system

Abstract

We provide the system. [Solution] A means for inputting the user's basic information, Means for collecting users' past behavioral data, A means of analyzing collected behavioral data to identify user preference patterns, A means for automatically generating customized content based on preference patterns, A means of delivering the generated content to the user, A means of receiving user feedback and updating preference data, A means of generating new customized content based on updated preference data and delivering it to the user again, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance 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] In the modern business environment, the needs and preferences of corporate customers are diverse and volatile. However, with conventional marketing methods, it has been difficult to accurately grasp these diverse preferences and provide optimal content to customers at appropriate times. As a result, feedback and behavioral data from customers cannot be effectively utilized, often leading to missed new business opportunities. To solve this problem, there is a need for a system that analyzes the preferences of corporate customers and provides customized content.

Means for Solving the Problems

[0005] This invention provides a system that takes user basic information as input, collects past user behavior data, and analyzes the collected data to identify user preference patterns. Furthermore, it automatically generates customized content based on preference patterns, delivers the generated content to the user, receives user feedback, and updates the preference data. By generating new customized content based on the updated preference data and delivering it to the user again, it is possible to meet the diverse needs of corporate clients and uncover potential business opportunities.

[0006] Specifically, the system solves the aforementioned problems by providing a system that includes means for inputting basic user information, means for collecting past user behavior data, means for analyzing the collected behavior data to identify preference patterns, means for automatically generating customized content based on preference patterns, means for delivering the generated content to the user, means for receiving user feedback and updating preference data, and means for generating new customized content based on the updated preference data and delivering it to the user again.

[0007] "User basic information" refers to fundamental information used to identify a company, such as the company name, industry, contact person's name, and contact information for corporate customers.

[0008] "Behavioral data" refers to information about a user's actions, such as their past purchase history, website browsing history, and feedback on the content they have been provided.

[0009] "Preference patterns" refer to characteristics such as a user's areas of interest and preferences, and their purchasing tendencies, which are revealed by analyzing behavioral data.

[0010] "Customized content" refers to information that includes specific information and product information based on the user's preference patterns, and is optimized for individual users.

[0011] "Automated generation" refers to the process of generating content using algorithms or programs without human intervention.

[0012] "Distribution" refers to the process of sending generated content to users via email, web portals, or other means.

[0013] "Feedback" refers to information such as reactions, evaluations, and requests for additional content provided by users.

[0014] "Preference data" refers to data about user characteristics and interests that is updated based on user preference patterns and feedback.

[0015] "Demand forecasting" is the process of predicting products and services that users are likely to need in the future, based on feedback and preference data. [Brief explanation of the drawing]

[0016] [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]It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0018] First, the language used in the following description will be explained.

[0019] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0021] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention is a system that uncovers potential demand by providing customized content tailored to the preferences of corporate clients and delivering messages to target customers accordingly. This system mainly consists of a server, user terminals, and users.

[0038] First, initial user registration takes place within this system. The terminal inputs the user's (corporate customer's) basic information (company name, industry, contact person's name, contact information, etc.), and the server saves this information to the database. The server assigns a unique identifier to the user information and creates a profile for the new user.

[0039] Next, the server collects data on the user's past behavior. This behavioral data includes the user's past purchase history, website browsing history, and feedback on the content provided. The server stores this data in a database and analyzes it using machine learning algorithms. Based on the results of this analysis, the server identifies each user's preference patterns. For example, it might detect that a user is interested in cloud services or security software.

[0040] After identifying user preference patterns, the server automatically generates customized content based on these patterns. This content may include product information and service announcements that are likely to interest the user, and may also utilize specialized marketing materials. The server optimizes the timing of content delivery, planning delivery times that do not interfere with the user's work.

[0041] The generated content is sent from the server to the device. The device receives the content and notifies the user. The user reviews the content and provides feedback. This feedback may include whether the content was useful or if there were any new areas of interest. The user's feedback is then sent back to the server via the device.

[0042] The server updates user preference data based on the feedback received. Based on the updated preference data, new customized content is generated again. For example, if a user starts to show interest in AI-related solutions, the server generates and delivers content that includes the latest AI-related information.

[0043] By repeating this cycle, the server can always maintain the latest user preference data and provide highly accurate customized content. This makes it possible to meet the diverse needs of corporate clients and avoid missing potential business opportunities.

[0044] Specific example

[0045] For example, let's assume a corporate client A has a deep interest in IT-related products. After the user completes initial registration, the server collects and analyzes A's past purchase data and website browsing history, detecting that A is interested in "cloud services" and "security software." Based on this, the server automatically generates customized content, including relevant product information and the latest white papers on cloud services, and sends it to the device at the optimal delivery time.

[0046] Company A receives the content and provides feedback on it. For example, if the feedback includes information that they are also interested in AI-related solutions, the server generates new customized content related to AI solutions and delivers it to Company A again. Through this continuous cycle, the system can respond promptly to the changing needs of corporate customers and uncover new business opportunities.

[0047] The following describes the processing flow.

[0048] Step 1:

[0049] The terminal inputs the corporate customer's basic information (company name, industry, contact person, contact information, etc.). The user (corporate customer) then uses the terminal to register the necessary information.

[0050] Step 2:

[0051] The server saves basic information received from the terminal to the database. The server assigns a unique identifier (user ID) to the user information and creates a new user profile.

[0052] Step 3:

[0053] The server collects data on the user's past behavior. This behavioral data includes the user's purchase history, website browsing history, and feedback on previously provided content.

[0054] Step 4:

[0055] The server stores the collected behavioral data in a database. The accumulated data serves as material for analyzing user behavioral trends.

[0056] Step 5:

[0057] The server uses machine learning algorithms to analyze collected behavioral data and identify user preference patterns (areas of interest, product categories, etc.). For example, it can detect whether a user has a high interest in IT-related products.

[0058] Step 6:

[0059] The server automatically generates customized content (product information, service guides, white papers, etc.) based on identified preference patterns. The generated content is optimized for the user's areas of interest.

[0060] Step 7:

[0061] The server plans the timing of content delivery and selects a time that does not interfere with the user's work. It then develops an optimal delivery schedule.

[0062] Step 8:

[0063] The server sends the generated customized content to the device. The device receives the content and notifies the user. The user receives the notification and checks the content.

[0064] Step 9:

[0065] Users provide feedback on the content they are given. This feedback includes whether the content was useful, what new areas of interest they discovered, and so on.

[0066] Step 10:

[0067] The device sends user feedback to the server. The server receives the feedback and updates its database.

[0068] Step 11:

[0069] Based on the feedback received by the server, user preference data is updated, and the latest preference patterns are re-evaluated. This allows for the response to newly emerging areas of interest and changes in interests.

[0070] Step 12:

[0071] The server regenerates new customized content based on updated preference data. For example, if a user has started to show interest in AI-related solutions, it will create content that includes the latest information on AI.

[0072] Step 13:

[0073] The server sends the regenerated customized content to the device, the device receives the content and notifies the user again. The user reviews the new content and provides further feedback as needed.

[0074] Through this series of steps, the system can flexibly respond to the diverse needs of users and continuously discover new business opportunities.

[0075] (Example 1)

[0076] 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."

[0077] Traditional marketing systems for corporate clients have struggled to accurately understand individual customer preferences and interests and provide customized content based on those preferences. Furthermore, optimizing delivery timing and collecting and incorporating feedback were inefficient. There is a growing need for a system that can quickly respond to changes in user interests.

[0078] 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.

[0079] In this invention, the server includes means for inputting the user's basic information, means for collecting the user's past behavioral data, means for analyzing the collected behavioral data and identifying the user's preference patterns, means for automatically generating customized content based on the preference patterns, means for delivering the generated content to the user, means for receiving feedback from the user and updating the preference data, means for generating new customized content based on the updated preference data and delivering it to the user again, means for optimizing the delivery timing, and means for notifying the user using a terminal. This enables the provision of highly accurate customized content tailored to the user's individual preferences and allows for a rapid response to changes in interests.

[0080] "Means for inputting basic user information" refers to devices or software used to input and collect initial information about corporate customers, such as company name, industry, contact person's name, and contact information.

[0081] "Means of collecting users' past behavioral data" refers to devices or software used to collect data on past behavior, such as corporate customers' purchase history, website browsing history, and feedback on provided content.

[0082] "Means of analyzing collected behavioral data to identify user preference patterns" refers to machine learning algorithms and data analysis tools used to analyze collected data and identify the interests and concerns of corporate clients.

[0083] "Means for automatically generating customized content based on preference patterns" refers to devices or software that automatically create product information and service guides that are likely to be of interest to corporate customers, according to identified preference patterns.

[0084] "Means of delivering generated content to users" refers to devices or software used to deliver generated customized content to corporate customers.

[0085] "Means for receiving user feedback and updating preference data" refers to devices or software for collecting reactions and opinions on content from corporate customers and updating preference data based on that.

[0086] "Means for generating and redistributing new customized content to users based on updated preference data" refers to devices or software for creating new customized content based on the latest preference data and redistributing it to corporate customers.

[0087] "Means for optimizing delivery timing" refers to devices or software that deliver content at the optimal time to avoid disrupting the business operations of corporate clients.

[0088] "Means of notifying users using a device" refers to devices or software used to notify corporate customers that new content has been delivered via their devices.

[0089] This invention is a system that uncovers potential demand by providing customized content tailored to the preferences of corporate clients and delivering messages to target specific customer segments. This system mainly consists of a server, user terminals, and users.

[0090] First, the user completes initial registration in this system. The user uses a terminal to access the initial registration screen. The terminal prompts the user to enter basic information (company name, industry, contact person's name, contact information, etc.), and the user enters this information. The terminal sends the collected information to the server, and the server stores the received information in a database. The server assigns a unique identifier and creates a profile for the new user.

[0091] Next, the server collects and analyzes the user's past behavioral data. This behavioral data includes the user's past purchase history, website browsing history, and feedback on the content provided. The server stores this data in a database and performs analysis using machine learning algorithms. This analysis allows the server to identify each user's preference patterns. For example, it might detect that a user is interested in cloud services or security software.

[0092] After identifying user preference patterns, the server automatically generates customized content. This content includes product information and service announcements likely to interest the user, and in some cases, specialized marketing materials. Furthermore, the server optimizes delivery timing, scheduling delivery to avoid disrupting the user's work.

[0093] The generated content is sent from the server to the device. The device receives the content and notifies the user. The user reviews the content and provides feedback. This feedback may include whether the content was useful or if they discovered any new areas of interest. The user's feedback is then sent back to the server via the device.

[0094] Based on the feedback received by the server, the user's preference data is updated. Based on the updated preference data, new customized content is generated again. For example, if a user starts to show interest in AI-related solutions, the server generates content including the latest AI-related information and delivers it to the user again.

[0095] By repeating this cycle, the server constantly maintains the latest user preference data and provides highly accurate customized content. This makes it possible to meet the diverse needs of corporate clients and avoid missing potential business opportunities.

[0096] Specific example

[0097] For example, let's assume a corporate client A has a deep interest in IT-related products. After the user completes initial registration, the server collects and analyzes A's past purchase data and website browsing history, detecting that A is interested in "cloud services" and "security software." Based on this, the server automatically generates customized content, including relevant product information and the latest white papers on cloud services, and sends it to the device at the optimal delivery time.

[0098] Company A receives the content and provides feedback on it. For example, if the feedback includes information that they are also interested in AI-related solutions, the server generates new customized content related to AI solutions and delivers it to Company A again. Through this continuous cycle, the system can respond promptly to the changing needs of corporate customers and uncover new business opportunities.

[0099] Examples of input prompts for a generative AI model

[0100] "If a user is detected as being interested in cloud services, generate customized content that includes relevant product information and service introductions. Additionally, if a new trend emerges showing interest in AI-related solutions, add corresponding content."

[0101] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0102] System program processing flow

[0103] Step 1: Initial Registration

[0104] The user accesses the initial registration screen using their device.

[0105] The terminal prompts the user to enter basic information (company name, industry, contact person's name, contact information, etc.).

[0106] Input data: Company name, industry, contact person's name, contact information.

[0107] The terminal receives the basic information entered by the user, organizes the data, and sends it to the server.

[0108] The server saves the received information to the database, assigns a unique identifier, and creates a profile for the new user.

[0109] Output data: Basic information and a unique identifier stored in the database.

[0110] Step 2: Collecting behavioral data

[0111] The server periodically collects data on the user's past behavior from multiple data sources.

[0112] Data collected: Past purchase history, website browsing history, and feedback on the content provided.

[0113] The server organizes the behavioral data and stores it in a database.

[0114] Output data: Behavioral data stored in the database.

[0115] Step 3: Behavioral Data Analysis

[0116] The server retrieves behavioral data from the database and performs analysis using machine learning algorithms.

[0117] Input data: Behavioral data stored in the database.

[0118] The server identifies user preference patterns based on the collected data.

[0119] Specific actions: Identify an interest in cloud services and security software.

[0120] Output data: User preference patterns.

[0121] Step 4: Generating customized content

[0122] The server automatically generates customized content based on identified preference patterns.

[0123] Input data: User preference patterns.

[0124] The server creates content using a generation AI model.

[0125] The generated content will include product information and service announcements that are likely to be of interest.

[0126] Output data: The generated customized content.

[0127] Step 5: Optimizing delivery timing

[0128] The server calculates the timing for delivering the generated content.

[0129] Input data: Data related to the user's work schedule and time slots.

[0130] The server calculates the optimal delivery timing and creates a delivery plan.

[0131] Specific action: Set the delivery time to avoid interfering with work.

[0132] Output data: Distribution plan.

[0133] Step 6: Content Distribution

[0134] The server sends the generated customized content to the terminal.

[0135] Input data: Generated customized content, delivery plan.

[0136] The device notifies the user of the content it has received.

[0137] Output data: User review history of content.

[0138] Step 7: Gathering Feedback

[0139] The user reviews the content they receive and provides feedback.

[0140] Input data: Customized content.

[0141] Specific action: Inputting feedback.

[0142] The user sends feedback to the server via their device.

[0143] Output data: Feedback information.

[0144] Step 8: Update preference data

[0145] The server analyzes the feedback it receives and updates the user preference data.

[0146] Input data: Feedback information.

[0147] Specific action: Update preference data.

[0148] Output data: Updated preference data.

[0149] Step 9: Generate and distribute new customized content.

[0150] The server regenerates new customized content based on the updated preference data.

[0151] Input data: Updated preference data.

[0152] The server uses a generated AI model to create and redistribute new content.

[0153] Specific actions: Create new content based on the previous broadcast and feedback.

[0154] Output data: New customized content.

[0155] (Application Example 1)

[0156] 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."

[0157] To meet the diverse needs of corporate clients and avoid missing potential business opportunities, it is crucial to provide customized content to each client in a timely manner. However, conventional systems have struggled to accurately analyze user preference patterns and deliver content at the optimal time. Furthermore, there have been insufficient methods for effectively utilizing user feedback to reflect new preferences.

[0158] 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.

[0159] In this invention, the server includes means for inputting the user's basic information, means for collecting the user's past behavioral data, means for analyzing the collected behavioral data and identifying the user's preference patterns, means for automatically generating customized content based on the preference patterns, means for delivering the generated content to the user, means for receiving feedback from the user and updating the preference data, means for generating new customized content based on the updated preference data and delivering it to the user again, means for analyzing and learning data using machine learning algorithms, and means for planning and executing the optimal content delivery timing. This makes it possible to respond immediately to the changing needs of corporate customers and discover new business opportunities.

[0160] "Means for entering basic user information" refers to system elements for entering initial registration information such as the company name, industry, contact person's name, and contact information of corporate customers.

[0161] "Means for collecting users' past behavioral data" refers to system elements for collecting data such as corporate customers' purchase history, website browsing history, and feedback on provided content.

[0162] "Means for analyzing collected behavioral data and identifying user preference patterns" refers to algorithms and system elements for analyzing collected data and identifying the interests and concerns of individual corporate customers.

[0163] "Means for automatically generating customized content based on preference patterns" refers to system elements for generating product information and service guides that are likely to be of interest to corporate customers, based on identified preference patterns.

[0164] "Means for delivering generated content to users" refers to system elements for delivering generated customized content to corporate customers at the appropriate time.

[0165] "Means for receiving user feedback and updating preference data" refers to system elements for collecting feedback from corporate customers and updating preference data based on that feedback.

[0166] "A means of generating new customized content based on updated preference data and redistributing it to users" refers to a system element for generating new customized content based on updated preference data and redistributing it to corporate customers.

[0167] "Means of analyzing and learning from data using machine learning algorithms" refers to system elements that use machine learning algorithms to analyze and learn from data.

[0168] "Means for planning and executing the optimal content delivery timing" refers to system elements for planning and executing the delivery of customized content at the optimal time that does not interfere with the business operations of corporate clients.

[0169] The system implementing this invention provides customized content to corporate clients and uncovers potential business opportunities. The system mainly consists of the following components:

[0170] System Configuration

[0171] 1. User Registration Method

[0172] The server provides a user registration mechanism for corporate customers to enter basic information such as company name, industry, contact person's name, and contact details. This basic information is entered via an electronic form and stored in a database.

[0173] 2. Data Collection Methods

[0174] The server collects past purchase history, website browsing history, and feedback data on the content provided to corporate customers. This data is collected via an omnichannel integration tool and stored in a database.

[0175] 3. Data Analysis Methods

[0176] The server analyzes the collected data using machine learning algorithms (such as Python's scikit-learn or TENSORFLOW®) to identify user preference patterns. Based on these identified preference patterns, it infers the product categories that the user is interested in.

[0177] 4. Content Generation Methods

[0178] The server generates customized content based on identified preference patterns. This content includes product information and service announcements that are likely to be of interest to corporate customers. The content is automatically generated using a generation AI model.

[0179] 5. Content distribution methods

[0180] The generated content is delivered to corporate clients at the optimal time. This includes using notification systems designed to prevent clients from interrupting their work, for example.

[0181] 6. Methods for collecting feedback

[0182] The server collects customer feedback (such as whether the content was useful or if they discovered any new areas of interest). This feedback information is then stored in the database.

[0183] 7. Data update and regeneration means

[0184] The server updates user preference data based on collected feedback, and then generates and delivers customized content again. This cycle is repeated automatically by the system.

[0185] 8. Optimal delivery timing planning method

[0186] The server plans and executes the optimal delivery timing to avoid disrupting the business operations of corporate clients. This ensures that information is provided without impairing the client's operational efficiency.

[0187] Specific examples and prompt statements

[0188] For example, if a corporate client has a strong interest in IT-related products, after the user completes initial registration, the server collects and analyzes the client's past purchase history and website browsing history. The server identifies that this client is interested in "cloud services" and "security software." Based on this, it automatically generates customized content, including relevant product information and the latest white papers on cloud services, and sends it to the terminal at the optimal delivery time.

[0189] Example of a prompt:

[0190] User ID 12345 has shown a strong interest in cloud services and security software, and has recently become interested in AI solutions as well. Based on this information, please create customized marketing materials on the latest AI solutions and distribute them at the optimal time.

[0191] In this way, the system can respond immediately to the changing needs of corporate clients and uncover new business opportunities.

[0192] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0193] Step 1:

[0194] Entering basic user information

[0195] The server provides a form for corporate clients to input basic information such as company name, industry, contact person's name, and contact details. When a user enters this information using a terminal, the data is sent to the server and stored in the database. The input data includes company name, industry, contact person's name, and contact details, while the output is the user's basic information stored in the database.

[0196] Step 2:

[0197] Collection of past behavioral data

[0198] After the user enters basic information, the server collects the corporate customer's past purchase history, website browsing history, and feedback on the content provided. This data is collected using an omnichannel integration tool and stored in a database. Past behavioral data is obtained as input, and the collected data is stored in the database for analysis.

[0199] Step 3:

[0200] Analysis of collected data

[0201] The server uses machine learning algorithms (such as Python's scikit-learn or TensorFlow) to analyze past behavioral data stored in the database. This identifies user preference patterns. The collected behavioral data is used as input, and the output is the identification of preference patterns. Specifically, the process involves data preprocessing, feature extraction, and model application.

[0202] Step 4:

[0203] Generating customized content

[0204] The server automatically generates customized content using a generative AI model based on identified preference patterns. This includes product information and service guides that corporate customers are likely to be interested in. Preference patterns are obtained as input, and customized content is generated as output. Specifically, this involves text generation and content assembly.

[0205] Step 5:

[0206] Content distribution

[0207] The generated customized content is delivered to corporate customers by the server at the optimal time. A notification system is used for delivery, allowing users to view the content on their devices. The generated content is the input, and the output is delivered to the corporate customer's device. Specifically, the delivery schedule is set and messages are sent.

[0208] Step 6:

[0209] Gathering feedback

[0210] Users provide feedback on the provided content. This feedback is sent back to the server and stored in the database. Feedback data is received as input and stored in the database as output. Specifically, the process involves receiving feedback from users and saving it to the database.

[0211] Step 7:

[0212] Data update and regeneration

[0213] The server updates user preference data based on collected feedback and generates customized content again based on that. The updated preference data is taken as input, and new customized content is generated as output. Specifically, the process involves updating data, reanalyzing it, and generating new content.

