system

Abstract

Provide a system. 【Solution means】 In an information processing apparatus, Means for acquiring transaction data in real time, Means for analyzing the acquired transaction data using a generation model to detect anomalies, Means for performing root cause analysis to identify the cause of the anomaly, Means for generating an on-demand report based on the analysis results, Means for providing personalized advice to the user, Means for protecting data security and privacy, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In order to quickly and accurately detect an abnormality from a large amount of generated transaction data and further identify the cause of the abnormality, a great deal of man-hours and time are required, and there is a problem that the conventional method places a great burden on system personnel. In addition, detailed analysis for taking appropriate measures when an abnormality occurs, prompt notification to users, and provision of personalized advice are required, but there is also a problem that it is difficult to perform these efficiently.

Means for Solving the Problems

[0005] This invention solves the above problems by providing an information processing device that acquires transaction data in real time and detects anomalies using a generative model. Furthermore, by providing means for performing root cause analysis to identify the cause of anomalies and generating on-demand reports based on the analysis results, it enables a rapid and accurate response. In addition, by providing personalized advice to users and protecting data security and privacy, it reduces the burden on system administrators and improves the overall quality of the system.

[0006] An "information processing device" is a device or system that uses a computer system to collect, analyze, store, and process information.

[0007] "Transaction data" refers to a record of all data generated during a transaction or business process, including timestamps and processing results.

[0008] A "generative model" is a type of artificial intelligence that learns patterns from large amounts of data and uses them to perform anomaly detection and prediction based on new data.

[0009] Anomaly detection is the process of identifying abnormal patterns or error data that fall outside the normal range.

[0010] "Root cause analysis" is a detailed investigation and analysis method used to clarify the cause of a particular problem or abnormality.

[0011] An "on-demand report" is a report that is generated based on a specific period or conditions in response to a user's request.

[0012] "Personalized advice" refers to information that provides recommendations and guidance tailored to each user's history and current situation.

[0013] "Security" refers to all protective measures taken to prevent unauthorized access and data loss.

[0014] "Privacy protection" refers to measures taken to prevent users' personal information and data from being misused by third parties. [Brief explanation of the drawing]

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

Embodiments for Carrying out the Invention

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

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

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

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

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

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

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

[0023] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0036] This invention is a system that uses an information processing device to monitor transaction data in real time, detect anomalies, and automatically take necessary actions. This significantly reduces the workload on system administrators and improves the efficiency and reliability of business processes.

[0037] System operation

[0038] The server automatically acquires and processes all transaction data occurring within the system in real time. This data is then fed into a generative model to identify normal processing results and abnormal patterns. For example, in an online shopping site, the server monitors data such as purchase processing and payment errors in real time and notifies the administrator if any anomalies are detected.

[0039] When an anomaly is detected, the server investigates the root cause and performs detailed data analysis. For example, it analyzes network latency and load during a specific time period to identify that the anomaly is due to network congestion. The results of this analysis are automatically generated as a report and provided to the user through their terminal.

[0040] Furthermore, the server analyzes the user's past transaction history and generates personalized advice based on it. For example, if a user frequently makes errors in a particular operation, the server will suggest alternative solutions.

[0041] Security and privacy are paramount in data processing and storage. Servers encrypt and securely store all transaction data. Access permissions are strictly controlled, ensuring that only specific users can access the data.

[0042] Thus, the system for implementing the invention enables efficient monitoring and anomaly detection of transaction data, facilitating rapid problem resolution and appropriate feedback to users. Furthermore, it provides a secure and reliable environment by ensuring data safety and privacy protection.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server acquires transaction data generated in real time as a result of various transactions and operations within the system. Each transaction is logged, recording its details.

[0046] Step 2:

[0047] The server preprocesses the acquired transaction data, cleaning and standardizing the format as needed. This preprocessing is necessary for the generative model to efficiently analyze the data.

[0048] Step 3:

[0049] The server inputs pre-processed data into a generative model to detect anomalous patterns and error data hidden within the data. Based on its learning, the generative model identifies normal patterns and identifies anomalies.

[0050] Step 4:

[0051] The server generates an alert based on anomalies detected by the generative model. This alert is immediately sent to the system administrator via the terminal to prompt a quick response.

[0052] Step 5:

[0053] The server performs a detailed analysis of the relevant data to identify the root cause of the anomaly. This involves identifying the circumstances and related factors at the time of the anomaly and conducting a detailed data analysis to determine the cause.

[0054] Step 6:

[0055] The server automatically generates a detailed report containing the cause of the problem and suggested solutions, and sends it to the user's terminal. This report includes an overview of the anomaly and recommended actions.

[0056] Step 7:

[0057] The server analyzes the user's past transaction data and analysis history to generate personalized advice optimized for the user. This allows the user to obtain the most suitable course of action.

[0058] Step 8:

[0059] The server implements security and privacy measures in all data processing and report generation. Data is encrypted and appropriate access controls are in place.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] In real-time monitoring and anomaly detection of transaction data in information processing systems, there is a need to reduce the burden on system administrators and enable rapid and appropriate problem resolution. Conventional systems required significant time and effort for anomaly notification, detailed data analysis, and security protection. Therefore, it is necessary to streamline these processes and improve the overall reliability of business processes.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes means for acquiring transaction data in real time, means for analyzing the acquired data using a generative model to identify normal and abnormal conditions, and means for performing detailed analysis to identify the cause when an abnormality is detected and automatically sending a report to the administrator. This makes it possible to reduce the workload on system administrators and enable rapid problem solving and effective feedback.

[0065] An "information processing device" is a device that uses a computer to collect, analyze, store, and manage data.

[0066] "Transaction data" refers to a collection of data that records various transactions and processes, and it flows through the system in real time.

[0067] A "generative model" is a mathematical model that uses artificial intelligence technology to perform pattern recognition and anomaly detection.

[0068] "Acquiring data in real time" refers to the action of immediately importing data into the system as soon as it is generated.

[0069] "Identifying anomalies" means detecting and understanding patterns or trends that are different from the norm in data.

[0070] "Detailed analysis for identifying the cause" refers to a detailed data investigation conducted when an anomaly occurs, in order to determine what caused it.

[0071] "Automatic sending of reports to administrators" refers to the process of automatically sending a report summarizing the analysis results to the administrator.

[0072] "Personalized operation guidance" is a feedback method that provides individual advice and recommendations based on the user's past data.

[0073] "Encryption" is a technology that transforms data based on a specific algorithm to protect it from unauthorized reading or tampering.

[0074] The embodiment for carrying out this invention is an information processing system configuration that monitors transaction data in real time and detects anomalies. The server collects transaction data and analyzes the data using a generated AI model. A general-purpose server machine is used as the hardware, and the software utilizes a database system and an AI model construction framework specialized for anomaly detection (e.g., TENSORFLOW®, PyTorch).

[0075] The server first interacts with a database system (e.g., MySQL® or PostgreSQL) to acquire all transaction data in real time. The acquired data is then passed to a generating AI model, which automatically identifies normal and abnormal patterns. In this process, the AI ​​model quickly recognizes anomalies based on the patterns it has learned.

[0076] When an anomaly is detected, the server performs a detailed data analysis to identify the root cause of the anomaly. The identified information is sent to the administrator as an automatically generated report. Email systems and messaging services (such as Slack) are used to send the report.

[0077] Users are provided with personalized operational guidance based on their past transaction history. For example, users who frequently encounter errors in specific operations are offered alternative solutions. This allows users to improve the efficiency of their work processes.

[0078] High security is required for data storage, and the server uses AES encryption technology to securely protect transaction data. Furthermore, access rights are strictly controlled, and only authorized users can access the data.

[0079] As a concrete example, in a small online store, using this system enables rapid anomaly detection and efficient problem resolution. For instance, if payment errors frequently occur during a specific time period and the cause is identified as server load, quick countermeasures can be taken based on that information.

[0080] An example of a prompt related to this system would be, "Please tell me the procedure for detecting abnormal patterns in recent transaction data using a generating AI model and identifying the cause of the problem."

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] The server works in conjunction with the information processing device to retrieve transaction data in real time. SQL queries are used to retrieve the latest transactions from the database system. In this step, the input consists of the data generation timestamp and transaction details, while the output is formatted transaction data.

[0084] Step 2:

[0085] The server preprocesses the acquired transaction data. This includes filling in missing data and removing unnecessary data. The input is the transaction data acquired in step 1, and the output is data formatted for analysis. Specifically, for example, it standardizes the date format to make it easier for the analysis model to read.

[0086] Step 3:

[0087] The server feeds pre-processed data into a generative AI model. The generative AI model analyzes the data patterns and detects anomalous patterns. In this step, the input is pre-processed transaction data, and the output is the detected anomalous patterns and their characteristics. The specific operation here is to apply the normal / anomalous discrimination algorithm that the AI ​​model has learned.

[0088] Step 4:

[0089] The server generates prompts for analyzing the details of anomalies based on the anomalies detected by the generation AI model, and then performs a detailed analysis. These prompts are input into a data analysis tool to support root cause analysis. The input for this step is the anomaly pattern, and the output is the result of the root cause analysis of the anomaly. Specifically, this includes operations to check network utilization and server load during specific time periods.

[0090] Step 5:

[0091] The server automatically generates a report containing the analyzed cause and solution of the anomaly, and sends it to the administrator via the terminal. The input is the result of the cause analysis, and the output is a report in a format that is easy for the administrator to understand. Specifically, a report generation tool is used to automatically create a report that incorporates charts, graphs, and key points.

[0092] Step 6:

[0093] The server analyzes the user's past transaction history and generates personalized advice. The input is the user's historical data, and the output is individually customized operational guidance. Specifically, it suggests alternative methods for specific errors.

[0094] Step 7:

[0095] The server encrypts and securely stores all transaction data. The data is stored securely using the AES encryption algorithm and is accessible only to authorized users. Input is raw data, and output is encrypted data storage. Specifically, this involves managing and periodically updating security keys.

[0096] (Application Example 1)

[0097] 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."

[0098] The objective is to provide a means to efficiently and accurately monitor transaction data in electronic payment services in real time and detect anomalies. In particular, the aim is to improve user convenience by automating rapid root cause analysis after anomaly detection and providing appropriate feedback and advice to users. Furthermore, the goal is to analyze environmental factors such as communication delays in transactions, propose effective countermeasures, and improve the user experience.

[0099] 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.

[0100] In this invention, the server includes means for (acquiring transaction data in real time), means for (analyzing the acquired transaction data using a generative model to detect anomalies), means for (performing root cause analysis to identify the cause of the anomaly), means for (presenting and notifying the user of recommended countermeasures using examples when an anomaly is detected), and means for (analyzing factors in the communication environment, including network delay, and deriving appropriate countermeasures). This enables the rapid and accurate detection of anomalies in electronic payments and the automation of appropriate countermeasures.

[0101] An "information processing device" is a computer system that acquires transaction data and processes and analyzes it in real time.

[0102] "Transaction data" refers to various types of data generated when using electronic payment services, including purchase information and payment information.

[0103] "Methods for acquiring data in real time" refer to functions that allow data to be collected immediately and processed without delay.

[0104] A "generative model" is a mathematical model for pattern recognition developed based on machine learning algorithms, and is used to detect anomalies in data.

[0105] "Means for detecting anomalies" refers to the process of identifying normal transaction patterns from deviant patterns and determining whether they are anomalies.

[0106] "Root cause analysis" is the process of identifying the primary cause of an abnormality when it occurs.

[0107] An "on-demand report" is a report that compiles necessary information based on analysis results and is generated when a specific action is requested.

[0108] "Personalized advice" refers to providing individual recommendations that are deemed appropriate based on the user's past behavior and data.

[0109] "Means of protecting data security and privacy" refer to technologies and methods for protecting transactional data from unauthorized access and leakage, and for managing it securely.

[0110] "A means of presenting and notifying users of recommended countermeasures using examples when an anomaly is detected" refers to a method of showing users the best possible countermeasures based on pre-prepared examples of responses when an anomaly is confirmed.

[0111] "Means for analyzing factors in the communication environment, including network latency, and deriving appropriate countermeasures" refers to a function that analyzes communication-related problems that occur during transactions and proposes improvement measures based on that analysis.

[0112] The system implementing this invention consists of a server-based information processing system. The server first acquires transaction data generated in the electronic payment service in real time. The acquired data is processed by a generative model implemented using Python (for example, TensorFlow or PyTorch) to detect abnormal patterns. This model quickly and accurately identifies abnormalities that deviate from normal transaction patterns.

[0113] When an anomaly is detected, the server uses Pandas and NumPy to perform a detailed root cause analysis. This analysis identifies specific communication environment problems, such as network latency, and derives solutions as needed. These solutions are provided to the user in a recommended format by the server and are immediately notified via smartphones or other devices.

[0114] Furthermore, the server analyzes the user's past transaction data and analytics history to generate personalized advice. This advice is based on problems the user frequently faces and provides specific guidance for taking better actions.

[0115] Regarding data security and privacy protection, the server encrypts transaction data using the latest security protocols and stores it in secure storage. Access rights are also strictly controlled, and personal information is thoroughly protected, providing users with an environment where they can use the system with peace of mind.

[0116] As a concrete example, let's consider transaction data generated when a user purchases a product online. This data is monitored immediately by the system, and if an anomaly is detected, advice such as "Please improve your communication environment and try again" is provided. An example of this prompt is, "Analyze the latest transaction data in real time, detect anomaly patterns, and provide the cause and recommended countermeasures."

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] The server retrieves transaction data in real time from the electronic payment service's API. The input is the transaction data obtained via the API, and the output is the transaction data ready for processing. This data is temporarily stored in the database in preparation for subsequent processing.

