system

Abstract

We provide the system. [Solution] A means for obtaining user history information from a database, An analytical method for identifying user characteristics by analyzing acquired historical information, A generation means for generating character information based on characteristics, Anonymization methods to anonymize users' personal information, A transmission means for sending the generated character information to the user's device, An improvement means that receives response information from the device and reflects it in improving the text information, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In current advertising systems, uniform messages using templates are mainstream, and personalization considering the individual characteristics and history information of users is insufficient. For this reason, it is difficult to send messages tailored to the interests and concerns of users, and there are limitations in improving the conversion rate and enhancing the customer experience, which is an issue.

Means for Solving the Problems

[0005] This invention provides a means for acquiring user history information from a database and identifying user characteristics by analyzing that information. It then provides a means for generating text information based on those characteristics to form individually optimized messages. Furthermore, it uses a means for anonymizing personal information within the generated text information to protect user privacy while transmitting the text information to the user's device. The invention also provides a system that includes a means for receiving response information from the device as feedback and reflecting it in subsequent message generation, thereby solving the aforementioned problems.

[0006] A "database" is an information infrastructure for systematically accumulating and managing various types of information, and it is possible to search and extract information based on specific conditions.

[0007] "History information" refers to records of a user's past actions and operations, and serves as basic data for inferring the user's characteristics.

[0008] "Acquisition means" refers to a function or device for extracting and utilizing necessary information from a database or similar source.

[0009] "Analysis means" refers to techniques or methods for processing collected information and revealing the characteristics and trends of users.

[0010] "Characteristics" refer to the characteristics of interests and behavioral patterns that users exhibit based on their past actions and history.

[0011] "Generation means" refers to a technology or device that creates new character information or data based on specific rules or algorithms.

[0012] "Textual information" refers to information in text format intended for users, created by a generation method.

[0013] "Anonymization methods" are technologies that make elements that could identify an individual invisible or remove them from information, and are intended to protect privacy.

[0014] "Transmission means" refers to a communication function or method for delivering generated character information to a specific device or user.

[0015] "Response information" refers to data about the reactions and responses that users give to text information, and is useful for future improvements.

[0016] "Improvement measures" refer to techniques or methods for improving processes or results based on collected response information. [Brief explanation of the drawing]

[0017] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10]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

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

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

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

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

[0022] 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.

[0023] 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).

[0024] 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."

[0025] [First Embodiment]

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

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0032] 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.

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

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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".

[0038] The system implementing this invention is a system that utilizes user history information to generate and deliver effective personalized advertisements. This system mainly consists of a server, a terminal, and a user.

[0039] The server first retrieves user history information from the database. This history information includes data such as what services the user has used in the past and what products they have purchased. Next, the server analyzes this history information to identify the user's characteristics. This is a process that uses machine learning and statistical methods to infer the user's behavior patterns and interests.

[0040] Based on identified characteristics, the server uses a generative AI model to generate personalized text information. This text information is customized according to the user's interests and preferences, making it a more effective advertisement.

[0041] After the text data is generated, the server anonymizes the personal information. This process removes any information that could identify the user, ensuring privacy. The anonymized text data is then sent from the server to the user's device.

[0042] The device displays the received text information to the user, who then reviews its content. The device then records the user's response to the message. This response information is sent back to the server and used to improve future personalized advertisements.

[0043] As a concrete example, consider a case where a user has an interest in cooking. The server analyzes the user's browsing history, identifies their cooking-related characteristics, and generates messages such as "new recipe information" or "cooking class campaign information." If the user receives this information on their device, shows interest, and clicks a link to see more details, the server can use that response to inform future ad generation.

[0044] Thus, the system for implementing the present invention enables the dynamic generation and efficient delivery of personalized advertisements that meet the needs of users.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The server accesses the database to retrieve the user's past history information. This information includes past purchase history, access logs, and search history. This data forms the basis for analyzing the user's behavior patterns and interests.

[0048] Step 2:

[0049] The historical information acquired by the server is organized using data cleansing techniques. Incomplete or inconsistent data is corrected, making it suitable for analysis. This process is crucial for ensuring data accuracy.

[0050] Step 3:

[0051] The server analyzes the cleansed data to identify user characteristics. Machine learning algorithms are used to model user interests and purchasing tendencies, creating characteristic profiles. These characteristic profiles form the basis for future personalization strategies.

[0052] Step 4:

[0053] The server utilizes a generation AI model to generate textual information based on characteristic profiles. The generated textual information is optimized for individual users and includes content designed to function as advertisements.

[0054] Step 5:

[0055] The server anonymizes the generated text information from a personal information protection standpoint. User privacy is maintained by removing or encrypting personally identifiable information.

[0056] Step 6:

[0057] The server sends anonymized text information to the user's device. The device receives this information and notifies the user, allowing the user to verify the content.

[0058] Step 7:

[0059] The device records the user's responses and sends the collected response information to the server. It also records user actions as data, such as opening a message or clicking a link.

[0060] Step 8:

[0061] The server analyzes the response information and uses it to improve future ad generation and user profile updates. This allows the generation AI model to continuously learn, resulting in more accurate personalization.

[0062] (Example 1)

[0063] 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."

[0064] In today's information and communication society, users are exposed to vast amounts of information, making it difficult to efficiently acquire information relevant to them. Furthermore, there is a lack of means to provide appropriately customized information to specific users while ensuring individual privacy. Additionally, there is a need for mechanisms to improve information quality by utilizing user feedback.

[0065] 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.

[0066] In this invention, the server includes means for acquiring user history information from a data management device, means for analyzing the acquired history information using information processing technology to identify user characteristics, and means for creating textual information using information generation technology based on those characteristics. This makes it possible to provide personalized information tailored to each user's needs while protecting their privacy, and to continuously improve the quality of the information based on user responses.

[0067] A "data management device" is equipment or a platform for organizing, storing, and managing information.

[0068] "User history information" refers to records of activities and behaviors associated with a specific user, including data on past service usage and product purchases.

[0069] "Information processing technology" is a general term for technologies used to analyze, interpret, and understand data.

[0070] "Methods for identifying characteristics" refer to methods for extracting patterns and trends from collected data to reveal users' preferences and behavioral characteristics.

[0071] "Information generation technology" refers to technology that automatically generates appropriate information based on the characteristics of the user.

[0072] "Textual information" refers to information expressed in written or text format.

[0073] "Personal identification information" refers to information used to directly or indirectly identify a specific individual.

[0074] "Means of communication" refers to the methods and protocols used to transmit information to its destination.

[0075] "Response information" refers to data that shows user feedback and behavioral records.

[0076] "Information optimization" is the process of improving the quality and relevance of the information provided, based on user feedback and other data.

[0077] This invention is a system for providing users with information tailored to their needs quickly and efficiently, and involves the server, terminal, and user working together to optimize ad delivery.

[0078] The server collects user history information from the data management device. This data includes the user's website visit history and purchase history. Next, the server uses a Python environment and formats the data using Pandas and NumPy. Then, it uses machine learning libraries such as TENSORFLOW® and Scikit-learn to analyze the collected data and identify user characteristics. This analysis helps to estimate what products and services the user is interested in.

[0079] Based on the identified user characteristics, the server uses a generative AI model to generate personalized text information. Specifically, it utilizes natural language processing technology as the generative model to create information based on pre-configured prompts. An example of a prompt might be, "Create customized ad copy based on the user's history." In this process, the generated ad copy is adjusted to match the user's interests and needs.

[0080] The server anonymizes personally identifiable information from the generated text data using Pandas or regular expressions. The anonymized data is then sent to the user's terminal using a secure communication protocol, such as HTTPS.

[0081] The terminal provides the user with anonymized text information received from the server. Front-end technologies such as HTML, CSS, and JavaScript (registered trademarks) are used to display the information in a user-friendly format.

[0082] Users can take action based on the displayed information. For example, they can obtain more detailed information by clicking on a provided link. Such user responses are recorded on the device and sent back to the server to be used to optimize future ad delivery.

[0083] This system maximizes the effectiveness of advertising and benefits all stakeholders by providing information that is tailored to the user's needs.

[0084] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0085] Step 1:

[0086] The server retrieves user history information from the data management device. At this stage, the server executes SQL queries against the database to extract relevant information such as the user's behavioral history and purchase history. The input is the user identifier, and the output is the data of the corresponding history information.

[0087] Step 2:

[0088] The server analyzes the acquired historical information using information processing technology. Here, the data is formatted and cleaned using the Python Pandas library. Next, machine learning models are applied to identify user characteristics using TensorFlow or Scikit-learn. The input is the historical information extracted in step 1, and the output is data points that indicate the user's interests and characteristics.

[0089] Step 3:

[0090] The server uses a generative AI model based on the user's characteristics to generate personalized text information. Specifically, it inputs prompt text into the generative AI model, which then generates ad copy that matches the user's characteristics. The input consists of user characteristic information and prompt text, while the output is personalized ad text directed at the user.

[0091] Step 4:

[0092] The server anonymizes the generated text information. Using Pandas and regular expressions, personally identifiable information is removed, and the data is processed to protect privacy. The input is the advertisement text obtained in step 3, and the output is the anonymized text information.

[0093] Step 5:

[0094] The server securely transmits anonymized text information to the user's device. Specifically, it uses the HTTPS protocol to transmit the data in an encrypted form. The input is the anonymized text obtained in step 4, and the output is the secure transmission of data to the user's device.

[0095] Step 6:

[0096] The terminal displays anonymized text information received from the server to the user. HTML, CSS, and JavaScript are used to generate an appropriate interface for visualizing the text for the user. The input is the data received from the server in step 5, and the output is the display screen on the terminal.

[0097] Step 7:

[0098] The user takes action based on the information displayed. For example, they might click a link in an advertisement, generating a response that is then recorded on their device. The input is the user's interaction, and the output is the generation of user behavior data.

[0099] Step 8:

[0100] The device sends user response information to the server, which is then used as feedback data for future ad generation. The input is user behavior data, and the output is the ad generation process for subsequent generations, reflecting the feedback.

[0101] (Application Example 1)

[0102] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0103] Traditional advertising delivery systems were limited to personalization based on user history information, making it difficult to deliver real-time advertisements tailored to the user's current situation and location. This resulted in limited advertising effectiveness and reduced relevance of information to the user.

[0104] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0105] In this invention, the server includes acquisition means for obtaining user history information from a database, analysis means for analyzing the acquired history information to identify user characteristics, generation means for generating text information based on characteristics, anonymization means for anonymizing the user's personal information, transmission means for transmitting the generated text information to the user's device, display means for immediately displaying relevant information using the device's location information, and improvement means for receiving response information from the device and reflecting it in improving the text information. This makes it possible to provide personalized advertisements in real time according to the user's situation and location.

[0106] "Acquisition method" refers to the method for retrieving user history information from a database.

[0107] "Analysis methods" refer to methods for extracting and analyzing acquired historical information to identify user characteristics.

[0108] "Generation means" refers to a method of creating textual information to be presented to a user based on specified characteristics.

[0109] An "anonymization method" is a method of removing users' personal information from generated text information to anonymize it.

[0110] "Transmission means" refers to a method for transferring the generated anonymized text information to the user's device.

[0111] "Display means" refers to a method of instantly displaying relevant information based on the location information of the device.

[0112] "Improvement methods" refer to methods of making improvements to future text information more effective based on response information obtained from the device.

[0113] The embodiment of this invention consists of a system centered on a server, a terminal, and a user. The server uses a cloud server such as Amazon Web Services (AWS®) or Google® Cloud, and the database uses MySQL®. On the terminal side, a smartphone application is developed using ANDROID® Studio or Swift.

[0114] The server first retrieves user history information from the database. This includes purchase history and location information. This data is preprocessed using Python, and user characteristics are analyzed using machine learning frameworks such as TensorFlow and PyTorch. Based on this characteristic analysis, generative AI models such as OpenAI's GPT are used to generate text information tailored to the user. This generated text information is processed using anonymization techniques (e.g., k-anonymization) to protect privacy.

[0115] The anonymized information is then sent to the device. The device uses location information obtained from GPS and other sensors to display relevant information at the appropriate time. This display aims to show the most relevant advertisements for the user's current location.

[0116] After information is displayed on the user's device, the user's reaction to that advertisement is recorded. For example, if the user clicks on the displayed advertisement, that data is sent from the device to the server and used to improve future ad generation processes.

[0117] For example, when a user is near a cafe, the app displays an advertisement such as, "Use our discount coupon for our new coffee product. Click here for details." An example of a prompt message is, "Generate a customized ad message based on the behavioral characteristics obtained from the history information of user ID: 12345. Present the most relevant offer based on the current location."

[0118] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0119] Step 1:

[0120] The server retrieves user history information from the database. In this step, SQL queries are executed based on the user ID to extract data such as past purchase history and location information. The input is the user ID, and the output is the history information associated with that user.

[0121] Step 2:

[0122] The system analyzes historical data acquired by the server to identify user characteristics. Data preprocessing is performed using Python, and the data is then fed into a model using machine learning frameworks such as TensorFlow or PyTorch. This identifies user behavior patterns and areas of interest. The input is historical data, and the output is extracted characteristic information.

[0123] Step 3:

[0124] The server generates text information using a generative AI model based on characteristics. It uses the OpenAI GPT model to create advertising messages tailored to the user's interests. The input is characteristic information, and the output is customized text information.

[0125] Step 4:

[0126] The server anonymizes personal information from the generated text data. Using k-anonymization technology, it creates text data that retains privacy. The input is the generated text data, and the output is the anonymized text data.

[0127] Step 5:

[0128] The server sends anonymized text information to the terminal. The data is then sent to the user's smartphone via network communication. The input is anonymized text information, and the output is confirmation that the information has been received on the terminal.

[0129] Step 6:

[0130] The system acquires text information received by the device and displays it appropriately based on location information. It uses a GPS sensor to adjust the display timing according to the user's current location. Input consists of text information and location data, while output is advertising information displayed on the user's screen.