[0214] Step 8:

[0215] Planning the optimal delivery timing

[0216] The server plans and executes the optimal content delivery timing to avoid disrupting the business operations of corporate clients. It receives client business information and generated content as input, and outputs an optimized delivery schedule. Specifically, it performs analysis of the business calendar and plans the delivery timing.

[0217] 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.

[0218] This invention is a system that uncovers potential demand by providing customized content tailored to the preferences and emotions of corporate clients and delivering messages to target specific customers. This system mainly consists of a server, user terminals, users, and an emotion engine.

[0219] First, initial user registration takes place within this system. The terminal inputs the user's (corporate customer's) basic information, and the server stores this information in a database. The server assigns a unique identifier to the user information and creates a profile for the new user. The user's basic information includes company name, industry, contact person's name, and contact information.

[0220] Next, the server collects data on the user's past behavior. This behavioral data includes the user's purchase history, website browsing history, and feedback on the content provided. The server stores this data in a database and uses machine learning algorithms to analyze it and identify each user's preference patterns. For example, it can determine whether a user is interested in cloud services or security software.

[0221] Furthermore, the server uses an emotion engine to recognize the user's emotions and collect emotion data. The emotion engine identifies the user's instantaneous emotional state by analyzing the feedback provided by the user and biometric information recorded when viewing content (e.g., facial expressions and tone of voice). This allows the server to complement the user's preference data with emotion data, building more accurate preference patterns.

[0222] Based on identified preference patterns and emotional data, the server automatically generates customized content. This content includes product and service information relevant to the user's interests, and the most appropriate presentation style is selected based on the emotional data. For example, if the user is excited, a positive and energetic message will be generated.

[0223] Next, the server optimizes the delivery timing and plans content delivery for times that do not disrupt the user's work. The generated customized content is sent from the server to the terminal. The terminal receives the content and notifies the user. The system is used when the user receives the notification and checks the content.

[0224] When a user provides feedback on the content they are given, their device sends that feedback to the server. This feedback includes whether the content was helpful and any new areas of interest they discovered. The server updates its database based on the received feedback and uses an emotion engine to evaluate the user's emotional state at the time of feedback. This data is then used to update the preference data again.

[0225] Based on updated preference data and new sentiment data, the server generates and delivers newly customized content to the user. For example, if a user becomes interested in AI-related solutions, the server will generate and deliver content that includes the latest information on AI.

[0226] Through this series of processing cycles, the system can flexibly respond to changes in user preferences and emotions, and by continuously understanding the diverse needs of corporate clients, it can quickly uncover new business opportunities.

[0227] Specific example

[0228] For example, let's assume a corporate client A has a deep interest in IT-related products. The user registers, and the server collects and analyzes past purchase data and website browsing history, revealing that company A is interested in "cloud services" and "security software." Simultaneously, an emotion engine analyzes the provided feedback and biometric information, identifying that the person in charge at company A has positive feelings towards these products.

[0229] Based on this, the server generates customized content, including relevant product information and white papers on the latest cloud services. This content is presented in a positive and energetic tone, and a distribution plan is formulated for optimal timing. Company A receives the content and provides feedback and biometric information. For example, if the feedback includes information such as "we are also interested in AI-related solutions," the server regenerates new customized content and delivers it to Company A again. Through this continuous cycle, the system can respond promptly to Company A's changing needs and continuously uncover new business opportunities.

[0230] The following describes the processing flow.

[0231] Step 1:

[0232] The terminal inputs the corporate customer's basic information. The user (corporate customer) uses the terminal to input basic information such as company name, industry, contact person's name, and contact information.

[0233] Step 2:

[0234] The server saves the entered basic information to the database. The server assigns a unique identifier (user ID) to the user information and creates a profile for the new user.

[0235] Step 3:

[0236] The server collects data on the user's past behavior. This behavioral data includes the user's purchase history, website browsing history, and feedback on the content provided.

[0237] Step 4:

[0238] The server stores the collected behavioral data in a database. This data accumulation allows for the maintenance of a detailed history of the user's activities.

[0239] Step 5:

[0240] The server uses machine learning algorithms to analyze collected behavioral data and identify user preference patterns. For example, it can detect an interest in cloud services or security software based on past purchase history.

[0241] Step 6:

[0242] The server uses an emotion engine to analyze feedback and biometric information (such as facial expressions and tone of voice) collected from the user to obtain emotional data. For example, it measures positive reactions and the degree of excitement.

[0243] Step 7:

[0244] The server combines emotional data and preference patterns to update the user profile. This enhances the user's detailed preference patterns.

[0245] Step 8:

[0246] The server automatically generates customized content based on preference patterns and sentiment data. This content includes product and service information relevant to the user's interests, presented in a tone appropriate to their sentiment data.

[0247] Step 9:

[0248] The server generates customized content and sends it to the device. The device receives the content and notifies the user.

[0249] Step 10:

[0250] Users review the content provided through their devices and provide feedback. For example, they can comment on the usefulness of the content or areas that have newly piqued their interest.

[0251] Step 11:

[0252] The device sends user feedback to the server. The server receives the feedback and stores it in a database.

[0253] Step 12:

[0254] The server uses feedback and an emotion engine to evaluate the user's emotional state. For example, it identifies emotions (satisfied, interested, excited, etc.) at the time of feedback.

[0255] Step 13:

[0256] The server updates user preference data based on feedback and sentiment data. This reconstructs the latest preference patterns.

[0257] Step 14:

[0258] The server regenerates new customized content based on updated preference and sentiment data. For example, if a user starts showing interest in AI-related solutions, it will generate content that includes the latest AI-related information.

[0259] Step 15:

[0260] The server sends the regenerated customized content to the device, the device receives the content and notifies the user again. The user reviews the new content and provides further feedback as needed.

[0261] Through this series of steps, the system can flexibly respond to the diverse needs and emotional changes of users, and by continuously understanding the diverse needs of corporate clients, it can quickly uncover new business opportunities.

[0262] (Example 2)

[0263] 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".

[0264] Traditional customer preference analysis systems primarily relied on user behavior data, failing to consider user emotions and instantaneous feedback, making it difficult to provide highly accurate, customized content. Furthermore, they were inadequate in optimizing delivery timing and automating continuous feedback processes. Consequently, the discovery of new business opportunities and improvements in user satisfaction were limited. There is a need for a system that addresses these challenges, enabling more effective marketing strategies and responding promptly to diverse customer needs.

[0265] In Example 2, the identification processing by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting the user's basic information, means for collecting the user's past behavioral data, means for analyzing preference patterns using a machine learning algorithm based on the collected behavioral data, means for collecting and analyzing the user's emotional data, means for automatically generating customized content based on the preference patterns and emotional data, means for delivering the generated content to the user, means for receiving feedback from the user and updating the preference data and emotional data, and means for generating new customized content based on the updated preference data and emotional data and delivering it to the user again. This enables highly accurate preference analysis by integrating the user's behavioral data and real-time emotional data, and makes it possible to effectively deliver customized content optimized for the user.

[0266] "User basic information" refers to information entered during initial registration, such as the company name, industry, contact person's name, and contact details for corporate clients.

[0267] "Past behavioral data" refers to information about a user's past actions, such as their purchase history, website browsing history, and feedback on the content they have been provided.

[0268] A "machine learning algorithm" is an algorithm that learns features based on large amounts of data and automatically performs predictions and classifications.

[0269] A "preference pattern" refers to a user's preferences and interests, identified by analyzing their past behavioral data.

[0270] "Emotional data" refers to information about a user's instantaneous emotional state, obtained by analyzing biometric information such as the user's facial expressions and tone of voice.

[0271] "Customized content" refers to content that is automatically generated based on the user's preference patterns and emotional data, and is optimized for each individual user.

[0272] "Feedback" refers to opinions and information that users provide in response to the content they have been given, such as the usefulness of the content or areas in which they have newly developed an interest.

[0273] "Updated preference data" refers to data about users' preferences and interests that has been updated to the latest state based on user feedback.

[0274] "Optimizing delivery timing" is the process of determining the most effective time to deliver customized content, taking into account times that will not disrupt the user's work.

[0275] This invention is a system that uncovers potential demand by providing customized content tailored to the preferences and emotions of corporate clients and delivering messages to target specific customers. This system mainly consists of a server, user terminals, users, and an emotion analysis engine.

[0276] Initial registration and entry of basic information

[0277] First, the user completes the initial registration. During this process, the user terminal inputs the corporate customer's (user's) basic information, which the server then stores in a database. The server assigns a unique identifier to the user information and creates a profile for the new user. This basic information includes company name, industry, contact person's name, and contact details.

[0278] Collection of behavioral data

[0279] Next, the server collects data on the user's past behavior. This behavioral data includes the user's purchase history, website browsing history, and feedback on the content provided. The collected data is stored in a database and analyzed using machine learning algorithms, such as the scikit-learn library in Python. This identifies each user's preference patterns.

[0280] Collection and analysis of emotional data

[0281] The server further collects user emotion data using an emotion analysis engine. This emotion data includes user feedback, as well as facial expressions and voice tone recorded while viewing content. This data is analyzed using emotion analysis software such as Amazon Rekognition or Microsoft® Azure® Emotion API to identify the user's instantaneous emotional state. The analysis results are stored in a database.

[0282] Generating customized content

[0283] Based on identified preference patterns and emotional data, the server automatically generates customized content. This customized content includes product information and service announcements that the user is interested in, and is presented in an optimal tone that matches the user's emotional data.

[0284] Optimization of Delivery Timing

[0285] Next, the server optimizes the delivery timing of the generated customized content. In optimizing the delivery timing, the server takes into account the user's working hours and past content viewing trends. As a result, a delivery plan is formulated for a time period that does not interfere with the user's work.

[0286] Content Delivery and Notification

[0287] The generated customized content is transmitted from the server to the user terminal. The user terminal notifies the arrival of the content, and the user checks it.

[0288] Feedback Collection and Data Update

[0289] When the user provides feedback on the content, the user terminal transmits the feedback to the server. The feedback includes the usefulness of the content and newly interesting fields. The server updates the database based on the received feedback and re-evaluates the emotional state at the time of feedback using the sentiment analysis engine.

[0290] Regeneration and Delivery of Customized Content

[0291] Based on the updated preference data and emotional data, the server generates new customized content and delivers it to the user again.

[0292] Specific Examples and Example Prompt Sentences

[0293] For example, if a corporate customer A has a deep interest in IT-related products, after initial registration, the server collects and analyzes past purchase data and website browsing history, and determines that A is interested in "cloud services" and "security software". At the same time, the sentiment analysis engine analyzes feedback and biometric information, and identifies that the person in charge of A has a positive sentiment towards these products.

[0294] Based on this, the server generates customized content, including relevant product information and white papers on the latest cloud services. This content is presented in a positive and energetic tone, and a plan is devised for its delivery at the optimal time. A receives the content and provides feedback and biometric information. For example, if the feedback indicates interest in "AI-related solutions," the server regenerates new customized content and delivers it to A again.

[0295] Examples of prompts include, "Retrieve the latest white paper on cloud services and generate content with a positive tone to deliver to corporate client A at the optimal time," and "Create a customized promotional message for security software based on the user's past purchase history and sentiment data."

[0296] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0297] Step 1:

[0298] The user terminal inputs the corporate customer's basic information and sends it to the server. The server stores the received basic information in a database, assigns a unique identifier, and creates a profile for the new user.

[0299] Input: Company name, industry, contact person's name, contact information

[0300] Output: User basic information and unique identifier stored in the database.

[0301] Specific operation: The user enters basic information into an input form on their terminal and presses the submit button. The server receives the HTTP request and writes the information to the database.

[0302] Step 2:

[0303] The server collects the user's past behavior data. The behavior data includes purchase history, website browsing history, and feedback on the provided content. The server stores the collected behavior data in a database.

[0304] Input: The user's past behavior data (purchase history, browsing history, feedback)

[0305] Output: The behavior data stored in the database

[0306] Specific operation: The server collects behavior data through a log analysis tool or API and records it in the database.

[0307] Step 3:

[0308] The server analyzes the preference pattern using a machine learning algorithm based on the collected behavior data. The Python scikit-learn library is used.

[0309] Input: The behavior data stored in the database

[0310] Output: The user's preference pattern

[0311] Specific operation: The server trains a machine learning model and predicts the preference pattern using the behavior data as input.

[0312] Step 4:

[0313] The server collects the user's emotion data using an emotion engine. The emotion data includes the feedback provided by the user and the biometric information (facial expression, voice tone) recorded during content browsing.

[0314] Input: The user's feedback, biometric information

[0315] Output: The emotion data stored in the database

[0316] Specific operation: The user's device collects biometric information using its camera and microphone and sends it to the server. The server analyzes the data using an emotion analysis engine and stores the results in a database.

[0317] Step 5:

[0318] The server generates customized content based on identified preference patterns and sentiment data. A generative AI model is used to create messages with the optimal tone and content for the user.

[0319] Input: Preference patterns, emotional data

[0320] Output: Customized content

[0321] Specific operation: The server uses a generated AI model to automatically generate customized messages based on feedback and preferences.

[0322] Step 6:

[0323] The server optimizes the delivery timing of the customized content it generates. This optimization is achieved by analyzing past content viewing trends.

[0324] Input: Preference patterns, past content viewing time data

[0325] Output: Optimal delivery timing

[0326] Specific operation: The server analyzes historical data to determine the most effective delivery time.

[0327] Step 7:

[0328] The server sends the generated customized content to the user's terminal and notifies the user. The user's terminal displays the received content to the user.

[0329] Input: Customized content, delivery timing

[0330] Output: Content notification to user terminal

[0331] Specific operation: The server sends customized content to the user's device using SMTP or push notifications, and the user's device notifies the user via a pop-up notification.

[0332] Step 8:

[0333] Users provide feedback on the content they are given, and their devices send that feedback to the server.

[0334] Input: User feedback

[0335] Output: Feedback data stored on the server

[0336] Specific operation: The user fills out a feedback form and presses the submit button. The user's device sends the feedback data to the server as an API request.

[0337] Step 9:

[0338] The server updates its database based on the feedback it receives, generates new customized content based on the updated preference and sentiment data, and delivers it to the user again.

[0339] Input: Feedback data, new preference data, sentiment data

[0340] Output: Updated customized content

[0341] Specific operation: The server analyzes the feedback and updates the preference patterns and sentiment data models. It generates new customized content and runs the process again from step 6.

[0342] (Application Example 2)

[0343] 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".

[0344] While conventional content distribution systems allowed for customization based on user preference data, they struggled to automatically generate and distribute content that considered users' instantaneous emotions. This made it difficult to capture user interest and achieve effective content distribution. Furthermore, effectively utilizing user feedback and their emotional state at the time was challenging. Consequently, it was difficult to flexibly respond to changes in user needs.

[0345] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting the user's basic information, means for collecting the user's past behavioral data, means for analyzing the collected behavioral data and identifying the user's preference patterns, means for collecting and analyzing the user's emotional data using an artificial intelligence analysis engine and supplementing the preference data with emotional data, means for automatically generating customized content based on the preference patterns and emotional data, means for delivering the generated content to the user, means for receiving feedback from the user, evaluating the emotional state and updating the preference data, and means for generating new customized content based on the updated preference data and delivering it to the user again. This makes it possible to deliver customized content that responds to changes in the user's preferences and emotions.

[0346] "Means for inputting basic user information" refers to an interface that allows the system to collect basic information from the user, such as company name, industry, contact person's name, and contact details.

[0347] "Means of collecting users' past behavioral data" refers to functions that include methods for collecting behavioral data such as users' purchase history, website browsing history, and feedback on content provided.

[0348] "Means for analyzing collected behavioral data and identifying user preference patterns" refers to methods and algorithms for analyzing collected behavioral data and identifying user interests and preferences based on that analysis.

[0349] "A means of collecting and analyzing user emotional data using an artificial intelligence analysis engine and supplementing it with preference data" refers to a process of analyzing emotions from a user's facial expressions, tone of voice, and feedback, and integrating that data with existing preference data.

[0350] "Means for automatically generating customized content based on preference patterns and sentiment data" refers to systems and algorithms for automatically creating content adapted to identified preference patterns and sentiment data.

[0351] "Means of delivering generated content to users" refers to delivery methods that ensure users receive content at the most appropriate time.

[0352] "A means of receiving user feedback, evaluating emotional states, and updating preference data" refers to the process of analyzing user feedback and the emotional data at that time, and updating preference data based on that information.

[0353] "Means for generating and redistributing new customized content to users based on updated preference data" refers to methods and systems for creating new content using updated preference data and redistributing it to users.

[0354] This invention is a system that uncovers potential demand by providing customized content tailored to the preferences and emotions of corporate clients and delivering messages to target specific customers. This system consists of a server, user terminals, users, and an emotion engine.

[0355] First, the server collects basic user information. Users (corporate customers) enter basic information such as company name, industry, contact person's name, and contact details through a smartphone app. This information is stored in a database by the server, and an initial user profile is created. Through this process, the system assigns a unique identifier to each user.

[0356] Next, the server collects data on the user's past behavior. This behavioral data includes the user's purchase history, website browsing history, and feedback on the content provided. Based on this data, machine learning algorithms (e.g., TensorFlow or Scikit-learn) are used to analyze preference patterns. This identifies the types of products and services the user is interested in (e.g., cloud services, security software, etc.).

[0357] Furthermore, the server uses an emotion engine to collect and analyze user emotion data. This data is collected using the smartphone's camera and microphone, analyzing user feedback and biometric information (e.g., facial expressions and voice tone) during content viewing. This analysis utilizes artificial intelligence analysis engines such as Google® Cloud Vision API and AWS® Rekognition. The obtained emotion data is complemented by preference data, which is then used to identify the user's instantaneous emotional state.

[0358] Next, the server automatically generates customized content based on preference patterns and emotional data. This content generation uses an AI-based generation engine to create content that includes product information and service guides that are likely to be of most interest to the user. In addition, the expression method (e.g., positive and cheerful tone) is selected according to the user's emotional state.

[0359] The generated customized content is delivered from the server to the user's smartphone. The server calculates the optimal delivery time and plans to deliver the content at a time that does not disrupt the user's work. The system is used when the user receives and confirms the content.

[0360] When a user provides feedback on the content provided, the server receives that feedback. This feedback includes the usefulness of the content and any new areas of interest the user has developed. Based on the received feedback, the server updates its database and uses an emotion engine to evaluate the emotional state at the time of feedback. This updates the preference data again.

[0361] Based on updated preference data and newly collected sentiment data, the server generates and delivers newly customized content to the user again. For example, if a user begins to show interest in AI-related solutions, the server generates and delivers customized content that includes the latest AI-related information. This entire process allows the system to respond immediately to the user's changing needs and continuously uncover new business opportunities.

[0362] Specific example

[0363] Consider a case where a company is interested in cloud services. When a company representative enters basic information using a smartphone app, the server saves that information to a database. Past behavioral data (such as cloud service purchase history) is collected and analyzed to identify that the company is interested in cloud services. At the same time, a sentiment analysis engine is used to identify the representative's positive emotions.

[0364] Based on identified preference patterns and sentiment data, the server generates customized content, including the latest cloud service information, and delivers it to the assigned person. The person reviews the content and provides feedback (e.g., "I'm also interested in the latest AI-related solutions"). The server updates its database based on this feedback, generates new customized content, and delivers it again.

[0365] Example of a prompt

[0366] "We will deliver content based on the behavioral and emotional data of company representatives. Our goal is to provide them with the latest cloud service information in a customized format. Particularly important is delivering the content at the optimal time, when the representative is experiencing positive emotions."

[0367] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0368] Step 1:

[0369] Users enter basic information using a smartphone app. This basic information includes company name, industry, contact person's name, and contact details. The entered data is stored in a database by the server. Input: User's basic information. Output: Basic information stored in the database.

[0370] Step 2:

[0371] The server collects data on the user's past behavior. This past behavior data includes purchase history, website browsing history, and feedback on previously provided content. This collected data is stored in a database. Input: User behavior data. Output: Stored behavior data.

[0372] Step 3:

[0373] The server analyzes behavioral data collected using machine learning algorithms to identify user preference patterns. The algorithms used include TensorFlow and Scikit-learn. Input: Past behavioral data. Output: Identification of preference patterns.

[0374] Step 4:

[0375] When a user provides feedback via their smartphone, the device uses its camera and microphone to collect the user's biometric information (e.g., facial expressions and voice tone). This collected biometric information is then analyzed by an emotion analysis engine (e.g., Google Cloud Vision API, AWS Rekognition) to generate instantaneous emotion data. Input: Biometric information. Output: Emotion data.

[0376] Step 5:

[0377] The server automatically generates customized content based on preference patterns and sentiment data. The generated content includes products and services that the user may be interested in, and the presentation style is selected according to the sentiment data. An AI-based generation engine is used for this generation process. Input: Preference patterns and sentiment data. Output: Customized content.

[0378] Step 6:

[0379] The server generates customized content and delivers it to the smartphone app. The server calculates the optimal delivery time and plans delivery to avoid disrupting the user's work. Input: Customized content. Output: Content delivered to the app.

[0380] Step 7:

[0381] Users provide feedback on the content they are given. A smartphone app collects this feedback and sends it to a server. The feedback includes whether the content is useful and information about products or services that the user has recently become interested in. Input: User feedback. Output: Feedback sent to the server.