[0120] Step 2:

[0121] The server inputs temporarily stored transaction data into a generative model to determine whether or not it is abnormal. The input is raw transaction data, and the output is data classified into normal patterns and abnormal patterns. In this process, a model using TensorFlow or PyTorch analyzes the data and detects abnormal patterns.

[0122] Step 3:

[0123] If an anomaly is detected, the server uses Pandas or NumPy to perform root cause analysis. The input is the transaction data that was determined to be anomaly, and the output is specific information about the cause of the anomaly. Through data analysis, problems such as network latency are identified, and information is prepared to show the user the specific cause.

[0124] Step 4:

[0125] The server generates and notifies the user of recommended actions based on the results of root cause analysis. The input is the result of the root cause analysis, and the output is a notification message to the user. The server sends the generated actions in the form of prompts to smartphones and other devices, enabling concrete actions to prompt a quick response.

[0126] Step 5:

[0127] The server analyzes the user's past transaction data and analytics history to generate individual trends and personalized advice based on them. The input is the user's past data, and the output is customized advice. The server provides this to the user to guide them toward appropriate actions.

[0128] Step 6:

[0129] The terminal receives notifications and advice sent from the server and displays them to the user. The input is notification information from the server, and the output is information displayed to the user on the terminal. Here, the user obtains specific means to use the service more safely and efficiently based on the information provided.

[0130] 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.

[0131] This invention combines an information processing device that acquires transaction data in real time and detects anomalies with an emotion engine that recognizes user emotions. This enables dynamic responses and the provision of personalized content that are tailored to the user's emotional state.

[0132] System operation

[0133] The server acquires and monitors transaction data generated from transactions and operations within the system in real time. This data is fed into generative models for anomaly detection, where abnormal patterns are identified. For example, the server monitors payment processing data in an e-commerce platform to quickly detect fraudulent transactions.

[0134] This system also incorporates an emotion engine that recognizes the user's emotional state. The terminal analyzes the user's input and actions, and the emotion engine determines the user's emotional state. This emotional state serves as an indicator of the user's stress level and satisfaction level while using the system.

[0135] The server dynamically adjusts the interface by leveraging the user's emotional state, as determined by the emotion engine. For example, if a user indicates anxiety, the system enhances the on-screen support options to improve the user experience in real time.

[0136] Furthermore, it is possible to provide personalized content based on the user's emotional state. Specifically, this can be done by prioritizing the display of products that the user is highly interested in, or by providing encouraging messages, thereby increasing user engagement.

[0137] The server ensures thorough data security and privacy protection throughout all analysis processes. All information, including user sentiment data, is properly encrypted and securely stored. In this way, the present invention achieves efficient management of transaction data and optimization of sentiment-based interfaces, thereby improving the user experience.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] The server retrieves transaction data in real time. This includes details of transactions and operations performed by the user, and the entire process within the system is recorded. The server continuously monitors this data and prepares it for processing.

[0141] Step 2:

[0142] The server feeds the acquired data into a generative model to detect anomalous patterns. For example, the server analyzes specific user behaviors where purchase frequency suddenly increases, identifying signs of fraud in real time.

[0143] Step 3:

[0144] If an anomaly is detected, the server activates the emotion engine and collects further necessary data from the device to analyze the user's emotional state. The device then extracts emotional indicators from the user's actions and inputs and sends them to the server.

[0145] Step 4:

[0146] The server adjusts the user interface based on the user's emotional state, as recognized by the emotion engine. For example, if the user shows signs of stress, the server provides assistance to the user, such as displaying operational guidelines.

[0147] Step 5:

[0148] The device displays personalized content tailored to the user's emotions. This content includes product suggestions that capture the user's interest and contextual messages, designed to enhance the user experience.

[0149] Step 6:

[0150] The server manages all data processing across the entire system to ensure strict protection of data security and privacy. This includes encrypting and securely storing both emotional and transactional data.

[0151] (Example 2)

[0152] 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".

[0153] While existing information processing systems perform real-time monitoring and anomaly detection of transaction data, they lack personalization that takes into account the user's emotional state. As a result, the user experience can be limited, and system responses may be delayed. This can prevent the provision of optimal support to users, potentially leading to decreased satisfaction.

[0154] 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.

[0155] In this invention, the server includes means for (acquiring and monitoring transaction data in real time), means for (analyzing the acquired data using a generative model and detecting anomalies), means for (incorporating an emotion recognition engine that analyzes the emotional state based on user input and actions), means for (dynamically adjusting the interface based on the analyzed emotional state), and means for (providing personalized content to the user). This enables efficient management of transaction data, optimization of the interface based on user emotions, and improvement of the user experience.

[0156] An "information processing device" is a device for collecting, analyzing, processing, and outputting data, and in particular has the function of processing transaction data and user emotional states in real time.

[0157] "Means for acquiring and monitoring transaction data in real time" refers to a function that immediately collects data generated by transactions and operations, and continuously observes it to detect anomalies early.

[0158] "Methods for analyzing and detecting anomalies using generative models" refers to the process of using machine learning or AI-based models to identify anomalies that deviate from normal patterns in collected data.

[0159] "Methods for conducting root cause analysis" refer to the process of thoroughly analyzing the background and causes of detected anomalies in order to identify the root cause of the problem.

[0160] "Methods for incorporating an emotion recognition engine" refer to the process of incorporating software or hardware into a system that analyzes user input data and behavioral patterns to infer their emotional state.

[0161] "Means of dynamically adjusting the interface" refers to a function that optimizes the user experience by changing the system's display and operation methods in real time according to the user's emotional state.

[0162] "Means of providing personalized content" refers to the process of selecting and providing information and services that are individually suited to each user based on their past behavior and emotional state.

[0163] "Means of protecting data security and privacy" refers to encryption technologies and access control measures to protect collected user data from unauthorized access and leakage.

[0164] This invention provides a system that incorporates an emotion engine for recognizing user emotions into an information processing device that acquires transaction data in real time and detects anomalies.

[0165] The server acquires and monitors transaction data generated from transactions and operations within the system in real time. For this purpose, high-speed database management systems and stream processing technologies can be used. For example, open-source software such as Apache® Kafka or existing commercial software may be used. The server utilizes AI models to analyze this data and detect anomalies. Python libraries such as Scikit-learn and TensorFlow may be used to build these models.

[0166] The device records user input and actions and sends them to an emotion recognition engine. This engine analyzes emotions using natural language processing (NLP) techniques. Common NLP libraries used include NLTK and spaCy. The device understands the user's emotional state, and the system dynamically adjusts the interface based on this information. In other words, the screen design and configuration change according to the emotional data, providing the user with the optimal operating environment.

[0167] Furthermore, the server provides personalized content based on the user's past behavior history and current emotional state. For example, it can prioritize displaying information related to product categories that the user frequently searches for, or incorporate a product recommendation system to provide appropriate information to each user.

[0168] The server prioritizes data security, encrypting collected sentiment and transaction data and implementing access controls. This enhances privacy protection and prevents unauthorized access by third parties.

[0169] To give a specific example, on an online shopping platform, when a user is considering purchasing a particular product, an emotion engine can determine the user's stress level and provide corresponding customer support options in real time. Such systems help improve customer satisfaction and create new purchasing opportunities.

[0170] A suitable example of a prompt would be, "Suggest a way to provide effective support based on the user's emotional state."

[0171] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0172] Step 1:

[0173] The server acquires and monitors transaction data in real time. This input data includes transaction details, timestamps, and user information. The server uses stream processing technology to store this data in containers and begins monitoring for anomalies in the database. Specifically, Apache Kafka is used to rapidly stream the data, enabling real-time analysis.

[0174] Step 2:

[0175] The server inputs the acquired transaction data into a generating AI model to detect anomalies. This model has learned normal patterns and analyzes inconsistencies in the input data. As output, it classifies the data into normal and anomaly data. The server records the generated anomaly data and notifies the administrator as needed. This process is performed using the Scikit-learn library.

[0176] Step 3:

[0177] The device collects user behavior data and input information and sends it to the emotion recognition engine. Input includes keystroke speed, mouse movements, and click frequency. At this stage, the device preprocesses and quantifies the input data. The output is a calculated estimated emotional state of the user. Specifically, natural language processing is performed using the spaCy library to classify the emotions.

[0178] Step 4:

[0179] The server receives output from the emotion recognition engine and dynamically adjusts the interface according to the user's emotional state. The input is analyzed emotion data, which the server uses to change the screen layout and operations to improve the user experience. The output is a customized interface provided to the user. Specifically, if the user expresses anxiety, more emphasized support information and FAQs are displayed.

[0180] Step 5:

[0181] The server provides personalized content based on the user's emotions and past behavior history. Input includes the user's past purchase history and browsing information. The server analyzes this data and prioritizes displaying products and information that are likely to interest the user. Output includes featured pages and recommended product lists that match the user's interests. For example, a recommendation engine can be used to automatically display new products that match the user's preferences at the top.

[0182] Step 6:

[0183] The server maintains data security and privacy throughout all processing. Inputs include sentiment data and transaction data. The server encrypts this data and stores it in a secure database. For output, access control is strictly managed to prevent unauthorized access. Specifically, data communication is protected using SSL / TLS standards, and an authentication system is implemented to restrict access.

[0184] (Application Example 2)

[0185] 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".

[0186] In recent years, as many information processing systems rely on the analysis of transaction data, real-time anomaly detection and improved user experience have become crucial. However, with existing technologies, it has been difficult to simultaneously achieve anomaly detection and dynamic interface adjustments and personalized suggestions based on the user's emotional state. This invention aims to improve system security and user experience by combining real-time transaction data analysis with user emotion recognition.

[0187] 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.

[0188] In this invention, the server includes means for acquiring transaction information in real time, means for analyzing the acquired transaction information using a generative model and detecting anomalies, and means for recognizing the user's emotional state and dynamically adjusting the interface based on that state. This enables rapid detection of anomalies in transaction data and allows for personalized suggestions and interface adjustments in accordance with the user's emotional state.

[0189] An "information processing device" is a device or system used for collecting, analyzing, and storing data.

[0190] "Means for acquiring transaction information in real time" refers to a method or device for immediately collecting generated transaction information through data communication.

[0191] "Methods for analyzing and detecting anomalies using generative models" refer to methods that use models based on machine learning or statistical techniques to evaluate data and identify events that deviate from normal patterns.

[0192] "Means of performing root cause analysis to identify the cause of an anomaly" refers to analytical techniques used to investigate and clarify the underlying cause behind an anomaly that has occurred.

[0193] "Means for generating on-demand reports" refers to a function that instantly creates and provides data analysis results as reports as needed.

[0194] "Means for recognizing a user's emotional state and dynamically adjusting the interface based on that emotion" refers to technology that determines the user's emotions based on their input and actions, and then changes the display and functions of the user interface in a timely manner based on the results.

[0195] "Means of providing personalized content based on user emotions" refers to methods of presenting information and suggestions that take into account the user's emotional state and are tailored to their specific needs and preferences.

[0196] "Means of protecting data security and privacy" refer to encryption and access control technologies that protect personal and confidential data from unauthorized access and leakage.

[0197] "Means for generating and notifying warnings" refers to technologies that, when an anomaly or emergency is detected, immediately create warning information and communicate it to the relevant parties.

[0198] "Means for analyzing individual trends based on a user's past transaction information and analysis history" refers to analytical techniques that use historical data to reveal the behavioral patterns and trends of specific users.

[0199] The system for realizing this invention consists of a server and a terminal as an information processing device. The server is preferably located on a cloud platform or data center with advanced computing capabilities. The server uses network communication to acquire various transaction information in real time. The acquired data is analyzed using a generative AI model to detect anomalies. This analysis process utilizes a processor and data storage with advanced computing capabilities.

[0200] Furthermore, the device itself is equipped with an emotion engine to recognize the user's emotional state. This engine analyzes the user's emotions based on voice input and behavioral pattern detection. The results of this analysis are sent to a server and used to dynamically adjust the user interface. For example, if the user is in an anxious situation, the system will immediately present supportive content to improve the user experience. Specifically, it will display messages and links on the device to provide emphasized help and ensure a sense of security.

[0201] This invention enables the detection of anomalies in transaction data and the provision of personalized content based on user emotions. If a user feels uneasy while browsing a particular product, the system will provide encouraging messages to facilitate a smoother purchasing decision.

[0202] An example of a prompt message is as follows:

[0203] "Please create support messages to be displayed when users are feeling anxious. Include specific examples of support to help users feel at ease."

[0204] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0205] Step 1:

[0206] The server retrieves transaction information in real time over the network. This input data is appropriately organized into corresponding data fields. The data, including timestamps and user IDs, is temporarily stored in a state ready for analysis.

[0207] Step 2:

[0208] The server inputs the acquired transaction information into a generating AI model to perform anomaly detection. The generating AI model uses statistical analysis and machine learning algorithms to identify abnormal patterns by comparing them with past normal data. As output, if an anomaly is detected, a warning flag is set and detailed information about the anomaly is generated.

[0209] Step 3:

[0210] The server inputs detailed anomaly information into a root cause analysis module to identify the root cause of the anomaly. This process analyzes the anomaly's historical data and related events, and applies algorithms to identify potential causes. The output is provided as a list of candidate root causes.

[0211] Step 4:

[0212] The server receives emotion data sent from the user to the terminal and recognizes the emotional state. This data includes features extracted from the user's input and actions. The server uses an emotion engine to analyze the emotions and generates an emotional state status as output.

[0213] Step 5:

[0214] The server dynamically adjusts the user interface based on the emotional state status. The terminal displays reassuring support messages and action items. The output consists of personalized interface elements designed to enhance the user experience.

[0215] Step 6:

[0216] If the user provides additional input through the provided interface, the server collects that feedback information and performs analysis for further personalization. The output provides insights for future interface optimization.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] [Second Embodiment]

[0221] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0222] 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.

