System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving data in real-time from an external system; means for cleansing the received data; means for detecting anomalies based on the pre-processed data; means for identifying causes of the detected anomalies; means for generating a report based on the anomalies and the causes; means for providing advice to a user regarding specific issues; and means for protecting security and privacy of user data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In system operations, monitoring, analyzing, detecting anomalies in transaction data, and developing countermeasures are extremely time-consuming and labor-intensive. Especially when handling large amounts of data in real time, this places a heavy burden on system personnel, making it difficult to quickly respond to errors and anomalies. Furthermore, manual processing carries the risk of error, which can have a negative impact on system quality. To solve these issues, it is necessary to automate the entire process, from receiving transaction data to detecting anomalies, analyzing root causes, developing countermeasures, and ensuring security and privacy. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for receiving data from an external system in real time, a means for cleansing the received data, a means for detecting anomalies based on the preprocessed data, a means for identifying the causes of the detected anomalies, a means for generating reports based on the anomalies and their causes, a means for providing advice to users regarding specific problems, and a means for protecting the security and privacy of user data. This significantly reduces the workload of system personnel and improves system quality. Furthermore, by including a means for analyzing the preprocessed data in real time to detect anomalies and a means for deleting unnecessary fields and duplicate records, the system can improve data reliability and processing efficiency.

[0006] "Means for receiving data" refers to a mechanism or method for receiving transaction data in real time from an external system.

[0007] A "data cleansing means" is a mechanism or method for removing unnecessary information and duplication from received data and performing processing to unify the data format.

[0008] An "anomaly detection means" is a method or algorithm that uses pre-processed data to find anomalous data or errors that deviate from normal patterns in real time.

[0009] A "cause determination means" is a method or process for analyzing and determining the root cause of a detected anomaly.

[0010] The "means for generating a report" refers to a mechanism or method for creating a detailed report based on the detected anomalies and their causes, and providing it to the user.

[0011] An "advice delivery mechanism" is a mechanism or method that uses a generative AI model to provide an appropriate solution or response when a user asks a question about a specific problem.

[0012] "Security and privacy measures" are mechanisms and methods for ensuring data security by encrypting user data and implementing appropriate access controls. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0014] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0017] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0018] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0019] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 1, a 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.

[0024] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0026] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0027] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0031] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0033] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0034] The present invention provides a system that automates the process from receiving transaction data to analyzing it, detecting anomalies, analyzing root causes, formulating countermeasures, and protecting security and privacy. Specific embodiments of the system are described below.

[0035] Overall flow

[0036] 1. Data Receipt

[0037] The server receives transaction data in real time from external systems, such as e-commerce site databases and applications. The received data is temporarily stored in data storage.

[0038] 2. Data cleansing

[0039] The server cleanses the data it receives, which includes removing duplicate records, standardizing data formats, and filtering out unnecessary information.

[0040] 3. Real-time analysis

[0041] The server analyzes the cleansed data in real time to detect anomalies, using generative AI models to analyze the data for patterns and trends and spot data that is out of the ordinary.

[0042] 4. Root Cause Analysis

[0043] The server identifies the specific cause of the detected anomaly using information such as the time and location of the anomaly and details of the associated transaction.

[0044] 5. Report Generation

[0045] The server generates a report based on the root cause analysis results and provides it to the user, containing details of the anomaly, its cause, and recommended actions to take.

[0046] 6. Providing advice

[0047] Users can pose questions to the generative AI model about a specific problem, and the server will provide personalized advice on the question, including solutions and troubleshooting tips.

[0048] 7. Security and Privacy Protection

[0049] The servers use strong encryption protocols and enforce access controls to ensure the security of user data when storing and processing data.

[0050] Specific examples

[0051] For example, a case will be described in which an e-commerce site uses the system of the present invention to monitor transaction data.

[0052] 1. Data Receipt

[0053] The server receives order data and user behavior data from the e-commerce site in real time. For example, transaction data is sent when a customer purchases a product.

[0054] 2. Data cleansing

[0055] The server performs cleansing to remove duplicate order data and data with inconsistent formats, thereby improving the accuracy of analysis.

[0056] 3. Real-time analysis

[0057] The server uses generative AI models to analyze the data in real time, detecting, for example, unusual purchase frequencies or unusual patterns in the sales of certain products.

[0058] 4. Root Cause Analysis

[0059] The server identifies a problem with inventory data in a particular product category as the cause of the detected anomaly.

[0060] 5. Report Generation

[0061] The server generates a report detailing the anomaly, its cause, and recommended countermeasures, and provides it to the e-commerce site's system administrator.

[0062] 6. Providing advice

[0063] When a user asks, "I would like to know more details about the abnormal data occurring in a specific product category and what to do about it," the server will recommend, "Recheck the data in your inventory system and correct it if necessary."

[0064] 7. Security and Privacy Protection

[0065] The server encrypts all communications and stored data and implements appropriate access controls to ensure data security.

[0066] In this way, the present invention can significantly reduce the man-hours required by system personnel and improve the quality of the system. By automating specific processes, it becomes possible to quickly and accurately detect and respond to abnormalities.

[0067] The processing flow will be explained below.

[0068] Step 1:

[0069] The server receives transaction data from external systems. Specifically, it retrieves data in real time from e-commerce sites and other systems using HTTP requests or APIs, and temporarily stores it in data storage.

[0070] Step 2:

[0071] The data received by the server is cleansed. Specifically, the data format and structure are checked, unnecessary and duplicate data is deleted, and only the necessary information is retained. This work also includes standardizing the data format and correcting inconsistent data.

[0072] Step 3:

[0073] The server sends the cleansed data to the analysis engine. Specifically, the cleansed data is passed to the generative AI model in real time, and analysis begins.

[0074] Step 4:

[0075] The server uses the generative AI model to analyze the data in real time. Specifically, the analysis engine learns patterns and trends in the data and detects anomalous data or errors that deviate from normal patterns.

[0076] Step 5:

[0077] The server logs any detected anomalies. Specifically, each time an anomaly is detected, details about it (such as time, location, and transaction ID) are added to the anomaly log.

[0078] Step 6:

[0079] The server performs root cause analysis of the anomaly. Specifically, it collects related data (the situation at the time the anomaly occurred and other transaction data) and analyzes the cause to identify the cause of the anomaly.

[0080] Step 7:

[0081] The server generates a report based on the results of the root cause analysis, summarizing the details of the anomaly, its cause, and recommended actions to take, and saves it in PDF or dashboard format.

[0082] Step 8:

[0083] When a user requests a report, the server provides it: the user requests a report through an interface (web browser or application), the server finds the saved report, and sends it to the user.

[0084] Step 9:

[0085] When a user inputs a question about a specific anomaly into the generative AI model, the server analyzes the question and generates appropriate advice. Specifically, it analyzes the question and generates an answer using relevant data and past case studies, and provides it to the user.

[0086] Step 10:

[0087] The server will implement strong security and privacy protections for all data processing and storage, including encrypting data and setting strict access controls to ensure that only a limited number of users can access the data.