[0131] Step 7:

[0132] The user reacts to the displayed advertisement, and this response information is recorded. The device collects data such as user clicks and viewing time. The input is the user's action log, and the output is the response information sent to the server.

[0133] Step 8:

[0134] The server analyzes the response information received from the terminal and incorporates it into subsequent advertisements. The ad generation process is updated to reflect changes in user interests and behavior. The input is the response information, and the output is the updated ad strategy.

[0135] 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.

[0136] The system implementing this invention is for generating and delivering personalized advertisements that also take into account the user's emotions. This system consists of a server, a terminal, and a user, and includes a novel element that incorporates an emotion engine in particular.

[0137] First, the server accesses the database to retrieve user history and purchase information. Based on this information, it analyzes the user's past behavior and interests. The server utilizes the characteristic profiles identified by the analysis tools, but a newly introduced sentiment engine extracts the user's sentiment trends from the history information. Sentiment trends play a crucial role in more accurately personalizing textual information.

[0138] The generation method incorporates the results of an emotion engine in addition to conventional algorithms, generating textual information that takes into account the user's emotional state and emotional changes. This textual information can include expressions and content that correspond to the user's emotions at that moment. Furthermore, the generated textual information is adjusted based on emotions and includes elements to deliver specific and empathetic messages to the user.

[0139] After generation, the server uses anonymization methods to remove personal information from the text data, protecting user privacy. The anonymized text data is then sent from the server to the terminal.

[0140] The device receives this information and notifies the user. When the user receives the message, their reaction (e.g., opening, clicking, replying) is recorded by the device. This record is reviewed based on emotional state and fed back to the server.

[0141] For example, if a user expresses interest in travel and the emotion engine detects from their recent history that they are experiencing stress, the server will generate an advertising message such as "Recommended travel destinations where you can relax." If the user sees this message on their device and makes a reservation, that response will be used as training data for the next generation process.

[0142] This system will enable companies to efficiently deliver personalized advertisements that resonate with users' emotions, and is expected to improve conversion rates and customer satisfaction.

[0143] The following describes the processing flow.

[0144] Step 1:

[0145] The server accesses the database to retrieve user history and purchase information. This information includes past purchase history, access logs, and search history. This allows for a comprehensive understanding of the user's behavior patterns.

[0146] Step 2:

[0147] The information acquired by the server is processed using data cleansing techniques. Missing or inconsistent data is removed, making it suitable for analysis. This allows for the creation of accurate user profiles.

[0148] Step 3:

[0149] The server uses an emotion engine to extract emotion trends from the user's history information. This process uses natural language processing techniques to recognize the user's emotional state from their text data.

[0150] Step 4:

[0151] The server uses analytical tools to identify user characteristics based on historical data and sentiment trends. This generates personalized information that addresses the user's areas of interest and emotional needs.

[0152] Step 5:

[0153] The server utilizes a generation AI model to generate text information based on characteristics and emotional trends. The generated text information includes content that corresponds to the user's current emotional state.

[0154] Step 6:

[0155] The server performs an anonymization process to remove personal information from text data. This ensures user privacy.

[0156] Step 7:

[0157] The server sends anonymized text information to the user's device. The device receives this information and manages when it is displayed to the user.

[0158] Step 8:

[0159] The device records the user's responses to messages. Data is collected when the user opens a message or clicks on a link, and this data is sent to the server.

[0160] Step 9:

[0161] The server analyzes the response information it collects and uses it to inform future message generation and user profile updates. This allows the entire system to continuously learn and provide more personalized services.

[0162] (Example 2)

[0163] 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".

[0164] Traditional personalized advertising systems primarily generated ads based on users' past history and purchase information. However, because they did not consider the user's emotional state, they sometimes delivered ads that were inconsistent with the user's mood at the time. This resulted in a failure to capture the user's attention and made effective ad delivery difficult. Furthermore, with the increasing demand for anonymization of users' personal information from a privacy protection perspective, there is a lack of technical means to achieve emotional personalization.

[0165] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0166] In this invention, the server includes means for acquiring user history information and purchase information from a data storage device; means for identifying the user's characteristic profile based on the acquired information; means for extracting the user's emotional trends using emotion analysis technology in addition to the characteristics identified by the analysis means and generating text information; means for transmitting the anonymized text information to the user's communication device; and means for receiving response information from the communication device and improving the text information. This makes it possible to provide personalized advertisements that take into account the user's emotional state while protecting personal information.

[0167] A "data storage device" is a storage medium that stores user history information and purchase information, and allows access and retrieval as needed.

[0168] "Acquisition means" refers to a function or process for acquiring user history information and purchase information from a data storage device.

[0169] "Analysis methods" refer to algorithms and techniques used to identify user characteristic profiles using acquired information.

[0170] "Generation means" refers to processes and devices for analyzing user characteristics and emotional trends to construct specific textual information.

[0171] "Sentiment analysis technology" is a technique for extracting emotional trends based on user history and purchase information, and it generally uses natural language processing.

[0172] An "anonymization method" is a process for removing or concealing personally identifiable information from generated textual information.

[0173] "Transmission means" refers to a function or system for transmitting anonymized text information to a user's communication device.

[0174] "Improvement measures" refer to technologies or processes for evaluating the effectiveness of text information based on response information from the user's device and reflecting this in the next generation process.

[0175] This invention relates to a system for efficiently generating and delivering personalized advertisements that take into account the emotions of users. The system consists of three elements: a server, a terminal, and a user, and incorporates a novel method using emotion analysis technology.

[0176] The server retrieves user history and purchase information from data storage devices. This retrieval is performed via a secure network connection and typically uses SQL database queries. Based on the retrieved information, the server uses machine learning algorithms to analyze the user's characteristic profile. This identifies the user's interests and behavioral patterns.

[0177] Next, the server uses sentiment analysis technology to extract sentiment trends from the user's past history. Here, analysis techniques utilizing natural language processing (NLP) are employed. For example, it calculates positive, negative, and neutral sentiment scores from the user's comments and reviews.

[0178] Based on the generated sentiment trends, the server utilizes a generative AI model to create text information optimized for the user. The generated advertisements reflect the user's current emotional state and include expressions tailored to individual needs. An example of inputting this prompt into the generative AI model would be: "Consider the user's past behavioral data and sentiment trends to generate a travel advertisement message with a relaxation theme."

[0179] After the advertisement is generated, the server uses an anonymization method to remove personal information from the generated text information in order to protect user privacy. This procedure removes personally identifiable information, thus protecting user privacy.

[0180] Anonymized text information is sent from the server to the device. Security protocols such as SSL / TLS are used for this transmission. The device notifies the user of the received text information and records the user's response. When the user opens an advertisement or clicks a link, that action is logged by the device.

[0181] Ultimately, the device feeds back the collected user response data to the server. This information is used to improve the next ad generation process. In this way, the accuracy and relatability of ads are improved, and user engagement is maximized.

[0182] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0183] Step 1:

[0184] The server accesses the data storage device to retrieve user history and purchase information. A specific user ID is given as input, and the output is a history dataset for that user. Specifically, the server executes SQL queries to aggregate data such as history and purchase history.

[0185] Step 2:

[0186] The server analyzes the user's characteristic profile based on the acquired data. The historical dataset obtained in Step 1 is used as input, and the user's characteristic profile is generated as output. Specifically, the server applies machine learning algorithms to analyze the user's interests and behavioral tendencies.

[0187] Step 3:

[0188] The server extracts user sentiment trends using sentiment analysis technology. The input is the historical information obtained in step 1, and sentiment trend data is generated as output. The server uses natural language processing (NLP) to calculate sentiment scores from reviews and comments.

[0189] Step 4:

[0190] The server generates text information that reflects the user's characteristic profile and sentiment trends using a generation method. The inputs are the characteristic profile from step 2 and the sentiment trend data from step 3, and the output is a personalized advertising message. The generation AI model generates customized messages tailored to the user's current situation.

[0191] Step 5:

[0192] The server performs an anonymization process to remove personal information from the generated text information. The input is the advertising message generated in step 4, and the output is an anonymized message. Specifically, identifiable personal information is masked by the algorithm.

[0193] Step 6:

[0194] The server sends anonymized text information to the terminal. The input is the anonymized message from step 5, and the output is the secure transmission of the message to the terminal. The server uses the SSL / TLS protocol to encrypt and send the message.

[0195] Step 7:

[0196] The device notifies the user of received advertising messages. The input is an anonymized message sent from the server, and the output is a notification displayed on the user interface. Specifically, the device displays the message in the smartphone's notification bar.

[0197] Step 8:

[0198] Users take action in response to advertising messages. The input is an advertising notification, and the output is the user's actions, such as clicks or link accesses, which are recorded on the device. Users open the message and click on links that interest them.

[0199] Step 9:

[0200] The device records user behavior data and sends feedback to the server. The input is the user's action, and the output is a log of behavior data, which is sent to the server. The device formats the log into JSON format and sends the data to the server.

[0201] (Application Example 2)

[0202] 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".

[0203] Traditional advertising systems generate personalized ads without considering the user's emotional state, sometimes resulting in users seeing ads they don't want. Furthermore, the lack of technology to analyze user emotions in real time and adjust ad content accordingly meant that ads failed to capture user interest, reducing their effectiveness.

[0204] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0205] In this invention, the server includes acquisition means for acquiring user behavior records from a data storage area, analysis means for analyzing the acquired behavior records to estimate the user's characteristics, and emotion analysis means for analyzing the user's emotional state using facial recognition and acoustic recognition. This makes it possible to display personalized advertisements in real time that are tailored to the user's emotional state.

[0206] "Data storage area" refers to the storage that stores user activity records, purchase history, and other related information.

[0207] A "user" is an individual or organization that uses the system, and is the subject of analysis of their behavioral records and emotional states.

[0208] "Activity log" refers to historical data about online or offline activities that a user has engaged in in the past.

[0209] "Acquisition means" refers to the mechanisms and processes for retrieving necessary information from the data storage area.

[0210] "Analysis means" refers to functions and methods for analyzing acquired behavioral records and extracting characteristics and trends.

[0211] "Characteristics" refer to information that indicates a user's interests, behavioral patterns, and personality.

[0212] A "generation method" is a method for assembling information that is optimal for the user based on the analyzed characteristics.

[0213] "Anonymization methods" are means used to remove or conceal personally identifiable information in order to protect the privacy of users.

[0214] "Transmission means" refers to the methods or techniques used to transmit generated information to the user's device.

[0215] "Response information" refers to the actions or responses that users exhibit in response to the information they receive.

[0216] "Improvement measures" refer to the process of making adjustments to the information generated based on reaction information, and the methods used to generate it, in order to make them more effective.

[0217] "Emotional analysis methods" refer to methods and technologies that use facial recognition or acoustic recognition of a user to evaluate their emotional state at any given time.

[0218] "Adjustment mechanisms" refer to functions that optimize the content and display method of information based on the results of sentiment analysis.

[0219] The system for implementing this invention mainly consists of a server, terminals, and users who utilize the terminals. The server accesses a data storage area and retrieves data such as user activity records and purchase history. This utilizes data storage systems such as SQL databases and NoSQL databases.

[0220] The server uses machine learning software such as TensorFlow and PyTorch as analysis tools to estimate user characteristics by analyzing acquired data. Furthermore, the emotion analysis tool uses input devices such as cameras and microphones to analyze the user's real-time emotional state. This analysis utilizes libraries such as OpenCV and natural language processing models.

[0221] Based on these analysis results, the server uses a generative AI model to generate information tailored to the user. This information is often structured in JSON or XML format. The generated information is anonymized, and any personally identifiable data is removed.

[0222] The device receives information sent from the server and displays it to the user visually or audibly. Examples of devices include smart glasses and portable computers. The device then records the user's reactions, such as ad click history, and sends this information back to the server as feedback. The server uses this feedback to improve the information it generates.

[0223] Specifically, if behavioral data indicates that a user is interested in a new gadget, the server will display a video demonstrating the gadget's use on the smart glasses when the user's emotions are heightened. Furthermore, if the user's face shows expressions of surprise or interest, additional promotional information will be displayed to encourage purchase.

[0224] An example of a prompt would be: "Show how to analyze a user's emotions in real time based on their video and audio data and generate personalized ads for new electronic devices."

[0225] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0226] Step 1:

[0227] The server accesses the data storage area to retrieve user activity records and purchase history. The input is a user ID, and the output is activity record data and purchase history data. This data is extracted from the database using SQL queries.

[0228] Step 2:

[0229] The server analyzes the acquired data and estimates the user's characteristics. The input is previously acquired behavioral record data and purchase history data, and the output is profile information indicating the user's interests and purchasing tendencies. A machine learning model using TensorFlow is used here. Profile information is generated by performing feature extraction and classification.

[0230] Step 3:

[0231] The server acquires real-time video and audio data from the user through the camera and microphone built into the smart glasses and performs emotion analysis. The input consists of video and audio data, and the output is analytical information indicating the user's emotional state. This process uses the OpenCV library for face recognition and applies an emotion estimation algorithm.

[0232] Step 4:

[0233] The server generates user-specific information using a generative AI model based on sentiment analysis and profile information. Input includes sentiment analysis and profile information, while output is user-specific advertising and presentation information. This generation process utilizes a machine learning model employing natural language processing techniques.

[0234] Step 5:

[0235] The server anonymizes the generated information to protect the user's personal information. The input is the generated advertising information, and the output is anonymized information from which personally identifiable elements have been removed. At this stage, the identification information is hashed.

[0236] Step 6:

[0237] The server sends anonymized information to the terminal. The input is the anonymized information, and the output is the data packet being transmitted. A secure communication protocol is used for this transmission.

[0238] Step 7:

[0239] The terminal displays received information to the user and records their response. The input is information sent from the server, and the output is user response data. Visual information is presented to the terminal via smart glasses.

