regular behavioral data, it is possible to capture the user's intentions more accurately. For example, past search history is compared with the user's current emotional state to select products and services that are predicted to be of genuine interest to the user.

[0638] The server then generates a customized document based on the selected information. This document takes into account the user's emotional state and incorporates expressions and suggestions that match that emotion. For example, if a positive emotion is detected, product suggestions may be presented in a more proactive tone.

[0639] The generated documents are delivered electronically from the server to the user's terminal. Users can access this information in digital format and, if necessary, receive physical copies via on-demand printing.

[0640] As a concrete example, consider a scenario where a user is entering a product review on a smartphone app, and sentiment analysis reveals that the review is very positive. In this case, the server determines that the user has a strong interest in the product and includes information on related accessories and services in "My Catalog," suggesting them to the user. This process enables the provision of information closely linked to the user's interests and emotions.

[0641] The following describes the processing flow.

[0642] Step 1:

[0643] The server collects user behavior data. This includes the process of obtaining and storing in a database the pages the user has viewed on a website, their online search history, and their past purchase history.

[0644] Step 2:

[0645] The server uses an emotion engine to acquire user emotion data. The emotion engine performs text and voice analysis to collect user reviews, feedback, or voice recordings, and analyzes their emotional state. For example, if there are many positive words in the reviews, it will be judged as having a positive emotion.

[0646] Step 3:

[0647] The server integrates and analyzes collected behavioral and emotional data. Machine learning models are used to clarify which products and services users are interested in and what suggestions align with their current emotions. These analysis results are used to identify user interests.

[0648] Step 4:

[0649] The server selects personalized information based on the user's identified interests and emotional state. This includes not only product features but also promotional messages and related products tailored to their emotions. For example, if a user leaves an enthusiastic review of a travel-related product, information including new travel products and special offers will be selected.

[0650] Step 5:

[0651] The server generates customized documents based on the selected information. This process utilizes templates and incorporates content and expressions tailored to specific emotions. Positive emotions are expressed using a cheerful writing style and encouraging language.

[0652] Step 6:

[0653] The server provides the generated documents electronically to the user's device. Users can view this catalog on their device and, if necessary, request a printed copy. The server then processes the on-demand printing and mails the printed copy.

[0654] (Example 2)

[0655] 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".

[0656] Modern information delivery systems often rely solely on user behavioral data to present information, making it difficult to accurately capture users' true interests and needs. Furthermore, the lack of appropriate information tailored to users' emotional states limits the user experience and reduces information receptivity.

[0657] 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.

[0658] In this invention, the server includes means for collecting user behavior information, means for acquiring user emotional information using emotion analysis technology, and means for generating customized documents that include expressions corresponding to the user's emotional state using a generative AI model. This makes it possible to provide personalized information that more accurately reflects the user's interests and emotions.

[0659] "User behavior information" refers to information such as operation history, search history, and purchase history that is generated when a user uses a device or service.

[0660] "Methods for identifying user interests" refer to technologies that analyze user behavior data to find topics and products that are likely to interest that user.

[0661] "Emotional analysis technology" is a technology that estimates a user's emotional state by analyzing data such as text, voice, or facial expressions obtained from the user.

[0662] "User emotional information" refers to information about the user's emotional state obtained using emotion analysis technology.

[0663] "Methods for selecting information" refer to technologies that select information deemed relevant to the user based on the user's behavioral and emotional information.

[0664] A "generative AI model" is an algorithm or framework that uses natural language processing technology to generate text and content that is tailored to the user's emotional state and interests.

[0665] "Means for generating customized documents" refers to technologies that create documents optimized for individual users by taking into account user behavioral and emotional information.

[0666] This invention relates to a system that provides personalized information using user behavioral and emotional information. Specifically, it is implemented using a server, a terminal, and a generative AI model.

[0667] The server's primary role is to collect user behavior information. This information includes web browsing history, application usage history, and purchase history, and is stored in a database. The server also uses sentiment analysis technology to obtain user emotional information. This emotional information is obtained using technologies such as text analysis, voice analysis, and facial expression analysis.

[0668] Next, the server integrates behavioral and emotional information and uses data analysis techniques to identify the user's interests. Based on the results of this analysis, the server utilizes a generative AI model to generate a customized document that includes expressions tailored to the user's emotional state. This document includes suggestions for products and services that match the user's interests and emotions.

[0669] The generated documents are provided electronically from the server to the user's terminal, allowing the user to view the information on their device. Physical printing is also possible if needed.

[0670] As a concrete example, consider a case where sentiment analysis reveals that a user's review on a smartphone app is very positive. In this case, the server determines that the user has a high level of interest in related products and suggests that information on related services and accessories be included in "My Catalog" for the user.

[0671] An example of a prompt generated by the AI ​​model is, "Consider the user's behavioral data and emotional state, and create a list of customized product suggestions related to electronic devices." In this way, valuable information is provided to the user.