[0088] Example 1

[0089] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0090] In conventional transaction data analysis systems, the process from receiving data to detecting anomalies, identifying causes, and proposing countermeasures is often done manually, which is time-consuming and labor-intensive. Security and privacy protections are often inadequate, raising concerns about data safety. Furthermore, it is difficult to detect anomalies in real time or provide specific advice to users regarding specific problems.

[0091] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0092] In this invention, the server includes means for receiving data from an external system in real time, means for cleansing the received data, and means for detecting anomalies using a generative AI model based on the preprocessed data. This enables real-time analysis of transaction data. The server also includes means for identifying specific causes of detected anomalies, means for generating reports based on the anomalies and their causes, means for providing advice to users regarding specific issues based on prompts, means for protecting the security and privacy of user data, means for storing the preprocessed data in storage, and means for implementing access control for the stored data. This enables efficient analysis of transaction data, anomaly detection, cause analysis, proposal of appropriate countermeasures, and secure data management.

[0093] "External System" refers to any other system or database to which transaction data can be transmitted in real time.

[0094] "Data receiving means" refers to a device or program that has the function of receiving transaction data from an external system in real time.

[0095] "Cleansing means" refers to a device or program that has the function of deleting duplicate records from received data, standardizing data formats, and filtering out unnecessary information.

[0096] "Pre-processed data" refers to data after it has been processed by a cleansing tool.

[0097] A "generative AI model" is a model that uses machine learning and deep learning algorithms to analyze patterns and trends in data and detect anomalies.

[0098] "Anomaly detection means" refers to a device or program that has the function of detecting anomalies using a generative AI model based on preprocessed data.

[0099] "Cause identification means" refers to a device or program with analytical capabilities to identify the specific cause of a detected abnormality.

[0100] "Report generation means" refers to a device or program that has the function of generating a report based on anomalies and their causes and providing the information to the user.

[0101] A "prompt" refers to a question that a user inputs into a generative AI model to obtain specific information.

[0102] The "advice providing means" refers to a device or program that has the function of providing personalized advice to a user regarding a specific problem based on a prompt sentence.

[0103] "Security and privacy measures" refers to devices and programs that use strong encryption protocols and access control when storing and processing user data.

[0104] "Data Storage" refers to storage systems and cloud storage for temporary or long-term storage of received and pre-processed data.

[0105] "Access control" refers to authentication and authorization functions for managing access rights to data and preventing unauthorized access.

[0106] This invention is a system that consistently performs processes from receiving transaction data to analyzing it, detecting anomalies, identifying causes, generating reports, providing advice, and protecting security and privacy. This system is equipped with functions for receiving real-time data from external systems, data cleansing, detecting anomalies using a generative AI model, identifying causes, generating reports, and providing advice based on prompts. It also has powerful security and privacy protection functions for storing data and controlling access.

[0107] This system operates mainly around the server. Each function is explained in detail below.

[0108] Data Receipt

[0109] The server receives transaction data in real time from external systems (e.g., e-commerce sites or databases for various applications). The received data is temporarily stored in data storage (e.g., cloud storage), making it easy to access the data in the next processing step.

[0110] Data Cleansing

[0111] The server cleanses the data it receives. This process includes removing duplicate records, standardizing data formats, and filtering out unnecessary information. Data processing libraries such as Python's Pandas and Dask can be used for data cleansing.

[0112] Real-time analytics

[0113] The server uses generative AI models (e.g., TensorFlow or PyTorch) to analyze the cleansed data in real time. The generative AI models analyze the data for patterns and trends and detect anomalies. If an anomaly is detected, the information is passed on to subsequent processes.

[0114] Root Cause Analysis

[0115] The server identifies the specific cause of the anomaly, for example by analyzing the time, location, and related transaction details of the detected anomaly. Root cause analysis can be performed using database queries or log analysis tools.

[0116] Report Generation

[0117] The server generates a report based on the results of the root cause analysis. The report includes details of the anomaly, its cause, and recommended actions. The generated report is saved in PDF or HTML format and provided to the user.

[0118] Providing advice

[0119] The user sends a prompt to the server, such as "I would like to know more about the abnormal data occurring in a specific product category and what to do about it." The server then uses a generative AI model based on the prompt to provide personalized advice. For example, the server might recommend, "Recheck the data in your inventory system and correct it if necessary."

[0120] Security and privacy protection

[0121] The server uses strong encryption protocols (e.g., AES-256) for storing and processing data and applies access controls, including access logging and authentication and authorization mechanisms, to ensure the security of user data.

[0122] Specific examples

[0123] For example, let us consider a case where an e-commerce site uses the system of the present invention to monitor transaction data. Order data and user behavior data from the e-commerce site are sent to a server in real time, which receives and stores them in data storage. After data cleansing and anomalies are detected using a generative AI model, a root cause analysis is performed to generate a report summarizing the causes of the anomaly and countermeasures, which is then provided to the user. When the user sends a prompt requesting advice, the server uses the generative AI model to provide appropriate advice.

[0124] In this way, the system enables efficient analysis of transaction data, anomaly detection, cause analysis, appropriate countermeasure proposals, and secure data management.

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Step 1: Data Reception

[0127] The server receives transaction data from external systems in real time. Input data is order data and user behavior data sent from the database of the e-commerce site or application. The server temporarily stores this data in data storage, allowing the data to be used efficiently in the next step.

[0128] Step 2: Data cleansing

[0129] The server cleanses the temporarily stored transaction data. The input data is the raw data received in the previous step. Specific operations include deleting duplicate records, standardizing data formats, and filtering out unnecessary information. For example, these operations are performed using the Python Pandas library. The output data is cleansed, consistent data.

[0130] Step 3: Real-time analysis

[0131] The server applies a generative AI model to the cleansed data to detect anomalies in real time. The input data is the data cleansed in step 2. The server uses a generative AI model (e.g., TensorFlow or PyTorch) to analyze the data for patterns and trends and detect anomalies. The output data is the anomaly detection results, which include a list of anomalous patterns and values.

[0132] Step 4: Root Cause Analysis

[0133] The server identifies the specific cause of the detected anomaly. The input data is the anomaly detection result obtained in step 3. The server analyzes the cause based on the time of the anomaly occurrence, location, and detailed information about the related transaction. For example, it extracts detailed information from the database using SQL queries or log analysis tools. The output data is the cause of the anomaly and its details.

[0134] Step 5: Generate a report

[0135] The server generates a report based on the results of the root cause analysis. The input data are the anomaly causes and their details obtained in step 4. The report contains details of the anomaly, its cause, and recommended actions. Specifically, the report is generated as a PDF or HTML file and saved on the server. The output data is the generated report, which is ready to be provided to the user.

[0136] Step 6: Providing advice

[0137] The user poses a question to the server based on a prompt about a specific problem. The input data is the prompt sent by the user (e.g., "I would like to know more about the abnormal data occurring in a specific product category and what to do about it"). The server uses a generative AI model to generate personalized advice corresponding to the prompt. The output data is the advice provided to the user. For example, it might recommend, "Recheck the data in your inventory system and correct it if necessary."