[0240] Step 8:

[0241] The terminal feeds back recorded response data to the server. The input is the user's response data, and the output is the feedback data. This data is stored on the server as training data for future information generation.

[0242] 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.

[0243] 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.

[0244] 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.

[0245] [Second Embodiment]

[0246] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0247] 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.

[0248] 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).

[0249] 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.

[0250] 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.

[0251] 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).

[0252] 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.

[0253] 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.

[0254] 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.

[0255] 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.

[0256] 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.

[0257] 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".

[0258] The system implementing this invention is a system that utilizes user history information to generate and deliver effective personalized advertisements. This system mainly consists of a server, a terminal, and a user.

[0259] The server first retrieves user history information from the database. This history information includes data such as what services the user has used in the past and what products they have purchased. Next, the server analyzes this history information to identify the user's characteristics. This is a process that uses machine learning and statistical methods to infer the user's behavior patterns and interests.

[0260] Based on identified characteristics, the server uses a generative AI model to generate personalized text information. This text information is customized according to the user's interests and preferences, making it a more effective advertisement.

[0261] After the text data is generated, the server anonymizes the personal information. This process removes any information that could identify the user, ensuring privacy. The anonymized text data is then sent from the server to the user's device.

[0262] The device displays the received text information to the user, who then reviews its content. The device then records the user's response to the message. This response information is sent back to the server and used to improve future personalized advertisements.

[0263] As a concrete example, consider a case where a user has an interest in cooking. The server analyzes the user's browsing history, identifies their cooking-related characteristics, and generates messages such as "new recipe information" or "cooking class campaign information." If the user receives this information on their device, shows interest, and clicks a link to see more details, the server can use that response to inform future ad generation.

[0264] Thus, the system for implementing the present invention enables the dynamic generation and efficient delivery of personalized advertisements that meet the needs of users.

[0265] The following describes the processing flow.

[0266] Step 1:

[0267] The server accesses the database to retrieve the user's past history information. This information includes past purchase history, access logs, and search history. This data forms the basis for analyzing the user's behavior patterns and interests.

[0268] Step 2:

[0269] The historical information acquired by the server is organized using data cleansing techniques. Incomplete or inconsistent data is corrected, making it suitable for analysis. This process is crucial for ensuring data accuracy.

[0270] Step 3:

[0271] The server analyzes the cleansed data to identify user characteristics. Machine learning algorithms are used to model user interests and purchasing tendencies, creating characteristic profiles. These characteristic profiles form the basis for future personalization strategies.

[0272] Step 4:

[0273] The server utilizes a generation AI model to generate textual information based on characteristic profiles. The generated textual information is optimized for individual users and includes content designed to function as advertisements.

[0274] Step 5:

[0275] The server anonymizes the generated text information from a personal information protection standpoint. User privacy is maintained by removing or encrypting personally identifiable information.

[0276] Step 6:

[0277] The server sends anonymized text information to the user's device. The device receives this information and notifies the user, allowing the user to verify the content.

[0278] Step 7:

[0279] The terminal records the user's reaction and transmits the collected response information to the server. When the user opens a message or clicks on a link, etc., that action is recorded as data.

[0280] Step 8:

[0281] The server analyzes the response information and reflects it in subsequent advertisement generation and updating of the user characteristic profile. Thereby, the generated AI model continuously learns and realizes more accurate personalization.

[0282] (Example 1)

[0283] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0284] In modern information and communication society, users are exposed to a vast amount of information, and it is difficult to efficiently obtain information relevant to themselves from it. Also, there is a lack of means to provide appropriately customized information to specific users while ensuring personal privacy. Furthermore, a mechanism for improving the quality of information by utilizing feedback from users is required.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following respective means.

[0286] In this invention, the server includes means for acquiring the user's history information from a data management device, means for analyzing the acquired history information with information processing technology to identify the user's characteristics, and means for creating character information using information generation technology based on the characteristics. Thereby, it is possible to provide personalized information according to the needs of each user while protecting privacy, and further continuously improve the quality of information based on the responses from users.

[0287] A "data management device" is equipment or a platform for organizing, storing, and managing information.

[0288] "User history information" refers to records of activities and behaviors associated with a specific user, including data on past service usage and product purchases.

[0289] "Information processing technology" is a general term for technologies used to analyze, interpret, and understand data.

[0290] "Methods for identifying characteristics" refer to methods for extracting patterns and trends from collected data to reveal users' preferences and behavioral characteristics.

[0291] "Information generation technology" refers to technology that automatically generates appropriate information based on the characteristics of the user.

[0292] "Textual information" refers to information expressed in written or text format.

[0293] "Personal identification information" refers to information used to directly or indirectly identify a specific individual.

[0294] "Means of communication" refers to the methods and protocols used to transmit information to its destination.

[0295] "Response information" refers to data that shows user feedback and behavioral records.

[0296] "Information optimization" is the process of improving the quality and relevance of the information provided, based on user feedback and other data.

[0297] This invention is a system for providing users with information tailored to their needs quickly and efficiently, and involves the server, terminal, and user working together to optimize ad delivery.

[0298] The server collects user history information from the data management device. This data includes the user's website visit history and purchase history. Next, the server uses a Python environment and formats the data using Pandas and NumPy. Then, it uses machine learning libraries such as TensorFlow and Scikit-learn to analyze the collected data and identify user characteristics. This analysis helps to estimate what products and services the user is interested in.

[0299] Based on the identified user characteristics, the server uses a generative AI model to generate personalized text information. Specifically, it utilizes natural language processing technology as the generative model to create information based on pre-configured prompts. An example of a prompt might be, "Create customized ad copy based on the user's history." In this process, the generated ad copy is adjusted to match the user's interests and needs.

[0300] The server anonymizes personally identifiable information from the generated text data using Pandas or regular expressions. The anonymized data is then sent to the user's terminal using a secure communication protocol, such as HTTPS.

[0301] The terminal provides the user with anonymized text information received from the server. Front-end technologies such as HTML, CSS, and JavaScript are used to display the information in a user-friendly format.

[0302] Users can take action based on the displayed information. For example, they can obtain more detailed information by clicking on a provided link. Such user responses are recorded on the device and sent back to the server to be used to optimize future ad delivery.

[0303] This system maximizes the effectiveness of advertising and benefits all stakeholders by providing information that is tailored to the user's needs.

[0304] The process of the specific process in Example 1 will be described with reference to FIG. 11.

[0305] Step 1:

[0306] The server obtains the user's history information from the data management device. At this stage, the server executes an SQL query on the database to extract relevant information such as the user's behavior history and purchase history. The input is the user identifier, and the output is the data of the corresponding history information.

[0307] Step 2:

[0308] The server analyzes the acquired history information using information processing technology. Here, the Pandas library in Python is used to format and clean the data. Next, machine learning models for identifying user characteristics are applied using TensorFlow or Scikit-learn. The input is the history information extracted in Step 1, and the output is the data points indicating the user's interests and characteristics.

[0309] Step 3:

[0310] The server generates personalized text information using the generated AI model based on the user's characteristics. As a specific operation, a prompt sentence is input into the generated AI model to generate an advertisement text that matches the user's characteristics. The input is the user's characteristic information and the prompt sentence, and the output is the text information of the personalized advertisement for the user.

[0311] Step 4:

[0312] The server anonymizes the generated text information. Using Pandas and regular expressions, information that can identify an individual is excluded, and processing is performed to protect privacy. The input is the advertisement text obtained in Step 3, and the output is the anonymized text information.

[0313] Step 5:

[0314] The server securely transmits anonymized text information to the user's device. Specifically, it uses the HTTPS protocol to transmit the data in an encrypted form. The input is the anonymized text obtained in step 4, and the output is the secure transmission of data to the user's device.

[0315] Step 6:

[0316] The terminal displays anonymized text information received from the server to the user. HTML, CSS, and JavaScript are used to generate an appropriate interface for visualizing the text for the user. The input is the data received from the server in step 5, and the output is the display screen on the terminal.

[0317] Step 7:

[0318] The user takes action based on the information displayed. For example, they might click a link in an advertisement, generating a response that is then recorded on their device. The input is the user's interaction, and the output is the generation of user behavior data.

[0319] Step 8:

[0320] The device sends user response information to the server, which is then used as feedback data for future ad generation. The input is user behavior data, and the output is the ad generation process for subsequent generations, reflecting the feedback.

[0321] (Application Example 1)

[0322] 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."

[0323] Traditional advertising delivery systems were limited to personalization based on user history information, making it difficult to deliver real-time advertisements tailored to the user's current situation and location. This resulted in limited advertising effectiveness and reduced relevance of information to the user.

[0324] 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.

[0325] In this invention, the server includes acquisition means for obtaining user history information from a database, analysis means for analyzing the acquired history information to identify user characteristics, generation means for generating text information based on characteristics, anonymization means for anonymizing the user's personal information, transmission means for transmitting the generated text information to the user's device, display means for immediately displaying relevant information using the device's location information, and improvement means for receiving response information from the device and reflecting it in improving the text information. This makes it possible to provide personalized advertisements in real time according to the user's situation and location.

[0326] "Acquisition method" refers to the method for retrieving user history information from a database.

[0327] "Analysis methods" refer to methods for extracting and analyzing acquired historical information to identify user characteristics.

[0328] "Generation means" refers to a method of creating textual information to be presented to a user based on specified characteristics.

[0329] An "anonymization method" is a method of removing users' personal information from generated text information to anonymize it.

[0330] "Transmission means" refers to a method for transferring the generated anonymized text information to the user's device.

[0331] "Display means" refers to a method of instantly displaying relevant information based on the location information of the device.

[0332] "Improvement methods" refer to methods of making improvements to future text information more effective based on response information obtained from the device.

[0333] The embodiment of this invention consists of a system centered on a server, a terminal, and a user. The server uses a cloud server such as Amazon Web Services (AWS) or Google Cloud, and the database uses MySQL. On the terminal side, a smartphone application is developed using Android Studio or Swift.

[0334] The server first retrieves user history information from the database. This includes purchase history and location information. This data is preprocessed using Python, and user characteristics are analyzed using machine learning frameworks such as TensorFlow and PyTorch. Based on this characteristic analysis, generative AI models such as OpenAI's GPT are used to generate text information tailored to the user. This generated text information is processed using anonymization techniques (e.g., k-anonymization) to protect privacy.

[0335] The anonymized information is then sent to the device. The device uses location information obtained from GPS and other sensors to display relevant information at the appropriate time. This display aims to show the most relevant advertisements for the user's current location.

[0336] After information is displayed on the user's device, the user's reaction to that advertisement is recorded. For example, if the user clicks on the displayed advertisement, that data is sent from the device to the server and used to improve future ad generation processes.

[0337] For example, when a user is near a cafe, the app displays an advertisement such as, "Use our discount coupon for our new coffee product. Click here for details." An example of a prompt message is, "Generate a customized ad message based on the behavioral characteristics obtained from the history information of user ID: 12345. Present the most relevant offer based on the current location."

[0338] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0339] Step 1:

[0340] The server retrieves user history information from the database. In this step, SQL queries are executed based on the user ID to extract data such as past purchase history and location information. The input is the user ID, and the output is the history information associated with that user.

[0341] Step 2:

[0342] The system analyzes historical data acquired by the server to identify user characteristics. Data preprocessing is performed using Python, and the data is then fed into a model using machine learning frameworks such as TensorFlow or PyTorch. This identifies user behavior patterns and areas of interest. The input is historical data, and the output is extracted characteristic information.

[0343] Step 3:

[0344] The server generates text information using a generative AI model based on characteristics. It uses the OpenAI GPT model to create advertising messages tailored to the user's interests. The input is characteristic information, and the output is customized text information.

[0345] Step 4:

[0346] The server anonymizes personal information from the generated text data. Using k-anonymization technology, it creates text data that retains privacy. The input is the generated text data, and the output is the anonymized text data.

[0347] Step 5:

[0348] The server sends anonymized text information to the terminal. The data is then sent to the user's smartphone via network communication. The input is anonymized text information, and the output is confirmation that the information has been received on the terminal.

[0349] Step 6:

[0350] The system acquires text information received by the device and displays it appropriately based on location information. It uses a GPS sensor to adjust the display timing according to the user's current location. Input consists of text information and location data, while output is advertising information displayed on the user's screen.

[0351] Step 7:

[0352] The user reacts to the displayed advertisement, and this response information is recorded. The device collects data such as user clicks and viewing time. The input is the user's action log, and the output is the response information sent to the server.

[0353] Step 8:

[0354] The server analyzes the response information received from the terminal and incorporates it into subsequent advertisements. The ad generation process is updated to reflect changes in user interests and behavior. The input is the response information, and the output is the updated ad strategy.

[0355] 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.

[0356] The system implementing this invention is for generating and delivering personalized advertisements that also take into account the user's emotions. This system consists of a server, a terminal, and a user, and includes a novel element that incorporates an emotion engine in particular.

[0357] First, the server accesses the database to retrieve user history and purchase information. Based on this information, it analyzes the user's past behavior and interests. The server utilizes the characteristic profiles identified by the analysis tools, but a newly introduced sentiment engine extracts the user's sentiment trends from the history information. Sentiment trends play a crucial role in more accurately personalizing textual information.

[0358] The generation method incorporates the results of an emotion engine in addition to conventional algorithms, generating textual information that takes into account the user's emotional state and emotional changes. This textual information can include expressions and content that correspond to the user's emotions at that moment. Furthermore, the generated textual information is adjusted based on emotions and includes elements to deliver specific and empathetic messages to the user.

[0359] After generation, the server uses anonymization methods to remove personal information from the text data, protecting user privacy. The anonymized text data is then sent from the server to the terminal.

[0360] The device receives this information and notifies the user. When the user receives the message, their reaction (e.g., opening, clicking, replying) is recorded by the device. This record is reviewed based on emotional state and fed back to the server.