[0223] 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).

[0224] 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.

[0225] 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.

[0226] 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).

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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".

[0233] This invention is a system that uses an information processing device to monitor transaction data in real time, detect anomalies, and automatically take necessary actions. This significantly reduces the workload on system administrators and improves the efficiency and reliability of business processes.

[0234] System operation

[0235] The server automatically acquires and processes all transaction data occurring within the system in real time. This data is then fed into a generative model to identify normal processing results and abnormal patterns. For example, in an online shopping site, the server monitors data such as purchase processing and payment errors in real time and notifies the administrator if any anomalies are detected.

[0236] When an anomaly is detected, the server investigates the root cause and performs detailed data analysis. For example, it analyzes network latency and load during a specific time period to identify that the anomaly is due to network congestion. The results of this analysis are automatically generated as a report and provided to the user through their terminal.

[0237] Furthermore, the server analyzes the user's past transaction history and generates personalized advice based on it. For example, if a user frequently makes errors in a particular operation, the server will suggest alternative solutions.

[0238] Security and privacy are paramount in data processing and storage. Servers encrypt and securely store all transaction data. Access permissions are strictly controlled, ensuring that only specific users can access the data.

[0239] Thus, the system for implementing the invention enables efficient monitoring and anomaly detection of transaction data, facilitating rapid problem resolution and appropriate feedback to users. Furthermore, it provides a secure and reliable environment by ensuring data safety and privacy protection.

[0240] The following describes the processing flow.

[0241] Step 1:

[0242] The server acquires transaction data generated in real time as a result of various transactions and operations within the system. Each transaction is logged, recording its details.

[0243] Step 2:

[0244] The server preprocesses the acquired transaction data, cleaning and standardizing the format as needed. This preprocessing is necessary for the generative model to efficiently analyze the data.

[0245] Step 3:

[0246] The server inputs pre-processed data into a generative model to detect anomalous patterns and error data hidden within the data. Based on its learning, the generative model identifies normal patterns and identifies anomalies.

[0247] Step 4:

[0248] The server generates an alert based on anomalies detected by the generative model. This alert is immediately sent to the system administrator via the terminal to prompt a quick response.

[0249] Step 5:

[0250] The server performs a detailed analysis of the relevant data to identify the root cause of the anomaly. This involves identifying the circumstances and related factors at the time of the anomaly and conducting a detailed data analysis to determine the cause.

[0251] Step 6:

[0252] The server automatically generates a detailed report containing the cause of the problem and suggested solutions, and sends it to the user's terminal. This report includes an overview of the anomaly and recommended actions.

[0253] Step 7:

[0254] The server analyzes the user's past transaction data and analysis history to generate personalized advice optimized for the user. This allows the user to obtain the most suitable course of action.

[0255] Step 8:

[0256] The server implements security and privacy measures in all data processing and report generation. Data is encrypted and appropriate access controls are in place.

[0257] (Example 1)

[0258] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0259] In real-time monitoring and anomaly detection of transaction data in information processing systems, there is a need to reduce the burden on system administrators and enable rapid and appropriate problem resolution. Conventional systems required significant time and effort for anomaly notification, detailed data analysis, and security protection. Therefore, it is necessary to streamline these processes and improve the overall reliability of business processes.

[0260] 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.

[0261] In this invention, the server includes means for acquiring transaction data in real time, means for analyzing the acquired data using a generative model to identify normal and abnormal conditions, and means for performing detailed analysis to identify the cause when an abnormality is detected and automatically sending a report to the administrator. This makes it possible to reduce the workload on system administrators and enable rapid problem solving and effective feedback.

[0262] An "information processing device" is a device that uses a computer to collect, analyze, store, and manage data.

[0263] "Transaction data" refers to a collection of data that records various transactions and processes, and it flows through the system in real time.

[0264] A "generative model" is a mathematical model that uses artificial intelligence technology to perform pattern recognition and anomaly detection.

[0265] "Acquiring data in real time" refers to the action of immediately importing data into the system as soon as it is generated.

[0266] "Identifying anomalies" means detecting and understanding patterns or trends that are different from the norm in data.

[0267] "Detailed analysis for identifying the cause" refers to a detailed data investigation conducted when an anomaly occurs, in order to determine what caused it.

[0268] "Automatic sending of reports to administrators" refers to the process of automatically sending a report summarizing the analysis results to the administrator.

[0269] "Personalized operation guidance" is a feedback method that provides individual advice and recommendations based on the user's past data.

[0270] "Encryption" is a technology that transforms data based on a specific algorithm to protect it from unauthorized reading or tampering.

[0271] One embodiment of this invention is an information processing system configuration that monitors transaction data in real time and detects anomalies. The server collects transaction data and analyzes the data using a generative AI model. A general-purpose server machine is used as the hardware, and the software utilizes a database system and an AI model construction framework specialized for anomaly detection (e.g., TensorFlow, PyTorch).

[0272] The server first interacts with a database system (e.g., MySQL or PostgreSQL) to acquire all transaction data in real time. The acquired data is then passed to a generating AI model, which automatically identifies normal and abnormal patterns. In this process, the AI ​​model quickly recognizes anomalies based on the patterns it has learned.

[0273] When an anomaly is detected, the server performs a detailed data analysis to identify the root cause of the anomaly. The identified information is sent to the administrator as an automatically generated report. Email systems and messaging services (such as Slack) are used to send the report.

[0274] Users are provided with personalized operational guidance based on their past transaction history. For example, users who frequently encounter errors in specific operations are offered alternative solutions. This allows users to improve the efficiency of their work processes.

[0275] High security is required for data storage, and the server uses AES encryption technology to securely protect transaction data. Furthermore, access rights are strictly controlled, and only authorized users can access the data.

[0276] As a concrete example, in a small online store, using this system enables rapid anomaly detection and efficient problem resolution. For instance, if payment errors frequently occur during a specific time period and the cause is identified as server load, quick countermeasures can be taken based on that information.

[0277] An example of a prompt related to this system would be, "Please tell me the procedure for detecting abnormal patterns in recent transaction data using a generating AI model and identifying the cause of the problem."

[0278] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0279] Step 1:

[0280] The server obtains transaction data in real time in cooperation with the information processing device. To obtain the latest transactions from the database system, SQL queries are used. In this step, the input is the data generation timestamp and transaction details, and the output is the formatted transaction data.

[0281] Step 2:

[0282] The server preprocesses the obtained transaction data. This includes complementing missing data and removing unnecessary data. The input is the transaction data obtained in Step 1, and the output is the data formatted in a form suitable for analysis. As a specific operation, for example, the date format is unified to make it easier for the analysis model to read.

[0283] Step 3:

[0284] The server inputs the preprocessed data into the generative AI model. The generative AI model analyzes the data patterns and detects abnormal patterns. In this step, the input is the preprocessed transaction data, and the output is the detected abnormal patterns and their characteristics. The specific operation here is to apply the discrimination algorithm of normal and abnormal learned by the AI model.

[0285] Step 4:

[0286] Based on the abnormalities detected by the generative AI model, the server generates a prompt for analyzing the details of the abnormalities and performs a detailed analysis. This prompt is input into the data analysis tool to assist in cause analysis. The input for this step is the abnormal pattern, and the output is the result of the cause analysis of the abnormality. Specifically, it includes operations such as checking the network usage rate and server load during a specific time period.

[0287] Step 5:

[0288] The server automatically generates a report containing the analyzed cause and solution of the anomaly, and sends it to the administrator via the terminal. The input is the result of the cause analysis, and the output is a report in a format that is easy for the administrator to understand. Specifically, a report generation tool is used to automatically create a report that incorporates charts, graphs, and key points.

[0289] Step 6:

[0290] The server analyzes the user's past transaction history and generates personalized advice. The input is the user's historical data, and the output is individually customized operational guidance. Specifically, it suggests alternative methods for specific errors.

[0291] Step 7:

[0292] The server encrypts and securely stores all transaction data. The data is stored securely using the AES encryption algorithm and is accessible only to authorized users. Input is raw data, and output is encrypted data storage. Specifically, this involves managing and periodically updating security keys.

[0293] (Application Example 1)

[0294] 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."

[0295] The objective is to provide a means to efficiently and accurately monitor transaction data in electronic payment services in real time and detect anomalies. In particular, the aim is to improve user convenience by automating rapid root cause analysis after anomaly detection and providing appropriate feedback and advice to users. Furthermore, the goal is to analyze environmental factors such as communication delays in transactions, propose effective countermeasures, and improve the user experience.

[0296] 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.

[0297] In this invention, the server includes means for (acquiring transaction data in real time), means for (analyzing the acquired transaction data using a generative model to detect anomalies), means for (performing root cause analysis to identify the cause of the anomaly), means for (presenting and notifying the user of recommended countermeasures using examples when an anomaly is detected), and means for (analyzing factors in the communication environment, including network delay, and deriving appropriate countermeasures). This enables the rapid and accurate detection of anomalies in electronic payments and the automation of appropriate countermeasures.

[0298] An "information processing device" is a computer system that acquires transaction data and processes and analyzes it in real time.

[0299] "Transaction data" refers to various types of data generated when using electronic payment services, including purchase information and payment information.

[0300] "Methods for acquiring data in real time" refer to functions that allow data to be collected immediately and processed without delay.

[0301] A "generative model" is a mathematical model for pattern recognition developed based on machine learning algorithms, and is used to detect anomalies in data.

[0302] "Means for detecting anomalies" refers to the process of identifying normal transaction patterns from deviant patterns and determining whether they are anomalies.

[0303] "Root cause analysis" is the process of identifying the primary cause of an abnormality when it occurs.

[0304] An "on-demand report" is a report that summarizes the necessary information based on the analysis results and is generated when a specific action is requested.

[0305] "Personalized advice" means providing individual recommendations that are judged appropriate based on the user's past behavior and data.

[0306] "Means for protecting data security and privacy" are technologies and methods for preventing transaction data from unauthorized access and leakage and managing it safely.

[0307] "Means for presenting and notifying recommended countermeasures to the user using examples when an anomaly is detected" is a method of showing the best countermeasures to the user based on pre-prepared countermeasure examples when an anomaly is confirmed.

[0308] "Means for analyzing factors in the communication environment including network delay and deriving appropriate countermeasures" is a function of analyzing problems in the communication relationship that occur during a transaction and proposing improvement measures based on it.

[0309] The system for implementing this invention is composed of an information processing system centered around a server. The server first acquires in real-time the transaction data generated in the electronic payment service. The acquired data is processed by a generation model implemented using Python (such as TensorFlow or PyTorch) to detect abnormal patterns. This model can quickly and accurately identify anomalies that deviate from normal transaction patterns.

[0310] When an anomaly is detected, the server conducts a detailed root cause analysis by leveraging Pandas and NumPy. Through this analysis, specific communication environment problems such as network delay are identified, and countermeasures are derived as needed. These countermeasures are provided in a form recommended by the server to the user and are immediately notified through a smartphone or other end-user devices.

[0311] Furthermore, the server analyzes the user's past transaction data and analytics history to generate personalized advice. This advice is based on problems the user frequently faces and provides specific guidance for taking better actions.

[0312] Regarding data security and privacy protection, the server encrypts transaction data using the latest security protocols and stores it in secure storage. Access rights are also strictly controlled, and personal information is thoroughly protected, providing users with an environment where they can use the system with peace of mind.

[0313] As a concrete example, let's consider transaction data generated when a user purchases a product online. This data is monitored immediately by the system, and if an anomaly is detected, advice such as "Please improve your communication environment and try again" is provided. An example of this prompt is, "Analyze the latest transaction data in real time, detect anomaly patterns, and provide the cause and recommended countermeasures."

[0314] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0315] Step 1:

[0316] The server retrieves transaction data in real time from the electronic payment service's API. The input is the transaction data obtained via the API, and the output is the transaction data ready for processing. This data is temporarily stored in the database in preparation for subsequent processing.

[0317] Step 2:

[0318] The server inputs temporarily stored transaction data into a generative model to determine whether or not it is abnormal. The input is raw transaction data, and the output is data classified into normal patterns and abnormal patterns. In this process, a model using TensorFlow or PyTorch analyzes the data and detects abnormal patterns.

[0319] Step 3:

[0320] If an anomaly is detected, the server uses Pandas or NumPy to perform root cause analysis. The input is the transaction data that was determined to be anomaly, and the output is specific information about the cause of the anomaly. Through data analysis, problems such as network latency are identified, and information is prepared to show the user the specific cause.

[0321] Step 4:

[0322] The server generates and notifies the user of recommended actions based on the results of root cause analysis. The input is the result of the root cause analysis, and the output is a notification message to the user. The server sends the generated actions in the form of prompts to smartphones and other devices, enabling concrete actions to prompt a quick response.

[0323] Step 5:

[0324] The server analyzes the user's past transaction data and analytics history to generate individual trends and personalized advice based on them. The input is the user's past data, and the output is customized advice. The server provides this to the user to guide them toward appropriate actions.

[0325] Step 6:

[0326] The terminal receives notifications and advice sent from the server and displays them to the user. The input is notification information from the server, and the output is information displayed to the user on the terminal. Here, the user obtains specific means to use the service more safely and efficiently based on the information provided.

[0327] 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.

[0328] This invention combines an information processing device that acquires transaction data in real time and detects anomalies with an emotion engine that recognizes user emotions. This enables dynamic responses and the provision of personalized content that are tailored to the user's emotional state.

[0329] System operation

[0330] The server acquires and monitors transaction data generated from transactions and operations within the system in real time. This data is fed into generative models for anomaly detection, where abnormal patterns are identified. For example, the server monitors payment processing data in an e-commerce platform to quickly detect fraudulent transactions.