[0138] Step 7: Protecting security and privacy

[0139] The server uses a strong encryption protocol (e.g., AES-256) to store and process data and implements access control. Input data is all data stored within the server. The server records access logs and sets authorization to ensure the safety of user data. Output data is encrypted and secure. This prevents unauthorized access or leakage of data.

[0140] (Application example 1)

[0141] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0142] Conventional technologies require a lot of manual work to receive and analyze transaction data, detect anomalies, identify the cause, and develop countermeasures, which can easily lead to human error. Furthermore, there was no system in place to respond quickly and appropriately after an anomaly was detected, resulting in insufficient security and privacy protection for user data. Therefore, there was a need for a system that could detect anomalies in real time and provide appropriate countermeasures to improve the safety of user data.

[0143] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0144] In this invention, the server includes means for receiving data from an external system in real time, means for cleansing the received data, means for detecting anomalies based on the preprocessed data, means for identifying the cause of the detected anomaly, means for generating a report based on the anomaly and its cause, means for providing advice to the user regarding the specific problem, means for protecting the security and privacy of the user data, means for linking with a smart device to notify the user of the generated report, means for generating a prompt message and providing advice to the user based on the anomaly detection result, and means for ensuring the portability and security of data using an encryption protocol. This enables rapid and accurate anomaly detection and provision of appropriate countermeasures, and further enhances the security of user data.

[0145] "External system" refers to other computer systems or networks that send and receive data.

[0146] "Means for receiving data" refers to a hardware or software part that has the function of obtaining data from an external system in real time.

[0147] "Means for cleansing data" refers to a function for purifying received data and eliminating duplicate data and unnecessary information.

[0148] "Means for detecting anomalies" refers to the part that has the functionality to identify unusual patterns or values ​​based on preprocessed data.

[0149] "Means for identifying the cause" refers to the function for analyzing and identifying the reason why an abnormality occurred.

[0150] "Means for generating reports" refers to a function for creating a report summarizing details and causes of anomalies and recommended actions to be taken.

[0151] "Means for providing advice" refers to a function that provides appropriate advice to users on specific issues.

[0152] "Security and privacy measures" refers to features designed to protect user data from unauthorized access and leaks.

[0153] "Means of collaboration with smart devices to notify users of generated reports" refers to the function for sending reports to devices such as users' smartphones and tablets.

[0154] "Means for generating prompt sentences and providing advice" refers to the function for generating appropriate responses to questions from users based on the results of anomaly detection.

[0155] "Means for ensuring data portability and security using cryptographic protocols" refers to functions that use strong cryptographic technology to ensure the security of data during transport and storage.

[0156] This invention is a system that automates the process from receiving transaction data to analyzing it, detecting anomalies, analyzing root causes, formulating countermeasures, and protecting security and privacy. Specific embodiments of this system are described below.

[0157] System Configuration

[0158] The system of the present invention includes a server, an external system, and a smart device. The server uses a cloud service such as AWS or GCP, and uses MySQL or MongoDB as the database. The generative AI model uses TensorFlow or PyTorch, and the data is encrypted using the AES encryption protocol.

[0159] Program processing

[0160] 1. Data Receipt

[0161] The server receives real-time transaction data from external systems, such as e-commerce sites and financial institutions, and temporarily stores the data in data storage.

[0162] 2. Data cleansing

[0163] The server cleanses the data it receives, which includes deleting duplicate data, removing unnecessary information, and standardizing data formats.

[0164] 3. Real-time analysis

[0165] The server analyzes the cleansed data in real time to detect anomalies, using generative AI models to analyze data patterns and trends and identify abnormal data.

[0166] 4. Root Cause Analysis

[0167] The server identifies the specific cause of the detected anomaly, analyzing it based on information such as time, location, and related transaction details.

[0168] 5. Report Generation

[0169] The server generates a report summarizing details of the anomaly, its cause, and recommended countermeasures, and this report is sent to smart devices such as smartphones and tablets.

[0170] 6. Providing advice

[0171] Users can pose questions to the generative AI model about a specific problem, and the server will provide personalized advice on that question, including solutions and troubleshooting tips.

[0172] 7. Security and Privacy Protection

[0173] The servers use strong encryption protocols for all data storage and processing and enforce access controls to ensure the security of user data.

[0174] Specific examples

[0175] For example, when an online shopping site uses the system of the present invention to monitor transaction data, the system operates as follows.

[0176] 1. Data Receipt

[0177] The server receives order data and user behavior data from an online shopping site in real time. For example, transaction data is sent when a customer purchases a product.

[0178] 2. Data cleansing

[0179] The server performs cleansing to remove duplicate order data and data with inconsistent formats, thereby improving the accuracy of the analysis.

[0180] 3. Real-time analysis

[0181] The server uses generative AI models to analyze the data in real time, detecting, for example, unusual purchase frequencies or unusual patterns in the sales of certain products.

[0182] 4. Root Cause Analysis

[0183] The server identifies a problem with inventory data in a particular product category as the cause of the detected anomaly.

[0184] 5. Report Generation

[0185] The server generates a report summarizing details of the anomaly, its cause, and recommended countermeasures, and notifies the system administrator of the online shopping site.

[0186] 6. Providing advice

[0187] When a user asks, "I'd like more details and solutions about abnormal data occurring in a specific product category," the server recommends, "Recheck the data in your inventory system and correct it if necessary."

[0188] Prompt Sentence Examples

[0189] Question: "Is there anything unusual about my latest transaction?"

[0190] Q: "What unusual activity occurred in trading in April?"

[0191] As described above, the system of the present invention can quickly and accurately detect anomalies and provide appropriate countermeasures, thereby increasing the security of user data.

[0192] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0193] Step 1:

[0194] The server receives transaction data from external systems in real time. The input here is various transaction data sent from the external systems, and the output is transaction data temporarily stored in data storage.

[0195] Step 2:

[0196] The server cleanses the received data by deleting duplicate data, removing unnecessary information, and standardizing data formats. The input here is the transaction data saved in step 1, and the output is the cleansed transaction data.

[0197] Step 3:

[0198] The server uses a generative AI model to perform real-time analysis of the cleansed data and detect anomalies. Specifically, it analyzes data patterns and trends to detect anomalous data. The input here is the cleansed transaction data obtained in step 2, and the output is the detected anomalous data.

[0199] Step 4:

[0200] The server identifies the specific cause of the detected anomaly by analyzing the time, location, and details of the related transaction to identify the cause of the anomaly. The input here is the anomaly data detected in step 3, and the output is information about the cause of the identified anomaly.

[0201] Step 5:

[0202] The server generates a report based on the anomaly and its cause and notifies the smart device. The report contains details of the anomaly, its cause, and recommended countermeasures. The input here is the anomaly cause information identified in step 4, and the output is the generated report.

[0203] Step 6:

[0204] When a user sends a question about a specific problem to the server as a prompt, the server uses a generative AI model to provide personalized advice. Specifically, the server generates an appropriate response to the user's question. The input here is the prompt from the user, and the output is the generated advice.

[0205] Step 7:

[0206] The server uses the AES encryption protocol to store and process user data and enforces access control to protect security and privacy. Specifically, it encrypts and decrypts data and manages access rights. The input here is the data to be stored and the access request, and the output is the encrypted data and the result of the access control.