[0361] For example, if a user expresses interest in travel and the emotion engine detects from their recent history that they are experiencing stress, the server will generate an advertising message such as "Recommended travel destinations where you can relax." If the user sees this message on their device and makes a reservation, that response will be used as training data for the next generation process.

[0362] This system will enable companies to efficiently deliver personalized advertisements that resonate with users' emotions, and is expected to improve conversion rates and customer satisfaction.

[0363] The following describes the processing flow.

[0364] Step 1:

[0365] The server accesses the database to retrieve user history and purchase information. This information includes past purchase history, access logs, and search history. This allows for a comprehensive understanding of the user's behavior patterns.

[0366] Step 2:

[0367] The information acquired by the server is processed using data cleansing techniques. Missing or inconsistent data is removed, making it suitable for analysis. This allows for the creation of accurate user profiles.

[0368] Step 3:

[0369] The server uses an emotion engine to extract emotion trends from the user's history information. This process uses natural language processing techniques to recognize the user's emotional state from their text data.

[0370] Step 4:

[0371] The server uses analytical tools to identify user characteristics based on historical data and sentiment trends. This generates personalized information that addresses the user's areas of interest and emotional needs.

[0372] Step 5:

[0373] The server utilizes a generation AI model to generate text information based on characteristics and emotional trends. The generated text information includes content that corresponds to the user's current emotional state.

[0374] Step 6:

[0375] The server performs an anonymization process to remove personal information from text data. This ensures user privacy.

[0376] Step 7:

[0377] The server sends anonymized text information to the user's device. The device receives this information and manages when it is displayed to the user.

[0378] Step 8:

[0379] The device records the user's responses to messages. Data is collected when the user opens a message or clicks on a link, and this data is sent to the server.

[0380] Step 9:

[0381] The server analyzes the response information it collects and uses it to inform future message generation and user profile updates. This allows the entire system to continuously learn and provide more personalized services.

[0382] (Example 2)

[0383] 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".

[0384] Traditional personalized advertising systems primarily generated ads based on users' past history and purchase information. However, because they did not consider the user's emotional state, they sometimes delivered ads that were inconsistent with the user's mood at the time. This resulted in a failure to capture the user's attention and made effective ad delivery difficult. Furthermore, with the increasing demand for anonymization of users' personal information from a privacy protection perspective, there is a lack of technical means to achieve emotional personalization.

[0385] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0386] In this invention, the server includes means for acquiring user history information and purchase information from a data storage device; means for identifying the user's characteristic profile based on the acquired information; means for extracting the user's emotional trends using emotion analysis technology in addition to the characteristics identified by the analysis means and generating text information; means for transmitting the anonymized text information to the user's communication device; and means for receiving response information from the communication device and improving the text information. This makes it possible to provide personalized advertisements that take into account the user's emotional state while protecting personal information.

[0387] A "data storage device" is a storage medium that stores user history information and purchase information, and allows access and retrieval as needed.

[0388] "Acquisition means" refers to a function or process for acquiring user history information and purchase information from a data storage device.

[0389] "Analysis methods" refer to algorithms and techniques used to identify user characteristic profiles using acquired information.

[0390] "Generation means" refers to processes and devices for analyzing user characteristics and emotional trends to construct specific textual information.

[0391] "Sentiment analysis technology" is a technique for extracting emotional trends based on user history and purchase information, and it generally uses natural language processing.

[0392] An "anonymization method" is a process for removing or concealing personally identifiable information from generated textual information.

[0393] "Transmission means" refers to a function or system for transmitting anonymized text information to a user's communication device.

[0394] "Improvement measures" refer to technologies or processes for evaluating the effectiveness of text information based on response information from the user's device and reflecting this in the next generation process.

[0395] This invention relates to a system for efficiently generating and delivering personalized advertisements that take into account the emotions of users. The system consists of three elements: a server, a terminal, and a user, and incorporates a novel method using emotion analysis technology.

[0396] The server retrieves user history and purchase information from data storage devices. This retrieval is performed via a secure network connection and typically uses SQL database queries. Based on the retrieved information, the server uses machine learning algorithms to analyze the user's characteristic profile. This identifies the user's interests and behavioral patterns.

[0397] Next, the server uses sentiment analysis technology to extract sentiment trends from the user's past history. Here, analysis techniques utilizing natural language processing (NLP) are employed. For example, it calculates positive, negative, and neutral sentiment scores from the user's comments and reviews.

[0398] Based on the generated sentiment trends, the server utilizes a generative AI model to create text information optimized for the user. The generated advertisements reflect the user's current emotional state and include expressions tailored to individual needs. An example of inputting this prompt into the generative AI model would be: "Consider the user's past behavioral data and sentiment trends to generate a travel advertisement message with a relaxation theme."

[0399] After the advertisement is generated, the server uses an anonymization method to remove personal information from the generated text information in order to protect user privacy. This procedure removes personally identifiable information, thus protecting user privacy.

[0400] Anonymized text information is sent from the server to the device. Security protocols such as SSL / TLS are used for this transmission. The device notifies the user of the received text information and records the user's response. When the user opens an advertisement or clicks a link, that action is logged by the device.

[0401] Ultimately, the device feeds back the collected user response data to the server. This information is then used to improve the next ad generation process. In this way, the accuracy and relatability of ads are enhanced, and user engagement is maximized.

[0402] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0403] Step 1:

[0404] The server accesses the data storage device to retrieve user history and purchase information. A specific user ID is given as input, and the output is a history dataset for that user. Specifically, the server executes SQL queries to aggregate data such as history and purchase history.

[0405] Step 2:

[0406] The server analyzes the user's characteristic profile based on the acquired data. The historical dataset obtained in Step 1 is used as input, and the user's characteristic profile is generated as output. Specifically, the server applies machine learning algorithms to analyze the user's interests and behavioral tendencies.

[0407] Step 3:

[0408] The server extracts user sentiment trends using sentiment analysis technology. The input is the historical information obtained in step 1, and sentiment trend data is generated as output. The server uses natural language processing (NLP) to calculate sentiment scores from reviews and comments.

[0409] Step 4:

[0410] The server generates text information that reflects the user's characteristic profile and sentiment trends using a generation method. The inputs are the characteristic profile from step 2 and the sentiment trend data from step 3, and the output is a personalized advertising message. The generation AI model generates customized messages tailored to the user's current situation.

[0411] Step 5:

[0412] The server performs an anonymization process to remove personal information from the generated text information. The input is the advertising message generated in step 4, and the output is an anonymized message. Specifically, identifiable personal information is masked by the algorithm.

[0413] Step 6:

[0414] The server sends anonymized text information to the terminal. The input is the anonymized message from step 5, and the output is the secure transmission of the message to the terminal. The server uses the SSL / TLS protocol to encrypt and send the message.

[0415] Step 7:

[0416] The device notifies the user of received advertising messages. The input is an anonymized message sent from the server, and the output is a notification displayed on the user interface. Specifically, the device displays the message in the smartphone's notification bar.

[0417] Step 8:

[0418] Users take action in response to advertising messages. The input is an advertising notification, and the output is the user's actions, such as clicks or link accesses, which are recorded on the device. Users open the message and click on links that interest them.

[0419] Step 9:

[0420] The device records user behavior data and sends feedback to the server. The input is the user's action, and the output is a log of behavior data, which is sent to the server. The device formats the log into JSON format and sends the data to the server.

[0421] (Application Example 2)

[0422] 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."

[0423] Traditional advertising systems generate personalized ads without considering the user's emotional state, sometimes resulting in users seeing ads they don't want. Furthermore, the lack of technology to analyze user emotions in real time and adjust ad content accordingly meant that ads failed to capture user interest, reducing their effectiveness.

[0424] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0425] In this invention, the server includes acquisition means for acquiring user behavior records from a data storage area, analysis means for analyzing the acquired behavior records to estimate the user's characteristics, and emotion analysis means for analyzing the user's emotional state using facial recognition and acoustic recognition. This makes it possible to display personalized advertisements in real time that are tailored to the user's emotional state.

[0426] "Data storage area" refers to the storage that stores user activity records, purchase history, and other related information.

[0427] A "user" is an individual or organization that uses the system, and is the subject of analysis of their behavioral records and emotional states.

[0428] "Activity log" refers to historical data about online or offline activities that a user has engaged in in the past.

[0429] "Acquisition means" refers to the mechanisms and processes for retrieving necessary information from the data storage area.

[0430] "Analysis means" refers to functions and methods for analyzing acquired behavioral records and extracting characteristics and trends.

[0431] "Characteristics" refer to information that indicates a user's interests, behavioral patterns, and personality.

[0432] A "generation method" is a method for assembling information that is optimal for the user based on the analyzed characteristics.

[0433] "Anonymization methods" are means used to remove or conceal personally identifiable information in order to protect the privacy of users.

[0434] "Transmission means" refers to the methods or techniques used to transmit generated information to the user's device.

[0435] "Response information" refers to the actions or responses that users exhibit in response to the information they receive.

[0436] "Improvement measures" refer to the process of making adjustments to the information generated based on reaction information, and the methods used to generate it, in order to make them more effective.

[0437] "Emotional analysis methods" refer to methods and technologies that use facial recognition or acoustic recognition of a user to evaluate their emotional state at any given time.

[0438] "Adjustment mechanisms" refer to functions that optimize the content and display method of information based on the results of sentiment analysis.

[0439] The system for implementing this invention mainly consists of a server, terminals, and users who utilize the terminals. The server accesses a data storage area and retrieves data such as user activity records and purchase history. This utilizes data storage systems such as SQL databases and NoSQL databases.

[0440] The server uses machine learning software such as TensorFlow and PyTorch as analysis tools to estimate user characteristics by analyzing acquired data. Furthermore, the emotion analysis tool uses input devices such as cameras and microphones to analyze the user's real-time emotional state. This analysis utilizes libraries such as OpenCV and natural language processing models.

[0441] Based on these analysis results, the server uses a generative AI model to generate information tailored to the user. This information is often structured in JSON or XML format. The generated information is anonymized, and any personally identifiable data is removed.

[0442] The device receives information sent from the server and displays it to the user visually or audibly. Examples of devices include smart glasses and portable computers. The device then records the user's reactions, such as ad click history, and sends this information back to the server as feedback. The server uses this feedback to improve the information it generates.

[0443] Specifically, if behavioral data indicates that a user is interested in a new gadget, the server will display a video demonstrating the gadget's use on the smart glasses when the user's emotions are heightened. Furthermore, if the user's face shows expressions of surprise or interest, additional promotional information will be displayed to encourage purchase.

[0444] An example of a prompt would be: "Show how to analyze a user's emotions in real time based on their video and audio data and generate personalized ads for new electronic devices."

[0445] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0446] Step 1:

[0447] The server accesses the data storage area to retrieve user activity records and purchase history. The input is a user ID, and the output is activity record data and purchase history data. This data is extracted from the database using SQL queries.

[0448] Step 2:

[0449] The server analyzes the acquired data and estimates the user's characteristics. The input is previously acquired behavioral record data and purchase history data, and the output is profile information indicating the user's interests and purchasing tendencies. A machine learning model using TensorFlow is used here. Profile information is generated by performing feature extraction and classification.

[0450] Step 3:

[0451] The server acquires real-time video and audio data from the user through the camera and microphone built into the smart glasses and performs emotion analysis. The input consists of video and audio data, and the output is analytical information indicating the user's emotional state. This process uses the OpenCV library for face recognition and applies an emotion estimation algorithm.

[0452] Step 4:

[0453] The server generates user-specific information using a generative AI model based on sentiment analysis and profile information. Input includes sentiment analysis and profile information, while output is user-specific advertising and presentation information. This generation process utilizes a machine learning model employing natural language processing techniques.

[0454] Step 5:

[0455] The server anonymizes the generated information to protect the user's personal information. The input is the generated advertising information, and the output is anonymized information from which personally identifiable elements have been removed. At this stage, the identification information is hashed.

[0456] Step 6:

[0457] The server sends anonymized information to the terminal. The input is the anonymized information, and the output is the data packet being transmitted. A secure communication protocol is used for this transmission.

[0458] Step 7:

[0459] The terminal displays received information to the user and records their response. The input is information sent from the server, and the output is user response data. Visual information is presented to the terminal via smart glasses.

[0460] Step 8:

[0461] The terminal feeds back recorded response data to the server. The input is the user's response data, and the output is the feedback data. This data is stored on the server as training data for future information generation.

[0462] 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.

[0463] 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.

[0464] 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.

[0465] [Third Embodiment]

[0466] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0467] 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.

[0468] 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).

[0469] 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.

[0470] 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.

[0471] 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).

[0472] 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.

[0473] 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.

[0474] 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.

[0475] 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.

[0476] 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.

[0477] 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".

[0478] The system implementing this invention is a system that utilizes user history information to generate and deliver effective personalized advertisements. This system mainly consists of a server, a terminal, and a user.

[0479] The server first retrieves user history information from the database. This history information includes data such as what services the user has used in the past and what products they have purchased. Next, the server analyzes this history information to identify the user's characteristics. This is a process that uses machine learning and statistical methods to infer the user's behavior patterns and interests.

[0480] Based on identified characteristics, the server uses a generative AI model to generate personalized text information. This text information is customized according to the user's interests and preferences, making it a more effective advertisement.

[0481] After the text data is generated, the server anonymizes the personal information. This process removes any information that could identify the user, ensuring privacy. The anonymized text data is then sent from the server to the user's device.

[0482] The device displays the received text information to the user, who then reviews its content. The device then records the user's response to the message. This response information is sent back to the server and used to improve future personalized advertisements.

[0483] As a concrete example, consider a case where a user has an interest in cooking. The server analyzes the user's browsing history, identifies their cooking-related characteristics, and generates messages such as "new recipe information" or "cooking class campaign information." If the user receives this information on their device, shows interest, and clicks a link to see more details, the server can use that response to inform future ad generation.