[0382] Step 8:

[0383] The server updates the database based on the feedback received and re-analyzes the preference data using machine learning algorithms. Simultaneously, it uses an emotion engine to evaluate the emotional state at the time of feedback and adds that data. Input: User feedback and emotion data. Output: Updated preference data.

[0384] Step 9:

[0385] The server automatically generates newly customized content based on updated preference and sentiment data and delivers it to the user again. Input: Updated preference and sentiment data. Output: Newly generated customized content.

[0386] 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.

[0387] 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.

[0388] 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.

[0389] [Second Embodiment]

[0390] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0391] 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.

[0392] 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).

[0393] 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.

[0394] 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.

[0395] 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).

[0396] 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.

[0397] 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.

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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".

[0402] This invention is a system that uncovers potential demand by providing customized content tailored to the preferences of corporate clients and delivering messages to target customers accordingly. This system mainly consists of a server, user terminals, and users.

[0403] First, initial user registration takes place within this system. The terminal inputs the user's (corporate customer's) basic information (company name, industry, contact person's name, contact information, etc.), and the server saves this information to the database. The server assigns a unique identifier to the user information and creates a profile for the new user.

[0404] Next, the server collects data on the user's past behavior. This behavioral data includes the user's past purchase history, website browsing history, and feedback on the content provided. The server stores this data in a database and analyzes it using machine learning algorithms. Based on the results of this analysis, the server identifies each user's preference patterns. For example, it might detect that a user is interested in cloud services or security software.

[0405] After identifying user preference patterns, the server automatically generates customized content based on these patterns. This content may include product information and service announcements that are likely to interest the user, and may also utilize specialized marketing materials. The server optimizes the timing of content delivery, planning delivery times that do not interfere with the user's work.

[0406] The generated content is sent from the server to the device. The device receives the content and notifies the user. The user reviews the content and provides feedback. This feedback may include whether the content was useful or if there were any new areas of interest. The user's feedback is then sent back to the server via the device.

[0407] The server updates user preference data based on the feedback received. Based on the updated preference data, new customized content is generated again. For example, if a user starts to show interest in AI-related solutions, the server generates and delivers content that includes the latest AI-related information.

[0408] By repeating this cycle, the server can always maintain the latest user preference data and provide highly accurate customized content. This makes it possible to meet the diverse needs of corporate clients and avoid missing potential business opportunities.

[0409] Specific example

[0410] For example, let's assume a corporate client A has a deep interest in IT-related products. After the user completes initial registration, the server collects and analyzes A's past purchase data and website browsing history, detecting that A is interested in "cloud services" and "security software." Based on this, the server automatically generates customized content, including relevant product information and the latest white papers on cloud services, and sends it to the device at the optimal delivery time.

[0411] Company A receives the content and provides feedback on it. For example, if the feedback includes information that they are also interested in AI-related solutions, the server generates new customized content related to AI solutions and delivers it to Company A again. Through this continuous cycle, the system can respond promptly to the changing needs of corporate customers and uncover new business opportunities.

[0412] The following describes the processing flow.

[0413] Step 1:

[0414] The terminal inputs the corporate customer's basic information (company name, industry, contact person, contact information, etc.). The user (corporate customer) then uses the terminal to register the necessary information.

[0415] Step 2:

[0416] The server saves basic information received from the terminal to the database. The server assigns a unique identifier (user ID) to the user information and creates a new user profile.

[0417] Step 3:

[0418] The server collects data on the user's past behavior. This behavioral data includes the user's purchase history, website browsing history, and feedback on previously provided content.

[0419] Step 4:

[0420] The server stores the collected behavioral data in a database. The accumulated data serves as material for analyzing user behavioral trends.

[0421] Step 5:

[0422] The server uses machine learning algorithms to analyze collected behavioral data and identify user preference patterns (areas of interest, product categories, etc.). For example, it can detect whether a user has a high interest in IT-related products.

[0423] Step 6:

[0424] The server automatically generates customized content (product information, service guides, white papers, etc.) based on identified preference patterns. The generated content is optimized for the user's areas of interest.

[0425] Step 7:

[0426] The server plans the timing of content delivery and selects a time that does not interfere with the user's work. It then develops an optimal delivery schedule.

[0427] Step 8:

[0428] The server sends the generated customized content to the device. The device receives the content and notifies the user. The user receives the notification and checks the content.

[0429] Step 9:

[0430] Users provide feedback on the content they are given. This feedback includes whether the content was useful, what new areas of interest they discovered, and so on.

[0431] Step 10:

[0432] The device sends user feedback to the server. The server receives the feedback and updates its database.

[0433] Step 11:

[0434] Based on the feedback received by the server, user preference data is updated, and the latest preference patterns are re-evaluated. This allows for the response to newly emerging areas of interest and changes in interests.

[0435] Step 12:

[0436] The server regenerates new customized content based on updated preference data. For example, if a user has started to show interest in AI-related solutions, it will create content that includes the latest information on AI.

[0437] Step 13:

[0438] The server sends the regenerated customized content to the device, the device receives the content and notifies the user again. The user reviews the new content and provides further feedback as needed.

[0439] Through this series of steps, the system can flexibly respond to the diverse needs of users and continuously discover new business opportunities.

[0440] (Example 1)

[0441] 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."

[0442] Traditional marketing systems for corporate clients have struggled to accurately understand individual customer preferences and interests and provide customized content based on those preferences. Furthermore, optimizing delivery timing and collecting and incorporating feedback were inefficient. There is a growing need for a system that can quickly respond to changes in user interests.

[0443] 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.

[0444] In this invention, the server includes means for inputting the user's basic information, means for collecting the user's past behavioral data, means for analyzing the collected behavioral data and identifying the user's preference patterns, means for automatically generating customized content based on the preference patterns, means for delivering the generated content to the user, means for receiving feedback from the user and updating the preference data, means for generating new customized content based on the updated preference data and delivering it to the user again, means for optimizing the delivery timing, and means for notifying the user using a terminal. This enables the provision of highly accurate customized content tailored to the user's individual preferences and allows for a rapid response to changes in interests.

[0445] "Means for inputting basic user information" refers to devices or software used to input and collect initial information about corporate customers, such as company name, industry, contact person's name, and contact information.

[0446] "Means of collecting users' past behavioral data" refers to devices or software used to collect data on past behavior, such as corporate customers' purchase history, website browsing history, and feedback on provided content.

[0447] "Means of analyzing collected behavioral data to identify user preference patterns" refers to machine learning algorithms and data analysis tools used to analyze collected data and identify the interests and concerns of corporate clients.

[0448] "Means for automatically generating customized content based on preference patterns" refers to devices or software that automatically create product information and service guides that are likely to be of interest to corporate customers, according to identified preference patterns.

[0449] "Means of delivering generated content to users" refers to devices or software used to deliver generated customized content to corporate customers.

[0450] "Means for receiving user feedback and updating preference data" refers to devices or software for collecting reactions and opinions on content from corporate customers and updating preference data based on that.

[0451] "Means for generating and redistributing new customized content based on updated preference data" refers to devices or software for creating new customized content based on the latest preference data and redistributing it to corporate customers.

[0452] "Means for optimizing delivery timing" refers to devices or software that deliver content at the optimal time to avoid disrupting the business operations of corporate clients.

[0453] "Means of notifying users using a device" refers to devices or software used to notify corporate customers that new content has been delivered via their devices.

[0454] This invention is a system that uncovers potential demand by providing customized content tailored to the preferences of corporate clients and delivering messages to target specific customer segments. This system mainly consists of a server, user terminals, and users.

[0455] First, the user completes initial registration in this system. The user uses a terminal to access the initial registration screen. The terminal prompts the user to enter basic information (company name, industry, contact person's name, contact information, etc.), and the user enters this information. The terminal sends the collected information to the server, and the server stores the received information in a database. The server assigns a unique identifier and creates a profile for the new user.

[0456] Next, the server collects and analyzes the user's past behavioral data. This behavioral data includes the user's past purchase history, website browsing history, and feedback on the content provided. The server stores this data in a database and performs analysis using machine learning algorithms. This analysis allows the server to identify each user's preference patterns. For example, it might detect that a user is interested in cloud services or security software.

[0457] After identifying user preference patterns, the server automatically generates customized content. This content includes product information and service announcements likely to interest the user, and in some cases, specialized marketing materials. Furthermore, the server optimizes delivery timing, scheduling delivery to avoid disrupting the user's work.

[0458] The generated content is sent from the server to the device. The device receives the content and notifies the user. The user reviews the content and provides feedback. This feedback may include whether the content was useful or if they discovered any new areas of interest. The user's feedback is then sent back to the server via the device.

[0459] Based on the feedback received by the server, the user's preference data is updated. Based on the updated preference data, new customized content is generated again. For example, if a user starts to show interest in AI-related solutions, the server generates content including the latest AI-related information and delivers it to the user again.

[0460] By repeating this cycle, the server constantly maintains the latest user preference data and provides highly accurate customized content. This makes it possible to meet the diverse needs of corporate clients and avoid missing potential business opportunities.

[0461] Specific example

[0462] For example, let's assume a corporate client A has a deep interest in IT-related products. After the user completes initial registration, the server collects and analyzes A's past purchase data and website browsing history, detecting that A is interested in "cloud services" and "security software." Based on this, the server automatically generates customized content, including relevant product information and the latest white papers on cloud services, and sends it to the device at the optimal delivery time.

[0463] Company A receives the content and provides feedback on it. For example, if the feedback includes information that they are also interested in AI-related solutions, the server generates new customized content related to AI solutions and delivers it to Company A again. Through this continuous cycle, the system can respond promptly to the changing needs of corporate customers and uncover new business opportunities.

[0464] Examples of input prompts for a generative AI model

[0465] "If a user is detected as being interested in cloud services, generate customized content that includes relevant product information and service introductions. Additionally, if a new trend emerges showing interest in AI-related solutions, add corresponding content."

[0466] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0467] System program processing flow

[0468] Step 1: Initial Registration

[0469] The user accesses the initial registration screen using their device.

[0470] The terminal prompts the user to enter basic information (company name, industry, contact person's name, contact information, etc.).

[0471] Input data: Company name, industry, contact person's name, contact information.

[0472] The terminal receives the basic information entered by the user, organizes the data, and sends it to the server.

[0473] The server saves the received information to the database, assigns a unique identifier, and creates a profile for the new user.

[0474] Output data: Basic information and a unique identifier stored in the database.

[0475] Step 2: Collecting behavioral data

[0476] The server periodically collects data on the user's past behavior from multiple data sources.

[0477] Data collected: Past purchase history, website browsing history, and feedback on the content provided.

[0478] The server organizes the behavioral data and stores it in a database.

[0479] Output data: Behavioral data stored in the database.

[0480] Step 3: Behavioral Data Analysis

[0481] The server retrieves behavioral data from the database and performs analysis using machine learning algorithms.

[0482] Input data: Behavioral data stored in the database.

[0483] The server identifies user preference patterns based on the collected data.

[0484] Specific actions: Identify an interest in cloud services and security software.

[0485] Output data: User preference patterns.

[0486] Step 4: Generating customized content

[0487] The server automatically generates customized content based on identified preference patterns.

[0488] Input data: User preference patterns.

[0489] The server creates content using a generation AI model.

[0490] The generated content will include product information and service announcements that are likely to be of interest.

[0491] Output data: The generated customized content.

[0492] Step 5: Optimizing delivery timing

[0493] The server calculates the timing for delivering the generated content.

[0494] Input data: Data related to the user's work schedule and time slots.

[0495] The server calculates the optimal delivery timing and creates a delivery plan.

[0496] Specific action: Set the delivery time to avoid interfering with work.

[0497] Output data: Distribution plan.

[0498] Step 6: Content Distribution

[0499] The server sends the generated customized content to the terminal.

[0500] Input data: Generated customized content, delivery plan.

[0501] The device notifies the user of the content it has received.

[0502] Output data: User review history of content.

[0503] Step 7: Gathering Feedback

[0504] The user reviews the content they receive and provides feedback.

[0505] Input data: Customized content.

[0506] Specific action: Inputting feedback.

[0507] The user sends feedback to the server via their device.

[0508] Output data: Feedback information.

[0509] Step 8: Update preference data

[0510] The server analyzes the feedback it receives and updates the user preference data.

[0511] Input data: Feedback information.

[0512] Specific action: Update preference data.

[0513] Output data: Updated preference data.

[0514] Step 9: Generate and distribute new customized content.

[0515] The server regenerates new customized content based on the updated preference data.

[0516] Input data: Updated preference data.

[0517] The server uses a generated AI model to create and redistribute new content.

[0518] Specific actions: Create new content based on the previous broadcast and feedback.

[0519] Output data: New customized content.

[0520] (Application Example 1)

[0521] 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."

[0522] To meet the diverse needs of corporate clients and avoid missing potential business opportunities, it is crucial to provide customized content to each client in a timely manner. However, conventional systems have struggled to accurately analyze user preference patterns and deliver content at the optimal time. Furthermore, there have been insufficient methods for effectively utilizing user feedback to reflect new preferences.

[0523] 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.

[0524] In this invention, the server includes means for inputting the user's basic information, means for collecting the user's past behavioral data, means for analyzing the collected behavioral data and identifying the user's preference patterns, means for automatically generating customized content based on the preference patterns, means for delivering the generated content to the user, means for receiving feedback from the user and updating the preference data, means for generating new customized content based on the updated preference data and delivering it to the user again, means for analyzing and learning data using machine learning algorithms, and means for planning and executing the optimal content delivery timing. This makes it possible to respond immediately to the changing needs of corporate customers and discover new business opportunities.

[0525] "Means for entering basic user information" refers to system elements for entering initial registration information such as the company name, industry, contact person's name, and contact information of corporate customers.

[0526] "Means for collecting users' past behavioral data" refers to system elements for collecting data such as corporate customers' purchase history, website browsing history, and feedback on provided content.

[0527] "Means for analyzing collected behavioral data and identifying user preference patterns" refers to algorithms and system elements for analyzing collected data and identifying the interests and concerns of individual corporate customers.

[0528] "Means for automatically generating customized content based on preference patterns" refers to system elements for generating product information and service guides that are likely to be of interest to corporate customers, based on identified preference patterns.

[0529] "Means for delivering generated content to users" refers to system elements for delivering generated customized content to corporate customers at the appropriate time.

[0530] "Means for receiving user feedback and updating preference data" refers to system elements for collecting feedback from corporate customers and updating preference data based on that feedback.

[0531] "A means of generating new customized content based on updated preference data and redistributing it to users" refers to a system element for generating new customized content based on updated preference data and redistributing it to corporate customers.

[0532] "Means of analyzing and learning from data using machine learning algorithms" refers to system elements that use machine learning algorithms to analyze and learn from data.

[0533] "Means for planning and executing the optimal content delivery timing" refers to system elements for planning and executing the delivery of customized content at the optimal time that does not interfere with the business operations of corporate clients.

[0534] The system implementing this invention provides customized content to corporate clients and uncovers potential business opportunities. The system mainly consists of the following components:

[0535] System Configuration

[0536] 1. User Registration Method

[0537] The server provides a user registration mechanism for corporate customers to enter basic information such as company name, industry, contact person's name, and contact details. This basic information is entered via an electronic form and stored in a database.

[0538] 2. Data Collection Methods

[0539] The server collects past purchase history, website browsing history, and feedback data on the content provided to corporate customers. This data is collected via an omnichannel integration tool and stored in a database.

[0540] 3. Data Analysis Methods

[0541] The server analyzes the collected data using machine learning algorithms (such as Python's scikit-learn or TensorFlow) to identify user preference patterns. Based on these identified preference patterns, it infers the product categories that the user is interested in.

[0542] 4. Content Generation Methods

[0543] The server generates customized content based on identified preference patterns. This content includes product information and service announcements that are likely to be of interest to corporate customers. The content is automatically generated using a generation AI model.

[0544] 5. Content distribution methods

[0545] The generated content is delivered to corporate clients at the optimal time. This includes using notification systems designed to prevent clients from interrupting their work, for example.

[0546] 6. Methods for collecting feedback

[0547] The server collects customer feedback (such as whether the content was useful or if they discovered any new areas of interest). This feedback information is then stored in the database.

[0548] 7. Data update and regeneration means

[0549] The server updates user preference data based on collected feedback, and then generates and delivers customized content again. This cycle is repeated automatically by the system.

[0550] 8. Optimal delivery timing planning method

[0551] The server plans and executes the optimal delivery timing to avoid disrupting the business operations of corporate clients. This ensures that information is provided without impairing the client's operational efficiency.

[0552] Specific examples and prompt statements

[0553] For example, if a corporate client has a strong interest in IT-related products, after the user completes initial registration, the server collects and analyzes the client's past purchase history and website browsing history. The server identifies that this client is interested in "cloud services" and "security software." Based on this, it automatically generates customized content, including relevant product information and the latest white papers on cloud services, and sends it to the terminal at the optimal delivery time.

[0554] Example of a prompt:

[0555] User ID 12345 has shown a strong interest in cloud services and security software, and has recently become interested in AI solutions as well. Based on this information, please create customized marketing materials on the latest AI solutions and distribute them at the optimal time.

[0556] In this way, the system can respond immediately to the changing needs of corporate clients and uncover new business opportunities.

[0557] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0558] Step 1:

[0559] Entering basic user information

[0560] The server provides a form for corporate clients to input basic information such as company name, industry, contact person's name, and contact details. When a user enters this information using a terminal, the data is sent to the server and stored in the database. The input data includes company name, industry, contact person's name, and contact details, while the output is the user's basic information stored in the database.

[0561] Step 2:

[0562] Collection of past behavioral data

[0563] After the user enters basic information, the server collects the corporate customer's past purchase history, website browsing history, and feedback on the content provided. This data is collected using an omnichannel integration tool and stored in a database. Past behavioral data is obtained as input, and the collected data is stored in the database for analysis.

[0564] Step 3:

[0565] Analysis of collected data

[0566] The server uses machine learning algorithms (such as Python's scikit-learn or TensorFlow) to analyze past behavioral data stored in the database. This identifies user preference patterns. The collected behavioral data is used as input, and the output is the identification of preference patterns. Specifically, the process involves data preprocessing, feature extraction, and model application.

[0567] Step 4:

[0568] Generating customized content

[0569] The server automatically generates customized content using a generative AI model based on identified preference patterns. This includes product information and service guides that corporate customers are likely to be interested in. Preference patterns are obtained as input, and customized content is generated as output. Specifically, this involves text generation and content assembly.

[0570] Step 5:

[0571] Content distribution

[0572] The generated customized content is delivered to corporate customers by the server at the optimal time. A notification system is used for delivery, allowing users to view the content on their devices. The generated content is the input, and the output is delivered to the corporate customer's device. Specifically, the delivery schedule is set and messages are sent.

[0573] Step 6:

[0574] Gathering feedback

[0575] Users provide feedback on the provided content. This feedback is sent back to the server and stored in the database. Feedback data is received as input and stored in the database as output. Specifically, the process involves receiving feedback from users and saving it to the database.

[0576] Step 7:

[0577] Data update and regeneration

[0578] The server updates user preference data based on collected feedback and generates customized content again based on that. The updated preference data is taken as input, and new customized content is generated as output. Specifically, the process involves updating data, reanalyzing it, and generating new content.

[0579] Step 8:

[0580] Planning the optimal delivery timing

[0581] The server plans and executes the optimal content delivery timing to avoid disrupting the business operations of corporate clients. It receives client business information and generated content as input, and outputs an optimized delivery schedule. Specifically, it performs analysis of the business calendar and plans the delivery timing.

[0582] 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.

[0583] This invention is a system that uncovers potential demand by providing customized content tailored to the preferences and emotions of corporate clients and delivering messages to target specific customers. This system mainly consists of a server, user terminals, users, and an emotion engine.

[0584] First, initial user registration takes place within this system. The terminal inputs the user's (corporate customer's) basic information, and the server stores this information in a database. The server assigns a unique identifier to the user information and creates a profile for the new user. The user's basic information includes company name, industry, contact person's name, and contact information.

[0585] Next, the server collects data on the user's past behavior. This behavioral data includes the user's purchase history, website browsing history, and feedback on the content provided. The server stores this data in a database and uses machine learning algorithms to analyze it and identify each user's preference patterns. For example, it can determine whether a user is interested in cloud services or security software.

[0586] Furthermore, the server uses an emotion engine to recognize the user's emotions and collect emotion data. The emotion engine identifies the user's instantaneous emotional state by analyzing the feedback provided by the user and biometric information recorded when viewing content (e.g., facial expressions and tone of voice). This allows the server to complement the user's preference data with emotion data, building more accurate preference patterns.

[0587] Based on identified preference patterns and emotional data, the server automatically generates customized content. This content includes product and service information relevant to the user's interests, and the most appropriate presentation style is selected based on the emotional data. For example, if the user is excited, a positive and energetic message will be generated.

[0588] Next, the server optimizes the delivery timing and plans content delivery for times that do not disrupt the user's work. The generated customized content is sent from the server to the terminal. The terminal receives the content and notifies the user. The system is used when the user receives the notification and checks the content.

[0589] When a user provides feedback on the content they are given, their device sends that feedback to the server. This feedback includes whether the content was helpful and any new areas of interest they discovered. The server updates its database based on the received feedback and uses an emotion engine to evaluate the user's emotional state at the time of feedback. This data is then used to update the preference data again.