[0207] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0208] The present invention is a system that provides users with a better interactive experience by combining the reception and analysis of transaction data, anomaly detection, root cause analysis, countermeasure planning, and security and privacy protection, as well as an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0209] Overall flow

[0210] 1. Data Receipt

[0211] The server receives transaction data in real time from external systems. Specifically, it retrieves data from databases such as e-commerce sites via HTTP requests or APIs and temporarily stores it in data storage.

[0212] 2. Data cleansing

[0213] The server cleanses the data it receives. Specifically, it checks the data format and structure, and deletes unnecessary and duplicated information. It also standardizes the data format of necessary information to improve the accuracy of analysis.

[0214] 3. Real-time analysis

[0215] The server then uses generative AI models to analyze the cleansed data in real time, detecting anomalous data or errors that deviate from normal patterns.

[0216] 4. Root Cause Analysis

[0217] To identify the cause of the detected anomaly, the server collects and analyzes relevant data (such as the circumstances surrounding the anomaly and other transaction data).

[0218] 5. Report Generation

[0219] The server generates a detailed report based on the root cause analysis results, including details of the anomaly, its cause, and recommended actions to take. The generated report is saved in PDF or dashboard format and provided to the user.

[0220] 6. Emotion recognition

[0221] The emotion engine analyzes the text entered by the user through the user interface and recognizes the emotion. The emotion engine uses natural language processing to identify emotions (joy, anger, sadness, surprise, etc.) from the user's input text.

[0222] 7. Personalized advice

[0223] The server takes into account the user's emotions and personalizes the advice it provides. For example, if a user types "I'm having trouble with too many errors," the emotion engine will recognize "stress" and provide advice with corresponding support and encouraging messages.

[0224] 8. Security and Privacy Protection

[0225] The server will implement strong security and privacy protection for all data processing and storage. Specifically, data will be encrypted and strict access control will be set to ensure the safety of user data.

[0226] Specific examples

[0227] For example, a case will be described in which an e-commerce site uses the system of the present invention to monitor transaction data.

[0228] 1. Data Receipt

[0229] The server receives order data and user behavior data from the e-commerce site in real time. The order data includes information such as product name, price, and purchase date and time.

[0230] 2. Data cleansing

[0231] The server cleanses the data it receives, removes duplicate order data, and standardizes the data format, thereby improving the efficiency and accuracy of the analysis process.

[0232] 3. Real-time analysis

[0233] The server uses generative AI models to analyze data in real time, for example to detect unusually high purchase frequency of a particular product or an abnormal number of transactions.

[0234] 4. Root Cause Analysis

[0235] The server examines the relevant transaction data and system logs to determine the cause of the identified anomaly, and determines that the cause is, for example, a data discrepancy in an inventory system.

[0236] 5. Report Generation

[0237] The server generates a report detailing the anomaly, its cause, and recommended actions to take, which is output in PDF format and sent to the e-commerce site's system administrator.

[0238] 6. Emotion recognition

[0239] The emotion engine analyzes feedback and inquiries from system administrators to recognize their emotions. For example, it can identify the emotion of stress from feedback such as "the frequency of errors is too high."

[0240] 7. Personalized advice

[0241] The server will provide specific advice based on the recognized emotion, for example, providing a support message along with detailed guidance on "how to improve your workflow to resolve this issue."

[0242] 8. Security and Privacy Protection

[0243] The servers encrypt all communications and data storage and implement strict access controls to prevent unauthorized access to user data and confidential information.

[0244] In this way, the present invention reduces the burden on system personnel and improves the quality of the system and the user experience. By combining it with an emotion engine, responses to users become more flexible and effective.

[0245] The processing flow will be explained below.

[0246] Step 1:

[0247] The server receives transaction data from external systems. Specifically, the data is obtained in real time through HTTP requests or API calls and temporarily stored in data storage. This process is performed by setting up a listener for receiving data, and when data arrives, the listener generates an event and receives the data stream.

[0248] Step 2:

[0249] The server cleanses the data it receives. Specifically, it checks the data format and structure, removes unnecessary information and duplicate records, standardizes the data format, and corrects inconsistent data, preparing the cleansed data for analysis.

[0250] Step 3:

[0251] The server sends the cleansed data to the analytics engine, which begins real-time analysis by feeding the data into a generative AI model and running algorithms to detect anomalous data or errors that deviate from normal patterns.

[0252] Step 4:

[0253] The server logs any detected anomalies, adding details such as the time and location of the anomaly and the transaction ID to the anomaly log for future reference by administrators.

[0254] Step 5:

[0255] The server performs root cause analysis of the anomaly. Specifically, it collects and analyzes the circumstances surrounding the anomaly and related transaction data to identify the cause of the anomaly. For example, it identifies unusual purchasing patterns in a particular product category or data discrepancies in an inventory system.

[0256] Step 6:

[0257] The server generates a detailed report based on the results of the root cause analysis, summarizing the details of the anomaly, its cause, and recommended actions to take, and saves it in PDF or dashboard format.

[0258] Step 7:

[0259] When a user requests a report, the server provides it: the user requests a report through an interface (web browser or application), the server finds the saved report, and sends it to the user.

[0260] Step 8:

[0261] The emotion engine analyzes the text entered by the user through the user interface and recognizes the emotion. Specifically, the emotion engine uses natural language processing to identify emotions (joy, anger, sadness, surprise, etc.) from the user's text input and records them in a database.

[0262] Step 9:

[0263] The server personalizes the advice it provides based on the results of emotion recognition. Specifically, it takes the user's emotions into account and generates solutions with appropriate support and encouraging messages. For example, if the user enters "I'm having trouble with too many errors," the emotion engine will recognize "stress" and provide warm-hearted advice accordingly.

[0264] Step 10:

[0265] The servers implement strong security and privacy protection for all data processing and storage. Specifically, data is encrypted and strict access control is set up to ensure the safety of user data. A monitoring system is also in place to respond immediately to any signs of unauthorized access.

[0266] Example 2

[0267] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0268] While conventional data analysis systems receive, cleanse, analyze, and detect anomalies in real time, they lack clear cause analysis of detected anomalies and provide countermeasures that take user sentiment into account. In terms of security and privacy protection, the safety of user data is also not sufficiently ensured, which is a problem.

[0269] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving data from an external system in real time, a means for cleansing the received data, a means for detecting anomalies based on the preprocessed data, a means for identifying the cause of the detected anomaly, a means for generating a report based on the anomaly and its cause, a means for recognizing emotions from a user's input, a means for providing personalized advice based on the recognized emotions, and a means for protecting the security and privacy of user data. This makes it possible to detect anomalies and analyze their causes, present countermeasures that take user emotions into consideration, and ensure the safety of user data.

[0270] "Means of receiving data in real time from external systems" refers to the processes and technologies for obtaining data in real time through external databases or application program interfaces (APIs).

[0271] "Means of cleansing received data" refers to the process of removing unnecessary information from the data and standardizing the data structure in order to improve the accuracy and consistency of the data obtained.