[0331] This system also incorporates an emotion engine that recognizes the user's emotional state. The terminal analyzes the user's input and actions, and the emotion engine determines the user's emotional state. This emotional state serves as an indicator of the user's stress level and satisfaction level while using the system.

[0332] The server dynamically adjusts the interface by leveraging the user's emotional state, as determined by the emotion engine. For example, if a user indicates anxiety, the system enhances the on-screen support options to improve the user experience in real time.

[0333] Furthermore, it is possible to provide personalized content based on the user's emotional state. Specifically, this can be done by prioritizing the display of products that the user is highly interested in, or by providing encouraging messages, thereby increasing user engagement.

[0334] The server ensures thorough data security and privacy protection throughout all analysis processes. All information, including user sentiment data, is properly encrypted and securely stored. In this way, the present invention achieves efficient management of transaction data and optimization of sentiment-based interfaces, thereby improving the user experience.

[0335] The following describes the processing flow.

[0336] Step 1:

[0337] The server retrieves transaction data in real time. This includes details of transactions and operations performed by the user, and the entire process within the system is recorded. The server continuously monitors this data and prepares it for processing.

[0338] Step 2:

[0339] The server feeds the acquired data into a generative model to detect anomalous patterns. For example, the server analyzes specific user behaviors where purchase frequency suddenly increases, identifying signs of fraud in real time.

[0340] Step 3:

[0341] If an anomaly is detected, the server activates the emotion engine and collects further necessary data from the device to analyze the user's emotional state. The device then extracts emotional indicators from the user's actions and inputs and sends them to the server.

[0342] Step 4:

[0343] The server adjusts the user interface based on the user's emotional state, as recognized by the emotion engine. For example, if the user shows signs of stress, the server provides assistance to the user, such as displaying operational guidelines.

[0344] Step 5:

[0345] The device displays personalized content tailored to the user's emotions. This content includes product suggestions that capture the user's interest and contextual messages, designed to enhance the user experience.

[0346] Step 6:

[0347] The server manages all data processing across the entire system to ensure strict protection of data security and privacy. This includes encrypting and securely storing both emotional and transactional data.

[0348] (Example 2)

[0349] 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".

[0350] While existing information processing systems perform real-time monitoring and anomaly detection of transaction data, they lack personalization that takes into account the user's emotional state. As a result, the user experience can be limited, and system responses may be delayed. This can prevent the provision of optimal support to users, potentially leading to decreased satisfaction.

[0351] 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.

[0352] In this invention, the server includes means for (acquiring and monitoring transaction data in real time), means for (analyzing the acquired data using a generative model and detecting anomalies), means for (incorporating an emotion recognition engine that analyzes the emotional state based on user input and actions), means for (dynamically adjusting the interface based on the analyzed emotional state), and means for (providing personalized content to the user). This enables efficient management of transaction data, optimization of the interface based on user emotions, and improvement of the user experience.

[0353] An "information processing device" is a device for collecting, analyzing, processing, and outputting data, and in particular has the function of processing transaction data and user emotional states in real time.

[0354] "Means for acquiring and monitoring transaction data in real time" refers to a function that immediately collects data generated by transactions and operations, and continuously observes it to detect anomalies early.

[0355] "Methods for analyzing and detecting anomalies using generative models" refers to the process of using machine learning or AI-based models to identify anomalies that deviate from normal patterns in collected data.

[0356] "Methods for conducting root cause analysis" refer to the process of thoroughly analyzing the background and causes of detected anomalies in order to identify the root cause of the problem.

[0357] "Methods for incorporating an emotion recognition engine" refer to the process of incorporating software or hardware into a system that analyzes user input data and behavioral patterns to infer their emotional state.

[0358] "Means of dynamically adjusting the interface" refers to a function that optimizes the user experience by changing the system's display and operation methods in real time according to the user's emotional state.

[0359] "Means of providing personalized content" refers to the process of selecting and providing information and services that are individually suited to each user based on their past behavior and emotional state.

[0360] "Means of protecting data security and privacy" refers to encryption technologies and access control measures to protect collected user data from unauthorized access and leakage.

[0361] This invention provides a system that incorporates an emotion engine for recognizing user emotions into an information processing device that acquires transaction data in real time and detects anomalies.

[0362] The server acquires and monitors transaction data generated from transactions and operations within the system in real time. For this purpose, high-speed database management systems and stream processing technologies can be used. For example, open-source software like Apache Kafka or existing commercial software may be used. The server leverages AI models to analyze this data and detect anomalies. Python libraries such as Scikit-learn and TensorFlow may be used to build these models.

[0363] The device records user input and actions and sends them to an emotion recognition engine. This engine analyzes emotions using natural language processing (NLP) techniques. Common NLP libraries used include NLTK and spaCy. The device understands the user's emotional state, and the system dynamically adjusts the interface based on this information. In other words, the screen design and configuration change according to the emotional data, providing the user with the optimal operating environment.

[0364] Furthermore, the server provides personalized content based on the user's past behavior history and current emotional state. For example, it can prioritize displaying information related to product categories that the user frequently searches for, or incorporate a product recommendation system to provide appropriate information to each user.

[0365] The server prioritizes data security, encrypting collected sentiment and transaction data and implementing access controls. This enhances privacy protection and prevents unauthorized access by third parties.

[0366] To give a specific example, on an online shopping platform, when a user is considering purchasing a particular product, an emotion engine can determine the user's stress level and provide corresponding customer support options in real time. Such systems help improve customer satisfaction and create new purchasing opportunities.

[0367] A suitable example of a prompt would be, "Suggest a way to provide effective support based on the user's emotional state."

[0368] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0369] Step 1:

[0370] The server acquires and monitors transaction data in real time. This input data includes transaction details, timestamps, and user information. The server uses stream processing technology to store this data in containers and begins monitoring for anomalies in the database. Specifically, Apache Kafka is used to rapidly stream the data, enabling real-time analysis.

[0371] Step 2:

[0372] The server inputs the acquired transaction data into a generating AI model to detect anomalies. This model has learned normal patterns and analyzes inconsistencies in the input data. As output, it classifies the data into normal and anomaly data. The server records the generated anomaly data and notifies the administrator as needed. This process is performed using the Scikit-learn library.

[0373] Step 3:

[0374] The device collects user behavior data and input information and sends it to the emotion recognition engine. Input includes keystroke speed, mouse movements, and click frequency. At this stage, the device preprocesses and quantifies the input data. The output is a calculated estimated emotional state of the user. Specifically, natural language processing is performed using the spaCy library to classify the emotions.

[0375] Step 4:

[0376] The server receives output from the emotion recognition engine and dynamically adjusts the interface according to the user's emotional state. The input is analyzed emotion data, which the server uses to change the screen layout and operations to improve the user experience. The output is a customized interface provided to the user. Specifically, if the user expresses anxiety, more emphasized support information and FAQs are displayed.

[0377] Step 5:

[0378] The server provides personalized content based on the user's emotions and past behavior history. Input includes the user's past purchase history and browsing information. The server analyzes this data and prioritizes displaying products and information that are likely to interest the user. Output includes featured pages and recommended product lists that match the user's interests. For example, a recommendation engine can be used to automatically display new products that match the user's preferences at the top.

[0379] Step 6:

[0380] The server maintains data security and privacy throughout all processing. Inputs include sentiment data and transaction data. The server encrypts this data and stores it in a secure database. For output, access control is strictly managed to prevent unauthorized access. Specifically, data communication is protected using SSL / TLS standards, and an authentication system is implemented to restrict access.

[0381] (Application Example 2)

[0382] 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."

[0383] In recent years, as many information processing systems rely on the analysis of transaction data, real-time anomaly detection and improved user experience have become crucial. However, with existing technologies, it has been difficult to simultaneously achieve anomaly detection and dynamic interface adjustments and personalized suggestions based on the user's emotional state. This invention aims to improve system security and user experience by combining real-time transaction data analysis with user emotion recognition.

[0384] 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.

[0385] In this invention, the server includes means for acquiring transaction information in real time, means for analyzing the acquired transaction information using a generative model and detecting anomalies, and means for recognizing the user's emotional state and dynamically adjusting the interface based on that state. This enables rapid detection of anomalies in transaction data and allows for personalized suggestions and interface adjustments in accordance with the user's emotional state.

[0386] An "information processing device" is a device or system used for collecting, analyzing, and storing data.

[0387] "Means for acquiring transaction information in real time" refers to a method or device for immediately collecting generated transaction information through data communication.

[0388] "Methods for analyzing and detecting anomalies using generative models" refer to methods that use models based on machine learning or statistical techniques to evaluate data and identify events that deviate from normal patterns.

[0389] "Means of performing root cause analysis to identify the cause of an anomaly" refers to analytical techniques used to investigate and clarify the underlying cause behind an anomaly that has occurred.

[0390] "Means for generating on-demand reports" refers to a function that instantly creates and provides data analysis results as reports as needed.

[0391] "Means for recognizing a user's emotional state and dynamically adjusting the interface based on that emotion" refers to technology that determines the user's emotions based on their input and actions, and then changes the display and functions of the user interface in a timely manner based on the results.

[0392] "Means of providing personalized content based on user emotions" refers to methods of presenting information and suggestions that take into account the user's emotional state and are tailored to their specific needs and preferences.

[0393] "Means of protecting data security and privacy" refer to encryption and access control technologies that protect personal and confidential data from unauthorized access and leakage.

[0394] "Means for generating and notifying warnings" refers to technologies that, when an anomaly or emergency is detected, immediately create warning information and communicate it to the relevant parties.

[0395] "Means for analyzing individual trends based on a user's past transaction information and analysis history" refers to analytical techniques that use historical data to reveal the behavioral patterns and trends of specific users.

[0396] The system for realizing this invention consists of a server and a terminal as an information processing device. The server is preferably located on a cloud platform or data center with advanced computing capabilities. The server uses network communication to acquire various transaction information in real time. The acquired data is analyzed using a generative AI model to detect anomalies. This analysis process utilizes a processor and data storage with advanced computing capabilities.

[0397] Furthermore, the device itself is equipped with an emotion engine to recognize the user's emotional state. This engine analyzes the user's emotions based on voice input and behavioral pattern detection. The results of this analysis are sent to a server and used to dynamically adjust the user interface. For example, if the user is in an anxious situation, the system will immediately present supportive content to improve the user experience. Specifically, it will display messages and links on the device to provide emphasized help and ensure a sense of security.

[0398] This invention enables the detection of anomalies in transaction data and the provision of personalized content based on user emotions. If a user feels uneasy while browsing a particular product, the system will provide encouraging messages to facilitate a smoother purchasing decision.

[0399] An example of a prompt message is as follows:

[0400] "Please create support messages to be displayed when users are feeling anxious. Include specific examples of support to help users feel at ease."

[0401] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0402] Step 1:

[0403] The server retrieves transaction information in real time over the network. This input data is appropriately organized into corresponding data fields. The data, including timestamps and user IDs, is temporarily stored in a state ready for analysis.

[0404] Step 2:

[0405] The server inputs the acquired transaction information into a generating AI model to perform anomaly detection. The generating AI model uses statistical analysis and machine learning algorithms to identify abnormal patterns by comparing them with past normal data. As output, if an anomaly is detected, a warning flag is set and detailed information about the anomaly is generated.

[0406] Step 3:

[0407] The server inputs detailed anomaly information into a root cause analysis module to identify the root cause of the anomaly. This process analyzes the anomaly's historical data and related events, and applies algorithms to identify potential causes. The output is provided as a list of candidate root causes.

[0408] Step 4:

[0409] The server receives emotion data sent from the user to the terminal and recognizes the emotional state. This data includes features extracted from the user's input and actions. The server uses an emotion engine to analyze the emotions and generates an emotional state status as output.

[0410] Step 5:

[0411] The server dynamically adjusts the user interface based on the emotional state status. The terminal displays reassuring support messages and action items. The output consists of personalized interface elements designed to enhance the user experience.

[0412] Step 6:

[0413] If the user provides additional input through the provided interface, the server collects that feedback information and performs analysis for further personalization. The output provides insights for future interface optimization.

[0414] 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.

[0415] 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.

[0416] 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.

[0417] [Third Embodiment]

[0418] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0419] 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.

[0420] 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).

[0421] 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.

[0422] 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.

[0423] 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).

[0424] 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.

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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".

[0430] This invention is a system that uses an information processing device to monitor transaction data in real time, detect anomalies, and automatically take necessary actions. This significantly reduces the workload on system administrators and improves the efficiency and reliability of business processes.

[0431] System operation

[0432] The server automatically acquires and processes all transaction data occurring within the system in real time. This data is then fed into a generative model to identify normal processing results and abnormal patterns. For example, in an online shopping site, the server monitors data such as purchase processing and payment errors in real time and notifies the administrator if any anomalies are detected.

[0433] When an anomaly is detected, the server investigates the root cause and performs detailed data analysis. For example, it analyzes network latency and load during a specific time period to identify that the anomaly is due to network congestion. The results of this analysis are automatically generated as a report and provided to the user through their terminal.

[0434] Furthermore, the server analyzes the user's past transaction history and generates personalized advice based on it. For example, if a user frequently makes errors in a particular operation, the server will suggest alternative solutions.

[0435] Security and privacy are paramount in data processing and storage. Servers encrypt and securely store all transaction data. Access permissions are strictly controlled, ensuring that only specific users can access the data.

[0436] Thus, the system for implementing the invention enables efficient monitoring and anomaly detection of transaction data, facilitating rapid problem resolution and appropriate feedback to users. Furthermore, it provides a secure and reliable environment by ensuring data safety and privacy protection.

[0437] The following describes the processing flow.

[0438] Step 1:

[0439] The server acquires transaction data generated in real time as a result of various transactions and operations within the system. Each transaction is logged, recording its details.