[0590] Based on updated preference data and new sentiment data, the server generates and delivers newly customized content to the user. For example, if a user becomes interested in AI-related solutions, the server will generate and deliver content that includes the latest information on AI.

[0591] Through this series of processing cycles, the system can flexibly respond to changes in user preferences and emotions, and by continuously understanding the diverse needs of corporate clients, it can quickly uncover new business opportunities.

[0592] Specific example

[0593] For example, let's assume a corporate client A has a deep interest in IT-related products. The user registers, and the server collects and analyzes past purchase data and website browsing history, revealing that company A is interested in "cloud services" and "security software." Simultaneously, an emotion engine analyzes the provided feedback and biometric information, identifying that the person in charge at company A has positive feelings towards these products.

[0594] Based on this, the server generates customized content, including relevant product information and white papers on the latest cloud services. This content is presented in a positive and energetic tone, and a distribution plan is formulated for optimal timing. Company A receives the content and provides feedback and biometric information. For example, if the feedback includes information such as "we are also interested in AI-related solutions," the server regenerates new customized content and delivers it to Company A again. Through this continuous cycle, the system can respond promptly to Company A's changing needs and continuously uncover new business opportunities.

[0595] The following describes the processing flow.

[0596] Step 1:

[0597] The terminal inputs the corporate customer's basic information. The user (corporate customer) uses the terminal to input basic information such as company name, industry, contact person's name, and contact information.

[0598] Step 2:

[0599] The server saves the entered basic information to the database. The server assigns a unique identifier (user ID) to the user information and creates a profile for the new user.

[0600] Step 3:

[0601] The server collects data on the user's past behavior. This behavioral data includes the user's purchase history, website browsing history, and feedback on the content provided.

[0602] Step 4:

[0603] The server stores the collected behavioral data in a database. This data accumulation allows for the maintenance of a detailed history of the user's activities.

[0604] Step 5:

[0605] The server uses machine learning algorithms to analyze collected behavioral data and identify user preference patterns. For example, it can detect an interest in cloud services or security software based on past purchase history.

[0606] Step 6:

[0607] The server uses an emotion engine to analyze feedback and biometric information (such as facial expressions and tone of voice) collected from the user to obtain emotional data. For example, it measures positive reactions and the degree of excitement.

[0608] Step 7:

[0609] The server combines emotional data and preference patterns to update the user profile. This enhances the user's detailed preference patterns.

[0610] Step 8:

[0611] The server automatically generates customized content based on preference patterns and sentiment data. This content includes product and service information relevant to the user's interests, presented in a tone appropriate to their sentiment data.

[0612] Step 9:

[0613] The server generates customized content and sends it to the device. The device receives the content and notifies the user.

[0614] Step 10:

[0615] Users review the content provided through their devices and provide feedback. For example, they can comment on the usefulness of the content or areas that have newly piqued their interest.

[0616] Step 11:

[0617] The device sends user feedback to the server. The server receives the feedback and stores it in a database.

[0618] Step 12:

[0619] The server uses feedback and an emotion engine to evaluate the user's emotional state. For example, it identifies emotions (satisfied, interested, excited, etc.) at the time of feedback.

[0620] Step 13:

[0621] The server updates user preference data based on feedback and sentiment data. This reconstructs the latest preference patterns.

[0622] Step 14:

[0623] The server regenerates new customized content based on updated preference and sentiment data. For example, if a user starts showing interest in AI-related solutions, it will generate content that includes the latest AI-related information.

[0624] Step 15:

[0625] The server sends the regenerated customized content to the device, the device receives the content and notifies the user again. The user reviews the new content and provides further feedback as needed.

[0626] Through this series of steps, the system can flexibly respond to the diverse needs and emotional changes of users, and by continuously understanding the diverse needs of corporate clients, it can quickly uncover new business opportunities.

[0627] (Example 2)

[0628] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0629] Traditional customer preference analysis systems primarily relied on user behavior data, failing to consider user emotions and instantaneous feedback, making it difficult to provide highly accurate, customized content. Furthermore, they were inadequate in optimizing delivery timing and automating continuous feedback processes. Consequently, the discovery of new business opportunities and improvements in user satisfaction were limited. There is a need for a system that addresses these challenges, enabling more effective marketing strategies and responding promptly to diverse customer needs.

[0630] In Example 2, the identification processing by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting the user's basic information, means for collecting the user's past behavioral data, means for analyzing preference patterns using a machine learning algorithm based on the collected behavioral data, means for collecting and analyzing the user's emotional data, means for automatically generating customized content based on the preference patterns and emotional data, means for delivering the generated content to the user, means for receiving feedback from the user and updating the preference data and emotional data, and means for generating new customized content based on the updated preference data and emotional data and delivering it to the user again. This enables highly accurate preference analysis by integrating the user's behavioral data and real-time emotional data, and makes it possible to effectively deliver customized content optimized for the user.

[0631] "User basic information" refers to information entered during initial registration, such as the company name, industry, contact person's name, and contact details for corporate clients.

[0632] "Past behavioral data" refers to information about a user's past actions, such as their purchase history, website browsing history, and feedback on the content they have been provided.

[0633] A "machine learning algorithm" is an algorithm that learns features based on large amounts of data and automatically performs predictions and classifications.

[0634] A "preference pattern" refers to a user's preferences and interests, identified by analyzing their past behavioral data.

[0635] "Emotional data" refers to information about a user's instantaneous emotional state, obtained by analyzing biometric information such as the user's facial expressions and tone of voice.

[0636] "Customized content" refers to content that is automatically generated based on the user's preference patterns and emotional data, and is optimized for each individual user.

[0637] "Feedback" refers to opinions and information that users provide in response to the content they have been given, such as the usefulness of the content or areas in which they have newly developed an interest.

[0638] "Updated preference data" refers to data about users' preferences and interests that has been updated to the latest state based on user feedback.

[0639] "Optimizing delivery timing" is the process of determining the most effective time to deliver customized content, taking into account times that will not disrupt the user's work.

[0640] This invention is a system that uncovers potential demand by providing customized content tailored to the preferences and emotions of corporate clients and delivering messages to target specific customers. This system mainly consists of a server, user terminals, users, and an emotion analysis engine.

[0641] Initial registration and entry of basic information

[0642] First, the user completes the initial registration. During this process, the user terminal inputs the corporate customer's (user's) basic information, which the server then stores in a database. The server assigns a unique identifier to the user information and creates a profile for the new user. This basic information includes company name, industry, contact person's name, and contact details.

[0643] Collection of behavioral data

[0644] Next, the server collects data on the user's past behavior. This behavioral data includes the user's purchase history, website browsing history, and feedback on the content provided. The collected data is stored in a database and analyzed using machine learning algorithms, such as the scikit-learn library in Python. This identifies each user's preference patterns.

[0645] Collection and analysis of emotional data

[0646] The server further collects user emotional data using an emotion analysis engine. This emotional data includes feedback provided by the user, as well as facial expressions and tone of voice recorded while viewing content. This data is analyzed using emotion analysis software such as Amazon Rekognition or Microsoft Azure Emotion API to identify the user's instantaneous emotional state. The analysis results are stored in a database.

[0647] Generating customized content

[0648] Based on identified preference patterns and emotional data, the server automatically generates customized content. This customized content includes product information and service announcements that the user is interested in, and is presented in an optimal tone that matches the user's emotional data.

[0649] Optimizing delivery timing

[0650] The server then optimizes the delivery timing of the generated customized content. This optimization takes into account the user's working hours and past content viewing trends. This ensures that the delivery plan is set for times that do not disrupt the user's work.

[0651] Content delivery and notifications

[0652] The generated customized content is sent from the server to the user's terminal. The user's terminal notifies the server of the content's arrival, and the user confirms it.

[0653] Gathering feedback and updating data

[0654] When a user provides feedback on the content provided, their device sends that feedback to the server. This feedback includes the usefulness of the content and any new areas of interest the user has developed. The server updates its database based on the received feedback and uses a sentiment analysis engine to re-evaluate the user's emotional state at the time of feedback.

[0655] Re-generating and distributing customized content

[0656] Based on updated preference and sentiment data, the server generates new, customized content and delivers it to the user again.

[0657] Examples of specific cases and prompt statements

[0658] For example, if a corporate client A has a strong interest in IT-related products, initial registration is performed, and the server collects and analyzes past purchase data and website browsing history to determine that A is interested in "cloud services" and "security software." Simultaneously, an emotion analysis engine analyzes feedback and biometric information to identify that A's representative has positive feelings towards these products.

[0659] Based on this, the server generates customized content, including relevant product information and white papers on the latest cloud services. This content is presented in a positive and energetic tone, and a plan is devised for its delivery at the optimal time. A receives the content and provides feedback and biometric information. For example, if the feedback indicates interest in "AI-related solutions," the server regenerates new customized content and delivers it to A again.

[0660] Examples of prompts include, "Retrieve the latest white paper on cloud services and generate content with a positive tone to deliver to corporate client A at the optimal time," and "Create a customized promotional message for security software based on the user's past purchase history and sentiment data."

[0661] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0662] Step 1:

[0663] The user terminal inputs the corporate customer's basic information and sends it to the server. The server stores the received basic information in a database, assigns a unique identifier, and creates a profile for the new user.

[0664] Input: Company name, industry, contact person's name, contact information

[0665] Output: User basic information and unique identifier stored in the database.

[0666] Specific operation: The user enters basic information into an input form on their terminal and presses the submit button. The server receives the HTTP request and writes the information to the database.

[0667] Step 2:

[0668] The server collects data on the user's past behavior. This behavioral data includes purchase history, website browsing history, and feedback on the content provided. The server stores the collected behavioral data in a database.

[0669] Input: User's past behavioral data (purchase history, browsing history, feedback)

[0670] Output: Behavioral data stored in the database

[0671] Specific operation: The server collects behavioral data through log analysis tools and APIs and records it in a database.

[0672] Step 3:

[0673] The server analyzes preference patterns using machine learning algorithms based on collected behavioral data. The Python scikit-learn library is used.

[0674] Input: Behavioral data stored in the database

[0675] Output: User preference patterns

[0676] Specific operation: The server trains a machine learning model and predicts preference patterns using behavioral data as input.

[0677] Step 4:

[0678] The server uses an emotion engine to collect user emotion data. This emotion data includes feedback provided by the user and biometric information (facial expressions, voice tone) recorded when viewing content.

[0679] Input: User feedback, biometric information

[0680] Output: Sentiment data stored in the database

[0681] Specific operation: The user's device collects biometric information using its camera and microphone and sends it to the server. The server analyzes the data using an emotion analysis engine and stores the results in a database.

[0682] Step 5:

[0683] The server generates customized content based on identified preference patterns and sentiment data. A generative AI model is used to create messages with the optimal tone and content for the user.

[0684] Input: Preference patterns, emotional data

[0685] Output: Customized content

[0686] Specific operation: The server uses a generated AI model to automatically generate customized messages based on feedback and preferences.

[0687] Step 6:

[0688] The server optimizes the delivery timing of the customized content it generates. This optimization is achieved by analyzing past content viewing trends.

[0689] Input: Preference patterns, past content viewing time data

[0690] Output: Optimal delivery timing

[0691] Specific operation: The server analyzes historical data to determine the most effective delivery time.

[0692] Step 7:

[0693] The server sends the generated customized content to the user's terminal and notifies the user. The user's terminal displays the received content to the user.

[0694] Input: Customized content, delivery timing

[0695] Output: Content notification to user terminal

[0696] Specific operation: The server sends customized content to the user's device using SMTP or push notifications, and the user's device notifies the user via a pop-up notification.

[0697] Step 8:

[0698] Users provide feedback on the content they are given, and their devices send that feedback to the server.

[0699] Input: User feedback

[0700] Output: Feedback data stored on the server

[0701] Specific operation: The user fills out a feedback form and presses the submit button. The user's device sends the feedback data to the server as an API request.

[0702] Step 9:

[0703] The server updates its database based on the feedback it receives, generates new customized content based on the updated preference and sentiment data, and delivers it to the user again.

[0704] Input: Feedback data, new preference data, sentiment data

[0705] Output: Updated customized content

[0706] Specific operation: The server analyzes the feedback and updates the preference patterns and sentiment data models. It generates new customized content and runs the process again from step 6.

[0707] (Application Example 2)

[0708] 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."

[0709] While conventional content distribution systems allowed for customization based on user preference data, they struggled to automatically generate and distribute content that considered users' instantaneous emotions. This made it difficult to capture user interest and achieve effective content distribution. Furthermore, effectively utilizing user feedback and their emotional state at the time was challenging. Consequently, it was difficult to flexibly respond to changes in user needs.

[0710] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting the user's basic information, means for collecting the user's past behavioral data, means for analyzing the collected behavioral data and identifying the user's preference patterns, means for collecting and analyzing the user's emotional data using an artificial intelligence analysis engine and supplementing the preference data with emotional data, means for automatically generating customized content based on the preference patterns and emotional data, means for delivering the generated content to the user, means for receiving feedback from the user, evaluating the emotional state and updating the preference data, and means for generating new customized content based on the updated preference data and delivering it to the user again. This makes it possible to deliver customized content that responds to changes in the user's preferences and emotions.

[0711] "Means for inputting basic user information" refers to an interface that allows a system to collect basic information from users, such as company name, industry, contact person's name, and contact details.

[0712] "Means of collecting users' past behavioral data" refers to functions that include methods for collecting behavioral data such as users' purchase history, website browsing history, and feedback on content provided.

[0713] "Means for analyzing collected behavioral data and identifying user preference patterns" refers to methods and algorithms for analyzing collected behavioral data and identifying user interests and preferences based on that analysis.

[0714] "A means of collecting and analyzing user emotional data using an artificial intelligence analysis engine and supplementing it with preference data" refers to a process of analyzing emotions from a user's facial expressions, tone of voice, and feedback, and integrating that data with existing preference data.

[0715] "Means for automatically generating customized content based on preference patterns and sentiment data" refers to systems and algorithms for automatically creating content adapted to identified preference patterns and sentiment data.

[0716] "Means of delivering generated content to users" refers to delivery methods that ensure users receive content at the most appropriate time.

[0717] "A means of receiving user feedback, evaluating emotional states, and updating preference data" refers to the process of analyzing user feedback and the emotional data at that time, and updating preference data based on that information.

[0718] "Means for generating and redistributing new customized content to users based on updated preference data" refers to methods and systems for creating new content using updated preference data and redistributing it to users.

[0719] This invention is a system that uncovers potential demand by providing customized content tailored to the preferences and emotions of corporate clients and delivering messages to target specific customers. This system consists of a server, user terminals, users, and an emotion engine.

[0720] First, the server collects basic user information. Users (corporate customers) enter basic information such as company name, industry, contact person's name, and contact details through a smartphone app. This information is stored in a database by the server, and an initial user profile is created. Through this process, the system assigns a unique identifier to each user.

[0721] Next, the server collects data on the user's past behavior. This behavioral data includes the user's purchase history, website browsing history, and feedback on the content provided. Based on this data, machine learning algorithms (e.g., TensorFlow or Scikit-learn) are used to analyze preference patterns. This identifies the types of products and services the user is interested in (e.g., cloud services, security software, etc.).

[0722] Furthermore, the server uses an emotion engine to collect and analyze user emotion data. This data is collected using the smartphone's camera and microphone, analyzing user feedback and biometric information (e.g., facial expressions and voice tone) during content viewing. This analysis utilizes artificial intelligence analysis engines such as Google Cloud Vision API and AWS Rekognition. The obtained emotion data is complemented by preference data, which is then used to identify the user's instantaneous emotional state.

[0723] Next, the server automatically generates customized content based on preference patterns and emotional data. This content generation uses an AI-based generation engine to create content that includes product information and service guides that are likely to be of most interest to the user. In addition, the expression method (e.g., positive and cheerful tone) is selected according to the user's emotional state.

[0724] The generated customized content is delivered from the server to the user's smartphone. The server calculates the optimal delivery time and plans to deliver the content at a time that does not disrupt the user's work. The system is used when the user receives and confirms the content.

[0725] When a user provides feedback on the content provided, the server receives that feedback. This feedback includes the usefulness of the content and any new areas of interest the user has developed. Based on the received feedback, the server updates its database and uses an emotion engine to evaluate the emotional state at the time of feedback. This updates the preference data again.

[0726] Based on updated preference data and newly collected sentiment data, the server generates and delivers newly customized content to the user again. For example, if a user begins to show interest in AI-related solutions, the server generates and delivers customized content that includes the latest AI-related information. This entire process allows the system to respond immediately to the user's changing needs and continuously uncover new business opportunities.

[0727] Specific example

[0728] Consider a case where a company is interested in cloud services. When a company representative enters basic information using a smartphone app, the server saves that information to a database. Past behavioral data (such as cloud service purchase history) is collected and analyzed to identify that the company is interested in cloud services. At the same time, a sentiment analysis engine is used to identify the representative's positive emotions.

[0729] Based on identified preference patterns and sentiment data, the server generates customized content, including the latest cloud service information, and delivers it to the assigned person. The person reviews the content and provides feedback (e.g., "I'm also interested in the latest AI-related solutions"). The server updates its database based on this feedback, generates new customized content, and delivers it again.

[0730] Example of a prompt

[0731] "We will deliver content based on the behavioral and emotional data of company representatives. Our goal is to provide them with the latest cloud service information in a customized format. Particularly important is delivering the content at the optimal time, when the representative is experiencing positive emotions."

[0732] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0733] Step 1:

[0734] Users enter basic information using a smartphone app. This basic information includes company name, industry, contact person's name, and contact details. The entered data is stored in a database by the server. Input: User's basic information. Output: Basic information stored in the database.

[0735] Step 2:

[0736] The server collects data on the user's past behavior. This past behavior data includes purchase history, website browsing history, and feedback on previously provided content. This collected data is stored in a database. Input: User behavior data. Output: Stored behavior data.

[0737] Step 3:

[0738] The server analyzes behavioral data collected using machine learning algorithms to identify user preference patterns. Algorithms used include TensorFlow and Scikit-learn. Input: Past behavioral data. Output: Identification of preference patterns.

[0739] Step 4:

[0740] When a user provides feedback via their smartphone, the device uses its camera and microphone to collect the user's biometric information (e.g., facial expressions and voice tone). This collected biometric information is then analyzed by an emotion analysis engine (e.g., Google Cloud Vision API, AWS Rekognition) to generate instantaneous emotion data. Input: Biometric information. Output: Emotion data.

[0741] Step 5:

[0742] The server automatically generates customized content based on preference patterns and sentiment data. The generated content includes products and services that the user may be interested in, and the presentation style is selected according to the sentiment data. An AI-based generation engine is used for this generation process. Input: Preference patterns and sentiment data. Output: Customized content.

[0743] Step 6:

[0744] The server generates customized content and delivers it to the smartphone app. The server calculates the optimal delivery time and plans delivery to avoid disrupting the user's work. Input: Customized content. Output: Content delivered to the app.

[0745] Step 7:

[0746] Users provide feedback on the content they are given. A smartphone app collects this feedback and sends it to a server. The feedback includes whether the content is useful and information about products or services that the user has recently become interested in. Input: User feedback. Output: Feedback sent to the server.

[0747] Step 8:

[0748] The server updates the database based on the feedback received and re-analyzes the preference data using machine learning algorithms. Simultaneously, it uses an emotion engine to evaluate the emotional state at the time of feedback and adds that data. Input: User feedback and emotion data. Output: Updated preference data.

[0749] Step 9:

[0750] The server automatically generates newly customized content based on updated preference and sentiment data and delivers it to the user again. Input: Updated preference and sentiment data. Output: Newly generated customized content.

[0751] 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.

[0752] 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.

[0753] 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.

[0754] [Third Embodiment]

[0755] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0756] 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.

[0757] 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).

[0758] 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.

[0759] 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.

[0760] 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).

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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".

[0767] This invention is a system that uncovers potential demand by providing customized content tailored to the preferences of corporate clients and delivering messages to target customers accordingly. This system mainly consists of a server, user terminals, and users.

[0768] First, initial user registration takes place within this system. The terminal inputs the user's (corporate customer's) basic information (company name, industry, contact person's name, contact information, etc.), and the server saves this information to the database. The server assigns a unique identifier to the user information and creates a profile for the new user.

[0769] Next, the server collects data on the user's past behavior. This behavioral data includes the user's past purchase history, website browsing history, and feedback on the content provided. The server stores this data in a database and analyzes it using machine learning algorithms. Based on the results of this analysis, the server identifies each user's preference patterns. For example, it might detect that a user is interested in cloud services or security software.

[0770] After identifying user preference patterns, the server automatically generates customized content based on these patterns. This content may include product information and service announcements that are likely to interest the user, and may also utilize specialized marketing materials. The server optimizes the timing of content delivery, planning delivery times that do not interfere with the user's work.

[0771] The generated content is sent from the server to the device. The device receives the content and notifies the user. The user reviews the content and provides feedback. This feedback may include whether the content was useful or if there were any new areas of interest. The user's feedback is then sent back to the server via the device.

[0772] The server updates user preference data based on the feedback received. Based on the updated preference data, new customized content is generated again. For example, if a user starts to show interest in AI-related solutions, the server generates and delivers content that includes the latest AI-related information.