[0484] Thus, the system for implementing the present invention enables the dynamic generation and efficient delivery of personalized advertisements that meet the needs of users.

[0485] The following describes the processing flow.

[0486] Step 1:

[0487] The server accesses the database to retrieve the user's past history information. This information includes past purchase history, access logs, and search history. This data forms the basis for analyzing the user's behavior patterns and interests.

[0488] Step 2:

[0489] The historical information acquired by the server is organized using data cleansing techniques. Incomplete or inconsistent data is corrected, making it suitable for analysis. This process is crucial for ensuring data accuracy.

[0490] Step 3:

[0491] The server analyzes the cleansed data to identify user characteristics. Machine learning algorithms are used to model user interests and purchasing tendencies, creating characteristic profiles. These characteristic profiles form the basis for future personalization strategies.

[0492] Step 4:

[0493] The server utilizes a generation AI model to generate textual information based on characteristic profiles. The generated textual information is optimized for individual users and includes content designed to function as advertisements.

[0494] Step 5:

[0495] The server anonymizes the generated text information from a personal information protection standpoint. User privacy is maintained by removing or encrypting personally identifiable information.

[0496] Step 6:

[0497] The server sends anonymized text information to the user's device. The device receives this information and notifies the user, allowing the user to verify the content.

[0498] Step 7:

[0499] The device records the user's responses and sends the collected response information to the server. It also records user actions as data, such as opening a message or clicking a link.

[0500] Step 8:

[0501] The server analyzes the response information and uses it to improve future ad generation and user profile updates. This allows the generation AI model to continuously learn, resulting in more accurate personalization.

[0502] (Example 1)

[0503] 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."

[0504] In today's information and communication society, users are exposed to vast amounts of information, making it difficult to efficiently acquire information relevant to them. Furthermore, there is a lack of means to provide appropriately customized information to specific users while ensuring individual privacy. Additionally, there is a need for mechanisms to improve information quality by utilizing user feedback.

[0505] 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.

[0506] In this invention, the server includes means for acquiring user history information from a data management device, means for analyzing the acquired history information using information processing technology to identify user characteristics, and means for creating textual information using information generation technology based on those characteristics. This makes it possible to provide personalized information tailored to each user's needs while protecting their privacy, and to continuously improve the quality of the information based on user responses.

[0507] A "data management device" is equipment or a platform for organizing, storing, and managing information.

[0508] "User history information" refers to records of activities and behaviors associated with a specific user, including data on past service usage and product purchases.

[0509] "Information processing technology" is a general term for technologies used to analyze, interpret, and understand data.

[0510] "Methods for identifying characteristics" refer to methods for extracting patterns and trends from collected data to reveal users' preferences and behavioral characteristics.

[0511] "Information generation technology" refers to technology that automatically generates appropriate information based on the characteristics of the user.

[0512] "Textual information" refers to information expressed in written or text format.

[0513] "Personal identification information" refers to information used to directly or indirectly identify a specific individual.

[0514] "Means of communication" refers to the methods and protocols used to transmit information to its destination.

[0515] "Response information" refers to data that shows user feedback and behavioral records.

[0516] "Information optimization" is the process of improving the quality and relevance of the information provided, based on user feedback and other data.

[0517] This invention is a system for providing users with information tailored to their needs quickly and efficiently, and involves the server, terminal, and user working together to optimize ad delivery.

[0518] The server collects user history information from the data management device. This data includes the user's website visit history and purchase history. Next, the server uses a Python environment and formats the data using Pandas and NumPy. Then, it uses machine learning libraries such as TensorFlow and Scikit-learn to analyze the collected data and identify user characteristics. This analysis helps to estimate what products and services the user is interested in.

[0519] Based on the identified user characteristics, the server uses a generative AI model to generate personalized text information. Specifically, it utilizes natural language processing technology as the generative model to create information based on pre-configured prompts. An example of a prompt might be, "Create customized ad copy based on the user's history." In this process, the generated ad copy is adjusted to match the user's interests and needs.

[0520] The server anonymizes personally identifiable information from the generated text data using Pandas or regular expressions. The anonymized data is then sent to the user's terminal using a secure communication protocol, such as HTTPS.

[0521] The terminal provides the user with anonymized text information received from the server. Front-end technologies such as HTML, CSS, and JavaScript are used to display the information in a user-friendly format.

[0522] Users can take action based on the displayed information. For example, they can obtain more detailed information by clicking on a provided link. Such user responses are recorded on the device and sent back to the server to be used to optimize future ad delivery.

[0523] This system maximizes the effectiveness of advertising and benefits all stakeholders by providing information that is tailored to the user's needs.

[0524] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0525] Step 1:

[0526] The server retrieves user history information from the data management device. At this stage, the server executes SQL queries against the database to extract relevant information such as the user's behavioral history and purchase history. The input is the user identifier, and the output is the data of the corresponding history information.

[0527] Step 2:

[0528] The server analyzes the acquired historical information using information processing technology. Here, the data is formatted and cleaned using the Python Pandas library. Next, machine learning models are applied to identify user characteristics using TensorFlow or Scikit-learn. The input is the historical information extracted in step 1, and the output is data points that indicate the user's interests and characteristics.

[0529] Step 3:

[0530] The server uses a generative AI model based on the user's characteristics to generate personalized text information. Specifically, it inputs prompt text into the generative AI model, which then generates ad copy that matches the user's characteristics. The input consists of user characteristic information and prompt text, while the output is personalized ad text directed at the user.

[0531] Step 4:

[0532] The server anonymizes the generated text information. Using Pandas and regular expressions, personally identifiable information is removed, and the data is processed to protect privacy. The input is the advertisement text obtained in step 3, and the output is the anonymized text information.

[0533] Step 5:

[0534] The server securely transmits anonymized text information to the user's device. Specifically, it uses the HTTPS protocol to transmit the data in an encrypted form. The input is the anonymized text obtained in step 4, and the output is the secure transmission of data to the user's device.

[0535] Step 6:

[0536] The terminal displays anonymized text information received from the server to the user. HTML, CSS, and JavaScript are used to generate an appropriate interface for visualizing the text for the user. The input is the data received from the server in step 5, and the output is the display screen on the terminal.

[0537] Step 7:

[0538] The user takes action based on the information displayed. For example, they might click a link in an advertisement, generating a response that is then recorded on their device. The input is the user's interaction, and the output is the generation of user behavior data.

[0539] Step 8:

[0540] The device sends user response information to the server, which is then used as feedback data for future ad generation. The input is user behavior data, and the output is the ad generation process for subsequent generations, reflecting the feedback.

[0541] (Application Example 1)

[0542] 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."

[0543] Traditional advertising delivery systems were limited to personalization based on user history information, making it difficult to deliver real-time advertisements tailored to the user's current situation and location. This resulted in limited advertising effectiveness and reduced relevance of information to the user.

[0544] 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.

[0545] In this invention, the server includes acquisition means for obtaining user history information from a database, analysis means for analyzing the acquired history information to identify user characteristics, generation means for generating text information based on characteristics, anonymization means for anonymizing the user's personal information, transmission means for transmitting the generated text information to the user's device, display means for immediately displaying relevant information using the device's location information, and improvement means for receiving response information from the device and reflecting it in improving the text information. This makes it possible to provide personalized advertisements in real time according to the user's situation and location.

[0546] "Acquisition method" refers to the method for retrieving user history information from a database.

[0547] "Analysis methods" refer to methods for extracting and analyzing acquired historical information to identify user characteristics.

[0548] "Generation means" refers to a method of creating textual information to be presented to a user based on specified characteristics.

[0549] An "anonymization method" is a method of removing users' personal information from generated text information to anonymize it.

[0550] "Transmission means" refers to a method for transferring the generated anonymized text information to the user's device.

[0551] "Display means" refers to a method of instantly displaying relevant information based on the location information of the device.

[0552] "Improvement methods" refer to methods of making improvements to future text information more effective based on response information obtained from the device.

[0553] The embodiment of this invention consists of a system centered on a server, a terminal, and a user. The server uses a cloud server such as Amazon Web Services (AWS) or Google Cloud, and the database uses MySQL. On the terminal side, a smartphone application is developed using Android Studio or Swift.

[0554] The server first retrieves user history information from the database. This includes purchase history and location information. This data is preprocessed using Python, and user characteristics are analyzed using machine learning frameworks such as TensorFlow and PyTorch. Based on this characteristic analysis, generative AI models such as OpenAI's GPT are used to generate text information tailored to the user. This generated text information is processed using anonymization techniques (e.g., k-anonymization) to protect privacy.

[0555] The anonymized information is then sent to the device. The device uses location information obtained from GPS and other sensors to display relevant information at the appropriate time. This display aims to show the most relevant advertisements for the user's current location.

[0556] After information is displayed on the user's device, the user's reaction to that advertisement is recorded. For example, if the user clicks on the displayed advertisement, that data is sent from the device to the server and used to improve future ad generation processes.

[0557] For example, when a user is near a cafe, the app displays an advertisement such as, "Use our discount coupon for our new coffee product. Click here for details." An example of a prompt message is, "Generate a customized ad message based on the behavioral characteristics obtained from the history information of user ID: 12345. Present the most relevant offer based on the current location."

[0558] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0559] Step 1:

[0560] The server retrieves user history information from the database. In this step, SQL queries are executed based on the user ID to extract data such as past purchase history and location information. The input is the user ID, and the output is the history information associated with that user.

[0561] Step 2:

[0562] The system analyzes historical data acquired by the server to identify user characteristics. Data preprocessing is performed using Python, and the data is then fed into a model using machine learning frameworks such as TensorFlow or PyTorch. This identifies user behavior patterns and areas of interest. The input is historical data, and the output is extracted characteristic information.

[0563] Step 3:

[0564] The server generates text information using a generative AI model based on characteristics. It uses the OpenAI GPT model to create advertising messages tailored to the user's interests. The input is characteristic information, and the output is customized text information.

[0565] Step 4:

[0566] The server anonymizes personal information from the generated text data. Using k-anonymization technology, it creates text data that retains privacy. The input is the generated text data, and the output is the anonymized text data.

[0567] Step 5:

[0568] The server sends anonymized text information to the terminal. The data is then sent to the user's smartphone via network communication. The input is anonymized text information, and the output is confirmation that the information has been received on the terminal.

[0569] Step 6:

[0570] The system acquires text information received by the device and displays it appropriately based on location information. It uses a GPS sensor to adjust the display timing according to the user's current location. Input consists of text information and location data, while output is advertising information displayed on the user's screen.

[0571] Step 7:

[0572] The user reacts to the displayed advertisement, and this response information is recorded. The device collects data such as user clicks and viewing time. The input is the user's action log, and the output is the response information sent to the server.

[0573] Step 8:

[0574] The server analyzes the response information received from the terminal and incorporates it into subsequent advertisements. The ad generation process is updated to reflect changes in user interests and behavior. The input is the response information, and the output is the updated ad strategy.

[0575] 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.

[0576] The system implementing this invention is for generating and delivering personalized advertisements that also take into account the user's emotions. This system consists of a server, a terminal, and a user, and includes a novel element that incorporates an emotion engine in particular.

[0577] First, the server accesses the database to retrieve user history and purchase information. Based on this information, it analyzes the user's past behavior and interests. The server utilizes the characteristic profiles identified by the analysis tools, but a newly introduced sentiment engine extracts the user's sentiment trends from the history information. Sentiment trends play a crucial role in more accurately personalizing textual information.

[0578] The generation method incorporates the results of an emotion engine in addition to conventional algorithms, generating textual information that takes into account the user's emotional state and emotional changes. This textual information can include expressions and content that correspond to the user's emotions at that moment. Furthermore, the generated textual information is adjusted based on emotions and includes elements to deliver specific and empathetic messages to the user.

[0579] After generation, the server uses anonymization methods to remove personal information from the text data, protecting user privacy. The anonymized text data is then sent from the server to the terminal.

[0580] The device receives this information and notifies the user. When the user receives the message, their reaction (e.g., opening, clicking, replying) is recorded by the device. This record is reviewed based on emotional state and fed back to the server.

[0581] For example, if a user expresses interest in travel and the emotion engine detects from their recent history that they are experiencing stress, the server will generate an advertising message such as "Recommended travel destinations where you can relax." If the user sees this message on their device and makes a reservation, that response will be used as training data for the next generation process.

[0582] This system will enable companies to efficiently deliver personalized advertisements that resonate with users' emotions, and is expected to improve conversion rates and customer satisfaction.

[0583] The following describes the processing flow.

[0584] Step 1:

[0585] The server accesses the database to retrieve user history and purchase information. This information includes past purchase history, access logs, and search history. This allows for a comprehensive understanding of the user's behavior patterns.

[0586] Step 2:

[0587] The information acquired by the server is processed using data cleansing techniques. Missing or inconsistent data is removed, making it suitable for analysis. This allows for the creation of accurate user profiles.

[0588] Step 3:

[0589] The server uses an emotion engine to extract emotion trends from the user's history information. This process uses natural language processing techniques to recognize the user's emotional state from their text data.

[0590] Step 4:

[0591] The server uses analytical tools to identify user characteristics based on historical data and sentiment trends. This generates personalized information that addresses the user's areas of interest and emotional needs.

[0592] Step 5:

[0593] The server utilizes a generation AI model to generate text information based on characteristics and emotional trends. The generated text information includes content that corresponds to the user's current emotional state.

[0594] Step 6:

[0595] The server performs an anonymization process to remove personal information from text data. This ensures user privacy.

[0596] Step 7:

[0597] The server sends anonymized text information to the user's device. The device receives this information and manages when it is displayed to the user.

[0598] Step 8:

[0599] The device records the user's responses to messages. Data is collected when the user opens a message or clicks on a link, and this data is sent to the server.