[0272] "Anomaly detection methods based on pre-processed data" refers to algorithms and techniques that use cleansed data to analyze the data for anomalous patterns or deviations.

[0273] "Means for identifying the cause of a detected abnormality" refers to the technology and process for conducting a detailed analysis of the background and factors that caused the abnormality and identifying them.

[0274] "Means for generating reports based on anomalies and their causes" refers to technologies and processes that organize information about detected anomalies and their causes, and automatically generate reports that can be presented to users in an easy-to-understand manner.

[0275] "Means for recognizing emotions from user input" refers to natural language processing techniques that analyze the text and feedback entered by users into the system and identify the emotions contained therein.

[0276] "Means for providing personalized advice based on perceived emotions" refers to algorithms or technologies that take into account a user's emotional state to provide advice or support messages that are appropriate for that user.

[0277] "Measures to protect the security and privacy of user data" refers to encryption technologies and access control policies to protect users' personal information and prevent unauthorized access or information leaks.

[0278] The present invention is a system that provides users with a better interactive experience by combining the reception and analysis of transaction data, anomaly detection, root cause analysis, countermeasure planning, and security and privacy protection, as well as an emotion engine that recognizes user emotions. A detailed embodiment of this system will now be described.

[0279] Hardware and Software Configuration

[0280] The server plays the central role in the system. Data is received in real time from external systems and stored on the server. This data reception process uses HTTP requests and APIs. The data is stored in, for example, an S3 bucket on Amazon Web Services (AWS) or Google Cloud Storage.

[0281] Data cleansing is performed by a program installed on a server, written in a programming language such as Python or Java, that performs, among other things, data normalization and the elimination of duplicate data.

[0282] Real-time analysis for anomaly detection uses generative AI models, trained using deep learning frameworks such as TensorFlow and PyTorch, which are then analyzed by a server in real time to detect unusual data patterns and errors.

[0283] The server also handles root cause analysis, which involves collecting relevant data and using statistical methods and AI models to identify the cause of an anomaly.

[0284] The generated reports can be provided to the user in PDF format or via a web-based dashboard, which can be emailed or uploaded to a dashboard.

[0285] The emotion engine is responsible for recognizing user emotions. This engine uses natural language processing (NLP) technology to extract emotions from the text entered by the user. NLP tools such as Google Cloud Natural Language API and IBM Watson are used for this.

[0286] Personalized advice based on emotion recognition is generated by the server, which implements an algorithm that takes into account the recognized emotions and provides appropriate advice and support messages to the user.

[0287] Security and privacy are ensured through data encryption and strict access control, using SSL / TLS for communication encryption and AWS IAM policies for access control.

[0288] Specific examples

[0289] For example, consider the case where an e-commerce site uses the system of the present invention to monitor transaction data.

[0290] 1. Data Receipt

[0291] The server receives order data and user behavior data from the e-commerce site in real time. The order data includes information such as product name, price, and purchase date and time.

[0292] 2. Data cleansing

[0293] The server cleanses the data it receives, removes duplicate order data, and standardizes the data format, thereby improving the efficiency and accuracy of the analysis process.

[0294] 3. Real-time analysis

[0295] The server uses generative AI models to analyze the data in real time, for example to detect unusually high purchase frequency of a particular product or an unusual number of transactions.

[0296] 4. Root Cause Analysis

[0297] The server examines the relevant transaction data and system logs to determine the cause of the identified anomaly, and determines that the cause is, for example, a data discrepancy in an inventory system.

[0298] 5. Report Generation

[0299] The server generates a report summarizing the details of the anomaly, its cause, and recommended countermeasures, which is output in PDF format and sent to the e-commerce site's system administrator.

[0300] 6. Emotion recognition

[0301] The emotion engine analyzes feedback and inquiries from system administrators to recognize their emotions. For example, it can identify the emotion of stress from feedback such as "the frequency of errors is too high."

[0302] 7. Personalized advice

[0303] The server will then provide specific advice based on the perceived emotion, for example providing a support message along with detailed guidance on "how to improve your workflow to resolve this issue."

[0304] 8. Security and Privacy Protection

[0305] The servers encrypt all communications and data storage and implement strict access controls to prevent unauthorized access to user data and confidential information.

[0306] Prompt Sentence Examples

[0307] Can you please elaborate on the anomaly detection algorithms for transaction data in this system, specifically the generative AI model used and its training data?

[0308] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0309] Step 1: Data Reception

[0310] The server receives transaction data from external systems. Inputs include HTTP requests from e-commerce sites, order data obtained via APIs, and user behavior data. Specifically, the server uses Amazon Web Services (AWS) or Google Cloud Platform (GCP) to store the data in its own storage in real time.

[0311] Input: Transaction data from external systems (e.g., order data, user behavior data)

[0312] Output: Temporarily stored transaction data

[0313] Step 2: Data cleansing

[0314] The server cleanses the data it receives. It checks the format and structure of the data and removes unnecessary and duplicated data. This is done using programming languages ​​such as Python and Java, applying regular expressions and data conversion scripts. If some data is missing, it also performs missing value imputation.

[0315] Input: Temporarily stored transaction data

[0316] Output: Cleansed data

[0317] Step 3: Real-time analysis

[0318] The server performs real-time analysis on the cleansed data using generative AI models implemented using frameworks such as TensorFlow and PyTorch. The server detects abnormal data patterns and errors and generates alerts and notifications.

[0319] Input: Cleansed data

[0320] Output: Anomaly detection results and notifications

[0321] Step 4: Root Cause Analysis

[0322] The server performs a detailed analysis of the cause of the detected anomaly. It collects relevant data (such as the circumstances surrounding the anomaly and other transaction data) and uses statistical techniques and additional AI models to identify the cause. Specifically, it analyzes whether the anomalous transaction is linked to a specific promotion code or system log.

[0323] Input: Anomaly detection results and associated data

[0324] Output: Cause identification and details

[0325] Step 5: Generate a report

[0326] The server generates a detailed report based on the results of the root cause analysis. The report includes details of the anomaly, its cause, and recommended actions to take. The generated report is saved in PDF or web dashboard format and provided to the user. Specifically, the generated PDF can be sent by email or uploaded to the dashboard.

[0327] Input: Cause identification and details

[0328] Output: Detailed report

[0329] Step 6: Emotion Recognition

[0330] The emotion engine analyzes the text entered by the user through the user interface and recognizes the emotion. It uses Google Cloud Natural Language API and IBM Watson to extract emotions (joy, anger, sadness, surprise, etc.) from the text.

[0331] Input: User-entered text

[0332] Output: Recognized emotion

[0333] Step 7: Personalized advice

[0334] The server considers the user's emotions and personalizes the advice it provides. For example, if a user types "I'm having trouble with too many errors," the emotion engine will recognize "stress" and generate appropriate advice or encouraging messages.

[0335] Input: Recognized emotion

[0336] Output: Personalized advice

[0337] Step 8: Protecting security and privacy

[0338] The server implements strong security and privacy protection for all data processing and storage. Specifically, SSL / TLS is used for data encryption and strict access control is set to ensure the safety of user data. This is achieved using AWS IAM policies, etc.