[0773] By repeating this cycle, the server can always maintain the latest user preference data and provide highly accurate customized content. This makes it possible to meet the diverse needs of corporate clients and avoid missing potential business opportunities.

[0774] Specific example

[0775] For example, let's assume a corporate client A has a deep interest in IT-related products. After the user completes initial registration, the server collects and analyzes A's past purchase data and website browsing history, detecting that A is interested in "cloud services" and "security software." Based on this, the server automatically generates customized content, including relevant product information and the latest white papers on cloud services, and sends it to the device at the optimal delivery time.

[0776] Company A receives the content and provides feedback on it. For example, if the feedback includes information that they are also interested in AI-related solutions, the server generates new customized content related to AI solutions and delivers it to Company A again. Through this continuous cycle, the system can respond promptly to the changing needs of corporate customers and uncover new business opportunities.

[0777] The following describes the processing flow.

[0778] Step 1:

[0779] The terminal inputs the corporate customer's basic information (company name, industry, contact person, contact information, etc.). The user (corporate customer) then uses the terminal to register the necessary information.

[0780] Step 2:

[0781] The server saves basic information received from the terminal to the database. The server assigns a unique identifier (user ID) to the user information and creates a new user profile.

[0782] Step 3:

[0783] The server collects data on the user's past behavior. This behavioral data includes the user's purchase history, website browsing history, and feedback on previously provided content.

[0784] Step 4:

[0785] The server stores the collected behavioral data in a database. The accumulated data serves as material for analyzing user behavioral trends.

[0786] Step 5:

[0787] The server uses machine learning algorithms to analyze collected behavioral data and identify user preference patterns (areas of interest, product categories, etc.). For example, it can detect whether a user has a high interest in IT-related products.

[0788] Step 6:

[0789] The server automatically generates customized content (product information, service guides, white papers, etc.) based on identified preference patterns. The generated content is optimized for the user's areas of interest.

[0790] Step 7:

[0791] The server plans the timing of content delivery and selects a time that does not interfere with the user's work. It then develops an optimal delivery schedule.

[0792] Step 8:

[0793] The server sends the generated customized content to the device. The device receives the content and notifies the user. The user receives the notification and checks the content.

[0794] Step 9:

[0795] Users provide feedback on the content they are given. This feedback includes whether the content was useful, what new areas of interest they discovered, and so on.

[0796] Step 10:

[0797] The device sends user feedback to the server. The server receives the feedback and updates its database.

[0798] Step 11:

[0799] Based on the feedback received by the server, user preference data is updated, and the latest preference patterns are re-evaluated. This allows for the response to newly emerging areas of interest and changes in interests.

[0800] Step 12:

[0801] The server regenerates new customized content based on updated preference data. For example, if a user has started to show interest in AI-related solutions, it will create content that includes the latest information on AI.

[0802] Step 13:

[0803] The server sends the regenerated customized content to the device, the device receives the content and notifies the user again. The user reviews the new content and provides further feedback as needed.

[0804] Through this series of steps, the system can flexibly respond to the diverse needs of users and continuously discover new business opportunities.

[0805] (Example 1)

[0806] 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."

[0807] Traditional marketing systems for corporate clients have struggled to accurately understand individual customer preferences and interests and provide customized content based on those preferences. Furthermore, optimizing delivery timing and collecting and incorporating feedback were inefficient. There is a growing need for a system that can quickly respond to changes in user interests.

[0808] 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.

[0809] In this invention, the server includes means for inputting the user's basic information, means for collecting the user's past behavioral data, means for analyzing the collected behavioral data and identifying the user's preference patterns, means for automatically generating customized content based on the preference patterns, means for delivering the generated content to the user, means for receiving feedback from the user and updating the preference data, means for generating new customized content based on the updated preference data and delivering it to the user again, means for optimizing the delivery timing, and means for notifying the user using a terminal. This enables the provision of highly accurate customized content tailored to the user's individual preferences and allows for a rapid response to changes in interests.

[0810] "Means for inputting basic user information" refers to devices or software used to input and collect initial information about corporate customers, such as company name, industry, contact person's name, and contact information.

[0811] "Means of collecting users' past behavioral data" refers to devices or software used to collect data on past behavior, such as corporate customers' purchase history, website browsing history, and feedback on provided content.

[0812] "Means of analyzing collected behavioral data to identify user preference patterns" refers to machine learning algorithms and data analysis tools used to analyze collected data and identify the interests and concerns of corporate clients.

[0813] "Means for automatically generating customized content based on preference patterns" refers to devices or software that automatically create product information and service guides that are likely to be of interest to corporate customers, according to identified preference patterns.

[0814] "Means of delivering generated content to users" refers to devices or software used to deliver generated customized content to corporate customers.

[0815] "Means for receiving user feedback and updating preference data" refers to devices or software for collecting reactions and opinions on content from corporate customers and updating preference data based on that.

[0816] "Means for generating and redistributing new customized content to users based on updated preference data" refers to devices or software for creating new customized content based on the latest preference data and redistributing it to corporate customers.

[0817] "Means for optimizing delivery timing" refers to devices or software that deliver content at the optimal time to avoid disrupting the business operations of corporate clients.

[0818] "Means of notifying users using a device" refers to devices or software used to notify corporate customers that new content has been delivered via their devices.

[0819] This invention is a system that uncovers potential demand by providing customized content tailored to the preferences of corporate clients and delivering messages to target specific customer segments. This system mainly consists of a server, user terminals, and users.

[0820] First, the user completes initial registration in this system. The user uses a terminal to access the initial registration screen. The terminal prompts the user to enter basic information (company name, industry, contact person's name, contact information, etc.), and the user enters this information. The terminal sends the collected information to the server, and the server stores the received information in a database. The server assigns a unique identifier and creates a profile for the new user.

[0821] Next, the server collects and analyzes the user's past behavioral data. This behavioral data includes the user's past purchase history, website browsing history, and feedback on the content provided. The server stores this data in a database and performs analysis using machine learning algorithms. This analysis allows the server to identify each user's preference patterns. For example, it might detect that a user is interested in cloud services or security software.

[0822] After identifying user preference patterns, the server automatically generates customized content. This content includes product information and service announcements likely to interest the user, and in some cases, specialized marketing materials. Furthermore, the server optimizes delivery timing, scheduling delivery to avoid disrupting the user's work.

[0823] The generated content is sent from the server to the device. The device receives the content and notifies the user. The user reviews the content and provides feedback. This feedback may include whether the content was useful or if they discovered any new areas of interest. The user's feedback is then sent back to the server via the device.

[0824] Based on the feedback received by the server, the user's preference data is updated. Based on the updated preference data, new customized content is generated again. For example, if a user starts to show interest in AI-related solutions, the server generates content including the latest AI-related information and delivers it to the user again.

[0825] By repeating this cycle, the server constantly maintains the latest user preference data and provides highly accurate customized content. This makes it possible to meet the diverse needs of corporate clients and avoid missing potential business opportunities.

[0826] Specific example

[0827] For example, let's assume a corporate client A has a deep interest in IT-related products. After the user completes initial registration, the server collects and analyzes A's past purchase data and website browsing history, detecting that A is interested in "cloud services" and "security software." Based on this, the server automatically generates customized content, including relevant product information and the latest white papers on cloud services, and sends it to the device at the optimal delivery time.

[0828] Company A receives the content and provides feedback on it. For example, if the feedback includes information that they are also interested in AI-related solutions, the server generates new customized content related to AI solutions and delivers it to Company A again. Through this continuous cycle, the system can respond promptly to the changing needs of corporate customers and uncover new business opportunities.

[0829] Examples of input prompts for a generative AI model

[0830] "If a user is detected as being interested in cloud services, generate customized content that includes relevant product information and service introductions. Additionally, if a new trend emerges showing interest in AI-related solutions, add corresponding content."

[0831] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0832] System program processing flow

[0833] Step 1: Initial Registration

[0834] The user accesses the initial registration screen using their device.

[0835] The terminal prompts the user to enter basic information (company name, industry, contact person's name, contact information, etc.).

[0836] Input data: Company name, industry, contact person's name, contact information.

[0837] The terminal receives the basic information entered by the user, organizes the data, and sends it to the server.

[0838] The server saves the received information to the database, assigns a unique identifier, and creates a profile for the new user.

[0839] Output data: Basic information and a unique identifier stored in the database.

[0840] Step 2: Collecting behavioral data

[0841] The server periodically collects data on the user's past behavior from multiple data sources.

[0842] Data collected: Past purchase history, website browsing history, and feedback on the content provided.

[0843] The server organizes the behavioral data and stores it in a database.

[0844] Output data: Behavioral data stored in the database.

[0845] Step 3: Behavioral Data Analysis

[0846] The server retrieves behavioral data from the database and performs analysis using machine learning algorithms.

[0847] Input data: Behavioral data stored in the database.

[0848] The server identifies user preference patterns based on the collected data.

[0849] Specific actions: Identify an interest in cloud services and security software.

[0850] Output data: User preference patterns.

[0851] Step 4: Generating customized content

[0852] The server automatically generates customized content based on identified preference patterns.

[0853] Input data: User preference patterns.

[0854] The server creates content using a generation AI model.

[0855] The generated content will include product information and service announcements that are likely to be of interest.

[0856] Output data: The generated customized content.

[0857] Step 5: Optimizing delivery timing

[0858] The server calculates the timing for delivering the generated content.

[0859] Input data: Data related to the user's work schedule and time slots.

[0860] The server calculates the optimal delivery timing and creates a delivery plan.

[0861] Specific action: Set the delivery time to avoid interfering with work.

[0862] Output data: Distribution plan.

[0863] Step 6: Content Distribution

[0864] The server sends the generated customized content to the terminal.

[0865] Input data: Generated customized content, delivery plan.

[0866] The device notifies the user of the content it has received.

[0867] Output data: User review history of content.

[0868] Step 7: Gathering Feedback

[0869] The user reviews the content they receive and provides feedback.

[0870] Input data: Customized content.

[0871] Specific action: Inputting feedback.

[0872] The user sends feedback to the server via their device.

[0873] Output data: Feedback information.

[0874] Step 8: Update preference data

[0875] The server analyzes the feedback it receives and updates the user preference data.

[0876] Input data: Feedback information.

[0877] Specific action: Update preference data.

[0878] Output data: Updated preference data.

[0879] Step 9: Generate and distribute new customized content.

[0880] The server regenerates new customized content based on the updated preference data.

[0881] Input data: Updated preference data.

[0882] The server uses a generated AI model to create and redistribute new content.

[0883] Specific actions: Create new content based on the previous broadcast and feedback.

[0884] Output data: New customized content.

[0885] (Application Example 1)

[0886] 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."

[0887] To meet the diverse needs of corporate clients and avoid missing potential business opportunities, it is crucial to provide customized content to each client in a timely manner. However, conventional systems have struggled to accurately analyze user preference patterns and deliver content at the optimal time. Furthermore, there have been insufficient methods for effectively utilizing user feedback to reflect new preferences.

[0888] 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.

[0889] In this invention, the server includes means for inputting the user's basic information, means for collecting the user's past behavioral data, means for analyzing the collected behavioral data and identifying the user's preference patterns, means for automatically generating customized content based on the preference patterns, means for delivering the generated content to the user, means for receiving feedback from the user and updating the preference data, means for generating new customized content based on the updated preference data and delivering it to the user again, means for analyzing and learning data using machine learning algorithms, and means for planning and executing the optimal content delivery timing. This makes it possible to respond immediately to the changing needs of corporate customers and discover new business opportunities.

[0890] "Means for entering basic user information" refers to system elements for entering initial registration information such as the company name, industry, contact person's name, and contact information of corporate customers.

[0891] "Means for collecting users' past behavioral data" refers to system elements for collecting data such as corporate customers' purchase history, website browsing history, and feedback on provided content.

[0892] "Means for analyzing collected behavioral data and identifying user preference patterns" refers to algorithms and system elements for analyzing collected data and identifying the interests and concerns of individual corporate customers.

[0893] "Means for automatically generating customized content based on preference patterns" refers to system elements for generating product information and service guides that are likely to be of interest to corporate customers, based on identified preference patterns.

[0894] "Means for delivering generated content to users" refers to system elements for delivering generated customized content to corporate customers at the appropriate time.

[0895] "Means for receiving user feedback and updating preference data" refers to system elements for collecting feedback from corporate customers and updating preference data based on that feedback.

[0896] "A means of generating new customized content based on updated preference data and redistributing it to users" refers to a system element for generating new customized content based on updated preference data and redistributing it to corporate customers.

[0897] "Means of analyzing and learning from data using machine learning algorithms" refers to system elements that use machine learning algorithms to analyze and learn from data.

[0898] "Means for planning and executing the optimal content delivery timing" refers to system elements for planning and executing the delivery of customized content at the optimal time that does not interfere with the business operations of corporate clients.

[0899] The system implementing this invention provides customized content to corporate clients and uncovers potential business opportunities. The system mainly consists of the following components:

[0900] System Configuration

[0901] 1. User Registration Method

[0902] The server provides a user registration mechanism for corporate customers to enter basic information such as company name, industry, contact person's name, and contact details. This basic information is entered via an electronic form and stored in a database.

[0903] 2. Data Collection Methods

[0904] The server collects past purchase history, website browsing history, and feedback data on the content provided to corporate customers. This data is collected via an omnichannel integration tool and stored in a database.

[0905] 3. Data Analysis Methods

[0906] The server analyzes the collected data using machine learning algorithms (such as Python's scikit-learn or TensorFlow) to identify user preference patterns. Based on these identified preference patterns, it infers the product categories that the user is interested in.

[0907] 4. Content Generation Methods

[0908] The server generates customized content based on identified preference patterns. This content includes product information and service announcements that are likely to be of interest to corporate customers. The content is automatically generated using a generation AI model.

[0909] 5. Content distribution methods

[0910] The generated content is delivered to corporate clients at the optimal time. This includes using notification systems designed to prevent clients from interrupting their work, for example.

[0911] 6. Methods for collecting feedback

[0912] The server collects customer feedback (such as whether the content was useful or if they discovered any new areas of interest). This feedback information is then stored in the database.

[0913] 7. Data update and regeneration means

[0914] The server updates user preference data based on collected feedback, and then generates and delivers customized content again. This cycle is repeated automatically by the system.

[0915] 8. Optimal delivery timing planning method

[0916] The server plans and executes the optimal delivery timing to avoid disrupting the business operations of corporate clients. This ensures that information is provided without impairing the client's operational efficiency.

[0917] Specific examples and prompt statements

[0918] For example, if a corporate client has a strong interest in IT-related products, after the user completes initial registration, the server collects and analyzes the client's past purchase history and website browsing history. The server identifies that this client is interested in "cloud services" and "security software." Based on this, it automatically generates customized content, including relevant product information and the latest white papers on cloud services, and sends it to the terminal at the optimal delivery time.

[0919] Example of a prompt:

[0920] User ID 12345 has shown a strong interest in cloud services and security software, and has recently become interested in AI solutions as well. Based on this information, please create customized marketing materials on the latest AI solutions and distribute them at the optimal time.

[0921] In this way, the system can respond immediately to the changing needs of corporate clients and uncover new business opportunities.

[0922] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0923] Step 1:

[0924] Entering basic user information

[0925] The server provides a form for corporate clients to input basic information such as company name, industry, contact person's name, and contact details. When a user enters this information using a terminal, the data is sent to the server and stored in the database. The input data includes company name, industry, contact person's name, and contact details, while the output is the user's basic information stored in the database.

[0926] Step 2:

[0927] Collection of past behavioral data

[0928] After the user enters basic information, the server collects the corporate customer's past purchase history, website browsing history, and feedback on the content provided. This data is collected using an omnichannel integration tool and stored in a database. Past behavioral data is obtained as input, and the collected data is stored in the database for analysis.

[0929] Step 3:

[0930] Analysis of collected data

[0931] The server uses machine learning algorithms (such as Python's scikit-learn or TensorFlow) to analyze past behavioral data stored in the database. This identifies user preference patterns. The collected behavioral data is used as input, and the output is the identification of preference patterns. Specifically, the process involves data preprocessing, feature extraction, and model application.

[0932] Step 4:

[0933] Generating customized content

[0934] The server automatically generates customized content using a generative AI model based on identified preference patterns. This includes product information and service guides that corporate customers are likely to be interested in. Preference patterns are obtained as input, and customized content is generated as output. Specifically, this involves text generation and content assembly.

[0935] Step 5:

[0936] Content distribution

[0937] The generated customized content is delivered to corporate customers by the server at the optimal time. A notification system is used for delivery, allowing users to view the content on their devices. The generated content is the input, and the output is delivered to the corporate customer's device. Specifically, the delivery schedule is set and messages are sent.

[0938] Step 6:

[0939] Gathering feedback

[0940] Users provide feedback on the provided content. This feedback is sent back to the server and stored in the database. Feedback data is received as input and stored in the database as output. Specifically, the process involves receiving feedback from users and saving it to the database.

[0941] Step 7:

[0942] Data update and regeneration

[0943] The server updates user preference data based on collected feedback and generates customized content again based on that. The updated preference data is taken as input, and new customized content is generated as output. Specifically, the process involves updating data, reanalyzing it, and generating new content.

[0944] Step 8:

[0945] Planning the optimal delivery timing

[0946] The server plans and executes the optimal content delivery timing to avoid disrupting the business operations of corporate clients. It receives client business information and generated content as input, and outputs an optimized delivery schedule. Specifically, it performs analysis of the business calendar and plans the delivery timing.

[0947] 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.

[0948] This invention is a system that uncovers potential demand by providing customized content tailored to the preferences and emotions of corporate clients and delivering messages to target specific customers. This system mainly consists of a server, user terminals, users, and an emotion engine.

[0949] First, initial user registration takes place within this system. The terminal inputs the user's (corporate customer's) basic information, and the server stores this information in a database. The server assigns a unique identifier to the user information and creates a profile for the new user. The user's basic information includes company name, industry, contact person's name, and contact information.

[0950] Next, the server collects data on the user's past behavior. This behavioral data includes the user's purchase history, website browsing history, and feedback on the content provided. The server stores this data in a database and uses machine learning algorithms to analyze it and identify each user's preference patterns. For example, it can determine whether a user is interested in cloud services or security software.

[0951] Furthermore, the server uses an emotion engine to recognize the user's emotions and collect emotion data. The emotion engine identifies the user's instantaneous emotional state by analyzing the feedback provided by the user and biometric information recorded when viewing content (e.g., facial expressions and tone of voice). This allows the server to complement the user's preference data with emotion data, building more accurate preference patterns.

[0952] Based on identified preference patterns and emotional data, the server automatically generates customized content. This content includes product and service information relevant to the user's interests, and the most appropriate presentation style is selected based on the emotional data. For example, if the user is excited, a positive and energetic message will be generated.

[0953] Next, the server optimizes the delivery timing and plans content delivery for times that do not disrupt the user's work. The generated customized content is sent from the server to the terminal. The terminal receives the content and notifies the user. The system is used when the user receives the notification and checks the content.

[0954] When a user provides feedback on the content they are given, their device sends that feedback to the server. This feedback includes whether the content was helpful and any new areas of interest they discovered. The server updates its database based on the received feedback and uses an emotion engine to evaluate the user's emotional state at the time of feedback. This data is then used to update the preference data again.

[0955] Based on updated preference data and new sentiment data, the server generates and delivers newly customized content to the user. For example, if a user becomes interested in AI-related solutions, the server will generate and deliver content that includes the latest information on AI.

[0956] Through this series of processing cycles, the system can flexibly respond to changes in user preferences and emotions, and by continuously understanding the diverse needs of corporate clients, it can quickly uncover new business opportunities.

[0957] Specific example

[0958] For example, let's assume a corporate client A has a deep interest in IT-related products. The user registers, and the server collects and analyzes past purchase data and website browsing history, revealing that company A is interested in "cloud services" and "security software." Simultaneously, an emotion engine analyzes the provided feedback and biometric information, identifying that the person in charge at company A has positive feelings towards these products.

[0959] Based on this, the server generates customized content, including relevant product information and white papers on the latest cloud services. This content is presented in a positive and energetic tone, and a distribution plan is formulated for optimal timing. Company A receives the content and provides feedback and biometric information. For example, if the feedback includes information such as "we are also interested in AI-related solutions," the server regenerates new customized content and delivers it to Company A again. Through this continuous cycle, the system can respond promptly to Company A's changing needs and continuously uncover new business opportunities.

[0960] The following describes the processing flow.

[0961] Step 1:

[0962] The terminal inputs the corporate customer's basic information. The user (corporate customer) uses the terminal to input basic information such as company name, industry, contact person's name, and contact information.

[0963] Step 2:

[0964] The server saves the entered basic information to the database. The server assigns a unique identifier (user ID) to the user information and creates a profile for the new user.

[0965] Step 3:

[0966] The server collects data on the user's past behavior. This behavioral data includes the user's purchase history, website browsing history, and feedback on the content provided.

[0967] Step 4:

[0968] The server stores the collected behavioral data in a database. This data accumulation allows for the maintenance of a detailed history of the user's activities.

[0969] Step 5:

[0970] The server uses machine learning algorithms to analyze collected behavioral data and identify user preference patterns. For example, it can detect an interest in cloud services or security software based on past purchase history.