[0600] Step 9:

[0601] The server analyzes the response information it collects and uses it to inform future message generation and user profile updates. This allows the entire system to continuously learn and provide more personalized services.

[0602] (Example 2)

[0603] 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."

[0604] Traditional personalized advertising systems primarily generated ads based on users' past history and purchase information. However, because they did not consider the user's emotional state, they sometimes delivered ads that were inconsistent with the user's mood at the time. This resulted in a failure to capture the user's attention and made effective ad delivery difficult. Furthermore, with the increasing demand for anonymization of users' personal information from a privacy protection perspective, there is a lack of technical means to achieve emotional personalization.

[0605] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0606] In this invention, the server includes means for acquiring user history information and purchase information from a data storage device; means for identifying the user's characteristic profile based on the acquired information; means for extracting the user's emotional trends using emotion analysis technology in addition to the characteristics identified by the analysis means and generating text information; means for transmitting the anonymized text information to the user's communication device; and means for receiving response information from the communication device and improving the text information. This makes it possible to provide personalized advertisements that take into account the user's emotional state while protecting personal information.

[0607] A "data storage device" is a storage medium that stores user history information and purchase information, and allows access and retrieval as needed.

[0608] "Acquisition means" refers to a function or process for acquiring user history information and purchase information from a data storage device.

[0609] "Analysis methods" refer to algorithms and techniques used to identify user characteristic profiles using acquired information.

[0610] "Generation means" refers to processes and devices for analyzing user characteristics and emotional trends to construct specific textual information.

[0611] "Sentiment analysis technology" is a technique for extracting emotional trends based on user history and purchase information, and it generally uses natural language processing.

[0612] An "anonymization method" is a process for removing or concealing personally identifiable information from generated textual information.

[0613] "Transmission means" refers to a function or system for transmitting anonymized text information to a user's communication device.

[0614] "Improvement measures" refer to technologies or processes for evaluating the effectiveness of text information based on response information from the user's device and reflecting this in the next generation process.

[0615] This invention relates to a system for efficiently generating and delivering personalized advertisements that take into account the emotions of users. The system consists of three elements: a server, a terminal, and a user, and incorporates a novel method using emotion analysis technology.

[0616] The server retrieves user history and purchase information from data storage devices. This retrieval is performed via a secure network connection and typically uses SQL database queries. Based on the retrieved information, the server uses machine learning algorithms to analyze the user's characteristic profile. This identifies the user's interests and behavioral patterns.

[0617] Next, the server uses sentiment analysis technology to extract sentiment trends from the user's past history. Here, analysis techniques utilizing natural language processing (NLP) are employed. For example, it calculates positive, negative, and neutral sentiment scores from the user's comments and reviews.

[0618] Based on the generated sentiment trends, the server utilizes a generative AI model to create text information optimized for the user. The generated advertisements reflect the user's current emotional state and include expressions tailored to individual needs. An example of inputting this prompt into the generative AI model would be: "Consider the user's past behavioral data and sentiment trends to generate a travel advertisement message with a relaxation theme."

[0619] After the advertisement is generated, the server uses an anonymization method to remove personal information from the generated text information in order to protect user privacy. This procedure removes personally identifiable information, thus protecting user privacy.

[0620] Anonymized text information is sent from the server to the device. Security protocols such as SSL / TLS are used for this transmission. The device notifies the user of the received text information and records the user's response. When the user opens an advertisement or clicks a link, that action is logged by the device.

[0621] Ultimately, the device feeds back the collected user response data to the server. This information is then used to improve the next ad generation process. In this way, the accuracy and relatability of ads are enhanced, and user engagement is maximized.

[0622] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0623] Step 1:

[0624] The server accesses the data storage device to retrieve user history and purchase information. A specific user ID is given as input, and the output is a history dataset for that user. Specifically, the server executes SQL queries to aggregate data such as history and purchase history.

[0625] Step 2:

[0626] The server analyzes the user's characteristic profile based on the acquired data. The historical dataset obtained in Step 1 is used as input, and the user's characteristic profile is generated as output. Specifically, the server applies machine learning algorithms to analyze the user's interests and behavioral tendencies.

[0627] Step 3:

[0628] The server extracts user sentiment trends using sentiment analysis technology. The input is the historical information obtained in step 1, and sentiment trend data is generated as output. The server uses natural language processing (NLP) to calculate sentiment scores from reviews and comments.

[0629] Step 4:

[0630] The server generates text information that reflects the user's characteristic profile and sentiment trends using a generation method. The inputs are the characteristic profile from step 2 and the sentiment trend data from step 3, and the output is a personalized advertising message. The generation AI model generates customized messages tailored to the user's current situation.

[0631] Step 5:

[0632] The server performs an anonymization process to remove personal information from the generated text information. The input is the advertising message generated in step 4, and the output is an anonymized message. Specifically, identifiable personal information is masked by the algorithm.

[0633] Step 6:

[0634] The server sends anonymized text information to the terminal. The input is the anonymized message from step 5, and the output is the secure transmission of the message to the terminal. The server uses the SSL / TLS protocol to encrypt and send the message.

[0635] Step 7:

[0636] The device notifies the user of received advertising messages. The input is an anonymized message sent from the server, and the output is a notification displayed on the user interface. Specifically, the device displays the message in the smartphone's notification bar.

[0637] Step 8:

[0638] Users take action in response to advertising messages. The input is an advertising notification, and the output is the user's actions, such as clicks or link accesses, which are recorded on the device. Users open the message and click on links that interest them.

[0639] Step 9:

[0640] The device records user behavior data and sends feedback to the server. The input is the user's action, and the output is a log of behavior data, which is sent to the server. The device formats the log into JSON format and sends the data to the server.

[0641] (Application Example 2)

[0642] 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."

[0643] Traditional advertising systems generate personalized ads without considering the user's emotional state, sometimes resulting in users seeing ads they don't want. Furthermore, the lack of technology to analyze user emotions in real time and adjust ad content accordingly meant that ads failed to capture user interest, reducing their effectiveness.

[0644] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0645] In this invention, the server includes acquisition means for acquiring user behavior records from a data storage area, analysis means for analyzing the acquired behavior records to estimate the user's characteristics, and emotion analysis means for analyzing the user's emotional state using facial recognition and acoustic recognition. This makes it possible to display personalized advertisements in real time that are tailored to the user's emotional state.

[0646] "Data storage area" refers to the storage that stores user activity records, purchase history, and other related information.

[0647] A "user" is an individual or organization that uses the system, and is the subject of analysis of their behavioral records and emotional states.

[0648] "Activity log" refers to historical data about online or offline activities that a user has engaged in in the past.

[0649] "Acquisition means" refers to the mechanisms and processes for retrieving necessary information from the data storage area.

[0650] "Analysis means" refers to functions and methods for analyzing acquired behavioral records and extracting characteristics and trends.

[0651] "Characteristics" refer to information that indicates a user's interests, behavioral patterns, and personality.

[0652] A "generation method" is a method for assembling information that is optimal for the user based on the analyzed characteristics.

[0653] "Anonymization methods" are means used to remove or conceal personally identifiable information in order to protect the privacy of users.

[0654] "Transmission means" refers to the methods or techniques used to transmit generated information to the user's device.

[0655] "Response information" refers to the actions or responses that users exhibit in response to the information they receive.

[0656] "Improvement measures" refer to the process of making adjustments to the information generated based on reaction information, and the methods used to generate it, in order to make them more effective.

[0657] "Emotional analysis methods" refer to methods and technologies that use facial recognition or acoustic recognition of a user to evaluate their emotional state at any given time.

[0658] "Adjustment mechanisms" refer to functions that optimize the content and display method of information based on the results of sentiment analysis.

[0659] The system for implementing this invention mainly consists of a server, terminals, and users who utilize the terminals. The server accesses a data storage area and retrieves data such as user activity records and purchase history. This utilizes data storage systems such as SQL databases and NoSQL databases.

[0660] The server uses machine learning software such as TensorFlow and PyTorch as analysis tools to estimate user characteristics by analyzing acquired data. Furthermore, the emotion analysis tool uses input devices such as cameras and microphones to analyze the user's real-time emotional state. This analysis utilizes libraries such as OpenCV and natural language processing models.

[0661] Based on these analysis results, the server uses a generative AI model to generate information tailored to the user. This information is often structured in JSON or XML format. The generated information is anonymized, and any personally identifiable data is removed.

[0662] The device receives information sent from the server and displays it to the user visually or audibly. Examples of devices include smart glasses and portable computers. The device then records the user's reactions, such as ad click history, and sends this information back to the server as feedback. The server uses this feedback to improve the information it generates.

[0663] Specifically, if behavioral data indicates that a user is interested in a new gadget, the server will display a video demonstrating the gadget's use on the smart glasses when the user's emotions are heightened. Furthermore, if the user's face shows expressions of surprise or interest, additional promotional information will be displayed to encourage purchase.

[0664] An example of a prompt would be: "Show how to analyze a user's emotions in real time based on their video and audio data and generate personalized ads for new electronic devices."

[0665] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0666] Step 1:

[0667] The server accesses the data storage area to retrieve user activity records and purchase history. The input is a user ID, and the output is activity record data and purchase history data. This data is extracted from the database using SQL queries.

[0668] Step 2:

[0669] The server analyzes the acquired data and estimates the user's characteristics. The input is previously acquired behavioral record data and purchase history data, and the output is profile information indicating the user's interests and purchasing tendencies. A machine learning model using TensorFlow is used here. Profile information is generated by performing feature extraction and classification.

[0670] Step 3:

[0671] The server acquires real-time video and audio data from the user through the camera and microphone built into the smart glasses and performs emotion analysis. The input consists of video and audio data, and the output is analytical information indicating the user's emotional state. This process uses the OpenCV library for face recognition and applies an emotion estimation algorithm.

[0672] Step 4:

[0673] The server generates user-specific information using a generative AI model based on sentiment analysis and profile information. Input includes sentiment analysis and profile information, while output is user-specific advertising and presentation information. This generation process utilizes a machine learning model employing natural language processing techniques.

[0674] Step 5:

[0675] The server anonymizes the generated information to protect the user's personal information. The input is the generated advertising information, and the output is anonymized information from which personally identifiable elements have been removed. At this stage, the identification information is hashed.

[0676] Step 6:

[0677] The server sends anonymized information to the terminal. The input is the anonymized information, and the output is the data packet being transmitted. A secure communication protocol is used for this transmission.

[0678] Step 7:

[0679] The terminal displays received information to the user and records their response. The input is information sent from the server, and the output is user response data. Visual information is presented to the terminal via smart glasses.

[0680] Step 8:

[0681] The terminal feeds back recorded response data to the server. The input is the user's response data, and the output is the feedback data. This data is stored on the server as training data for future information generation.

[0682] 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.

[0683] 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.

[0684] 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.

[0685] [Fourth Embodiment]

[0686] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0687] 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.

[0688] 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).

[0689] 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.

[0690] 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.

[0691] 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).

[0692] 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.

[0693] 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.

[0694] 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.

[0695] 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.

[0696] 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.

[0697] 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.

[0698] 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".

[0699] The system implementing this invention is a system that utilizes user history information to generate and deliver effective personalized advertisements. This system mainly consists of a server, a terminal, and a user.

[0700] The server first retrieves user history information from the database. This history information includes data such as what services the user has used in the past and what products they have purchased. Next, the server analyzes this history information to identify the user's characteristics. This is a process that uses machine learning and statistical methods to infer the user's behavior patterns and interests.

[0701] Based on identified characteristics, the server uses a generative AI model to generate personalized text information. This text information is customized according to the user's interests and preferences, making it a more effective advertisement.

[0702] After the text data is generated, the server anonymizes the personal information. This process removes any information that could identify the user, ensuring privacy. The anonymized text data is then sent from the server to the user's device.

[0703] The device displays the received text information to the user, who then reviews its content. The device then records the user's response to the message. This response information is sent back to the server and used to improve future personalized advertisements.

[0704] As a concrete example, consider a case where a user has an interest in cooking. The server analyzes the user's browsing history, identifies their cooking-related characteristics, and generates messages such as "new recipe information" or "cooking class campaign information." If the user receives this information on their device, shows interest, and clicks a link to see more details, the server can use that response to inform future ad generation.

[0705] Thus, the system for implementing the present invention enables the dynamic generation and efficient delivery of personalized advertisements that meet the needs of users.

[0706] The following describes the processing flow.

[0707] Step 1:

[0708] The server accesses the database to retrieve the user's past history information. This information includes past purchase history, access logs, and search history. This data forms the basis for analyzing the user's behavior patterns and interests.

[0709] Step 2:

[0710] The historical information acquired by the server is organized using data cleansing techniques. Incomplete or inconsistent data is corrected, making it suitable for analysis. This process is crucial for ensuring data accuracy.

[0711] Step 3:

[0712] The server analyzes the cleansed data to identify user characteristics. Machine learning algorithms are used to model user interests and purchasing tendencies, creating characteristic profiles. These characteristic profiles form the basis for future personalization strategies.

[0713] Step 4:

[0714] The server utilizes a generation AI model to generate textual information based on characteristic profiles. The generated textual information is optimized for individual users and includes content designed to function as advertisements.

[0715] Step 5:

[0716] The server anonymizes the generated text information from a personal information protection standpoint. User privacy is maintained by removing or encrypting personally identifiable information.

[0717] Step 6:

[0718] The server sends anonymized text information to the user's device. The device receives this information and notifies the user, allowing the user to verify the content.

[0719] Step 7:

[0720] The device records the user's responses and sends the collected response information to the server. It also records user actions as data, such as opening a message or clicking a link.

[0721] Step 8:

[0722] The server analyzes the response information and uses it to improve future ad generation and user profile updates. This allows the generation AI model to continuously learn, resulting in more accurate personalization.

[0723] (Example 1)

[0724] 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".