[0339] Input: All user data

[0340] Output: Securely stored and processed user data

[0341] (Application example 2)

[0342] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0343] While traditional transaction monitoring systems are equipped with basic functions such as anomaly detection, cause identification, and user advice provision, they lack the ability to recognize user emotions and provide personalized advice based on those emotions. This makes it difficult to improve user experience or quickly resolve problems. Furthermore, robust measures are required from the perspective of security and privacy protection, but these measures are often not adequately provided.

[0344] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving data from an external system in real time, means for cleansing the received data, means for detecting anomalies based on the preprocessed data, means for identifying the cause of the detected anomaly, means for generating a report based on the anomaly and its cause, means for providing advice to the user regarding a specific problem, means for analyzing user feedback via a user interface and recognizing emotions, means for personalizing advice based on the recognized emotions, and means for protecting the security and privacy of user data. This makes it possible to provide advice that takes user emotions into consideration and to enhance security and privacy protection.

[0345] An "external system" refers to an external information processing device such as a server, database, or application that provides transaction data in real time.

[0346] "Means of receiving data" refers to a mechanism that uses an interface or protocol, such as an HTTP request or API, to obtain data from an external system.

[0347] "Data cleansing methods" refers to the process of removing unnecessary information and redundant data from received data and preparing the necessary data in an appropriate format.

[0348] "Means for detecting anomalies" refers to algorithms or systems that analyze and identify anomalous data that deviates from normal patterns in pre-processed data.

[0349] "Means for identifying the cause" refers to the mechanisms and methods for analyzing and identifying the factors behind the detected abnormality.

[0350] "Means for generating reports" refers to the process of creating and providing a report to the user that includes details of the anomaly, its cause, and recommended actions to take.

[0351] "Advice methods" refer to methods that provide users with appropriate solutions or guidance for specific problems.

[0352] "User interface" refers to the screens and input devices that allow a user to interact with a system, providing feedback and receiving information.

[0353] "Emotion recognition means" refers to natural language processing techniques and models for analyzing and identifying emotions from user feedback and input text.

[0354] "Means of personalizing advice" refers to the process of providing relevant and tailored advice based on perceived user sentiment.

[0355] "Security and privacy measures" refers to encryption technologies and access control mechanisms to ensure the security of user data and protect privacy.

[0356] This invention includes a system that provides real-time monitoring of transaction data in electronic payment services, anomaly detection, cause analysis, emotion recognition, and personalized advice. The overall flow of the system and the hardware and software used are described below.

[0357] Hardware and Software

[0358] The server receives transaction data and performs analysis and anomaly detection. The specific software and hardware used includes Python, scikit-learn, TensorFlow, Transformers, and Cryptography libraries.

[0359] Data Receipt

[0360] The server receives transaction data in real time from external systems. Specifically, it retrieves data from external databases and applications via HTTP requests or APIs and temporarily stores it in data storage.

[0361] Data Cleansing

[0362] The server cleanses the received data. Using Pandas, it checks the data format and structure, and removes unnecessary and duplicated data. It also standardizes the data format of necessary information to improve the accuracy of analysis.

[0363] Real-time analytics and anomaly detection

[0364] The server uses the Isolation Forest algorithm to detect anomalies in real time based on the cleansed data, a process that involves analyzing pre-processed data and identifying anomalies.

[0365] Root Cause Analysis and Report Generation

[0366] The server collects and analyzes relevant data to identify the cause of the detected anomaly. Based on the results, it generates a report containing details of the anomaly, its cause, and recommended actions to take. The generated report is saved in PDF or dashboard format and provided to the user.

[0367] Emotion Recognition and Personalized Advice

[0368] The server receives user feedback through the user interface and recognizes emotions using Transformers' natural language processing model. For example, from feedback such as "I'm having trouble with the frequency of errors," it identifies the emotion "stress." It then provides specific, personalized advice based on the recognized emotion. This makes the advice the user receives more appropriate and effective.

[0369] Security and Privacy Protection

[0370] The server implements strong security and privacy protection for all data processing and storage, specifically encrypting data using the Cryptography library and setting strict access control.

[0371] Specific examples

[0372] For example, if an e-commerce site uses the system of the present invention to monitor transaction data, it can receive order data and user behavior data in real time and detect anomalies. If an anomaly occurs, a detailed report is generated and an administrator is notified. Furthermore, emotions are recognized based on the administrator's feedback, and appropriate advice is provided.

[0373] Prompt Sentence Examples

[0374] User feedback: "I've been having a lot of payment errors lately."

[0375] Prompt: "Analyze feedback statements that are likely to cause users anger."

[0376] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0377] Step 1:

[0378] The server receives transaction data in real time from external systems via HTTP requests or APIs. The input is the transaction data obtained from the external system, and the output is the received data that is temporarily stored. This received data consists of various transactions (e.g., product purchase data, payment data, etc.).

[0379] Step 2:

[0380] The server uses the Pandas library to cleanse the incoming data by removing duplicates and unnecessary fields and converting the data into a uniform format. The input is the temporarily stored incoming data, and the output is a cleansed, consistent dataset. This cleansing improves the accuracy of the data for analysis.

[0381] Step 3:

[0382] The server uses the Isolation Forest algorithm to detect anomalies in real time based on the cleansed data. The input is the cleansed dataset, and the output is the identification of anomalous data. Specifically, transaction data is converted into a feature vector and classified as anomalous or normal.

[0383] Step 4:

[0384] The server collects and analyzes related transaction data and system logs to identify the cause of the detected anomaly. The input is the anomaly data and related complementary data, and the output is the analysis result of the anomaly's cause. The server uses machine learning models and statistical methods in this analysis process.

[0385] Step 5:

[0386] The server generates a report that summarizes the details of the anomaly, its cause, and recommended countermeasures. The input is the cause analysis result, and the output is a report in PDF or dashboard format. This report details the specific content of the anomaly, the scope of its impact, and the countermeasures.

[0387] Step 6:

[0388] The server receives user feedback through the user interface and recognizes emotions using Transformers' natural language processing model. The input is the user's feedback text, and the output is the recognized emotion (e.g., anger, sadness, joy, etc.). As a specific example, the server identifies the emotion "stress" from the feedback, "I've been having trouble with a lot of payment errors lately."

[0389] Step 7:

[0390] The server then personalizes and provides advice to users based on the recognized emotions. The input is the recognized user's emotions and the analysis results of transaction data, and the output is a personalized advice message. For example, if stressful emotions are recognized, advice is generated that includes a link to a support guide that explains the solution in detail.

[0391] Step 8:

[0392] The server uses the Cryptography library to encrypt all data during processing and storage, and sets strict access control. All transaction data and analysis data are input, and the output is encrypted and secure data. This protects user security and privacy.

[0393] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0394] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0395] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0396] [Second embodiment]

[0397] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0398] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0399] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0400] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0401] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0402] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0403] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0404] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0405] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0406] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0407] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0408] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0409] The present invention provides a system that automates the process from receiving transaction data to analyzing it, detecting anomalies, analyzing root causes, formulating countermeasures, and protecting security and privacy. Specific embodiments of the system are described below.