[0440] Step 2:

[0441] The server preprocesses the acquired transaction data, cleaning and standardizing the format as needed. This preprocessing is necessary for the generative model to efficiently analyze the data.

[0442] Step 3:

[0443] The server inputs pre-processed data into a generative model to detect anomalous patterns and error data hidden within the data. Based on its learning, the generative model identifies normal patterns and identifies anomalies.

[0444] Step 4:

[0445] The server generates an alert based on anomalies detected by the generative model. This alert is immediately sent to the system administrator via the terminal to prompt a quick response.

[0446] Step 5:

[0447] The server performs a detailed analysis of the relevant data to identify the root cause of the anomaly. This involves identifying the circumstances and related factors at the time of the anomaly and conducting a detailed data analysis to determine the cause.

[0448] Step 6:

[0449] The server automatically generates a detailed report containing the cause of the problem and suggested solutions, and sends it to the user's terminal. This report includes an overview of the anomaly and recommended actions.

[0450] Step 7:

[0451] The server analyzes the user's past transaction data and analysis history to generate personalized advice optimized for the user. This allows the user to obtain the most suitable course of action.

[0452] Step 8:

[0453] The server implements security and privacy measures in all data processing and report generation. Data is encrypted and appropriate access controls are in place.

[0454] (Example 1)

[0455] 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."

[0456] In real-time monitoring and anomaly detection of transaction data in information processing systems, there is a need to reduce the burden on system administrators and enable rapid and appropriate problem resolution. Conventional systems required significant time and effort for anomaly notification, detailed data analysis, and security protection. Therefore, it is necessary to streamline these processes and improve the overall reliability of business processes.

[0457] 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.

[0458] In this invention, the server includes means for acquiring transaction data in real time, means for analyzing the acquired data using a generative model to identify normal and abnormal conditions, and means for performing detailed analysis to identify the cause when an abnormality is detected and automatically sending a report to the administrator. This makes it possible to reduce the workload on system administrators and enable rapid problem solving and effective feedback.

[0459] An "information processing device" is a device that uses a computer to collect, analyze, store, and manage data.

[0460] "Transaction data" refers to a collection of data that records various transactions and processes, and it flows through the system in real time.

[0461] A "generative model" is a mathematical model that uses artificial intelligence technology to perform pattern recognition and anomaly detection.

[0462] "Acquiring data in real time" refers to the action of immediately importing data into the system as soon as it is generated.

[0463] "Identifying anomalies" means detecting and understanding patterns or trends that are different from the norm in data.

[0464] "Detailed analysis for identifying the cause" refers to a detailed data investigation conducted when an anomaly occurs, in order to determine what caused it.

[0465] "Automatic sending of reports to administrators" refers to the process of automatically sending a report summarizing the analysis results to the administrator.

[0466] "Personalized operation guidance" is a feedback method that provides individual advice and recommendations based on the user's past data.

[0467] "Encryption" is a technology that transforms data based on a specific algorithm to protect it from unauthorized reading or tampering.

[0468] One embodiment of this invention is an information processing system configuration that monitors transaction data in real time and detects anomalies. The server collects transaction data and analyzes the data using a generative AI model. A general-purpose server machine is used as the hardware, and the software utilizes a database system and an AI model construction framework specialized for anomaly detection (e.g., TensorFlow, PyTorch).

[0469] The server first interacts with a database system (e.g., MySQL or PostgreSQL) to acquire all transaction data in real time. The acquired data is then passed to a generating AI model, which automatically identifies normal and abnormal patterns. In this process, the AI ​​model quickly recognizes anomalies based on the patterns it has learned.

[0470] When an anomaly is detected, the server performs a detailed data analysis to identify the root cause of the anomaly. The identified information is sent to the administrator as an automatically generated report. Email systems and messaging services (such as Slack) are used to send the report.

[0471] Users are provided with personalized operational guidance based on their past transaction history. For example, users who frequently encounter errors in specific operations are offered alternative solutions. This allows users to improve the efficiency of their work processes.

[0472] High security is required for data storage, and the server uses AES encryption technology to securely protect transaction data. Furthermore, access rights are strictly controlled, and only authorized users can access the data.

[0473] As a concrete example, in a small online store, using this system enables rapid anomaly detection and efficient problem resolution. For instance, if payment errors frequently occur during a specific time period and the cause is identified as server load, quick countermeasures can be taken based on that information.

[0474] An example of a prompt related to this system would be, "Please tell me the procedure for detecting abnormal patterns in recent transaction data using a generating AI model and identifying the cause of the problem."

[0475] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0476] Step 1:

[0477] The server works in conjunction with the information processing device to retrieve transaction data in real time. SQL queries are used to retrieve the latest transactions from the database system. In this step, the input consists of the data generation timestamp and transaction details, while the output is formatted transaction data.

[0478] Step 2:

[0479] The server preprocesses the acquired transaction data. This includes filling in missing data and removing unnecessary data. The input is the transaction data acquired in step 1, and the output is data formatted for analysis. Specifically, for example, it standardizes the date format to make it easier for the analysis model to read.

[0480] Step 3:

[0481] The server feeds pre-processed data into a generative AI model. The generative AI model analyzes the data patterns and detects anomalous patterns. In this step, the input is pre-processed transaction data, and the output is the detected anomalous patterns and their characteristics. The specific operation here is to apply the normal / anomalous discrimination algorithm that the AI ​​model has learned.

[0482] Step 4:

[0483] The server generates prompts for analyzing the details of anomalies based on the anomalies detected by the generation AI model, and then performs a detailed analysis. These prompts are input into a data analysis tool to support root cause analysis. The input for this step is the anomaly pattern, and the output is the result of the root cause analysis of the anomaly. Specifically, this includes operations to check network utilization and server load during specific time periods.

[0484] Step 5:

[0485] The server automatically generates a report containing the analyzed cause and solution of the anomaly, and sends it to the administrator via the terminal. The input is the result of the cause analysis, and the output is a report in a format that is easy for the administrator to understand. Specifically, a report generation tool is used to automatically create a report that incorporates charts, graphs, and key points.

[0486] Step 6:

[0487] The server analyzes the user's past transaction history and generates personalized advice. The input is the user's historical data, and the output is individually customized operational guidance. Specifically, it suggests alternative methods for specific errors.

[0488] Step 7:

[0489] The server encrypts and securely stores all transaction data. The data is stored securely using the AES encryption algorithm and is accessible only to authorized users. Input is raw data, and output is encrypted data storage. Specifically, this involves managing and periodically updating security keys.

[0490] (Application Example 1)

[0491] 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."

[0492] The objective is to provide a means to efficiently and accurately monitor transaction data in electronic payment services in real time and detect anomalies. In particular, the aim is to improve user convenience by automating rapid root cause analysis after anomaly detection and providing appropriate feedback and advice to users. Furthermore, the goal is to analyze environmental factors such as communication delays in transactions, propose effective countermeasures, and improve the user experience.

[0493] 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.

[0494] In this invention, the server includes means for (acquiring transaction data in real time), means for (analyzing the acquired transaction data using a generative model to detect anomalies), means for (performing root cause analysis to identify the cause of the anomaly), means for (presenting and notifying the user of recommended countermeasures using examples when an anomaly is detected), and means for (analyzing factors in the communication environment, including network delay, and deriving appropriate countermeasures). This enables the rapid and accurate detection of anomalies in electronic payments and the automation of appropriate countermeasures.

[0495] An "information processing device" is a computer system that acquires transaction data and processes and analyzes it in real time.

[0496] "Transaction data" refers to various types of data generated when using electronic payment services, including purchase information and payment information.

[0497] "Methods for acquiring data in real time" refer to functions that allow data to be collected immediately and processed without delay.

[0498] A "generative model" is a mathematical model for pattern recognition developed based on machine learning algorithms, and is used to detect anomalies in data.

[0499] "Means for detecting anomalies" refers to the process of identifying normal transaction patterns from deviant patterns and determining whether they are anomalies.

[0500] "Root cause analysis" is the process of identifying the primary cause of an abnormality when it occurs.

[0501] An "on-demand report" is a report that compiles necessary information based on analysis results and is generated when a specific action is requested.

[0502] "Personalized advice" refers to providing individual recommendations that are deemed appropriate based on the user's past behavior and data.

[0503] "Means of protecting data security and privacy" refer to technologies and methods for protecting transactional data from unauthorized access and leakage, and for managing it securely.

[0504] "A means of presenting and notifying users of recommended countermeasures using examples when an anomaly is detected" refers to a method of showing users the best possible countermeasures based on pre-prepared examples of responses when an anomaly is confirmed.

[0505] "Means for analyzing factors in the communication environment, including network latency, and deriving appropriate countermeasures" refers to a function that analyzes communication-related problems that occur during transactions and proposes improvement measures based on that analysis.

[0506] The system implementing this invention consists of a server-based information processing system. The server first acquires transaction data generated in the electronic payment service in real time. The acquired data is processed by a generative model implemented using Python (for example, TensorFlow or PyTorch) to detect abnormal patterns. This model quickly and accurately identifies abnormalities that deviate from normal transaction patterns.

[0507] When an anomaly is detected, the server uses Pandas and NumPy to perform a detailed root cause analysis. This analysis identifies specific communication environment problems, such as network latency, and derives solutions as needed. These solutions are provided to the user in a recommended format by the server and are immediately notified via smartphones or other devices.

[0508] Furthermore, the server analyzes the user's past transaction data and analytics history to generate personalized advice. This advice is based on problems the user frequently faces and provides specific guidance for taking better actions.

[0509] Regarding data security and privacy protection, the server encrypts transaction data using the latest security protocols and stores it in secure storage. Access rights are also strictly controlled, and personal information is thoroughly protected, providing users with an environment where they can use the system with peace of mind.

[0510] As a concrete example, let's consider transaction data generated when a user purchases a product online. This data is monitored immediately by the system, and if an anomaly is detected, advice such as "Please improve your communication environment and try again" is provided. An example of this prompt is, "Analyze the latest transaction data in real time, detect anomaly patterns, and provide the cause and recommended countermeasures."

[0511] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0512] Step 1:

[0513] The server retrieves transaction data in real time from the electronic payment service's API. The input is the transaction data obtained via the API, and the output is the transaction data ready for processing. This data is temporarily stored in the database in preparation for subsequent processing.

[0514] Step 2:

[0515] The server inputs temporarily stored transaction data into a generative model to determine whether or not it is abnormal. The input is raw transaction data, and the output is data classified into normal patterns and abnormal patterns. In this process, a model using TensorFlow or PyTorch analyzes the data and detects abnormal patterns.

[0516] Step 3:

[0517] If an anomaly is detected, the server uses Pandas or NumPy to perform root cause analysis. The input is the transaction data that was determined to be anomaly, and the output is specific information about the cause of the anomaly. Through data analysis, problems such as network latency are identified, and information is prepared to show the user the specific cause.

[0518] Step 4:

[0519] The server generates and notifies the user of recommended actions based on the results of root cause analysis. The input is the result of the root cause analysis, and the output is a notification message to the user. The server sends the generated actions in the form of prompts to smartphones and other devices, enabling concrete actions to prompt a quick response.

[0520] Step 5:

[0521] The server analyzes the user's past transaction data and analytics history to generate individual trends and personalized advice based on them. The input is the user's past data, and the output is customized advice. The server provides this to the user to guide them toward appropriate actions.

[0522] Step 6:

[0523] The terminal receives notifications and advice sent from the server and displays them to the user. The input is notification information from the server, and the output is information displayed to the user on the terminal. Here, the user obtains specific means to use the service more safely and efficiently based on the information provided.

[0524] 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.

[0525] This invention combines an information processing device that acquires transaction data in real time and detects anomalies with an emotion engine that recognizes user emotions. This enables dynamic responses and the provision of personalized content that are tailored to the user's emotional state.

[0526] System operation

[0527] The server acquires and monitors transaction data generated from transactions and operations within the system in real time. This data is fed into generative models for anomaly detection, where abnormal patterns are identified. For example, the server monitors payment processing data in an e-commerce platform to quickly detect fraudulent transactions.

[0528] This system also incorporates an emotion engine that recognizes the user's emotional state. The terminal analyzes the user's input and actions, and the emotion engine determines the user's emotional state. This emotional state serves as an indicator of the user's stress level and satisfaction level while using the system.

[0529] The server dynamically adjusts the interface by leveraging the user's emotional state, as determined by the emotion engine. For example, if a user indicates anxiety, the system enhances the on-screen support options to improve the user experience in real time.

[0530] Furthermore, it is possible to provide personalized content based on the user's emotional state. Specifically, this can be done by prioritizing the display of products that the user is highly interested in, or by providing encouraging messages, thereby increasing user engagement.

[0531] The server ensures thorough data security and privacy protection throughout all analysis processes. All information, including user sentiment data, is properly encrypted and securely stored. In this way, the present invention achieves efficient management of transaction data and optimization of sentiment-based interfaces, thereby improving the user experience.

[0532] The following describes the processing flow.

[0533] Step 1:

[0534] The server retrieves transaction data in real time. This includes details of transactions and operations performed by the user, and the entire process within the system is recorded. The server continuously monitors this data and prepares it for processing.

[0535] Step 2:

[0536] The server feeds the acquired data into a generative model to detect anomalous patterns. For example, the server analyzes specific user behaviors where purchase frequency suddenly increases, identifying signs of fraud in real time.

[0537] Step 3:

[0538] If an anomaly is detected, the server activates the emotion engine and collects further necessary data from the device to analyze the user's emotional state. The device then extracts emotional indicators from the user's actions and inputs and sends them to the server.