[0725] In today's information and communication society, users are exposed to vast amounts of information, making it difficult to efficiently acquire information relevant to them. Furthermore, there is a lack of means to provide appropriately customized information to specific users while ensuring individual privacy. Additionally, there is a need for mechanisms to improve information quality by utilizing user feedback.

[0726] 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.

[0727] In this invention, the server includes means for acquiring user history information from a data management device, means for analyzing the acquired history information using information processing technology to identify user characteristics, and means for creating textual information using information generation technology based on those characteristics. This makes it possible to provide personalized information tailored to each user's needs while protecting their privacy, and to continuously improve the quality of the information based on user responses.

[0728] A "data management device" is equipment or a platform for organizing, storing, and managing information.

[0729] "User history information" refers to records of activities and behaviors associated with a specific user, including data on past service usage and product purchases.

[0730] "Information processing technology" is a general term for technologies used to analyze, interpret, and understand data.

[0731] "Methods for identifying characteristics" refer to methods for extracting patterns and trends from collected data to reveal users' preferences and behavioral characteristics.

[0732] "Information generation technology" refers to technology that automatically generates appropriate information based on the characteristics of the user.

[0733] "Textual information" refers to information expressed in written or text format.

[0734] "Personal identification information" refers to information used to directly or indirectly identify a specific individual.

[0735] "Means of communication" refers to the methods and protocols used to transmit information to its destination.

[0736] "Response information" refers to data that shows user feedback and behavioral records.

[0737] "Information optimization" is the process of improving the quality and relevance of the information provided, based on user feedback and other data.

[0738] This invention is a system for providing users with information tailored to their needs quickly and efficiently, and involves the server, terminal, and user working together to optimize ad delivery.

[0739] The server collects user history information from the data management device. This data includes the user's website visit history and purchase history. Next, the server uses a Python environment and formats the data using Pandas and NumPy. Then, it uses machine learning libraries such as TensorFlow and Scikit-learn to analyze the collected data and identify user characteristics. This analysis helps to estimate what products and services the user is interested in.

[0740] Based on the identified user characteristics, the server uses a generative AI model to generate personalized text information. Specifically, it utilizes natural language processing technology as the generative model to create information based on pre-configured prompts. An example of a prompt might be, "Create customized ad copy based on the user's history." In this process, the generated ad copy is adjusted to match the user's interests and needs.

[0741] The server anonymizes personally identifiable information from the generated text data using Pandas or regular expressions. The anonymized data is then sent to the user's terminal using a secure communication protocol, such as HTTPS.

[0742] The terminal provides the user with anonymized text information received from the server. Front-end technologies such as HTML, CSS, and JavaScript are used to display the information in a user-friendly format.

[0743] Users can take action based on the displayed information. For example, they can obtain more detailed information by clicking on a provided link. Such user responses are recorded on the device and sent back to the server to be used to optimize future ad delivery.

[0744] This system maximizes the effectiveness of advertising and benefits all stakeholders by providing information that is tailored to the user's needs.

[0745] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0746] Step 1:

[0747] The server retrieves user history information from the data management device. At this stage, the server executes SQL queries against the database to extract relevant information such as the user's behavioral history and purchase history. The input is the user identifier, and the output is the data of the corresponding history information.

[0748] Step 2:

[0749] The server analyzes the acquired historical information using information processing technology. Here, the data is formatted and cleaned using the Python Pandas library. Next, machine learning models are applied to identify user characteristics using TensorFlow or Scikit-learn. The input is the historical information extracted in step 1, and the output is data points that indicate the user's interests and characteristics.

[0750] Step 3:

[0751] The server uses a generative AI model based on the user's characteristics to generate personalized text information. Specifically, it inputs prompt text into the generative AI model, which then generates ad copy that matches the user's characteristics. The input consists of user characteristic information and prompt text, while the output is personalized ad text directed at the user.

[0752] Step 4:

[0753] The server anonymizes the generated text information. Using Pandas and regular expressions, personally identifiable information is removed, and the data is processed to protect privacy. The input is the advertisement text obtained in step 3, and the output is the anonymized text information.

[0754] Step 5:

[0755] The server securely transmits anonymized text information to the user's device. Specifically, it uses the HTTPS protocol to transmit the data in an encrypted form. The input is the anonymized text obtained in step 4, and the output is the secure transmission of data to the user's device.

[0756] Step 6:

[0757] The terminal displays anonymized text information received from the server to the user. HTML, CSS, and JavaScript are used to generate an appropriate interface for visualizing the text for the user. The input is the data received from the server in step 5, and the output is the display screen on the terminal.

[0758] Step 7:

[0759] The user takes action based on the information displayed. For example, they might click a link in an advertisement, generating a response that is then recorded on their device. The input is the user's interaction, and the output is the generation of user behavior data.

[0760] Step 8:

[0761] The device sends user response information to the server, which is then used as feedback data for future ad generation. The input is user behavior data, and the output is the ad generation process for subsequent generations, reflecting the feedback.

[0762] (Application Example 1)

[0763] 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".

[0764] Traditional advertising delivery systems were limited to personalization based on user history information, making it difficult to deliver real-time advertisements tailored to the user's current situation and location. This resulted in limited advertising effectiveness and reduced relevance of information to the user.

[0765] 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.

[0766] In this invention, the server includes acquisition means for obtaining user history information from a database, analysis means for analyzing the acquired history information to identify user characteristics, generation means for generating text information based on characteristics, anonymization means for anonymizing the user's personal information, transmission means for transmitting the generated text information to the user's device, display means for immediately displaying relevant information using the device's location information, and improvement means for receiving response information from the device and reflecting it in improving the text information. This makes it possible to provide personalized advertisements in real time according to the user's situation and location.

[0767] "Acquisition method" refers to the method for retrieving user history information from a database.

[0768] "Analysis methods" refer to methods for extracting and analyzing acquired historical information to identify user characteristics.

[0769] "Generation means" refers to a method of creating textual information to be presented to a user based on specified characteristics.

[0770] An "anonymization method" is a method of removing users' personal information from generated text information to anonymize it.

[0771] "Transmission means" refers to a method for transferring the generated anonymized text information to the user's device.

[0772] "Display means" refers to a method of instantly displaying relevant information based on the location information of the device.

[0773] "Improvement methods" refer to methods of making improvements to future text information more effective based on response information obtained from the device.

[0774] The embodiment of this invention consists of a system centered on a server, a terminal, and a user. The server uses a cloud server such as Amazon Web Services (AWS) or Google Cloud, and the database uses MySQL. On the terminal side, a smartphone application is developed using Android Studio or Swift.

[0775] The server first retrieves user history information from the database. This includes purchase history and location information. This data is preprocessed using Python, and user characteristics are analyzed using machine learning frameworks such as TensorFlow and PyTorch. Based on this characteristic analysis, generative AI models such as OpenAI's GPT are used to generate text information tailored to the user. This generated text information is processed using anonymization techniques (e.g., k-anonymization) to protect privacy.

[0776] The anonymized information is then sent to the device. The device uses location information obtained from GPS and other sensors to display relevant information at the appropriate time. This display aims to show the most relevant advertisements for the user's current location.

[0777] After information is displayed on the user's device, the user's reaction to that advertisement is recorded. For example, if the user clicks on the displayed advertisement, that data is sent from the device to the server and used to improve future ad generation processes.

[0778] For example, when a user is near a cafe, the app displays an advertisement such as, "Use our discount coupon for our new coffee product. Click here for details." An example of a prompt message is, "Generate a customized ad message based on the behavioral characteristics obtained from the history information of user ID: 12345. Present the most relevant offer based on the current location."

[0779] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0780] Step 1:

[0781] The server retrieves user history information from the database. In this step, SQL queries are executed based on the user ID to extract data such as past purchase history and location information. The input is the user ID, and the output is the history information associated with that user.

[0782] Step 2:

[0783] The system analyzes historical data acquired by the server to identify user characteristics. Data preprocessing is performed using Python, and the data is then fed into a model using machine learning frameworks such as TensorFlow or PyTorch. This identifies user behavior patterns and areas of interest. The input is historical data, and the output is extracted characteristic information.

[0784] Step 3:

[0785] The server generates text information using a generative AI model based on characteristics. It uses the OpenAI GPT model to create advertising messages tailored to the user's interests. The input is characteristic information, and the output is customized text information.

[0786] Step 4:

[0787] The server anonymizes personal information from the generated text data. Using k-anonymization technology, it creates text data that retains privacy. The input is the generated text data, and the output is the anonymized text data.

[0788] Step 5:

[0789] The server sends anonymized text information to the terminal. The data is then sent to the user's smartphone via network communication. The input is anonymized text information, and the output is confirmation that the information has been received on the terminal.

[0790] Step 6:

[0791] The system acquires text information received by the device and displays it appropriately based on location information. It uses a GPS sensor to adjust the display timing according to the user's current location. Input consists of text information and location data, while output is advertising information displayed on the user's screen.

[0792] Step 7:

[0793] The user reacts to the displayed advertisement, and this response information is recorded. The device collects data such as user clicks and viewing time. The input is the user's action log, and the output is the response information sent to the server.

[0794] Step 8:

[0795] The server analyzes the response information received from the terminal and incorporates it into subsequent advertisements. The ad generation process is updated to reflect changes in user interests and behavior. The input is the response information, and the output is the updated ad strategy.

[0796] 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.

[0797] The system implementing this invention is for generating and delivering personalized advertisements that also take into account the user's emotions. This system consists of a server, a terminal, and a user, and includes a novel element that incorporates an emotion engine in particular.

[0798] First, the server accesses the database to retrieve user history and purchase information. Based on this information, it analyzes the user's past behavior and interests. The server utilizes the characteristic profiles identified by the analysis tools, but a newly introduced sentiment engine extracts the user's sentiment trends from the history information. Sentiment trends play a crucial role in more accurately personalizing textual information.

[0799] The generation method incorporates the results of an emotion engine in addition to conventional algorithms, generating textual information that takes into account the user's emotional state and emotional changes. This textual information can include expressions and content that correspond to the user's emotions at that moment. Furthermore, the generated textual information is adjusted based on emotions and includes elements to deliver specific and empathetic messages to the user.

[0800] After generation, the server uses anonymization methods to remove personal information from the text data, protecting user privacy. The anonymized text data is then sent from the server to the terminal.

[0801] The device receives this information and notifies the user. When the user receives the message, their reaction (e.g., opening, clicking, replying) is recorded by the device. This record is reviewed based on emotional state and fed back to the server.

[0802] For example, if a user expresses interest in travel and the emotion engine detects from their recent history that they are experiencing stress, the server will generate an advertising message such as "Recommended travel destinations where you can relax." If the user sees this message on their device and makes a reservation, that response will be used as training data for the next generation process.

[0803] This system will enable companies to efficiently deliver personalized advertisements that resonate with users' emotions, and is expected to improve conversion rates and customer satisfaction.

[0804] The following describes the processing flow.

[0805] Step 1:

[0806] The server accesses the database to retrieve user history and purchase information. This information includes past purchase history, access logs, and search history. This allows for a comprehensive understanding of the user's behavior patterns.

[0807] Step 2:

[0808] The information acquired by the server is processed using data cleansing techniques. Missing or inconsistent data is removed, making it suitable for analysis. This allows for the creation of accurate user profiles.

[0809] Step 3:

[0810] The server uses an emotion engine to extract emotion trends from the user's history information. This process uses natural language processing techniques to recognize the user's emotional state from their text data.

[0811] Step 4:

[0812] The server uses analytical tools to identify user characteristics based on historical data and sentiment trends. This generates personalized information that addresses the user's areas of interest and emotional needs.

[0813] Step 5:

[0814] The server utilizes a generation AI model to generate text information based on characteristics and emotional trends. The generated text information includes content that corresponds to the user's current emotional state.

[0815] Step 6:

[0816] The server performs an anonymization process to remove personal information from text data. This ensures user privacy.

[0817] Step 7:

[0818] The server sends anonymized text information to the user's device. The device receives this information and manages when it is displayed to the user.

[0819] Step 8:

[0820] The device records the user's responses to messages. Data is collected when the user opens a message or clicks on a link, and this data is sent to the server.

[0821] Step 9:

[0822] The server analyzes the response information it collects and uses it to inform future message generation and user profile updates. This allows the entire system to continuously learn and provide more personalized services.

[0823] (Example 2)

[0824] 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".

[0825] Traditional personalized advertising systems primarily generated ads based on users' past history and purchase information. However, because they did not consider the user's emotional state, they sometimes delivered ads that were inconsistent with the user's mood at the time. This resulted in a failure to capture the user's attention and made effective ad delivery difficult. Furthermore, with the increasing demand for anonymization of users' personal information from a privacy protection perspective, there is a lack of technical means to achieve emotional personalization.

[0826] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0827] In this invention, the server includes means for acquiring user history information and purchase information from a data storage device; means for identifying the user's characteristic profile based on the acquired information; means for extracting the user's emotional trends using emotion analysis technology in addition to the characteristics identified by the analysis means and generating text information; means for transmitting the anonymized text information to the user's communication device; and means for receiving response information from the communication device and improving the text information. This makes it possible to provide personalized advertisements that take into account the user's emotional state while protecting personal information.

[0828] A "data storage device" is a storage medium that stores user history information and purchase information, and allows access and retrieval as needed.

[0829] "Acquisition means" refers to a function or process for acquiring user history information and purchase information from a data storage device.

[0830] "Analysis methods" refer to algorithms and techniques used to identify user characteristic profiles using acquired information.

[0831] "Generation means" refers to processes and devices for analyzing user characteristics and emotional trends to construct specific textual information.

[0832] "Sentiment analysis technology" is a technique for extracting emotional trends based on user history and purchase information, and it generally uses natural language processing.

[0833] An "anonymization method" is a process for removing or concealing personally identifiable information from generated textual information.

[0834] "Transmission means" refers to a function or system for transmitting anonymized text information to a user's communication device.