[0410] Overall flow

[0411] 1. Data Receipt

[0412] The server receives transaction data in real time from external systems, such as e-commerce site databases and applications. The received data is temporarily stored in data storage.

[0413] 2. Data cleansing

[0414] The server cleanses the data it receives, which includes removing duplicate records, standardizing data formats, and filtering out unnecessary information.

[0415] 3. Real-time analysis

[0416] The server analyzes the cleansed data in real time to detect anomalies, using generative AI models to analyze the data for patterns and trends and spot data that is out of the ordinary.

[0417] 4. Root Cause Analysis

[0418] The server identifies the specific cause of the detected anomaly using information such as the time and location of the anomaly and details of the associated transaction.

[0419] 5. Report Generation

[0420] The server generates a report based on the root cause analysis results and provides it to the user, containing details of the anomaly, its cause, and recommended actions to take.

[0421] 6. Providing advice

[0422] Users can pose questions to the generative AI model about a specific problem, and the server will provide personalized advice on the question, including solutions and troubleshooting tips.

[0423] 7. Security and Privacy Protection

[0424] The servers use strong encryption protocols and enforce access controls to ensure the security of user data when storing and processing data.

[0425] Specific examples

[0426] For example, a case will be described in which an e-commerce site uses the system of the present invention to monitor transaction data.

[0427] 1. Data Receipt

[0428] The server receives order data and user behavior data from the e-commerce site in real time. For example, transaction data is sent when a customer purchases a product.

[0429] 2. Data cleansing

[0430] The server performs cleansing to remove duplicate order data and data with inconsistent formats, thereby improving the accuracy of analysis.

[0431] 3. Real-time analysis

[0432] The server uses generative AI models to analyze the data in real time, detecting, for example, unusual purchase frequencies or unusual patterns in the sales of certain products.

[0433] 4. Root Cause Analysis

[0434] The server identifies a problem with inventory data in a particular product category as the cause of the detected anomaly.

[0435] 5. Report Generation

[0436] The server generates a report detailing the anomaly, its cause, and recommended countermeasures, and provides it to the e-commerce site's system administrator.

[0437] 6. Providing advice

[0438] When a user asks, "I would like to know more details about the abnormal data occurring in a specific product category and what to do about it," the server will recommend, "Recheck the data in your inventory system and correct it if necessary."

[0439] 7. Security and Privacy Protection

[0440] The server encrypts all communications and stored data and implements appropriate access controls to ensure data security.

[0441] In this way, the present invention can significantly reduce the man-hours required by system personnel and improve the quality of the system. By automating specific processes, it becomes possible to quickly and accurately detect and respond to abnormalities.

[0442] The processing flow will be explained below.

[0443] Step 1:

[0444] The server receives transaction data from external systems. Specifically, it retrieves data in real time from e-commerce sites and other systems using HTTP requests or APIs, and temporarily stores it in data storage.

[0445] Step 2:

[0446] The data received by the server is cleansed. Specifically, the data format and structure are checked, unnecessary and duplicate data is deleted, and only the necessary information is retained. This work also includes standardizing the data format and correcting inconsistent data.

[0447] Step 3:

[0448] The server sends the cleansed data to the analysis engine. Specifically, the cleansed data is passed to the generative AI model in real time, and analysis begins.

[0449] Step 4:

[0450] The server uses the generative AI model to analyze the data in real time. Specifically, the analysis engine learns patterns and trends in the data and detects anomalous data or errors that deviate from normal patterns.

[0451] Step 5:

[0452] The server logs any detected anomalies. Specifically, each time an anomaly is detected, details about it (such as time, location, and transaction ID) are added to the anomaly log.

[0453] Step 6:

[0454] The server performs root cause analysis of the anomaly. Specifically, it collects related data (the situation at the time the anomaly occurred and other transaction data) and analyzes the cause to identify the cause of the anomaly.

[0455] Step 7:

[0456] The server generates a report based on the results of the root cause analysis, summarizing the details of the anomaly, its cause, and recommended actions to take, and saves it in PDF or dashboard format.

[0457] Step 8:

[0458] When a user requests a report, the server provides it: the user requests a report through an interface (web browser or application), the server finds the saved report, and sends it to the user.

[0459] Step 9:

[0460] When a user inputs a question about a specific anomaly into the generative AI model, the server analyzes the question and generates appropriate advice. Specifically, it analyzes the question and generates an answer using relevant data and past case studies, and provides it to the user.

[0461] Step 10:

[0462] The server will implement strong security and privacy protections for all data processing and storage, including encrypting data and setting strict access controls to ensure that only a limited number of users can access the data.

[0463] Example 1

[0464] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0465] In conventional transaction data analysis systems, the process from receiving data to detecting anomalies, identifying causes, and proposing countermeasures is often done manually, which is time-consuming and labor-intensive. Security and privacy protections are often inadequate, raising concerns about data safety. Furthermore, it is difficult to detect anomalies in real time or provide specific advice to users regarding specific problems.

[0466] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0467] In this invention, the server includes means for receiving data from an external system in real time, means for cleansing the received data, and means for detecting anomalies using a generative AI model based on the preprocessed data. This enables real-time analysis of transaction data. The server also includes means for identifying specific causes of detected anomalies, means for generating reports based on the anomalies and their causes, means for providing advice to users regarding specific issues based on prompts, means for protecting the security and privacy of user data, means for storing the preprocessed data in storage, and means for implementing access control for the stored data. This enables efficient analysis of transaction data, anomaly detection, cause analysis, proposal of appropriate countermeasures, and secure data management.

[0468] "External System" refers to any other system or database to which transaction data can be transmitted in real time.

[0469] "Data receiving means" refers to a device or program that has the function of receiving transaction data from an external system in real time.

[0470] "Cleansing means" refers to a device or program that has the function of deleting duplicate records from received data, standardizing data formats, and filtering out unnecessary information.

[0471] "Pre-processed data" refers to data after it has been processed by a cleansing tool.

[0472] A "generative AI model" is a model that uses machine learning and deep learning algorithms to analyze patterns and trends in data and detect anomalies.

[0473] "Anomaly detection means" refers to a device or program that has the function of detecting anomalies using a generative AI model based on preprocessed data.

[0474] "Cause identification means" refers to a device or program with analytical capabilities to identify the specific cause of a detected abnormality.

[0475] "Report generation means" refers to a device or program that has the function of generating a report based on anomalies and their causes and providing the information to the user.

[0476] A "prompt" refers to a question that a user inputs into a generative AI model to obtain specific information.

[0477] The "advice providing means" refers to a device or program that has the function of providing personalized advice to a user regarding a specific problem based on a prompt sentence.

[0478] "Security and privacy measures" refers to devices and programs that use strong encryption protocols and access control when storing and processing user data.

[0479] "Data Storage" refers to storage systems and cloud storage for temporary or long-term storage of received and pre-processed data.

[0480] "Access control" refers to authentication and authorization functions for managing access rights to data and preventing unauthorized access.