[0971] Step 6:

[0972] The server uses an emotion engine to analyze feedback and biometric information (such as facial expressions and tone of voice) collected from the user to obtain emotional data. For example, it measures positive reactions and the degree of excitement.

[0973] Step 7:

[0974] The server combines emotional data and preference patterns to update the user profile. This enhances the user's detailed preference patterns.

[0975] Step 8:

[0976] The server automatically generates customized content based on preference patterns and sentiment data. This content includes product and service information relevant to the user's interests, presented in a tone appropriate to their sentiment data.

[0977] Step 9:

[0978] The server generates customized content and sends it to the device. The device receives the content and notifies the user.

[0979] Step 10:

[0980] Users review the content provided through their devices and provide feedback. For example, they can comment on the usefulness of the content or areas that have newly piqued their interest.

[0981] Step 11:

[0982] The device sends user feedback to the server. The server receives the feedback and stores it in a database.

[0983] Step 12:

[0984] The server uses feedback and an emotion engine to evaluate the user's emotional state. For example, it identifies emotions (satisfied, interested, excited, etc.) at the time of feedback.

[0985] Step 13:

[0986] The server updates user preference data based on feedback and sentiment data. This reconstructs the latest preference patterns.

[0987] Step 14:

[0988] The server regenerates new customized content based on updated preference and sentiment data. For example, if a user starts showing interest in AI-related solutions, it will generate content that includes the latest AI-related information.

[0989] Step 15:

[0990] The server sends the regenerated customized content to the device, the device receives the content and notifies the user again. The user reviews the new content and provides further feedback as needed.

[0991] Through this series of steps, the system can flexibly respond to the diverse needs and emotional changes of users, and by continuously understanding the diverse needs of corporate clients, it can quickly uncover new business opportunities.

[0992] (Example 2)

[0993] 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."

[0994] Traditional customer preference analysis systems primarily relied on user behavior data, failing to consider user emotions and instantaneous feedback, making it difficult to provide highly accurate, customized content. Furthermore, they were inadequate in optimizing delivery timing and automating continuous feedback processes. Consequently, the discovery of new business opportunities and improvements in user satisfaction were limited. There is a need for a system that addresses these challenges, enabling more effective marketing strategies and responding promptly to diverse customer needs.

[0995] In Example 2, the identification processing by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting the user's basic information, means for collecting the user's past behavioral data, means for analyzing preference patterns using a machine learning algorithm based on the collected behavioral data, means for collecting and analyzing the user's emotional data, means for automatically generating customized content based on the preference patterns and emotional data, means for delivering the generated content to the user, means for receiving feedback from the user and updating the preference data and emotional data, and means for generating new customized content based on the updated preference data and emotional data and delivering it to the user again. This enables highly accurate preference analysis by integrating the user's behavioral data and real-time emotional data, and makes it possible to effectively deliver customized content optimized for the user.

[0996] "User basic information" refers to information entered during initial registration, such as the company name, industry, contact person's name, and contact details for corporate clients.

[0997] "Past behavioral data" refers to information about a user's past actions, such as their purchase history, website browsing history, and feedback on the content they have been provided.

[0998] A "machine learning algorithm" is an algorithm that learns features based on large amounts of data and automatically performs predictions and classifications.

[0999] A "preference pattern" refers to a user's preferences and interests, identified by analyzing their past behavioral data.

[1000] "Emotional data" refers to information about a user's instantaneous emotional state, obtained by analyzing biometric information such as the user's facial expressions and tone of voice.

[1001] "Customized content" refers to content that is automatically generated based on the user's preference patterns and emotional data, and is optimized for each individual user.

[1002] "Feedback" refers to opinions and information that users provide in response to the content they have been given, such as the usefulness of the content or areas in which they have newly developed an interest.

[1003] "Updated preference data" refers to data about users' preferences and interests that has been updated to the latest state based on user feedback.

[1004] "Optimizing delivery timing" is the process of determining the most effective time to deliver customized content, taking into account times that will not disrupt the user's work.

[1005] This invention is a system that uncovers potential demand by providing customized content tailored to the preferences and emotions of corporate clients and delivering messages to target specific customers. This system mainly consists of a server, user terminals, users, and an emotion analysis engine.

[1006] Initial registration and entry of basic information

[1007] First, the user completes the initial registration. During this process, the user terminal inputs the corporate customer's (user's) basic information, which the server then stores in a database. The server assigns a unique identifier to the user information and creates a profile for the new user. This basic information includes company name, industry, contact person's name, and contact details.

[1008] Collection of behavioral data

[1009] Next, the server collects data on the user's past behavior. This behavioral data includes the user's purchase history, website browsing history, and feedback on the content provided. The collected data is stored in a database and analyzed using machine learning algorithms, such as the scikit-learn library in Python. This identifies each user's preference patterns.

[1010] Collection and analysis of emotional data

[1011] The server further collects user emotional data using an emotion analysis engine. This emotional data includes feedback provided by the user, as well as facial expressions and tone of voice recorded while viewing content. This data is analyzed using emotion analysis software such as Amazon Rekognition or Microsoft Azure Emotion API to identify the user's instantaneous emotional state. The analysis results are stored in a database.

[1012] Generating customized content

[1013] Based on identified preference patterns and emotional data, the server automatically generates customized content. This customized content includes product information and service announcements that the user is interested in, and is presented in an optimal tone that matches the user's emotional data.

[1014] Optimizing delivery timing

[1015] The server then optimizes the delivery timing of the generated customized content. This optimization takes into account the user's working hours and past content viewing trends. This ensures that the delivery plan is set up to avoid disrupting the user's work.

[1016] Content delivery and notifications

[1017] The generated customized content is sent from the server to the user's terminal. The user's terminal notifies the user of the content's arrival, and the user confirms it.

[1018] Gathering feedback and updating data

[1019] When a user provides feedback on the content provided, their device sends that feedback to the server. This feedback includes the usefulness of the content and any new areas of interest the user has developed. The server updates its database based on the received feedback and uses a sentiment analysis engine to re-evaluate the user's emotional state at the time of feedback.

[1020] Re-generating and distributing customized content

[1021] Based on updated preference and sentiment data, the server generates new, customized content and delivers it to the user again.

[1022] Examples of specific cases and prompt statements

[1023] For example, if a corporate client A has a strong interest in IT-related products, initial registration is performed, and the server collects and analyzes past purchase data and website browsing history to determine that A is interested in "cloud services" and "security software." Simultaneously, an emotion analysis engine analyzes feedback and biometric information to identify that A's representative has positive feelings towards these products.

[1024] Based on this, the server generates customized content, including relevant product information and white papers on the latest cloud services. This content is presented in a positive and energetic tone, and a plan is devised for its delivery at the optimal time. A receives the content and provides feedback and biometric information. For example, if the feedback indicates interest in "AI-related solutions," the server regenerates new customized content and delivers it to A again.

[1025] Examples of prompts include, "Retrieve the latest white paper on cloud services and generate content with a positive tone to deliver to corporate client A at the optimal time," and "Create a customized promotional message for security software based on the user's past purchase history and sentiment data."

[1026] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1027] Step 1:

[1028] The user terminal inputs the corporate customer's basic information and sends it to the server. The server stores the received basic information in a database, assigns a unique identifier, and creates a profile for the new user.

[1029] Input: Company name, industry, contact person's name, contact information

[1030] Output: User basic information and unique identifier stored in the database.

[1031] Specific operation: The user enters basic information into an input form on their terminal and presses the submit button. The server receives the HTTP request and writes the information to the database.

[1032] Step 2:

[1033] The server collects data on the user's past behavior. This behavioral data includes purchase history, website browsing history, and feedback on the content provided. The server stores the collected behavioral data in a database.

[1034] Input: User's past behavioral data (purchase history, browsing history, feedback)

[1035] Output: Behavioral data stored in the database

[1036] Specific operation: The server collects behavioral data through log analysis tools and APIs and records it in a database.

[1037] Step 3:

[1038] The server analyzes preference patterns using machine learning algorithms based on collected behavioral data. The Python scikit-learn library is used.

[1039] Input: Behavioral data stored in the database

[1040] Output: User preference patterns

[1041] Specific operation: The server trains a machine learning model and predicts preference patterns using behavioral data as input.

[1042] Step 4:

[1043] The server uses an emotion engine to collect user emotion data. This emotion data includes feedback provided by the user and biometric information (facial expressions, voice tone) recorded when viewing content.

[1044] Input: User feedback, biometric information

[1045] Output: Sentiment data stored in the database

[1046] Specific operation: The user's device collects biometric information using its camera and microphone and sends it to the server. The server analyzes the data using an emotion analysis engine and stores the results in a database.

[1047] Step 5:

[1048] The server generates customized content based on identified preference patterns and sentiment data. A generative AI model is used to create messages with the optimal tone and content for the user.

[1049] Input: Preference patterns, emotional data

[1050] Output: Customized content

[1051] Specific operation: The server uses a generated AI model to automatically generate customized messages based on feedback and preferences.

[1052] Step 6:

[1053] The server optimizes the delivery timing of the customized content it generates. This optimization is achieved by analyzing past content viewing trends.

[1054] Input: Preference patterns, past content viewing time data

[1055] Output: Optimal delivery timing

[1056] Specific operation: The server analyzes historical data to determine the most effective delivery time.

[1057] Step 7:

[1058] The server sends the generated customized content to the user's terminal and notifies the user. The user's terminal displays the received content to the user.

[1059] Input: Customized content, delivery timing

[1060] Output: Content notification to user terminal

[1061] Specific operation: The server sends customized content to the user's device using SMTP or push notifications, and the user's device notifies the user via a pop-up notification.

[1062] Step 8:

[1063] Users provide feedback on the content they are given, and their devices send that feedback to the server.

[1064] Input: User feedback

[1065] Output: Feedback data stored on the server

[1066] Specific operation: The user fills out a feedback form and presses the submit button. The user's device sends the feedback data to the server as an API request.

[1067] Step 9:

[1068] The server updates its database based on the feedback it receives, generates new customized content based on the updated preference and sentiment data, and delivers it to the user again.

[1069] Input: Feedback data, new preference data, sentiment data

[1070] Output: Updated customized content

[1071] Specific operation: The server analyzes the feedback and updates the preference patterns and sentiment data models. It generates new customized content and runs the process again from step 6.

[1072] (Application Example 2)

[1073] 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."

[1074] While conventional content distribution systems allowed for customization based on user preference data, they struggled to automatically generate and distribute content that considered users' instantaneous emotions. This made it difficult to capture user interest and achieve effective content distribution. Furthermore, effectively utilizing user feedback and their emotional state at the time was challenging. Consequently, it was difficult to flexibly respond to changes in user needs.

[1075] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting the user's basic information, means for collecting the user's past behavioral data, means for analyzing the collected behavioral data and identifying the user's preference patterns, means for collecting and analyzing the user's emotional data using an artificial intelligence analysis engine and supplementing the preference data with emotional data, means for automatically generating customized content based on the preference patterns and emotional data, means for delivering the generated content to the user, means for receiving feedback from the user, evaluating the emotional state and updating the preference data, and means for generating new customized content based on the updated preference data and delivering it to the user again. This makes it possible to deliver customized content that responds to changes in the user's preferences and emotions.

[1076] "Means for inputting basic user information" refers to an interface that allows a system to collect basic information from users, such as company name, industry, contact person's name, and contact details.

[1077] "Means of collecting users' past behavioral data" refers to functions that include methods for collecting behavioral data such as users' purchase history, website browsing history, and feedback on content provided.

[1078] "Means for analyzing collected behavioral data and identifying user preference patterns" refers to methods and algorithms for analyzing collected behavioral data and identifying user interests and preferences based on that analysis.

[1079] "A means of collecting and analyzing user emotional data using an artificial intelligence analysis engine and supplementing it with preference data" refers to a process of analyzing emotions from a user's facial expressions, tone of voice, and feedback, and integrating that data with existing preference data.

[1080] "Means for automatically generating customized content based on preference patterns and sentiment data" refers to systems and algorithms for automatically creating content adapted to identified preference patterns and sentiment data.

[1081] "Means of delivering generated content to users" refers to delivery methods that ensure users receive content at the most appropriate time.

[1082] "A means of receiving user feedback, evaluating emotional states, and updating preference data" refers to the process of analyzing user feedback and the emotional data at that time, and updating preference data based on that information.

[1083] "Means for generating and redistributing new customized content to users based on updated preference data" refers to methods and systems for creating new content using updated preference data and redistributing it to users.

[1084] This invention is a system that uncovers potential demand by providing customized content tailored to the preferences and emotions of corporate clients and delivering messages to target specific customers. This system consists of a server, user terminals, users, and an emotion engine.

[1085] First, the server collects basic user information. Users (corporate customers) enter basic information such as company name, industry, contact person's name, and contact details through a smartphone app. This information is stored in a database by the server, and an initial user profile is created. Through this process, the system assigns a unique identifier to each user.

[1086] Next, the server collects data on the user's past behavior. This behavioral data includes the user's purchase history, website browsing history, and feedback on the content provided. Based on this data, machine learning algorithms (e.g., TensorFlow or Scikit-learn) are used to analyze preference patterns. This identifies the types of products and services the user is interested in (e.g., cloud services, security software, etc.).

[1087] Furthermore, the server uses an emotion engine to collect and analyze user emotion data. This data is collected using the smartphone's camera and microphone, analyzing user feedback and biometric information (e.g., facial expressions and voice tone) during content viewing. This analysis utilizes artificial intelligence analysis engines such as Google Cloud Vision API and AWS Rekognition. The obtained emotion data is complemented by preference data, which is then used to identify the user's instantaneous emotional state.

[1088] Next, the server automatically generates customized content based on preference patterns and emotional data. This content generation uses an AI-based generation engine to create content that includes product information and service guides that are likely to be of most interest to the user. In addition, the expression method (e.g., positive and cheerful tone) is selected according to the user's emotional state.

[1089] The generated customized content is delivered from the server to the user's smartphone. The server calculates the optimal delivery time and plans to deliver the content at a time that does not disrupt the user's work. The system is used when the user receives and confirms the content.

[1090] When a user provides feedback on the content provided, the server receives that feedback. This feedback includes the usefulness of the content and any new areas of interest the user has developed. Based on the received feedback, the server updates its database and uses an emotion engine to evaluate the emotional state at the time of feedback. This updates the preference data again.

[1091] Based on updated preference data and newly collected sentiment data, the server generates and delivers newly customized content to the user again. For example, if a user begins to show interest in AI-related solutions, the server generates and delivers customized content that includes the latest AI-related information. This entire process allows the system to respond immediately to the user's changing needs and continuously uncover new business opportunities.

[1092] Specific example

[1093] Consider a case where a company is interested in cloud services. When a company representative enters basic information using a smartphone app, the server saves that information to a database. Past behavioral data (such as cloud service purchase history) is collected and analyzed to identify that the company is interested in cloud services. At the same time, a sentiment analysis engine is used to identify the representative's positive emotions.

[1094] Based on identified preference patterns and sentiment data, the server generates customized content, including the latest cloud service information, and delivers it to the assigned person. The person reviews the content and provides feedback (e.g., "I'm also interested in the latest AI-related solutions"). The server updates its database based on this feedback, generates new customized content, and delivers it again.

[1095] Example of a prompt

[1096] "We will deliver content based on the behavioral and emotional data of company representatives. Our goal is to provide them with the latest cloud service information in a customized format. Particularly important is delivering the content at the optimal time, when the representative is experiencing positive emotions."

[1097] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1098] Step 1:

[1099] Users enter basic information using a smartphone app. This basic information includes company name, industry, contact person's name, and contact details. The entered data is stored in a database by the server. Input: User's basic information. Output: Basic information stored in the database.

[1100] Step 2:

[1101] The server collects data on the user's past behavior. This past behavior data includes purchase history, website browsing history, and feedback on previously provided content. This collected data is stored in a database. Input: User behavior data. Output: Stored behavior data.

[1102] Step 3:

[1103] The server analyzes behavioral data collected using machine learning algorithms to identify user preference patterns. Algorithms used include TensorFlow and Scikit-learn. Input: Past behavioral data. Output: Identification of preference patterns.

[1104] Step 4:

[1105] When a user provides feedback via their smartphone, the device uses its camera and microphone to collect the user's biometric information (e.g., facial expressions and voice tone). This collected biometric information is then analyzed by an emotion analysis engine (e.g., Google Cloud Vision API, AWS Rekognition) to generate instantaneous emotion data. Input: Biometric information. Output: Emotion data.

[1106] Step 5:

[1107] The server automatically generates customized content based on preference patterns and sentiment data. The generated content includes products and services that the user may be interested in, and the presentation style is selected according to the sentiment data. An AI-based generation engine is used for this generation process. Input: Preference patterns and sentiment data. Output: Customized content.

[1108] Step 6:

[1109] The server generates customized content and delivers it to the smartphone app. The server calculates the optimal delivery time and plans delivery to avoid disrupting the user's work. Input: Customized content. Output: Content delivered to the app.

[1110] Step 7:

[1111] Users provide feedback on the content they are given. A smartphone app collects this feedback and sends it to a server. The feedback includes whether the content is useful and information about products or services that the user has recently become interested in. Input: User feedback. Output: Feedback sent to the server.

[1112] Step 8:

[1113] The server updates the database based on the feedback received and re-analyzes the preference data using machine learning algorithms. Simultaneously, it uses an emotion engine to evaluate the emotional state at the time of feedback and adds that data. Input: User feedback and emotion data. Output: Updated preference data.

[1114] Step 9:

[1115] The server automatically generates newly customized content based on updated preference and sentiment data and delivers it to the user again. Input: Updated preference and sentiment data. Output: Newly generated customized content.

[1116] 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.

[1117] 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.

[1118] 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.

[1119] [Fourth Embodiment]

[1120] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1121] 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.

[1122] 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).

[1123] 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.

[1124] 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.

[1125] 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).

[1126] 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.

[1127] 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.

[1128] 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.

[1129] 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.

[1130] 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.

[1131] 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.

[1132] 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".

[1133] This invention is a system that uncovers potential demand by providing customized content tailored to the preferences of corporate clients and delivering messages to target customers accordingly. This system mainly consists of a server, user terminals, and users.

[1134] First, initial user registration takes place within this system. The terminal inputs the user's (corporate customer's) basic information (company name, industry, contact person's name, contact information, etc.), and the server saves this information to the database. The server assigns a unique identifier to the user information and creates a profile for the new user.

[1135] Next, the server collects data on the user's past behavior. This behavioral data includes the user's past purchase history, website browsing history, and feedback on the content provided. The server stores this data in a database and analyzes it using machine learning algorithms. Based on the results of this analysis, the server identifies each user's preference patterns. For example, it might detect that a user is interested in cloud services or security software.

[1136] After identifying user preference patterns, the server automatically generates customized content based on these patterns. This content may include product information and service announcements that are likely to interest the user, and may also utilize specialized marketing materials. The server optimizes the timing of content delivery, planning delivery times that do not interfere with the user's work.

[1137] The generated content is sent from the server to the device. The device receives the content and notifies the user. The user reviews the content and provides feedback. This feedback may include whether the content was useful or if there were any new areas of interest. The user's feedback is then sent back to the server via the device.

[1138] The server updates user preference data based on the feedback received. Based on the updated preference data, new customized content is generated again. For example, if a user starts to show interest in AI-related solutions, the server generates and delivers content that includes the latest AI-related information.

[1139] By repeating this cycle, the server can always maintain the latest user preference data and provide highly accurate customized content. This makes it possible to meet the diverse needs of corporate clients and avoid missing potential business opportunities.

[1140] Specific example

[1141] For example, let's assume a corporate client A has a deep interest in IT-related products. After the user completes initial registration, the server collects and analyzes A's past purchase data and website browsing history, detecting that A is interested in "cloud services" and "security software." Based on this, the server automatically generates customized content, including relevant product information and the latest white papers on cloud services, and sends it to the device at the optimal delivery time.

[1142] Company A receives the content and provides feedback on it. For example, if the feedback includes information that they are also interested in AI-related solutions, the server generates new customized content related to AI solutions and delivers it to Company A again. Through this continuous cycle, the system can respond promptly to the changing needs of corporate customers and uncover new business opportunities.

[1143] The following describes the processing flow.

[1144] Step 1:

[1145] The terminal inputs the corporate customer's basic information (company name, industry, contact person, contact information, etc.). The user (corporate customer) then uses the terminal to register the necessary information.

[1146] Step 2:

[1147] The server saves basic information received from the terminal to the database. The server assigns a unique identifier (user ID) to the user information and creates a new user profile.

[1148] Step 3:

[1149] The server collects data on the user's past behavior. This behavioral data includes the user's purchase history, website browsing history, and feedback on previously provided content.

[1150] Step 4:

[1151] The server stores the collected behavioral data in a database. The accumulated data serves as material for analyzing user behavioral trends.

[1152] Step 5:

[1153] The server uses machine learning algorithms to analyze collected behavioral data and identify user preference patterns (areas of interest, product categories, etc.). For example, it can detect whether a user has a high interest in IT-related products.

[1154] Step 6:

[1155] The server automatically generates customized content (product information, service guides, white papers, etc.) based on identified preference patterns. The generated content is optimized for the user's areas of interest.

[1156] Step 7:

[1157] The server plans the timing of content delivery and selects a time that does not interfere with the user's work. It then develops an optimal delivery schedule.