[0539] Step 4:

[0540] The server adjusts the user interface based on the user's emotional state, as recognized by the emotion engine. For example, if the user shows signs of stress, the server provides assistance to the user, such as displaying operational guidelines.

[0541] Step 5:

[0542] The device displays personalized content tailored to the user's emotions. This content includes product suggestions that capture the user's interest and contextual messages, designed to enhance the user experience.

[0543] Step 6:

[0544] The server manages all data processing across the entire system to ensure strict protection of data security and privacy. This includes encrypting and securely storing both emotional and transactional data.

[0545] (Example 2)

[0546] 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."

[0547] While existing information processing systems perform real-time monitoring and anomaly detection of transaction data, they lack personalization that takes into account the user's emotional state. As a result, the user experience can be limited, and system responses may be delayed. This can prevent the provision of optimal support to users, potentially leading to decreased satisfaction.

[0548] 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.

[0549] In this invention, the server includes means for (acquiring and monitoring transaction data in real time), means for (analyzing the acquired data using a generative model and detecting anomalies), means for (incorporating an emotion recognition engine that analyzes the emotional state based on user input and actions), means for (dynamically adjusting the interface based on the analyzed emotional state), and means for (providing personalized content to the user). This enables efficient management of transaction data, optimization of the interface based on user emotions, and improvement of the user experience.

[0550] An "information processing device" is a device for collecting, analyzing, processing, and outputting data, and in particular has the function of processing transaction data and user emotional states in real time.

[0551] "Means for acquiring and monitoring transaction data in real time" refers to a function that immediately collects data generated by transactions and operations, and continuously observes it to detect anomalies early.

[0552] "Methods for analyzing and detecting anomalies using generative models" refers to the process of using machine learning or AI-based models to identify anomalies that deviate from normal patterns in collected data.

[0553] "Methods for conducting root cause analysis" refer to the process of thoroughly analyzing the background and causes of detected anomalies in order to identify the root cause of the problem.

[0554] "Methods for incorporating an emotion recognition engine" refer to the process of incorporating software or hardware into a system that analyzes user input data and behavioral patterns to infer their emotional state.

[0555] "Means of dynamically adjusting the interface" refers to a function that optimizes the user experience by changing the system's display and operation methods in real time according to the user's emotional state.

[0556] "Means of providing personalized content" refers to the process of selecting and providing information and services that are individually suited to each user based on their past behavior and emotional state.

[0557] "Means of protecting data security and privacy" refers to encryption technologies and access control measures to protect collected user data from unauthorized access and leakage.

[0558] This invention provides a system that incorporates an emotion engine for recognizing user emotions into an information processing device that acquires transaction data in real time and detects anomalies.

[0559] The server acquires and monitors transaction data generated from transactions and operations within the system in real time. For this purpose, high-speed database management systems and stream processing technologies can be used. For example, open-source software like Apache Kafka or existing commercial software may be used. The server leverages AI models to analyze this data and detect anomalies. Python libraries such as Scikit-learn and TensorFlow may be used to build these models.

[0560] The device records user input and actions and sends them to an emotion recognition engine. This engine analyzes emotions using natural language processing (NLP) techniques. Common NLP libraries used include NLTK and spaCy. The device understands the user's emotional state, and the system dynamically adjusts the interface based on this information. In other words, the screen design and configuration change according to the emotional data, providing the user with the optimal operating environment.

[0561] Furthermore, the server provides personalized content based on the user's past behavior history and current emotional state. For example, it can prioritize displaying information related to product categories that the user frequently searches for, or incorporate a product recommendation system to provide appropriate information to each user.

[0562] The server prioritizes data security, encrypting collected sentiment and transaction data and implementing access controls. This enhances privacy protection and prevents unauthorized access by third parties.

[0563] To give a specific example, on an online shopping platform, when a user is considering purchasing a particular product, an emotion engine can determine the user's stress level and provide corresponding customer support options in real time. Such systems help improve customer satisfaction and create new purchasing opportunities.

[0564] A suitable example of a prompt would be, "Suggest a way to provide effective support based on the user's emotional state."

[0565] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0566] Step 1:

[0567] The server acquires and monitors transaction data in real time. This input data includes transaction details, timestamps, and user information. The server uses stream processing technology to store this data in containers and begins monitoring for anomalies in the database. Specifically, Apache Kafka is used to rapidly stream the data, enabling real-time analysis.

[0568] Step 2:

[0569] The server inputs the acquired transaction data into a generating AI model to detect anomalies. This model has learned normal patterns and analyzes inconsistencies in the input data. As output, it classifies the data into normal and anomaly data. The server records the generated anomaly data and notifies the administrator as needed. This process is performed using the Scikit-learn library.

[0570] Step 3:

[0571] The device collects user behavior data and input information and sends it to the emotion recognition engine. Input includes keystroke speed, mouse movements, and click frequency. At this stage, the device preprocesses and quantifies the input data. The output is a calculated estimated emotional state of the user. Specifically, natural language processing is performed using the spaCy library to classify the emotions.

[0572] Step 4:

[0573] The server receives output from the emotion recognition engine and dynamically adjusts the interface according to the user's emotional state. The input is analyzed emotion data, which the server uses to change the screen layout and operations to improve the user experience. The output is a customized interface provided to the user. Specifically, if the user expresses anxiety, more emphasized support information and FAQs are displayed.

[0574] Step 5:

[0575] The server provides personalized content based on the user's emotions and past behavior history. Input includes the user's past purchase history and browsing information. The server analyzes this data and prioritizes displaying products and information that are likely to interest the user. Output includes featured pages and recommended product lists that match the user's interests. For example, a recommendation engine can be used to automatically display new products that match the user's preferences at the top.

[0576] Step 6:

[0577] The server maintains data security and privacy throughout all processing. Inputs include sentiment data and transaction data. The server encrypts this data and stores it in a secure database. For output, access control is strictly managed to prevent unauthorized access. Specifically, data communication is protected using SSL / TLS standards, and an authentication system is implemented to restrict access.

[0578] (Application Example 2)

[0579] 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."

[0580] In recent years, as many information processing systems rely on the analysis of transaction data, real-time anomaly detection and improved user experience have become crucial. However, with existing technologies, it has been difficult to simultaneously achieve anomaly detection and dynamic interface adjustments and personalized suggestions based on the user's emotional state. This invention aims to improve system security and user experience by combining real-time transaction data analysis with user emotion recognition.

[0581] 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.

[0582] In this invention, the server includes means for acquiring transaction information in real time, means for analyzing the acquired transaction information using a generative model and detecting anomalies, and means for recognizing the user's emotional state and dynamically adjusting the interface based on that state. This enables rapid detection of anomalies in transaction data and allows for personalized suggestions and interface adjustments in accordance with the user's emotional state.

[0583] An "information processing device" is a device or system used for collecting, analyzing, and storing data.

[0584] "Means for acquiring transaction information in real time" refers to a method or device for immediately collecting generated transaction information through data communication.

[0585] "Methods for analyzing and detecting anomalies using generative models" refer to methods that use models based on machine learning or statistical techniques to evaluate data and identify events that deviate from normal patterns.

[0586] "Means of performing root cause analysis to identify the cause of an anomaly" refers to analytical techniques used to investigate and clarify the underlying cause behind an anomaly that has occurred.

[0587] "Means for generating on-demand reports" refers to a function that instantly creates and provides data analysis results as reports as needed.

[0588] "Means for recognizing a user's emotional state and dynamically adjusting the interface based on that emotion" refers to technology that determines the user's emotions based on their input and actions, and then changes the display and functions of the user interface in a timely manner based on the results.

[0589] "Means of providing personalized content based on user emotions" refers to methods of presenting information and suggestions that take into account the user's emotional state and are tailored to their specific needs and preferences.

[0590] "Means of protecting data security and privacy" refer to encryption and access control technologies that protect personal and confidential data from unauthorized access and leakage.

[0591] "Means for generating and notifying warnings" refers to technologies that, when an anomaly or emergency is detected, immediately create warning information and communicate it to the relevant parties.

[0592] "Means for analyzing individual trends based on a user's past transaction information and analysis history" refers to analytical techniques that use historical data to reveal the behavioral patterns and trends of specific users.

[0593] The system for realizing this invention consists of a server and a terminal as an information processing device. The server is preferably located on a cloud platform or data center with advanced computing capabilities. The server uses network communication to acquire various transaction information in real time. The acquired data is analyzed using a generative AI model to detect anomalies. This analysis process utilizes a processor and data storage with advanced computing capabilities.

[0594] Furthermore, the device itself is equipped with an emotion engine to recognize the user's emotional state. This engine analyzes the user's emotions based on voice input and behavioral pattern detection. The results of this analysis are sent to a server and used to dynamically adjust the user interface. For example, if the user is in an anxious situation, the system will immediately present supportive content to improve the user experience. Specifically, it will display messages and links on the device to provide emphasized help and ensure a sense of security.

[0595] This invention enables the detection of anomalies in transaction data and the provision of personalized content based on user emotions. If a user feels uneasy while browsing a particular product, the system will provide encouraging messages to facilitate a smoother purchasing decision.

[0596] An example of a prompt message is as follows:

[0597] "Please create support messages to be displayed when users are feeling anxious. Include specific examples of support to help users feel at ease."

[0598] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0599] Step 1:

[0600] The server retrieves transaction information in real time over the network. This input data is appropriately organized into corresponding data fields. The data, including timestamps and user IDs, is temporarily stored in a state ready for analysis.

[0601] Step 2:

[0602] The server inputs the acquired transaction information into a generating AI model to perform anomaly detection. The generating AI model uses statistical analysis and machine learning algorithms to identify abnormal patterns by comparing them with past normal data. As output, if an anomaly is detected, a warning flag is set and detailed information about the anomaly is generated.

[0603] Step 3:

[0604] The server inputs detailed anomaly information into a root cause analysis module to identify the root cause of the anomaly. This process analyzes the anomaly's historical data and related events, and applies algorithms to identify potential causes. The output is provided as a list of candidate root causes.

[0605] Step 4:

[0606] The server receives emotion data sent from the user to the terminal and recognizes the emotional state. This data includes features extracted from the user's input and actions. The server uses an emotion engine to analyze the emotions and generates an emotional state status as output.

[0607] Step 5:

[0608] The server dynamically adjusts the user interface based on the emotional state status. The terminal displays reassuring support messages and action items. The output consists of personalized interface elements designed to enhance the user experience.

[0609] Step 6:

[0610] If the user provides additional input through the provided interface, the server collects that feedback information and performs analysis for further personalization. The output provides insights for future interface optimization.

[0611] 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.

[0612] 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.

[0613] 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.

[0614] [Fourth Embodiment]

[0615] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0616] 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.

[0617] 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).

[0618] 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.

[0619] 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.

[0620] 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).

[0621] 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.

[0622] 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.

[0623] 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.

[0624] 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.

[0625] 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.

[0626] 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.

[0627] 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".

[0628] This invention is a system that uses an information processing device to monitor transaction data in real time, detect anomalies, and automatically take necessary actions. This significantly reduces the workload on system administrators and improves the efficiency and reliability of business processes.

[0629] System operation

[0630] The server automatically acquires and processes all transaction data occurring within the system in real time. This data is then fed into a generative model to identify normal processing results and abnormal patterns. For example, in an online shopping site, the server monitors data such as purchase processing and payment errors in real time and notifies the administrator if any anomalies are detected.

[0631] When an anomaly is detected, the server investigates the root cause and performs detailed data analysis. For example, it analyzes network latency and load during a specific time period to identify that the anomaly is due to network congestion. The results of this analysis are automatically generated as a report and provided to the user through their terminal.

[0632] Furthermore, the server analyzes the user's past transaction history and generates personalized advice based on it. For example, if a user frequently makes errors in a particular operation, the server will suggest alternative solutions.

[0633] Security and privacy are paramount in data processing and storage. Servers encrypt and securely store all transaction data. Access permissions are strictly controlled, ensuring that only specific users can access the data.

[0634] Thus, the system for implementing the invention enables efficient monitoring and anomaly detection of transaction data, facilitating rapid problem resolution and appropriate feedback to users. Furthermore, it provides a secure and reliable environment by ensuring data safety and privacy protection.

[0635] The following describes the processing flow.

[0636] Step 1:

[0637] The server acquires transaction data generated in real time as a result of various transactions and operations within the system. Each transaction is logged, recording its details.

[0638] Step 2:

[0639] The server preprocesses the acquired transaction data, cleaning and standardizing the format as needed. This preprocessing is necessary for the generative model to efficiently analyze the data.

[0640] Step 3:

[0641] The server inputs pre-processed data into a generative model to detect anomalous patterns and error data hidden within the data. Based on its learning, the generative model identifies normal patterns and identifies anomalies.

[0642] Step 4:

[0643] The server generates an alert based on anomalies detected by the generative model. This alert is immediately sent to the system administrator via the terminal to prompt a quick response.

[0644] Step 5:

[0645] The server performs a detailed analysis of the relevant data to identify the root cause of the anomaly. This involves identifying the circumstances and related factors at the time of the anomaly and conducting a detailed data analysis to determine the cause.

[0646] Step 6:

[0647] The server automatically generates a detailed report containing the cause of the problem and suggested solutions, and sends it to the user's terminal. This report includes an overview of the anomaly and recommended actions.

[0648] Step 7:

[0649] The server analyzes the user's past transaction data and analysis history to generate personalized advice optimized for the user. This allows the user to obtain the most suitable course of action.

[0650] Step 8:

[0651] The server implements security and privacy measures in all data processing and report generation. Data is encrypted and appropriate access controls are in place.

[0652] (Example 1)

[0653] 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".

[0654] In real-time monitoring and anomaly detection of transaction data in information processing systems, there is a need to reduce the burden on system administrators and enable rapid and appropriate problem resolution. Conventional systems required significant time and effort for anomaly notification, detailed data analysis, and security protection. Therefore, it is necessary to streamline these processes and improve the overall reliability of business processes.