[0672] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0673] Step 1:

[0674] The server collects user behavior information. The main inputs at this stage are operation history, search history, and purchase history obtained from the user's device. The server organizes this raw data, converts it into a unified format, and stores it in the database. This process prepares the basic information necessary for subsequent analysis.

[0675] Step 2:

[0676] The server uses sentiment analysis technology to acquire user emotional information. Inputs include text data, audio data, and image data generated by the user. The sentiment analysis algorithm analyzes this data to identify the user's emotional state. The output generates metadata about the emotional state (e.g., positive, negative, neutral).

[0677] Step 3:

[0678] The server integrates collected behavioral and emotional information and uses a data analysis engine to identify user interests. It performs correlation analysis and pattern recognition using behavioral and emotional information as input. The output is a list of topics and products that are presumed to be of interest to the user.

[0679] Step 4:

[0680] The server uses a generative AI model based on the user's interests identified in the previous step to generate a customized document. The input to this process includes metadata about identified interests and emotional states. Based on these inputs, the generative AI model automatically creates a document containing expressions and suggestions relevant to the user's situation. The output is a document containing content that matches the user's interests and emotions.

[0681] Step 5:

[0682] The server electronically delivers the generated customized document to the user's terminal. The input for this step is the generated and saved document. The server securely transmits the document to the user's terminal, where the user views this information. The output is a document accessible to the user, allowing them to obtain personalized information.

[0683] This series of steps allows users to receive personalized information tailored to their emotional state and enjoy a richer experience.

[0684] (Application Example 2)

[0685] 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".

[0686] Modern information delivery systems rely solely on user behavior data for customization, which limits their accuracy. Furthermore, the information provided often doesn't reflect the user's current emotional state, making it difficult to obtain information that truly interests them. This is particularly true in the advertising field, where there's a demand for optimal suggestions that respond to the user's immediate emotions.

[0687] 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.

[0688] In this invention, the server includes means for collecting user behavior data, means for analyzing user expressions to obtain emotional data, means for identifying the user's interests based on the behavior data and emotional data, means for selecting information relevant to the user based on the interests and emotional state, means for aggregating the selected information to generate customized expressions, and means for electronically providing the generated expressions. This enables the provision of more accurate and customized information by comprehensively considering the user's behavior and emotions.

[0689] "Users" refer to individuals or organizations targeted by this system, whose behavioral and emotional data are collected and analyzed by the system.

[0690] "Behavioral data" refers to information about a user's actions and habits, such as their application usage history, web browsing history, and location information.

[0691] "Expression" refers to the linguistic and non-linguistic elements that users exhibit, including voice, text, and facial expressions, and is a component used for emotion analysis.

[0692] "Emotional data" refers to data indicating emotional states obtained through user expressions, and is integrated with behavioral data using analytical methods.

[0693] "Interest" refers to events or information that the system estimates to be of interest to the user, based on behavioral and emotional data.

[0694] "Information" refers to the content of products, services, and other materials provided to users based on their interests and emotional states.

[0695] "Customized presentation" refers to information presentation and advertising formats that are tailored to the user's interests and emotional state, and are adapted to capture the user's attention.

[0696] "Means of providing information electronically" refers to technical methods that allow information to be transmitted to users via digital devices, and internet-based distribution is the most common method.

[0697] One possible embodiment of this invention is a system combining a server, a user terminal, and an analysis method. The server first collects behavioral data from the user's terminal. This data includes application usage history and web browsing history. In addition, a speech analysis system and facial recognition technology are used to analyze the user's expressions. Specific software options include "Google Cloud Speech-to-Text" and "Microsoft Face API." These make it possible to obtain user emotion data.

[0698] The server uses machine learning platforms such as AWS SageMaker to integrate collected behavioral and emotional data and identify user interests. Furthermore, it selects information based on these interests and emotional states. This selected information is then digitized and delivered to the user's device via the internet, in the form of customized advertisements. For example, if a user is relaxing using a music app, advertisements for relaxation-related products and services will be appropriately suggested.

[0699] An example of a prompt statement is, "If the user's current emotional state is positive and they are watching content, what special suggestions should be made?" This prompt statement provides appropriate information to the generative AI model. Thus, this invention enables highly customized information provision that takes into account the user's behavior and emotions.

[0700] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0701] Step 1:

[0702] The server collects behavioral data from the user's device. Inputs include the user's app usage history and web browsing history, while output is the collected behavioral data. Specifically, it collects various operation logs from the user's device and sends them to the server in real time.

[0703] Step 2:

[0704] The server analyzes the user's expressions using a voice analysis system and facial recognition technology to acquire emotional data. The input is the user's voice and facial data, and the output is data indicating the user's emotional state. Specifically, it uses a microphone and camera to capture voice and video, and then analyzes this data to derive emotional data.

[0705] Step 3:

[0706] The server integrates collected behavioral and emotional data to identify interests. The input is behavioral and emotional data, and the output is the identified user interests. The server feeds this data into machine learning models such as AWS SageMaker to identify patterns of interest.