[1158] Step 8:

[1159] The server sends the generated customized content to the device. The device receives the content and notifies the user. The user receives the notification and checks the content.

[1160] Step 9:

[1161] Users provide feedback on the content they are given. This feedback includes whether the content was useful, what new areas of interest they discovered, and so on.

[1162] Step 10:

[1163] The device sends user feedback to the server. The server receives the feedback and updates its database.

[1164] Step 11:

[1165] Based on the feedback received by the server, user preference data is updated, and the latest preference patterns are re-evaluated. This allows for the response to newly emerging areas of interest and changes in interests.

[1166] Step 12:

[1167] The server regenerates new customized content based on updated preference data. For example, if a user has started to show interest in AI-related solutions, it will create content that includes the latest information on AI.

[1168] Step 13:

[1169] The server sends the regenerated customized content to the device, the device receives the content and notifies the user again. The user reviews the new content and provides further feedback as needed.

[1170] Through this series of steps, the system can flexibly respond to the diverse needs of users and continuously discover new business opportunities.

[1171] (Example 1)

[1172] 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".

[1173] Traditional marketing systems for corporate clients have struggled to accurately understand individual customer preferences and interests and provide customized content based on those preferences. Furthermore, optimizing delivery timing and collecting and incorporating feedback were inefficient. There is a growing need for a system that can quickly respond to changes in user interests.

[1174] 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.

[1175] In this invention, the server includes means for inputting the user's basic information, means for collecting the user's past behavioral data, means for analyzing the collected behavioral data and identifying the user's preference patterns, means for automatically generating customized content based on the preference patterns, means for delivering the generated content to the user, means for receiving feedback from the user and updating the preference data, means for generating new customized content based on the updated preference data and delivering it to the user again, means for optimizing the delivery timing, and means for notifying the user using a terminal. This enables the provision of highly accurate customized content tailored to the user's individual preferences and allows for a rapid response to changes in interests.

[1176] "Means for inputting basic user information" refers to devices or software used to input and collect initial information about corporate customers, such as company name, industry, contact person's name, and contact information.

[1177] "Means of collecting users' past behavioral data" refers to devices or software used to collect data on past behavior, such as corporate customers' purchase history, website browsing history, and feedback on provided content.

[1178] "Means of analyzing collected behavioral data to identify user preference patterns" refers to machine learning algorithms and data analysis tools used to analyze collected data and identify the interests and concerns of corporate clients.

[1179] "Means for automatically generating customized content based on preference patterns" refers to devices or software that automatically create product information and service guides that are likely to be of interest to corporate customers, according to identified preference patterns.

[1180] "Means of delivering generated content to users" refers to devices or software used to deliver generated customized content to corporate customers.

[1181] "Means for receiving user feedback and updating preference data" refers to devices or software for collecting reactions and opinions on content from corporate customers and updating preference data based on that.

[1182] "Means for generating and redistributing new customized content to users based on updated preference data" refers to devices or software for creating new customized content based on the latest preference data and redistributing it to corporate customers.

[1183] "Means for optimizing delivery timing" refers to devices or software that deliver content at the optimal time to avoid disrupting the business operations of corporate clients.

[1184] "Means of notifying users using a device" refers to devices or software used to notify corporate customers that new content has been delivered via their devices.

[1185] This invention is a system that uncovers potential demand by providing customized content tailored to the preferences of corporate clients and delivering messages to target specific customer segments. This system mainly consists of a server, user terminals, and users.

[1186] First, the user completes initial registration in this system. The user uses a terminal to access the initial registration screen. The terminal prompts the user to enter basic information (company name, industry, contact person's name, contact information, etc.), and the user enters this information. The terminal sends the collected information to the server, and the server stores the received information in a database. The server assigns a unique identifier and creates a profile for the new user.

[1187] Next, the server collects and analyzes the user's past behavioral data. This behavioral data includes the user's past purchase history, website browsing history, and feedback on the content provided. The server stores this data in a database and performs analysis using machine learning algorithms. This analysis allows the server to identify each user's preference patterns. For example, it might detect that a user is interested in cloud services or security software.

[1188] After identifying user preference patterns, the server automatically generates customized content. This content includes product information and service announcements likely to interest the user, and in some cases, specialized marketing materials. Furthermore, the server optimizes delivery timing, scheduling delivery to avoid disrupting the user's work.

[1189] The generated content is sent from the server to the device. The device receives the content and notifies the user. The user reviews the content and provides feedback. This feedback may include whether the content was useful or if they discovered any new areas of interest. The user's feedback is then sent back to the server via the device.

[1190] Based on the feedback received by the server, the user's preference data is updated. Based on the updated preference data, new customized content is generated again. For example, if a user starts to show interest in AI-related solutions, the server generates content including the latest AI-related information and delivers it to the user again.

[1191] By repeating this cycle, the server constantly maintains the latest user preference data and provides highly accurate customized content. This makes it possible to meet the diverse needs of corporate clients and avoid missing potential business opportunities.

[1192] Specific example

[1193] For example, let's assume a corporate client A has a deep interest in IT-related products. After the user completes initial registration, the server collects and analyzes A's past purchase data and website browsing history, detecting that A is interested in "cloud services" and "security software." Based on this, the server automatically generates customized content, including relevant product information and the latest white papers on cloud services, and sends it to the device at the optimal delivery time.

[1194] Company A receives the content and provides feedback on it. For example, if the feedback includes information that they are also interested in AI-related solutions, the server generates new customized content related to AI solutions and delivers it to Company A again. Through this continuous cycle, the system can respond promptly to the changing needs of corporate customers and uncover new business opportunities.

[1195] Examples of input prompts for a generative AI model

[1196] "If a user is detected as being interested in cloud services, generate customized content that includes relevant product information and service introductions. Additionally, if a new trend emerges showing interest in AI-related solutions, add corresponding content."

[1197] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1198] System program processing flow

[1199] Step 1: Initial Registration

[1200] The user accesses the initial registration screen using their device.

[1201] The terminal prompts the user to enter basic information (company name, industry, contact person's name, contact information, etc.).

[1202] Input data: Company name, industry, contact person's name, contact information.

[1203] The terminal receives the basic information entered by the user, organizes the data, and sends it to the server.

[1204] The server saves the received information to the database, assigns a unique identifier, and creates a profile for the new user.

[1205] Output data: Basic information and a unique identifier stored in the database.

[1206] Step 2: Collecting behavioral data

[1207] The server periodically collects data on the user's past behavior from multiple data sources.

[1208] Data collected: Past purchase history, website browsing history, and feedback on the content provided.

[1209] The server organizes the behavioral data and stores it in a database.

[1210] Output data: Behavioral data stored in the database.

[1211] Step 3: Behavioral Data Analysis

[1212] The server retrieves behavioral data from the database and performs analysis using machine learning algorithms.

[1213] Input data: Behavioral data stored in the database.

[1214] The server identifies user preference patterns based on the collected data.

[1215] Specific actions: Identify an interest in cloud services and security software.

[1216] Output data: User preference patterns.

[1217] Step 4: Generating customized content

[1218] The server automatically generates customized content based on identified preference patterns.

[1219] Input data: User preference patterns.

[1220] The server creates content using a generation AI model.

[1221] The generated content will include product information and service announcements that are likely to be of interest.

[1222] Output data: The generated customized content.

[1223] Step 5: Optimizing delivery timing

[1224] The server calculates the timing for delivering the generated content.

[1225] Input data: Data related to the user's work schedule and time slots.

[1226] The server calculates the optimal delivery timing and creates a delivery plan.

[1227] Specific action: Set the delivery time to avoid interfering with work.

[1228] Output data: Distribution plan.

[1229] Step 6: Content Distribution

[1230] The server sends the generated customized content to the terminal.

[1231] Input data: Generated customized content, delivery plan.

[1232] The device notifies the user of the content it has received.

[1233] Output data: User review history of content.

[1234] Step 7: Gathering Feedback

[1235] The user reviews the content they receive and provides feedback.

[1236] Input data: Customized content.

[1237] Specific action: Inputting feedback.

[1238] The user sends feedback to the server via their device.

[1239] Output data: Feedback information.

[1240] Step 8: Update preference data

[1241] The server analyzes the feedback it receives and updates the user preference data.

[1242] Input data: Feedback information.

[1243] Specific action: Update preference data.

[1244] Output data: Updated preference data.

[1245] Step 9: Generate and distribute new customized content.

[1246] The server regenerates new customized content based on the updated preference data.

[1247] Input data: Updated preference data.

[1248] The server uses a generated AI model to create and redistribute new content.

[1249] Specific actions: Create new content based on the previous broadcast and feedback.

[1250] Output data: New customized content.

[1251] (Application Example 1)

[1252] 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".

[1253] To meet the diverse needs of corporate clients and avoid missing potential business opportunities, it is crucial to provide customized content to each client in a timely manner. However, conventional systems have struggled to accurately analyze user preference patterns and deliver content at the optimal time. Furthermore, there have been insufficient methods for effectively utilizing user feedback to reflect new preferences.

[1254] 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.

[1255] In this invention, the server includes means for inputting the user's basic information, means for collecting the user's past behavioral data, means for analyzing the collected behavioral data and identifying the user's preference patterns, means for automatically generating customized content based on the preference patterns, means for delivering the generated content to the user, means for receiving feedback from the user and updating the preference data, means for generating new customized content based on the updated preference data and delivering it to the user again, means for analyzing and learning data using machine learning algorithms, and means for planning and executing the optimal content delivery timing. This makes it possible to respond immediately to the changing needs of corporate customers and discover new business opportunities.

[1256] "Means for entering basic user information" refers to system elements for entering initial registration information such as the company name, industry, contact person's name, and contact information of corporate customers.

[1257] "Means for collecting users' past behavioral data" refers to system elements for collecting data such as corporate customers' purchase history, website browsing history, and feedback on provided content.

[1258] "Means for analyzing collected behavioral data and identifying user preference patterns" refers to algorithms and system elements for analyzing collected data and identifying the interests and concerns of individual corporate customers.

[1259] "Means for automatically generating customized content based on preference patterns" refers to system elements for generating product information and service guides that are likely to be of interest to corporate customers, based on identified preference patterns.

[1260] "Means for delivering generated content to users" refers to system elements for delivering generated customized content to corporate customers at the appropriate time.

[1261] "Means for receiving user feedback and updating preference data" refers to system elements for collecting feedback from corporate customers and updating preference data based on that feedback.

[1262] "A means of generating new customized content based on updated preference data and redistributing it to users" refers to a system element for generating new customized content based on updated preference data and redistributing it to corporate customers.

[1263] "Means of analyzing and learning from data using machine learning algorithms" refers to system elements that use machine learning algorithms to analyze and learn from data.

[1264] "Means for planning and executing the optimal content delivery timing" refers to system elements for planning and executing the delivery of customized content at the optimal time that does not interfere with the business operations of corporate clients.

[1265] The system implementing this invention provides customized content to corporate clients and uncovers potential business opportunities. The system mainly consists of the following components:

[1266] System Configuration

[1267] 1. User Registration Method

[1268] The server provides a user registration mechanism for corporate customers to enter basic information such as company name, industry, contact person's name, and contact details. This basic information is entered via an electronic form and stored in a database.

[1269] 2. Data Collection Methods

[1270] The server collects past purchase history, website browsing history, and feedback data on the content provided to corporate customers. This data is collected via an omnichannel integration tool and stored in a database.

[1271] 3. Data Analysis Methods

[1272] The server analyzes the collected data using machine learning algorithms (such as Python's scikit-learn or TensorFlow) to identify user preference patterns. Based on these identified preference patterns, it infers the product categories that the user is interested in.

[1273] 4. Content Generation Methods

[1274] The server generates customized content based on identified preference patterns. This content includes product information and service announcements that are likely to be of interest to corporate customers. The content is automatically generated using a generation AI model.

[1275] 5. Content distribution methods

[1276] The generated content is delivered to corporate clients at the optimal time. This includes using notification systems designed to prevent clients from interrupting their work, for example.

[1277] 6. Methods for collecting feedback

[1278] The server collects customer feedback (such as whether the content was useful or if they discovered any new areas of interest). This feedback information is then stored in the database.

[1279] 7. Data update and regeneration means

[1280] The server updates user preference data based on collected feedback, and then generates and delivers customized content again. This cycle is repeated automatically by the system.

[1281] 8. Optimal delivery timing planning method

[1282] The server plans and executes the optimal delivery timing to avoid disrupting the business operations of corporate clients. This ensures that information is provided without impairing the client's operational efficiency.

[1283] Specific examples and prompt statements

[1284] For example, if a corporate client has a strong interest in IT-related products, after the user completes initial registration, the server collects and analyzes the client's past purchase history and website browsing history. The server identifies that this client is interested in "cloud services" and "security software." Based on this, it automatically generates customized content, including relevant product information and the latest white papers on cloud services, and sends it to the terminal at the optimal delivery time.

[1285] Example of a prompt:

[1286] User ID 12345 has shown a strong interest in cloud services and security software, and has recently become interested in AI solutions as well. Based on this information, please create customized marketing materials on the latest AI solutions and distribute them at the optimal time.

[1287] In this way, the system can respond immediately to the changing needs of corporate clients and uncover new business opportunities.

[1288] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1289] Step 1:

[1290] Entering basic user information

[1291] The server provides a form for corporate clients to input basic information such as company name, industry, contact person's name, and contact details. When a user enters this information using a terminal, the data is sent to the server and stored in the database. The input data includes company name, industry, contact person's name, and contact details, while the output is the user's basic information stored in the database.

[1292] Step 2:

[1293] Collection of past behavioral data

[1294] After the user enters basic information, the server collects the corporate customer's past purchase history, website browsing history, and feedback on the content provided. This data is collected using an omnichannel integration tool and stored in a database. Past behavioral data is obtained as input, and the collected data is stored in the database for analysis.

[1295] Step 3:

[1296] Analysis of collected data

[1297] The server uses machine learning algorithms (such as Python's scikit-learn or TensorFlow) to analyze past behavioral data stored in the database. This identifies user preference patterns. The collected behavioral data is used as input, and the output is the identification of preference patterns. Specifically, the process involves data preprocessing, feature extraction, and model application.

[1298] Step 4:

[1299] Generating customized content

[1300] The server automatically generates customized content using a generative AI model based on identified preference patterns. This includes product information and service guides that corporate customers are likely to be interested in. Preference patterns are obtained as input, and customized content is generated as output. Specifically, this involves text generation and content assembly.

[1301] Step 5:

[1302] Content distribution

[1303] The generated customized content is delivered to corporate customers by the server at the optimal time. A notification system is used for delivery, allowing users to view the content on their devices. The generated content is the input, and the output is delivered to the corporate customer's device. Specifically, the delivery schedule is set and messages are sent.

[1304] Step 6:

[1305] Gathering feedback

[1306] Users provide feedback on the provided content. This feedback is sent back to the server and stored in the database. Feedback data is received as input and stored in the database as output. Specifically, the process involves receiving feedback from users and saving it to the database.

[1307] Step 7:

[1308] Data update and regeneration

[1309] The server updates user preference data based on collected feedback and generates customized content again based on that. The updated preference data is taken as input, and new customized content is generated as output. Specifically, the process involves updating data, reanalyzing it, and generating new content.

[1310] Step 8:

[1311] Planning the optimal delivery timing

[1312] The server plans and executes the optimal content delivery timing to avoid disrupting the business operations of corporate clients. It receives client business information and generated content as input, and outputs an optimized delivery schedule. Specifically, it performs analysis of the business calendar and plans the delivery timing.

[1313] 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.

[1314] This invention is a system that uncovers potential demand by providing customized content tailored to the preferences and emotions of corporate clients and delivering messages to target specific customers. This system mainly consists of a server, user terminals, users, and an emotion engine.

[1315] First, initial user registration takes place within this system. The terminal inputs the user's (corporate customer's) basic information, and the server stores this information in a database. The server assigns a unique identifier to the user information and creates a profile for the new user. The user's basic information includes company name, industry, contact person's name, and contact information.

[1316] Next, the server collects data on the user's past behavior. This behavioral data includes the user's purchase history, website browsing history, and feedback on the content provided. The server stores this data in a database and uses machine learning algorithms to analyze it and identify each user's preference patterns. For example, it can determine whether a user is interested in cloud services or security software.

[1317] Furthermore, the server uses an emotion engine to recognize the user's emotions and collect emotion data. The emotion engine identifies the user's instantaneous emotional state by analyzing the feedback provided by the user and biometric information recorded when viewing content (e.g., facial expressions and tone of voice). This allows the server to complement the user's preference data with emotion data, building more accurate preference patterns.

[1318] Based on identified preference patterns and emotional data, the server automatically generates customized content. This content includes product and service information relevant to the user's interests, and the most appropriate presentation style is selected based on the emotional data. For example, if the user is excited, a positive and energetic message will be generated.

[1319] Next, the server optimizes the delivery timing and plans content delivery for times that do not disrupt the user's work. The generated customized content is sent from the server to the terminal. The terminal receives the content and notifies the user. The system is used when the user receives the notification and checks the content.

[1320] When a user provides feedback on the content they are given, their device sends that feedback to the server. This feedback includes whether the content was helpful and any new areas of interest they discovered. The server updates its database based on the received feedback and uses an emotion engine to evaluate the user's emotional state at the time of feedback. This data is then used to update the preference data again.

[1321] Based on updated preference data and new sentiment data, the server generates and delivers newly customized content to the user. For example, if a user becomes interested in AI-related solutions, the server will generate and deliver content that includes the latest information on AI.

[1322] Through this series of processing cycles, the system can flexibly respond to changes in user preferences and emotions, and by continuously understanding the diverse needs of corporate clients, it can quickly uncover new business opportunities.

[1323] Specific example

[1324] For example, let's assume a corporate client A has a deep interest in IT-related products. The user registers, and the server collects and analyzes past purchase data and website browsing history, revealing that company A is interested in "cloud services" and "security software." Simultaneously, an emotion engine analyzes the provided feedback and biometric information, identifying that the person in charge at company A has positive feelings towards these products.

[1325] Based on this, the server generates customized content, including relevant product information and white papers on the latest cloud services. This content is presented in a positive and energetic tone, and a distribution plan is formulated for optimal timing. Company A receives the content and provides feedback and biometric information. For example, if the feedback includes information such as "we are also interested in AI-related solutions," the server regenerates new customized content and delivers it to Company A again. Through this continuous cycle, the system can respond promptly to Company A's changing needs and continuously uncover new business opportunities.

[1326] The following describes the processing flow.

[1327] Step 1:

[1328] The terminal inputs the corporate customer's basic information. The user (corporate customer) uses the terminal to input basic information such as company name, industry, contact person's name, and contact information.

[1329] Step 2:

[1330] The server saves the entered basic information to the database. The server assigns a unique identifier (user ID) to the user information and creates a profile for the new user.

[1331] Step 3:

[1332] The server collects data on the user's past behavior. This behavioral data includes the user's purchase history, website browsing history, and feedback on the content provided.

[1333] Step 4:

[1334] The server stores the collected behavioral data in a database. This data accumulation allows for the maintenance of a detailed history of the user's activities.

[1335] Step 5:

[1336] The server uses machine learning algorithms to analyze collected behavioral data and identify user preference patterns. For example, it can detect an interest in cloud services or security software based on past purchase history.

[1337] Step 6:

[1338] The server uses an emotion engine to analyze feedback and biometric information (such as facial expressions and tone of voice) collected from the user to obtain emotional data. For example, it measures positive reactions and the degree of excitement.

[1339] Step 7:

[1340] The server combines emotional data and preference patterns to update the user profile. This enhances the user's detailed preference patterns.

[1341] Step 8:

[1342] The server automatically generates customized content based on preference patterns and sentiment data. This content includes product and service information relevant to the user's interests, presented in a tone appropriate to their sentiment data.

[1343] Step 9:

[1344] The server generates customized content and sends it to the device. The device receives the content and notifies the user.

[1345] Step 10:

[1346] Users review the content provided through their devices and provide feedback. For example, they can comment on the usefulness of the content or areas that have newly piqued their interest.

[1347] Step 11:

[1348] The device sends user feedback to the server. The server receives the feedback and stores it in a database.

[1349] Step 12:

[1350] The server uses feedback and an emotion engine to evaluate the user's emotional state. For example, it identifies emotions (satisfied, interested, excited, etc.) at the time of feedback.

[1351] Step 13:

[1352] The server updates user preference data based on feedback and sentiment data. This reconstructs the latest preference patterns.

[1353] Step 14:

[1354] The server regenerates new customized content based on updated preference and sentiment data. For example, if a user starts showing interest in AI-related solutions, it will generate content that includes the latest AI-related information.

[1355] Step 15:

[1356] The server sends the regenerated customized content to the device, the device receives the content and notifies the user again. The user reviews the new content and provides further feedback as needed.

[1357] Through this series of steps, the system can flexibly respond to the diverse needs and emotional changes of users, and by continuously understanding the diverse needs of corporate clients, it can quickly uncover new business opportunities.

[1358] (Example 2)

[1359] 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".