[0655] 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.

[0656] In this invention, the server includes means for acquiring transaction data in real time, means for analyzing the acquired data using a generative model to identify normal and abnormal conditions, and means for performing detailed analysis to identify the cause when an abnormality is detected and automatically sending a report to the administrator. This makes it possible to reduce the workload on system administrators and enable rapid problem solving and effective feedback.

[0657] An "information processing device" is a device that uses a computer to collect, analyze, store, and manage data.

[0658] "Transaction data" refers to a collection of data that records various transactions and processes, and it flows through the system in real time.

[0659] A "generative model" is a mathematical model that uses artificial intelligence technology to perform pattern recognition and anomaly detection.

[0660] "Acquiring data in real time" refers to the action of immediately importing data into the system as soon as it is generated.

[0661] "Identifying anomalies" means detecting and understanding patterns or trends that are different from the norm in data.

[0662] "Detailed analysis for identifying the cause" refers to a detailed data investigation conducted when an anomaly occurs, in order to determine what caused it.

[0663] "Automatic sending of reports to administrators" refers to the process of automatically sending a report summarizing the analysis results to the administrator.

[0664] "Personalized operation guidance" is a feedback method that provides individual advice and recommendations based on the user's past data.

[0665] "Encryption" is a technology that transforms data based on a specific algorithm to protect it from unauthorized reading or tampering.

[0666] One embodiment of this invention is an information processing system configuration that monitors transaction data in real time and detects anomalies. The server collects transaction data and analyzes the data using a generative AI model. A general-purpose server machine is used as the hardware, and the software utilizes a database system and an AI model construction framework specialized for anomaly detection (e.g., TensorFlow, PyTorch).

[0667] The server first interacts with a database system (e.g., MySQL or PostgreSQL) to acquire all transaction data in real time. The acquired data is then passed to a generating AI model, which automatically identifies normal and abnormal patterns. In this process, the AI ​​model quickly recognizes anomalies based on the patterns it has learned.

[0668] When an anomaly is detected, the server performs a detailed data analysis to identify the root cause of the anomaly. The identified information is sent to the administrator as an automatically generated report. Email systems and messaging services (such as Slack) are used to send the report.

[0669] Users are provided with personalized operational guidance based on their past transaction history. For example, users who frequently encounter errors in specific operations are offered alternative solutions. This allows users to improve the efficiency of their work processes.

[0670] High security is required for data storage, and the server uses AES encryption technology to securely protect transaction data. Furthermore, access rights are strictly controlled, and only authorized users can access the data.

[0671] As a concrete example, in a small online store, using this system enables rapid anomaly detection and efficient problem resolution. For instance, if payment errors frequently occur during a specific time period and the cause is identified as server load, quick countermeasures can be taken based on that information.

[0672] An example of a prompt related to this system would be, "Please tell me the procedure for detecting abnormal patterns in recent transaction data using a generating AI model and identifying the cause of the problem."

[0673] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0674] Step 1:

[0675] The server works in conjunction with the information processing device to retrieve transaction data in real time. SQL queries are used to retrieve the latest transactions from the database system. In this step, the input consists of the data generation timestamp and transaction details, while the output is formatted transaction data.

[0676] Step 2:

[0677] The server preprocesses the acquired transaction data. This includes filling in missing data and removing unnecessary data. The input is the transaction data acquired in step 1, and the output is data formatted for analysis. Specifically, for example, it standardizes the date format to make it easier for the analysis model to read.

[0678] Step 3:

[0679] The server feeds pre-processed data into a generative AI model. The generative AI model analyzes the data patterns and detects anomalous patterns. In this step, the input is pre-processed transaction data, and the output is the detected anomalous patterns and their characteristics. The specific operation here is to apply the normal / anomalous discrimination algorithm that the AI ​​model has learned.

[0680] Step 4:

[0681] The server generates prompts for analyzing the details of anomalies based on the anomalies detected by the generation AI model, and then performs a detailed analysis. These prompts are input into a data analysis tool to support root cause analysis. The input for this step is the anomaly pattern, and the output is the result of the root cause analysis of the anomaly. Specifically, this includes operations to check network utilization and server load during specific time periods.

[0682] Step 5:

[0683] The server automatically generates a report containing the analyzed cause and solution of the anomaly, and sends it to the administrator via the terminal. The input is the result of the cause analysis, and the output is a report in a format that is easy for the administrator to understand. Specifically, a report generation tool is used to automatically create a report that incorporates charts, graphs, and key points.

[0684] Step 6:

[0685] The server analyzes the user's past transaction history and generates personalized advice. The input is the user's historical data, and the output is individually customized operational guidance. Specifically, it suggests alternative methods for specific errors.

[0686] Step 7:

[0687] The server encrypts and securely stores all transaction data. The data is stored securely using the AES encryption algorithm and is accessible only to authorized users. Input is raw data, and output is encrypted data storage. Specifically, this involves managing and periodically updating security keys.

[0688] (Application Example 1)

[0689] 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".

[0690] The objective is to provide a means to efficiently and accurately monitor transaction data in electronic payment services in real time and detect anomalies. In particular, the aim is to improve user convenience by automating rapid root cause analysis after anomaly detection and providing appropriate feedback and advice to users. Furthermore, the goal is to analyze environmental factors such as communication delays in transactions, propose effective countermeasures, and improve the user experience.

[0691] 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.

[0692] In this invention, the server includes means for (acquiring transaction data in real time), means for (analyzing the acquired transaction data using a generative model to detect anomalies), means for (performing root cause analysis to identify the cause of the anomaly), means for (presenting and notifying the user of recommended countermeasures using examples when an anomaly is detected), and means for (analyzing factors in the communication environment, including network delay, and deriving appropriate countermeasures). This enables the rapid and accurate detection of anomalies in electronic payments and the automation of appropriate countermeasures.

[0693] An "information processing device" is a computer system that acquires transaction data and processes and analyzes it in real time.

[0694] "Transaction data" refers to various types of data generated when using electronic payment services, including purchase information and payment information.

[0695] "Methods for acquiring data in real time" refer to functions that allow data to be collected immediately and processed without delay.

[0696] A "generative model" is a mathematical model for pattern recognition developed based on machine learning algorithms, and is used to detect anomalies in data.

[0697] "Means for detecting anomalies" refers to the process of identifying normal transaction patterns from deviant patterns and determining whether they are anomalies.

[0698] "Root cause analysis" is the process of identifying the primary cause of an abnormality when it occurs.

[0699] An "on-demand report" is a report that compiles necessary information based on analysis results and is generated when a specific action is requested.

[0700] "Personalized advice" refers to providing individual recommendations that are deemed appropriate based on the user's past behavior and data.

[0701] "Means of protecting data security and privacy" refer to technologies and methods for protecting transactional data from unauthorized access and leakage, and for managing it securely.

[0702] "A means of presenting and notifying users of recommended countermeasures using examples when an anomaly is detected" refers to a method of showing users the best possible countermeasures based on pre-prepared examples of responses when an anomaly is confirmed.

[0703] "Means for analyzing factors in the communication environment, including network latency, and deriving appropriate countermeasures" refers to a function that analyzes communication-related problems that occur during transactions and proposes improvement measures based on that analysis.

[0704] The system implementing this invention consists of a server-based information processing system. The server first acquires transaction data generated in the electronic payment service in real time. The acquired data is processed by a generative model implemented using Python (for example, TensorFlow or PyTorch) to detect abnormal patterns. This model quickly and accurately identifies abnormalities that deviate from normal transaction patterns.

[0705] When an anomaly is detected, the server uses Pandas and NumPy to perform a detailed root cause analysis. This analysis identifies specific communication environment problems, such as network latency, and derives solutions as needed. These solutions are provided to the user in a recommended format by the server and are immediately notified via smartphones or other devices.

[0706] Furthermore, the server analyzes the user's past transaction data and analytics history to generate personalized advice. This advice is based on problems the user frequently faces and provides specific guidance for taking better actions.

[0707] Regarding data security and privacy protection, the server encrypts transaction data using the latest security protocols and stores it in secure storage. Access rights are also strictly controlled, and personal information is thoroughly protected, providing users with an environment where they can use the system with peace of mind.

[0708] As a concrete example, let's consider transaction data generated when a user purchases a product online. This data is monitored immediately by the system, and if an anomaly is detected, advice such as "Please improve your communication environment and try again" is provided. An example of this prompt is, "Analyze the latest transaction data in real time, detect anomaly patterns, and provide the cause and recommended countermeasures."

[0709] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0710] Step 1:

[0711] The server retrieves transaction data in real time from the electronic payment service's API. The input is the transaction data obtained via the API, and the output is the transaction data ready for processing. This data is temporarily stored in the database in preparation for subsequent processing.

[0712] Step 2:

[0713] The server inputs temporarily stored transaction data into a generative model to determine whether or not it is abnormal. The input is raw transaction data, and the output is data classified into normal patterns and abnormal patterns. In this process, a model using TensorFlow or PyTorch analyzes the data and detects abnormal patterns.

[0714] Step 3:

[0715] If an anomaly is detected, the server uses Pandas or NumPy to perform root cause analysis. The input is the transaction data that was determined to be anomaly, and the output is specific information about the cause of the anomaly. Through data analysis, problems such as network latency are identified, and information is prepared to show the user the specific cause.

[0716] Step 4:

[0717] The server generates and notifies the user of recommended actions based on the results of root cause analysis. The input is the result of the root cause analysis, and the output is a notification message to the user. The server sends the generated actions in the form of prompts to smartphones and other devices, enabling concrete actions to prompt a quick response.

[0718] Step 5:

[0719] The server analyzes the user's past transaction data and analytics history to generate individual trends and personalized advice based on them. The input is the user's past data, and the output is customized advice. The server provides this to the user to guide them toward appropriate actions.

[0720] Step 6:

[0721] The terminal receives notifications and advice sent from the server and displays them to the user. The input is notification information from the server, and the output is information displayed to the user on the terminal. Here, the user obtains specific means to use the service more safely and efficiently based on the information provided.

[0722] 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.

[0723] This invention combines an information processing device that acquires transaction data in real time and detects anomalies with an emotion engine that recognizes user emotions. This enables dynamic responses and the provision of personalized content that are tailored to the user's emotional state.

[0724] System operation

[0725] The server acquires and monitors transaction data generated from transactions and operations within the system in real time. This data is fed into generative models for anomaly detection, where abnormal patterns are identified. For example, the server monitors payment processing data in an e-commerce platform to quickly detect fraudulent transactions.

[0726] This system also incorporates an emotion engine that recognizes the user's emotional state. The terminal analyzes the user's input and actions, and the emotion engine determines the user's emotional state. This emotional state serves as an indicator of the user's stress level and satisfaction level while using the system.

[0727] The server dynamically adjusts the interface by leveraging the user's emotional state, as determined by the emotion engine. For example, if a user indicates anxiety, the system enhances the on-screen support options to improve the user experience in real time.

[0728] Furthermore, it is possible to provide personalized content based on the user's emotional state. Specifically, this can be done by prioritizing the display of products that the user is highly interested in, or by providing encouraging messages, thereby increasing user engagement.

[0729] The server ensures thorough data security and privacy protection throughout all analysis processes. All information, including user sentiment data, is properly encrypted and securely stored. In this way, the present invention achieves efficient management of transaction data and optimization of sentiment-based interfaces, thereby improving the user experience.

[0730] The following describes the processing flow.

[0731] Step 1:

[0732] The server retrieves transaction data in real time. This includes details of transactions and operations performed by the user, and the entire process within the system is recorded. The server continuously monitors this data and prepares it for processing.

[0733] Step 2:

[0734] The server feeds the acquired data into a generative model to detect anomalous patterns. For example, the server analyzes specific user behaviors where purchase frequency suddenly increases, identifying signs of fraud in real time.

[0735] Step 3:

[0736] If an anomaly is detected, the server activates the emotion engine and collects further necessary data from the device to analyze the user's emotional state. The device then extracts emotional indicators from the user's actions and inputs and sends them to the server.

[0737] Step 4:

[0738] The server adjusts the user interface based on the user's emotional state, as recognized by the emotion engine. For example, if the user shows signs of stress, the server provides assistance to the user, such as displaying operational guidelines.

[0739] Step 5:

[0740] The device displays personalized content tailored to the user's emotions. This content includes product suggestions that capture the user's interest and contextual messages, designed to enhance the user experience.

[0741] Step 6:

[0742] The server manages all data processing across the entire system to ensure strict protection of data security and privacy. This includes encrypting and securely storing both emotional and transactional data.

[0743] (Example 2)

[0744] 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".

[0745] While existing information processing systems perform real-time monitoring and anomaly detection of transaction data, they lack personalization that takes into account the user's emotional state. As a result, the user experience can be limited, and system responses may be delayed. This can prevent the provision of optimal support to users, potentially leading to decreased satisfaction.

[0746] 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.

[0747] In this invention, the server includes means for (acquiring and monitoring transaction data in real time), means for (analyzing the acquired data using a generative model and detecting anomalies), means for (incorporating an emotion recognition engine that analyzes the emotional state based on user input and actions), means for (dynamically adjusting the interface based on the analyzed emotional state), and means for (providing personalized content to the user). This enables efficient management of transaction data, optimization of the interface based on user emotions, and improvement of the user experience.

[0748] An "information processing device" is a device for collecting, analyzing, processing, and outputting data, and in particular has the function of processing transaction data and user emotional states in real time.

[0749] "Means for acquiring and monitoring transaction data in real time" refers to a function that immediately collects data generated by transactions and operations, and continuously observes it to detect anomalies early.