[0707] Step 4:

[0708] The server selects information relevant to the user based on identified interests and emotional states. The input is user interest and emotional data, and the output is the selected information. Prompt sentences are fed into an AI model to select appropriate advertisements and information.

[0709] Step 5:

[0710] The server generates a customized representation based on the selected information. The input is the selected information, and the output is the customized representation. Specifically, it personalizes the information appropriately and formats it into a display format.

[0711] Step 6:

[0712] The server electronically delivers the generated representation to the user's device via the internet. The input is a customized representation, and the output is information displayed on the user's device. Specifically, information is delivered via email or in-app notifications.

[0713] 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.

[0714] 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.

[0715] 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.

[0716] 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.

[0717] 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. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, 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.

[0718] 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.

[0719] 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.

[0720] 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.

[0721] 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."

[0722] 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.

[0723] 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.

[0724] 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.

[0725] 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.

[0726] 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.

[0727] 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.

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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.

[0734] The following is further disclosed regarding the embodiments described above.

[0735] (Claim 1)

[0736] Means for collecting user behavior data,

[0737] A means for identifying user interests based on the aforementioned behavioral data,

[0738] A means for selecting information relevant to the user based on the aforementioned interests,

[0739] A means of aggregating selected information and generating a customized document,

[0740] Means for providing the generated documents electronically,

[0741] A system that includes this.

[0742] (Claim 2)

[0743] The system according to claim 1, which prints and physically provides the generated documents.

[0744] (Claim 3)

[0745] The system according to claim 1, which selects information based on the user's interests, taking into consideration the user's contract information.

[0746] "Example 1"

[0747] (Claim 1)

[0748] Means for collecting information about user behavior,

[0749] A means for analyzing the aforementioned information to identify the user's interests,

[0750] A means for selecting relevant information based on the user's interests,

[0751] A means of integrating selected information and generating personalized documents,

[0752] A means of providing the generated document to the user in digital format,

[0753] An information processing system that includes this.

[0754] (Claim 2)

[0755] The information processing system according to claim 1, which prints and physically provides the generated document.

[0756] (Claim 3)

[0757] The information processing system according to claim 1, which selects information based on the user's interests, taking into consideration information related to the user's contract.

[0758] "Application Example 1"

[0759] (Claim 1)

[0760] Means for collecting user behavior data,

[0761] A means for identifying user interests based on the aforementioned behavioral data,

[0762] A means for selecting information relevant to the user based on the aforementioned interests,

[0763] A means for aggregating selected information and generating a customized data set,

[0764] A means of providing the generated data set electronically,

[0765] A means of presenting the aforementioned data set within a virtual store environment and supporting the user's purchasing activities,

[0766] A system that includes this.

[0767] (Claim 2)

[0768] The system according to claim 1, which visually presents the generated data set and provides optimized information in response to user operations.

[0769] (Claim 3)

[0770] The system according to claim 1, which selects information based on the user's interests, taking into consideration the user's purchase history information.

[0771] "Example 2 of combining an emotion engine"

[0772] (Claim 1)

[0773] Means for collecting user behavior information,

[0774] A means for identifying the user's interests based on the aforementioned behavioral information,

[0775] A means of obtaining user emotional information using emotion analysis technology,

[0776] A means for integrating and analyzing the aforementioned behavioral information and emotional information, and selecting information relevant to the user,

[0777] A means for generating customized documents that include expressions corresponding to the user's emotional state using a generative AI model,

[0778] A means of providing the generated document on an electronic terminal,

[0779] A system that includes this.

[0780] (Claim 2)

[0781] The system according to claim 1, which prints and physically provides the generated documents.

[0782] (Claim 3)

[0783] The system according to claim 1, which selects information based on the user's interests, taking into consideration the user's contract information.

[0784] "Application example 2 of combining emotional engines"

[0785] (Claim 1)

[0786] Means for collecting user behavior data,

[0787] A means of analyzing user expressions to obtain emotional data,

[0788] A means for identifying the user's interests based on the aforementioned behavioral data and emotional data,

[0789] A means for selecting information relevant to the user based on the aforementioned interests and emotional state,

[0790] A means of aggregating selected information and generating a customized expression,

[0791] Means for providing the generated representation electronically,

[0792] A system that includes this.

[0793] (Claim 2)

[0794] The system according to claim 1, which prints and physically provides the generated representation.

[0795] (Claim 3)

[0796] The system according to claim 1, which selects information based on the user's interests and emotional state, taking into consideration the user's contract information. [Explanation of Symbols]

[0797] 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 for collecting user behavior data, A means for identifying user interests based on the aforementioned behavioral data, A means for selecting information relevant to the user based on the aforementioned interests, A means of aggregating selected information and generating a customized document, Means for providing the generated documents electronically, A system that includes this.

2. The system according to claim 1, which prints and physically provides the generated documents.

3. The system according to claim 1, which selects information based on the user's interests, taking into consideration the user's contract information.

Images