[1360] Traditional customer preference analysis systems primarily relied on user behavior data, failing to consider user emotions and instantaneous feedback, making it difficult to provide highly accurate, customized content. Furthermore, they were inadequate in optimizing delivery timing and automating continuous feedback processes. Consequently, the discovery of new business opportunities and improvements in user satisfaction were limited. There is a need for a system that addresses these challenges, enabling more effective marketing strategies and responding promptly to diverse customer needs.

[1361] In Example 2, the identification processing by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting the user's basic information, means for collecting the user's past behavioral data, means for analyzing preference patterns using a machine learning algorithm based on the collected behavioral data, means for collecting and analyzing the user's emotional data, means for automatically generating customized content based on the preference patterns and emotional data, means for delivering the generated content to the user, means for receiving feedback from the user and updating the preference data and emotional data, and means for generating new customized content based on the updated preference data and emotional data and delivering it to the user again. This enables highly accurate preference analysis by integrating the user's behavioral data and real-time emotional data, and makes it possible to effectively deliver customized content optimized for the user.

[1362] "User basic information" refers to information entered during initial registration, such as the company name, industry, contact person's name, and contact details for corporate clients.

[1363] "Past behavioral data" refers to information about a user's past actions, such as their purchase history, website browsing history, and feedback on the content they have been provided.

[1364] A "machine learning algorithm" is an algorithm that learns features based on large amounts of data and automatically performs predictions and classifications.

[1365] A "preference pattern" refers to a user's preferences and interests, identified by analyzing their past behavioral data.

[1366] "Emotional data" refers to information about a user's instantaneous emotional state, obtained by analyzing biometric information such as the user's facial expressions and tone of voice.

[1367] "Customized content" refers to content that is automatically generated based on the user's preference patterns and emotional data, and is optimized for each individual user.

[1368] "Feedback" refers to opinions and information that users provide in response to the content they have been given, such as the usefulness of the content or areas in which they have newly developed an interest.

[1369] "Updated preference data" refers to data about users' preferences and interests that has been updated to the latest state based on user feedback.

[1370] "Optimizing delivery timing" is the process of determining the most effective time to deliver customized content, taking into account times that will not disrupt the user's work.

[1371] This invention is a system that uncovers potential demand by providing customized content tailored to the preferences and emotions of corporate clients and delivering messages to target specific customers. This system mainly consists of a server, user terminals, users, and an emotion analysis engine.

[1372] Initial registration and entry of basic information

[1373] First, the user completes the initial registration. During this process, the user terminal inputs the corporate customer's (user's) basic information, which the server then stores in a database. The server assigns a unique identifier to the user information and creates a profile for the new user. This basic information includes company name, industry, contact person's name, and contact details.

[1374] Collection of behavioral data

[1375] Next, the server collects data on the user's past behavior. This behavioral data includes the user's purchase history, website browsing history, and feedback on the content provided. The collected data is stored in a database and analyzed using machine learning algorithms, such as the scikit-learn library in Python. This identifies each user's preference patterns.

[1376] Collection and analysis of emotional data

[1377] The server further collects user emotional data using an emotion analysis engine. This emotional data includes feedback provided by the user, as well as facial expressions and tone of voice recorded while viewing content. This data is analyzed using emotion analysis software such as Amazon Rekognition or Microsoft Azure Emotion API to identify the user's instantaneous emotional state. The analysis results are stored in a database.

[1378] Generating customized content

[1379] Based on identified preference patterns and emotional data, the server automatically generates customized content. This customized content includes product information and service announcements that the user is interested in, and is presented in an optimal tone that matches the user's emotional data.

[1380] Optimizing delivery timing

[1381] The server then optimizes the delivery timing of the generated customized content. This optimization takes into account the user's working hours and past content viewing trends. This ensures that the delivery plan is set up to avoid disrupting the user's work.

[1382] Content delivery and notifications

[1383] The generated customized content is sent from the server to the user's terminal. The user's terminal notifies the user of the content's arrival, and the user confirms it.

[1384] Gathering feedback and updating data

[1385] When a user provides feedback on the content provided, their device sends that feedback to the server. This feedback includes the usefulness of the content and any new areas of interest the user has developed. The server updates its database based on the received feedback and uses a sentiment analysis engine to re-evaluate the user's emotional state at the time of feedback.

[1386] Re-generating and distributing customized content

[1387] Based on updated preference and sentiment data, the server generates new, customized content and delivers it to the user again.

[1388] Examples of specific cases and prompt statements

[1389] For example, if a corporate client A has a strong interest in IT-related products, initial registration is performed, and the server collects and analyzes past purchase data and website browsing history to determine that A is interested in "cloud services" and "security software." Simultaneously, an emotion analysis engine analyzes feedback and biometric information to identify that A's representative has positive feelings towards these products.

[1390] Based on this, the server generates customized content, including relevant product information and white papers on the latest cloud services. This content is presented in a positive and energetic tone, and a plan is devised for its delivery at the optimal time. A receives the content and provides feedback and biometric information. For example, if the feedback indicates interest in "AI-related solutions," the server regenerates new customized content and delivers it to A again.

[1391] Examples of prompts include, "Retrieve the latest white paper on cloud services and generate content with a positive tone to deliver to corporate client A at the optimal time," and "Create a customized promotional message for security software based on the user's past purchase history and sentiment data."

[1392] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1393] Step 1:

[1394] The user terminal inputs the corporate customer's basic information and sends it to the server. The server stores the received basic information in a database, assigns a unique identifier, and creates a profile for the new user.

[1395] Input: Company name, industry, contact person's name, contact information

[1396] Output: User basic information and unique identifier stored in the database.

[1397] Specific operation: The user enters basic information into an input form on their terminal and presses the submit button. The server receives the HTTP request and writes the information to the database.

[1398] Step 2:

[1399] The server collects data on the user's past behavior. This behavioral data includes purchase history, website browsing history, and feedback on the content provided. The server stores the collected behavioral data in a database.

[1400] Input: User's past behavioral data (purchase history, browsing history, feedback)

[1401] Output: Behavioral data stored in the database

[1402] Specific operation: The server collects behavioral data through log analysis tools and APIs and records it in a database.

[1403] Step 3:

[1404] The server analyzes preference patterns using machine learning algorithms based on collected behavioral data. The Python scikit-learn library is used.

[1405] Input: Behavioral data stored in the database

[1406] Output: User preference patterns

[1407] Specific operation: The server trains a machine learning model and predicts preference patterns using behavioral data as input.

[1408] Step 4:

[1409] The server uses an emotion engine to collect user emotion data. This emotion data includes feedback provided by the user and biometric information (facial expressions, voice tone) recorded when viewing content.

[1410] Input: User feedback, biometric information

[1411] Output: Sentiment data stored in the database

[1412] Specific operation: The user's device collects biometric information using its camera and microphone and sends it to the server. The server analyzes the data using an emotion analysis engine and stores the results in a database.

[1413] Step 5:

[1414] The server generates customized content based on identified preference patterns and sentiment data. A generative AI model is used to create messages with the optimal tone and content for the user.

[1415] Input: Preference patterns, emotional data

[1416] Output: Customized content

[1417] Specific operation: The server uses a generated AI model to automatically generate customized messages based on feedback and preferences.

[1418] Step 6:

[1419] The server optimizes the delivery timing of the customized content it generates. This optimization is achieved by analyzing past content viewing trends.

[1420] Input: Preference patterns, past content viewing time data

[1421] Output: Optimal delivery timing

[1422] Specific operation: The server analyzes historical data to determine the most effective delivery time.

[1423] Step 7:

[1424] The server sends the generated customized content to the user's terminal and notifies the user. The user's terminal displays the received content to the user.

[1425] Input: Customized content, delivery timing

[1426] Output: Content notification to user terminal

[1427] Specific operation: The server sends customized content to the user's device using SMTP or push notifications, and the user's device notifies the user via a pop-up notification.

[1428] Step 8:

[1429] Users provide feedback on the content they are given, and their devices send that feedback to the server.

[1430] Input: User feedback

[1431] Output: Feedback data stored on the server

[1432] Specific operation: The user fills out a feedback form and presses the submit button. The user's device sends the feedback data to the server as an API request.

[1433] Step 9:

[1434] The server updates its database based on the feedback it receives, generates new customized content based on the updated preference and sentiment data, and delivers it to the user again.

[1435] Input: Feedback data, new preference data, sentiment data

[1436] Output: Updated customized content

[1437] Specific operation: The server analyzes the feedback and updates the preference patterns and sentiment data models. It generates new customized content and runs the process again from step 6.

[1438] (Application Example 2)

[1439] 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".

[1440] While conventional content distribution systems allowed for customization based on user preference data, they struggled to automatically generate and distribute content that considered users' instantaneous emotions. This made it difficult to capture user interest and achieve effective content distribution. Furthermore, effectively utilizing user feedback and their emotional state at the time was challenging. Consequently, it was difficult to flexibly respond to changes in user needs.

[1441] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting the user's basic information, means for collecting the user's past behavioral data, means for analyzing the collected behavioral data and identifying the user's preference patterns, means for collecting and analyzing the user's emotional data using an artificial intelligence analysis engine and supplementing the preference data with emotional data, means for automatically generating customized content based on the preference patterns and emotional data, means for delivering the generated content to the user, means for receiving feedback from the user, evaluating the emotional state and updating the preference data, and means for generating new customized content based on the updated preference data and delivering it to the user again. This makes it possible to deliver customized content that responds to changes in the user's preferences and emotions.

[1442] "Means for inputting basic user information" refers to an interface that allows the system to collect basic information from the user, such as company name, industry, contact person's name, and contact details.

[1443] "Means of collecting users' past behavioral data" refers to functions that include methods for collecting behavioral data such as users' purchase history, website browsing history, and feedback on content provided.

[1444] "Means for analyzing collected behavioral data and identifying user preference patterns" refers to methods and algorithms for analyzing collected behavioral data and identifying user interests and preferences based on that analysis.

[1445] "A means of collecting and analyzing user emotional data using an artificial intelligence analysis engine and supplementing it with preference data" refers to a process of analyzing emotions from a user's facial expressions, tone of voice, and feedback, and integrating that data with existing preference data.

[1446] "Means for automatically generating customized content based on preference patterns and sentiment data" refers to systems and algorithms for automatically creating content adapted to identified preference patterns and sentiment data.

[1447] "Means of delivering generated content to users" refers to delivery methods that ensure users receive content at the most appropriate time.

[1448] "A means of receiving user feedback, evaluating emotional states, and updating preference data" refers to the process of analyzing user feedback and the emotional data at that time, and updating preference data based on that information.

[1449] "Means for generating and redistributing new customized content to users based on updated preference data" refers to methods and systems for creating new content using updated preference data and redistributing it to users.

[1450] This invention is a system that uncovers potential demand by providing customized content tailored to the preferences and emotions of corporate clients and delivering messages to target specific customers. This system consists of a server, user terminals, users, and an emotion engine.

[1451] First, the server collects basic user information. Users (corporate customers) enter basic information such as company name, industry, contact person's name, and contact details through a smartphone app. This information is stored in a database by the server, and an initial user profile is created. Through this process, the system assigns a unique identifier to each user.

[1452] Next, the server collects data on the user's past behavior. This behavioral data includes the user's purchase history, website browsing history, and feedback on the content provided. Based on this data, machine learning algorithms (e.g., TensorFlow or Scikit-learn) are used to analyze preference patterns. This identifies the types of products and services the user is interested in (e.g., cloud services, security software, etc.).

[1453] Furthermore, the server uses an emotion engine to collect and analyze user emotion data. This data is collected using the smartphone's camera and microphone, analyzing user feedback and biometric information (e.g., facial expressions and voice tone) during content viewing. This analysis utilizes artificial intelligence analysis engines such as Google Cloud Vision API and AWS Rekognition. The obtained emotion data is complemented by preference data, which is then used to identify the user's instantaneous emotional state.

[1454] Next, the server automatically generates customized content based on preference patterns and emotional data. This content generation uses an AI-based generation engine to create content that includes product information and service guides that are likely to be of most interest to the user. In addition, the expression method (e.g., positive and cheerful tone) is selected according to the user's emotional state.

[1455] The generated customized content is delivered from the server to the user's smartphone. The server calculates the optimal delivery time and plans to deliver the content at a time that does not disrupt the user's work. The system is used when the user receives and confirms the content.

[1456] When a user provides feedback on the content provided, the server receives that feedback. This feedback includes the usefulness of the content and any new areas of interest the user has developed. Based on the received feedback, the server updates its database and uses an emotion engine to evaluate the emotional state at the time of feedback. This updates the preference data again.

[1457] Based on updated preference data and newly collected sentiment data, the server generates and delivers newly customized content to the user again. For example, if a user begins to show interest in AI-related solutions, the server generates and delivers customized content that includes the latest AI-related information. This entire process allows the system to respond immediately to the user's changing needs and continuously uncover new business opportunities.

[1458] Specific example

[1459] Consider a case where a company is interested in cloud services. When a company representative enters basic information using a smartphone app, the server saves that information to a database. Past behavioral data (such as cloud service purchase history) is collected and analyzed to identify that the company is interested in cloud services. At the same time, a sentiment analysis engine is used to identify the representative's positive emotions.

[1460] Based on identified preference patterns and sentiment data, the server generates customized content, including the latest cloud service information, and delivers it to the assigned person. The person reviews the content and provides feedback (e.g., "I'm also interested in the latest AI-related solutions"). The server updates its database based on this feedback, generates new customized content, and delivers it again.

[1461] Example of a prompt

[1462] "We will deliver content based on the behavioral and emotional data of company representatives. Our goal is to provide them with the latest cloud service information in a customized format. Particularly important is delivering the content at the optimal time, when the representative is experiencing positive emotions."

[1463] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1464] Step 1:

[1465] Users enter basic information using a smartphone app. This basic information includes company name, industry, contact person's name, and contact details. The entered data is stored in a database by the server. Input: User's basic information. Output: Basic information stored in the database.

[1466] Step 2:

[1467] The server collects data on the user's past behavior. This past behavior data includes purchase history, website browsing history, and feedback on previously provided content. This collected data is stored in a database. Input: User behavior data. Output: Stored behavior data.

[1468] Step 3:

[1469] The server analyzes behavioral data collected using machine learning algorithms to identify user preference patterns. The algorithms used include TensorFlow and Scikit-learn. Input: Past behavioral data. Output: Identification of preference patterns.

[1470] Step 4:

[1471] When a user provides feedback via their smartphone, the device uses its camera and microphone to collect the user's biometric information (e.g., facial expressions and voice tone). This collected biometric information is then analyzed by an emotion analysis engine (e.g., Google Cloud Vision API, AWS Rekognition) to generate instantaneous emotion data. Input: Biometric information. Output: Emotion data.

[1472] Step 5:

[1473] The server automatically generates customized content based on preference patterns and sentiment data. The generated content includes products and services that the user may be interested in, and the presentation style is selected according to the sentiment data. An AI-based generation engine is used for this generation process. Input: Preference patterns and sentiment data. Output: Customized content.

[1474] Step 6:

[1475] The server generates customized content and delivers it to the smartphone app. The server calculates the optimal delivery time and plans delivery to avoid disrupting the user's work. Input: Customized content. Output: Content delivered to the app.

[1476] Step 7:

[1477] Users provide feedback on the content they are given. A smartphone app collects this feedback and sends it to a server. The feedback includes whether the content is useful and information about products or services that the user has recently become interested in. Input: User feedback. Output: Feedback sent to the server.

[1478] Step 8:

[1479] The server updates the database based on the feedback received and re-analyzes the preference data using machine learning algorithms. Simultaneously, it uses an emotion engine to evaluate the emotional state at the time of feedback and adds that data. Input: User feedback and emotion data. Output: Updated preference data.

[1480] Step 9:

[1481] The server automatically generates newly customized content based on updated preference and sentiment data and delivers it to the user again. Input: Updated preference and sentiment data. Output: Newly generated customized content.

[1482] 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.

[1483] 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.

[1484] 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 robot 414.

[1485] 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.

[1486] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1487] 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.

[1488] 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.

[1489] 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.

[1490] 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."

[1491] 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.

[1492] 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.

[1493] 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.

[1494] 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.

[1495] 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.

[1496] 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.

[1497] 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.

[1498] 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.

[1499] 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.

[1500] 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.

[1501] 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.

[1502] 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.

[1503] The following is further disclosed regarding the embodiments described above.

[1504] (Claim 1)

[1505] A means of entering the user's basic information,

[1506] Means for collecting users' past behavioral data,

[1507] A means of analyzing collected behavioral data to identify user preference patterns,

[1508] A means for automatically generating customized content based on preference patterns,

[1509] A means of delivering the generated content to the user,

[1510] A means of receiving user feedback and updating preference data,

[1511] A means of generating new customized content based on updated preference data and delivering it to the user again,

[1512] A system that includes this.

[1513] (Claim 2)

[1514] The system according to claim 1, which stores the user's basic information in a database.

[1515] (Claim 3)

[1516] The system according to claim 1, which analyzes preference patterns using a machine learning algorithm based on collected behavioral data.

[1517] (Claim 4)

[1518] The system according to claim 1, which creates a content delivery plan at the optimal timing based on preference data.

[1519] (Claim 5)

[1520] The system according to claim 1, which performs demand forecasting based on user feedback.

[1521] "Example 1"

[1522] (Claim 1)

[1523] A means of entering the user's basic information,

[1524] Means for collecting users' past behavioral data,

[1525] A means of analyzing collected behavioral data to identify user preference patterns,

[1526] A means for automatically generating customized content based on preference patterns,

[1527] A means of delivering the generated content to the user,

[1528] A means of receiving user feedback and updating preference data,

[1529] A means of generating new customized content based on updated preference data and delivering it to the user again,

[1530] A means to optimize the timing of delivery,

[1531] A means of notifying the user using a device,

[1532] A system that includes this.

[1533] (Claim 2)

[1534] The system according to claim 1, which stores the user's basic information in a database.

[1535] (Claim 3)

[1536] The system according to claim 1, which analyzes preference patterns using a machine learning algorithm based on collected behavioral data.

[1537] "Application Example 1"

[1538] (Claim 1)

[1539] A means of entering the user's basic information,

[1540] Means for collecting users' past behavioral data,

[1541] A means of analyzing collected behavioral data to identify user preference patterns,

[1542] A means for automatically generating customized content based on preference patterns,

[1543] A means of delivering the generated content to the user,

[1544] A means of receiving user feedback and updating preference data,

[1545] A means of generating new customized content based on updated preference data and delivering it to the user again,

[1546] Methods for analyzing and learning data using machine learning algorithms,

[1547] Means for planning and executing the optimal content delivery timing,

[1548] A system that includes this.

[1549] (Claim 2)

[1550] The system according to claim 1, which stores the user's basic information in a database.

[1551] (Claim 3)

[1552] The system according to claim 1, which analyzes preference patterns using a machine learning algorithm based on collected behavioral data.

[1553] "Example 2 of combining an emotion engine"

[1554] (Claim 1)

[1555] A means of entering the user's basic information,

[1556] Means for collecting users' past behavioral data,

[1557] A method for analyzing preference patterns using machine learning algorithms based on collected behavioral data,

[1558] A means of collecting and analyzing user sentiment data,

[1559] A means of automatically generating customized content based on preference patterns and emotional data,

[1560] A means of delivering the generated content to the user,

[1561] A means of receiving user feedback and updating preference data and sentiment data,

[1562] A means of generating new customized content based on updated preference and sentiment data and delivering it to the user again,

[1563] A system that includes this.

[1564] (Claim 2)

[1565] The system according to claim 1, which stores the user's basic information in a database.

[1566] (Claim 3)

[1567] The system according to claim 1, which analyzes preference patterns and emotional patterns using a machine learning algorithm based on collected behavioral data and emotional data.

[1568] "Application example 2 when combining with an emotional engine"

[1569] (Claim 1)

[1570] A means of entering the user's basic information,

[1571] Means for collecting users' past behavioral data,

[1572] A means of analyzing collected behavioral data to identify user preference patterns,

[1573] A means of collecting and analyzing user emotional data using an artificial intelligence analysis engine, and supplementing preference data with emotional data,

[1574] A means of automatically generating customized content based on preference patterns and emotional data,

[1575] A means of delivering the generated content to the user,

[1576] A means of receiving user feedback, evaluating emotional states, and updating preference data,

[1577] A means of generating new customized content based on updated preference data and delivering it to the user again,

[1578] A system that includes this.

[1579] (Claim 2)

[1580] The system according to claim 1, which stores the user's basic information in a database.

[1581] (Claim 3)

[1582] The system according to claim 1, which analyzes preference patterns using a machine learning algorithm based on collected behavioral and emotional data. [Explanation of symbols]

[1583] 10, 210, 310, 410 Data Processing Systems 12 D...

Claims

1. A means of entering the user's basic information, Means for collecting users' past behavioral data, A means of analyzing collected behavioral data to identify user preference patterns, A means for automatically generating customized content based on preference patterns, A means of delivering the generated content to the user, A means of receiving user feedback and updating preference data, A means of generating new customized content based on updated preference data and delivering it to the user again, A system that includes this.

2. The system according to claim 1, which stores the user's basic information in a database.

3. The system according to claim 1, which analyzes preference patterns using a machine learning algorithm based on collected behavioral data.

4. The system according to claim 1, which creates a content delivery plan at the optimal timing based on preference data.

5. The system according to claim 1, which performs demand forecasting based on user feedback.

Images