[0835] "Improvement measures" refer to technologies or processes for evaluating the effectiveness of text information based on response information from the user's device and reflecting this in the next generation process.

[0836] This invention relates to a system for efficiently generating and delivering personalized advertisements that take into account the emotions of users. The system consists of three elements: a server, a terminal, and a user, and incorporates a novel method using emotion analysis technology.

[0837] The server retrieves user history and purchase information from data storage devices. This retrieval is performed via a secure network connection and typically uses SQL database queries. Based on the retrieved information, the server uses machine learning algorithms to analyze the user's characteristic profile. This identifies the user's interests and behavioral patterns.

[0838] Next, the server uses sentiment analysis technology to extract sentiment trends from the user's past history. Here, analysis techniques utilizing natural language processing (NLP) are employed. For example, it calculates positive, negative, and neutral sentiment scores from the user's comments and reviews.

[0839] Based on the generated sentiment trends, the server utilizes a generative AI model to create text information optimized for the user. The generated advertisements reflect the user's current emotional state and include expressions tailored to individual needs. An example of inputting this prompt into the generative AI model would be: "Consider the user's past behavioral data and sentiment trends to generate a travel advertisement message with a relaxation theme."

[0840] After the advertisement is generated, the server uses an anonymization method to remove personal information from the generated text information in order to protect user privacy. This procedure removes personally identifiable information, thus protecting user privacy.

[0841] Anonymized text information is sent from the server to the device. Security protocols such as SSL / TLS are used for this transmission. The device notifies the user of the received text information and records the user's response. When the user opens an advertisement or clicks a link, that action is logged by the device.

[0842] Ultimately, the device feeds back the collected user response data to the server. This information is then used to improve the next ad generation process. In this way, the accuracy and relatability of ads are enhanced, and user engagement is maximized.

[0843] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0844] Step 1:

[0845] The server accesses the data storage device to retrieve user history and purchase information. A specific user ID is given as input, and the output is a history dataset for that user. Specifically, the server executes SQL queries to aggregate data such as history and purchase history.

[0846] Step 2:

[0847] The server analyzes the user's characteristic profile based on the acquired data. The historical dataset obtained in Step 1 is used as input, and the user's characteristic profile is generated as output. Specifically, the server applies machine learning algorithms to analyze the user's interests and behavioral tendencies.

[0848] Step 3:

[0849] The server extracts user sentiment trends using sentiment analysis technology. The input is the historical information obtained in step 1, and sentiment trend data is generated as output. The server uses natural language processing (NLP) to calculate sentiment scores from reviews and comments.

[0850] Step 4:

[0851] The server generates text information that reflects the user's characteristic profile and sentiment trends using a generation method. The inputs are the characteristic profile from step 2 and the sentiment trend data from step 3, and the output is a personalized advertising message. The generation AI model generates customized messages tailored to the user's current situation.

[0852] Step 5:

[0853] The server performs an anonymization process to remove personal information from the generated text information. The input is the advertising message generated in step 4, and the output is an anonymized message. Specifically, identifiable personal information is masked by the algorithm.

[0854] Step 6:

[0855] The server sends anonymized text information to the terminal. The input is the anonymized message from step 5, and the output is the secure transmission of the message to the terminal. The server uses the SSL / TLS protocol to encrypt and send the message.

[0856] Step 7:

[0857] The device notifies the user of received advertising messages. The input is an anonymized message sent from the server, and the output is a notification displayed on the user interface. Specifically, the device displays the message in the smartphone's notification bar.

[0858] Step 8:

[0859] Users take action in response to advertising messages. The input is an advertising notification, and the output is the user's actions, such as clicks or link accesses, which are recorded on the device. Users open the message and click on links that interest them.

[0860] Step 9:

[0861] The device records user behavior data and sends feedback to the server. The input is the user's action, and the output is a log of behavior data, which is sent to the server. The device formats the log into JSON format and sends the data to the server.

[0862] (Application Example 2)

[0863] 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".

[0864] Traditional advertising systems generate personalized ads without considering the user's emotional state, sometimes resulting in users seeing ads they don't want. Furthermore, the lack of technology to analyze user emotions in real time and adjust ad content accordingly meant that ads failed to capture user interest, reducing their effectiveness.

[0865] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0866] In this invention, the server includes acquisition means for acquiring user behavior records from a data storage area, analysis means for analyzing the acquired behavior records to estimate the user's characteristics, and emotion analysis means for analyzing the user's emotional state using facial recognition and acoustic recognition. This makes it possible to display personalized advertisements in real time that are tailored to the user's emotional state.

[0867] "Data storage area" refers to the storage that stores user activity records, purchase history, and other related information.

[0868] A "user" is an individual or organization that uses the system, and is the subject of analysis of their behavioral records and emotional states.

[0869] "Activity log" refers to historical data about online or offline activities that a user has engaged in in the past.

[0870] "Acquisition means" refers to the mechanisms and processes for retrieving necessary information from the data storage area.

[0871] "Analysis means" refers to functions and methods for analyzing acquired behavioral records and extracting characteristics and trends.

[0872] "Characteristics" refer to information that indicates a user's interests, behavioral patterns, and personality.

[0873] A "generation method" is a method for assembling information that is optimal for the user based on the analyzed characteristics.

[0874] "Anonymization methods" are means used to remove or conceal personally identifiable information in order to protect the privacy of users.

[0875] "Transmission means" refers to the methods or techniques used to transmit generated information to the user's device.

[0876] "Response information" refers to the actions or responses that users exhibit in response to the information they receive.

[0877] "Improvement measures" refer to the process of making adjustments to the information generated based on reaction information, and the methods used to generate it, in order to make them more effective.

[0878] "Emotional analysis methods" refer to methods and technologies that use facial recognition or acoustic recognition of a user to evaluate their emotional state at any given time.

[0879] "Adjustment mechanisms" refer to functions that optimize the content and display method of information based on the results of sentiment analysis.

[0880] The system for implementing this invention mainly consists of a server, terminals, and users who utilize the terminals. The server accesses a data storage area and retrieves data such as user activity records and purchase history. This utilizes data storage systems such as SQL databases and NoSQL databases.

[0881] The server uses machine learning software such as TensorFlow and PyTorch as analysis tools to estimate user characteristics by analyzing acquired data. Furthermore, the emotion analysis tool uses input devices such as cameras and microphones to analyze the user's real-time emotional state. This analysis utilizes libraries such as OpenCV and natural language processing models.

[0882] Based on these analysis results, the server uses a generative AI model to generate information tailored to the user. This information is often structured in JSON or XML format. The generated information is anonymized, and any personally identifiable data is removed.

[0883] The device receives information sent from the server and displays it to the user visually or audibly. Examples of devices include smart glasses and portable computers. The device then records the user's reactions, such as ad click history, and sends this information back to the server as feedback. The server uses this feedback to improve the information it generates.

[0884] Specifically, if behavioral data indicates that a user is interested in a new gadget, the server will display a video demonstrating the gadget's use on the smart glasses when the user's emotions are heightened. Furthermore, if the user's face shows expressions of surprise or interest, additional promotional information will be displayed to encourage purchase.

[0885] An example of a prompt would be: "Show how to analyze a user's emotions in real time based on their video and audio data and generate personalized ads for new electronic devices."

[0886] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0887] Step 1:

[0888] The server accesses the data storage area to retrieve user activity records and purchase history. The input is a user ID, and the output is activity record data and purchase history data. This data is extracted from the database using SQL queries.

[0889] Step 2:

[0890] The server analyzes the acquired data and estimates the user's characteristics. The input is previously acquired behavioral record data and purchase history data, and the output is profile information indicating the user's interests and purchasing tendencies. A machine learning model using TensorFlow is used here. Profile information is generated by performing feature extraction and classification.

[0891] Step 3:

[0892] The server acquires real-time video and audio data from the user through the camera and microphone built into the smart glasses and performs emotion analysis. The input consists of video and audio data, and the output is analytical information indicating the user's emotional state. This process uses the OpenCV library for face recognition and applies an emotion estimation algorithm.

[0893] Step 4:

[0894] The server generates user-specific information using a generative AI model based on sentiment analysis and profile information. Input includes sentiment analysis and profile information, while output is user-specific advertising and presentation information. This generation process utilizes a machine learning model employing natural language processing techniques.

[0895] Step 5:

[0896] The server anonymizes the generated information to protect the user's personal information. The input is the generated advertising information, and the output is anonymized information from which personally identifiable elements have been removed. At this stage, the identification information is hashed.

[0897] Step 6:

[0898] The server sends anonymized information to the terminal. The input is the anonymized information, and the output is the data packet being transmitted. A secure communication protocol is used for this transmission.

[0899] Step 7:

[0900] The terminal displays received information to the user and records their response. The input is information sent from the server, and the output is user response data. Visual information is presented to the terminal via smart glasses.

[0901] Step 8:

[0902] The terminal feeds back recorded response data to the server. The input is the user's response data, and the output is the feedback data. This data is stored on the server as training data for future information generation.

[0903] 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.

[0904] 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.

[0905] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0906] 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.

[0907] 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.

[0908] 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.

[0909] 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.

[0910] 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.

[0911] 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."

[0912] 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.

[0913] 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.

[0914] 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.

[0915] 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.

[0916] 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.

[0917] 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.

[0918] 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.

[0919] 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.

[0920] 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.

[0921] 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.

[0922] 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.

[0923] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0924] The following is further disclosed regarding the embodiments described above.

[0925] (Claim 1)

[0926] A means for obtaining user history information from a database,

[0927] An analytical method for identifying user characteristics by analyzing acquired historical information,

[0928] A generation means for generating character information based on characteristics,

[0929] Anonymization methods to anonymize users' personal information,

[0930] A transmission means for sending the generated character information to the user's device,

[0931] An improvement means that receives response information from the device and reflects it in improving the text information,

[0932] A system that includes this.

[0933] (Claim 2)

[0934] The system according to claim 1, wherein the acquisition means acquires purchase information in addition to the user's history information.

[0935] (Claim 3)

[0936] The system according to claim 1, wherein the generation means utilizes natural language processing as a fundamental technology.

[0937] "Example 1"

[0938] (Claim 1)

[0939] A means for obtaining user history information from a data management device,

[0940] A means of analyzing acquired historical information using information processing technology to identify user characteristics,

[0941] A means of creating textual information using information generation technology based on its characteristics,

[0942] A means of anonymizing users' personally identifiable information using processing technology,

[0943] A means for communicating the generated character information to the user's computing device,

[0944] A means for receiving response information from a computing device and using it for optimizing character information,

[0945] A system that includes this.

[0946] (Claim 2)

[0947] The system according to claim 1, wherein the acquisition means acquires not only user history information but also purchase history.

[0948] (Claim 3)

[0949] The system according to claim 1, wherein the information generation technology applies natural language processing technology as a foundational technology.

[0950] "Application Example 1"

[0951] (Claim 1)

[0952] A means for obtaining user history information from a database,

[0953] An analytical method for identifying user characteristics by analyzing acquired historical information,

[0954] A generation means for generating character information based on characteristics,

[0955] Anonymization methods to anonymize users' personal information,

[0956] A transmission means for sending the generated character information to the user's device,

[0957] A display means that instantly displays relevant information using the location information of the device,

[0958] An improvement means that receives response information from the device and reflects it in improving the text information,

[0959] A system that includes this.

[0960] (Claim 2)

[0961] The system according to claim 1, wherein the acquisition means acquires not only user history information but also purchase information and location information.

[0962] (Claim 3)

[0963] The system according to claim 1, wherein the generation means utilizes natural language processing and location-dependent advertising technology as underlying technologies.

[0964] "Example 2 of combining an emotion engine"

[0965] (Claim 1)

[0966] A means for acquiring user history information and purchase information from a data storage device,

[0967] An analytical method for identifying user characteristic profiles based on acquired information,

[0968] In addition to the characteristics identified by the analysis method, a generation method is used to extract the user's emotional trends using emotion analysis technology and generate textual information.

[0969] A method for anonymizing generated text information by removing personally identifiable information,

[0970] A transmission means for sending anonymized text information to a user's communication device,

[0971] An improvement method that receives response information from a communication device and improves textual information based on the accumulated data,

[0972] A system that includes this.

[0973] (Claim 2)

[0974] The system according to claim 1, wherein the emotion analysis technology is an analysis technology using natural language processing.

[0975] (Claim 3)

[0976] The system according to claim 1, wherein the acquisition means records and analyzes the user's emotional trends over time.

[0977] "Application example 2 when combining with an emotional engine"

[0978] (Claim 1)

[0979] A means for obtaining user behavior records from a data storage area,

[0980] An analytical means for estimating user characteristics by analyzing acquired behavioral records,

[0981] A generation means for generating information based on characteristics,

[0982] An anonymization method for anonymizing user identification information,

[0983] A transmission means for sending the generated information to the user's device,

[0984] An improvement method that receives reaction information from the device and uses that information to improve the device,

[0985] An emotion analysis means that analyzes the emotional state of a user using facial recognition and acoustic recognition,

[0986] An adjustment means for adjusting display information based on the results of emotion analysis,

[0987] A system that includes this.

[0988] (Claim 2)

[0989] The system according to claim 1, wherein the acquisition means acquires not only user activity records but also purchase history.

[0990] (Claim 3)

[0991] The system according to claim 1, wherein the generation means utilizes a language processing method as a base technology and also takes into account the results of sentiment analysis. [Explanation of Symbols]

[0992] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for obtaining user history information from a database, An analytical method for identifying user characteristics by analyzing acquired historical information, A generation means for generating character information based on characteristics, Anonymization methods to anonymize users' personal information, A transmission means for sending the generated character information to the user's device, An improvement means that receives response information from the device and reflects it in improving the text information, A system that includes this.

2. The system according to claim 1, wherein the acquisition means acquires purchase information in addition to the user's history information.

3. The system according to claim 1, wherein the generation means utilizes natural language processing as a fundamental technology.

Images