[0750] "Methods for analyzing and detecting anomalies using generative models" refers to the process of using machine learning or AI-based models to identify anomalies that deviate from normal patterns in collected data.

[0751] "Methods for conducting root cause analysis" refer to the process of thoroughly analyzing the background and causes of detected anomalies in order to identify the root cause of the problem.

[0752] "Methods for incorporating an emotion recognition engine" refer to the process of incorporating software or hardware into a system that analyzes user input data and behavioral patterns to infer their emotional state.

[0753] "Means of dynamically adjusting the interface" refers to a function that optimizes the user experience by changing the system's display and operation methods in real time according to the user's emotional state.

[0754] "Means of providing personalized content" refers to the process of selecting and providing information and services that are individually suited to each user based on their past behavior and emotional state.

[0755] "Means of protecting data security and privacy" refers to encryption technologies and access control measures to protect collected user data from unauthorized access and leakage.

[0756] This invention provides a system that incorporates an emotion engine for recognizing user emotions into an information processing device that acquires transaction data in real time and detects anomalies.

[0757] The server acquires and monitors transaction data generated from transactions and operations within the system in real time. For this purpose, high-speed database management systems and stream processing technologies can be used. For example, open-source software like Apache Kafka or existing commercial software may be used. The server leverages AI models to analyze this data and detect anomalies. Python libraries such as Scikit-learn and TensorFlow may be used to build these models.

[0758] The device records user input and actions and sends them to an emotion recognition engine. This engine analyzes emotions using natural language processing (NLP) techniques. Common NLP libraries used include NLTK and spaCy. The device understands the user's emotional state, and the system dynamically adjusts the interface based on this information. In other words, the screen design and configuration change according to the emotional data, providing the user with the optimal operating environment.

[0759] Furthermore, the server provides personalized content based on the user's past behavior history and current emotional state. For example, it can prioritize displaying information related to product categories that the user frequently searches for, or incorporate a product recommendation system to provide appropriate information to each user.

[0760] The server prioritizes data security, encrypting collected sentiment and transaction data and implementing access controls. This enhances privacy protection and prevents unauthorized access by third parties.

[0761] To give a specific example, on an online shopping platform, when a user is considering purchasing a particular product, an emotion engine can determine the user's stress level and provide corresponding customer support options in real time. Such systems help improve customer satisfaction and create new purchasing opportunities.

[0762] A suitable example of a prompt would be, "Suggest a way to provide effective support based on the user's emotional state."

[0763] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0764] Step 1:

[0765] The server acquires and monitors transaction data in real time. This input data includes transaction details, timestamps, and user information. The server uses stream processing technology to store this data in containers and begins monitoring for anomalies in the database. Specifically, Apache Kafka is used to rapidly stream the data, enabling real-time analysis.

[0766] Step 2:

[0767] The server inputs the acquired transaction data into a generating AI model to detect anomalies. This model has learned normal patterns and analyzes inconsistencies in the input data. As output, it classifies the data into normal and anomaly data. The server records the generated anomaly data and notifies the administrator as needed. This process is performed using the Scikit-learn library.

[0768] Step 3:

[0769] The device collects user behavior data and input information and sends it to the emotion recognition engine. Input includes keystroke speed, mouse movements, and click frequency. At this stage, the device preprocesses and quantifies the input data. The output is a calculated estimated emotional state of the user. Specifically, natural language processing is performed using the spaCy library to classify the emotions.

[0770] Step 4:

[0771] The server receives output from the emotion recognition engine and dynamically adjusts the interface according to the user's emotional state. The input is analyzed emotion data, which the server uses to change the screen layout and operations to improve the user experience. The output is a customized interface provided to the user. Specifically, if the user expresses anxiety, more emphasized support information and FAQs are displayed.

[0772] Step 5:

[0773] The server provides personalized content based on the user's emotions and past behavior history. Input includes the user's past purchase history and browsing information. The server analyzes this data and prioritizes displaying products and information that are likely to interest the user. Output includes featured pages and recommended product lists that match the user's interests. For example, a recommendation engine can be used to automatically display new products that match the user's preferences at the top.

[0774] Step 6:

[0775] The server maintains data security and privacy throughout all processing. Inputs include sentiment data and transaction data. The server encrypts this data and stores it in a secure database. For output, access control is strictly managed to prevent unauthorized access. Specifically, data communication is protected using SSL / TLS standards, and an authentication system is implemented to restrict access.

[0776] (Application Example 2)

[0777] 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".

[0778] In recent years, as many information processing systems rely on the analysis of transaction data, real-time anomaly detection and improved user experience have become crucial. However, with existing technologies, it has been difficult to simultaneously achieve anomaly detection and dynamic interface adjustments and personalized suggestions based on the user's emotional state. This invention aims to improve system security and user experience by combining real-time transaction data analysis with user emotion recognition.

[0779] 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.

[0780] In this invention, the server includes means for acquiring transaction information in real time, means for analyzing the acquired transaction information using a generative model and detecting anomalies, and means for recognizing the user's emotional state and dynamically adjusting the interface based on that state. This enables rapid detection of anomalies in transaction data and allows for personalized suggestions and interface adjustments in accordance with the user's emotional state.

[0781] An "information processing device" is a device or system used for collecting, analyzing, and storing data.

[0782] "Means for acquiring transaction information in real time" refers to a method or device for immediately collecting generated transaction information through data communication.

[0783] "Methods for analyzing and detecting anomalies using generative models" refer to methods that use models based on machine learning or statistical techniques to evaluate data and identify events that deviate from normal patterns.

[0784] "Means of performing root cause analysis to identify the cause of an anomaly" refers to analytical techniques used to investigate and clarify the underlying cause behind an anomaly that has occurred.

[0785] "Means for generating on-demand reports" refers to a function that instantly creates and provides data analysis results as reports as needed.

[0786] "Means for recognizing a user's emotional state and dynamically adjusting the interface based on that emotion" refers to technology that determines the user's emotions based on their input and actions, and then changes the display and functions of the user interface in a timely manner based on the results.

[0787] "Means of providing personalized content based on user emotions" refers to methods of presenting information and suggestions that take into account the user's emotional state and are tailored to their specific needs and preferences.

[0788] "Means of protecting data security and privacy" refer to encryption and access control technologies that protect personal and confidential data from unauthorized access and leakage.

[0789] "Means for generating and notifying warnings" refers to technologies that, when an anomaly or emergency is detected, immediately create warning information and communicate it to the relevant parties.

[0790] "Means for analyzing individual trends based on a user's past transaction information and analysis history" refers to analytical techniques that use historical data to reveal the behavioral patterns and trends of specific users.

[0791] The system for realizing this invention consists of a server and a terminal as an information processing device. The server is preferably located on a cloud platform or data center with advanced computing capabilities. The server uses network communication to acquire various transaction information in real time. The acquired data is analyzed using a generative AI model to detect anomalies. This analysis process utilizes a processor and data storage with advanced computing capabilities.

[0792] Furthermore, the device itself is equipped with an emotion engine to recognize the user's emotional state. This engine analyzes the user's emotions based on voice input and behavioral pattern detection. The results of this analysis are sent to a server and used to dynamically adjust the user interface. For example, if the user is in an anxious situation, the system will immediately present supportive content to improve the user experience. Specifically, it will display messages and links on the device to provide emphasized help and ensure a sense of security.

[0793] This invention enables the detection of anomalies in transaction data and the provision of personalized content based on user emotions. If a user feels uneasy while browsing a particular product, the system will provide encouraging messages to facilitate a smoother purchasing decision.

[0794] An example of a prompt message is as follows:

[0795] "Please create support messages to be displayed when users are feeling anxious. Include specific examples of support to help users feel at ease."

[0796] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0797] Step 1:

[0798] The server retrieves transaction information in real time over the network. This input data is appropriately organized into corresponding data fields. The data, including timestamps and user IDs, is temporarily stored in a state ready for analysis.

[0799] Step 2:

[0800] The server inputs the acquired transaction information into a generating AI model to perform anomaly detection. The generating AI model uses statistical analysis and machine learning algorithms to identify abnormal patterns by comparing them with past normal data. As output, if an anomaly is detected, a warning flag is set and detailed information about the anomaly is generated.

[0801] Step 3:

[0802] The server inputs detailed anomaly information into a root cause analysis module to identify the root cause of the anomaly. This process analyzes the anomaly's historical data and related events, and applies algorithms to identify potential causes. The output is provided as a list of candidate root causes.

[0803] Step 4:

[0804] The server receives emotion data sent from the user to the terminal and recognizes the emotional state. This data includes features extracted from the user's input and actions. The server uses an emotion engine to analyze the emotions and generates an emotional state status as output.

[0805] Step 5:

[0806] The server dynamically adjusts the user interface based on the emotional state status. The terminal displays reassuring support messages and action items. The output consists of personalized interface elements designed to enhance the user experience.

[0807] Step 6:

[0808] If the user provides additional input through the provided interface, the server collects that feedback information and performs analysis for further personalization. The output provides insights for future interface optimization.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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."

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0830] The following is further disclosed regarding the embodiments described above.

[0831] (Claim 1)

[0832] In (information processing device),

[0833] (Means for obtaining transaction data in real time)

[0834] (Methods for analyzing acquired transaction data using a generative model to detect anomalies),

[0835] (Methods for conducting root cause analysis to identify the cause of the abnormality),

[0836] (Methods for generating on-demand reports based on analysis results),

[0837] (Means of providing personalized advice to users)

[0838] (Means to protect data security and privacy),

[0839] A system that includes this.

[0840] (Claim 2)

[0841] (When an anomaly in transaction data is detected, an alert is generated and a notification is sent.)

[0842] The system according to claim 1.

[0843] (Claim 3)

[0844] (Analyzes individual trends based on the user's past transaction data and analysis history)

[0845] The system according to claim 1.

[0846] "Example 1"

[0847] (Claim 1)

[0848] [In an information processing device, means for acquiring transaction data in real time,

[0849] [Methods for analyzing acquired transaction data using a generative model to identify normal and abnormal patterns,

[0850] [Means for conducting detailed data analysis to identify the cause when an anomaly is detected,

[0851] [A means to automatically create on-demand reports based on analysis results and send them to the administrator,

[0852] [Means of providing users with personalized operational guidance based on their past transaction history,

[0853] [Means of protecting information security and privacy through the encryption of transaction data,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] [The system according to claim 1, which automatically creates an alert and notifies the administrator when an anomaly in transaction data is detected.

[0857] (Claim 3)

[0858] [The system according to claim 1, which analyzes individual behavioral trends based on the user's past transaction data and analysis history and provides alternative means.

[0859] "Application Example 1"

[0860] (Claim 1)

[0861] In (information processing device),

[0862] (Means for obtaining transaction data in real time)

[0863] (Methods for analyzing acquired transaction data using a generative model to detect anomalies),

[0864] (Methods for conducting root cause analysis to identify the cause of the abnormality),

[0865] (Methods for generating on-demand reports based on analysis results),

[0866] (Means of providing personalized advice to users)

[0867] (Means to protect data security and privacy),

[0868] (A means of presenting and notifying the user of recommended countermeasures using examples when an anomaly is detected),

[0869] (Means for analyzing factors in the communication environment, including network latency, and deriving appropriate countermeasures),

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1 (which generates and notifies an alert when an anomaly in transaction data is detected).

[0873] (Claim 3)

[0874] The system according to claim 1 (which analyzes individual trends based on the user's past transaction data and analysis history).

[0875] "Example 2 of combining an emotion engine"

[0876] (Claim 1)

[0877] In (information processing device),

[0878] (Methods for acquiring and monitoring transaction data in real time)

[0879] (Methods for analyzing acquired transaction data using a generative model to detect anomalies),

[0880] (Methods for conducting root cause analysis to identify the cause of the abnormality),

[0881] (Methods for incorporating an emotion recognition engine that analyzes emotional states based on user input and operations),

[0882] (Means of dynamically adjusting the interface based on user emotions),

[0883] (Means of providing personalized content to users)

[0884] (Means to protect data security and privacy),

[0885] A system that includes this.

[0886] (Claim 2)

[0887] The system according to claim 1 (which generates and notifies an alert when an anomaly in transaction data is detected).

[0888] (Claim 3)

[0889] The system according to claim 1 (which analyzes individual trends based on the user's past data and analysis history, and introduces elements corresponding to their emotional state).

[0890] "Application example 2 when combining with an emotional engine"

[0891] (Claim 1)

[0892] In (information processing device),

[0893] (Means for obtaining transaction information in real time)

[0894] (Methods for analyzing acquired transaction information using a generative model to detect anomalies),

[0895] (Methods for conducting root cause analysis to identify the cause of the abnormality),

[0896] (Means for generating on-demand reports based on analysis results),

[0897] (Means for recognizing the user's emotional state and dynamically adjusting the interface based on those emotions),

[0898] (Means of providing personalized content based on user emotions)

[0899] (Means to protect data security and privacy),

[0900] A system that includes this.

[0901] (Claim 2)

[0902] The system according to claim 1 (which generates and notifies a warning when it detects an anomaly in transaction information).

[0903] (Claim 3)

[0904] The system according to claim 1 (which analyzes individual trends based on the user's past transaction information and analysis history). [Explanation of Symbols]

[0905] 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. In an information processing device, A means of obtaining transaction data in real time, A means for analyzing acquired transaction data using a generative model to detect anomalies, A means of conducting root cause analysis to identify the cause of the abnormality, A means of generating on-demand reports based on analysis results, A means of providing personalized advice to users, Means to protect data security and privacy, A system that includes this.

2. An alert is generated and a notification is sent when an anomaly in transaction data is detected. The system according to claim 1.

3. Analyze individual trends based on users' past transaction data and analysis history. The system according to claim 1.

Images