[0481] This invention is a system that consistently performs processes from receiving transaction data to analyzing it, detecting anomalies, identifying causes, generating reports, providing advice, and protecting security and privacy. This system is equipped with functions for receiving real-time data from external systems, data cleansing, detecting anomalies using a generative AI model, identifying causes, generating reports, and providing advice based on prompts. It also has powerful security and privacy protection functions for storing data and controlling access.

[0482] This system operates mainly around the server. Each function is explained in detail below.

[0483] Data Receipt

[0484] The server receives transaction data in real time from external systems (e.g., e-commerce sites or databases for various applications). The received data is temporarily stored in data storage (e.g., cloud storage), making it easy to access the data in the next processing step.

[0485] Data Cleansing

[0486] The server cleanses the data it receives. This process includes removing duplicate records, standardizing data formats, and filtering out unnecessary information. Data processing libraries such as Python's Pandas and Dask can be used for data cleansing.

[0487] Real-time analytics

[0488] The server uses generative AI models (e.g., TensorFlow or PyTorch) to analyze the cleansed data in real time. The generative AI models analyze the data for patterns and trends and detect anomalies. If an anomaly is detected, the information is passed on to subsequent processes.

[0489] Root Cause Analysis

[0490] The server identifies the specific cause of the anomaly, for example by analyzing the time, location, and related transaction details of the detected anomaly. Root cause analysis can be performed using database queries or log analysis tools.

[0491] Report Generation

[0492] The server generates a report based on the results of the root cause analysis. The report includes details of the anomaly, its cause, and recommended actions. The generated report is saved in PDF or HTML format and provided to the user.

[0493] Providing advice

[0494] The user sends a prompt to the server, such as "I would like to know more about the abnormal data occurring in a specific product category and what to do about it." The server then uses a generative AI model based on the prompt to provide personalized advice. For example, the server might recommend, "Recheck the data in your inventory system and correct it if necessary."

[0495] Security and privacy protection

[0496] The server uses strong encryption protocols (e.g., AES-256) for storing and processing data and applies access controls, including access logging and authentication and authorization mechanisms, to ensure the security of user data.

[0497] Specific examples

[0498] For example, let us consider a case where an e-commerce site uses the system of the present invention to monitor transaction data. Order data and user behavior data from the e-commerce site are sent to a server in real time, which receives and stores them in data storage. After data cleansing and anomalies are detected using a generative AI model, a root cause analysis is performed to generate a report summarizing the causes of the anomaly and countermeasures, which is then provided to the user. When the user sends a prompt requesting advice, the server uses the generative AI model to provide appropriate advice.

[0499] In this way, the system enables efficient analysis of transaction data, anomaly detection, cause analysis, appropriate countermeasure proposals, and secure data management.

[0500] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0501] Step 1: Data Reception

[0502] The server receives transaction data from external systems in real time. Input data is order data and user behavior data sent from the database of the e-commerce site or application. The server temporarily stores this data in data storage, allowing the data to be used efficiently in the next step.

[0503] Step 2: Data cleansing

[0504] The server cleanses the temporarily stored transaction data. The input data is the raw data received in the previous step. Specific operations include deleting duplicate records, standardizing data formats, and filtering out unnecessary information. For example, these operations are performed using the Python Pandas library. The output data is cleansed, consistent data.

[0505] Step 3: Real-time analysis

[0506] The server applies a generative AI model to the cleansed data to detect anomalies in real time. The input data is the data cleansed in step 2. The server uses a generative AI model (e.g., TensorFlow or PyTorch) to analyze the data for patterns and trends and detect anomalies. The output data is the anomaly detection results, which include a list of anomalous patterns and values.

[0507] Step 4: Root Cause Analysis

[0508] The server identifies the specific cause of the detected anomaly. The input data is the anomaly detection result obtained in step 3. The server analyzes the cause based on the time of the anomaly occurrence, location, and detailed information about the related transaction. For example, it extracts detailed information from the database using SQL queries or log analysis tools. The output data is the cause of the anomaly and its details.

[0509] Step 5: Generate a report

[0510] The server generates a report based on the results of the root cause analysis. The input data are the anomaly causes and their details obtained in step 4. The report contains details of the anomaly, its cause, and recommended actions. Specifically, the report is generated as a PDF or HTML file and saved on the server. The output data is the generated report, which is ready to be provided to the user.

[0511] Step 6: Providing advice

[0512] The user poses a question to the server based on a prompt about a specific problem. The input data is the prompt sent by the user (e.g., "I would like to know more about the abnormal data occurring in a specific product category and what to do about it"). The server uses a generative AI model to generate personalized advice corresponding to the prompt. The output data is the advice provided to the user. For example, it might recommend, "Recheck the data in your inventory system and correct it if necessary."

[0513] Step 7: Protecting security and privacy

[0514] The server uses a strong encryption protocol (e.g., AES-256) to store and process data and implements access control. Input data is all data stored within the server. The server records access logs and sets authorization to ensure the safety of user data. Output data is encrypted and secure. This prevents unauthorized access or leakage of data.

[0515] (Application example 1)

[0516] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0517] Conventional technologies require a lot of manual work to receive and analyze transaction data, detect anomalies, identify the cause, and develop countermeasures, which can easily lead to human error. Furthermore, there was no system in place to respond quickly and appropriately after an anomaly was detected, resulting in insufficient security and privacy protection for user data. Therefore, there was a need for a system that could detect anomalies in real time and provide appropriate countermeasures to improve the safety of user data.

[0518] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0519] In this invention, the server includes means for receiving data from an external system in real time, means for cleansing the received data, means for detecting anomalies based on the preprocessed data, means for identifying the cause of the detected anomaly, means for generating a report based on the anomaly and its cause, means for providing advice to the user regarding the specific problem, means for protecting the security and privacy of the user data, means for linking with a smart device to notify the user of the generated report, means for generating a prompt message and providing advice to the user based on the anomaly detection result, and means for ensuring the portability and security of data using an encryption protocol. This enables rapid and accurate anomaly detection and provision of appropriate countermeasures, and further enhances the security of user data.

[0520] "External system" refers to other computer systems or networks that send and receive data.

[0521] "Means for receiving data" refers to a hardware or software part that has the function of obtaining data from an external system in real time.

[0522] "Means for cleansing data" refers to a function for purifying received data and eliminating duplicate data and unnecessary information.

[0523] "Means for detecting anomalies" refers to the part that has the functionality to identify unusual patterns or values ​​based on preprocessed data.

[0524] "Means for identifying the cause" refers to the function for analyzing and identifying the reason why an abnormality occurred.

[0525] "Means for generating reports" refers to a function for creating a report summarizing details and causes of anomalies and recommended actions to be taken.

[0526] "Means for providing advice" refers to a function that provides appropriate advice to users on specific issues.

[0527] "Security and privacy measures" refers to features designed to protect user data from unauthorized access and leaks.

[0528] "Means of collaboration with smart devices to notify users of generated reports" refers to the function for sending reports to devices such as users' smartphones and tablets.

[0529] "Means for generating prompt sentences and providing advice" refers to the function for generating appropriate responses to questions from users based on the results of anomaly detection.

[0530] "Means for ensuring data portability and security using cryptographic protocols" refers to functions that use strong cryptographic technology to ensure the security of data during transport and storage.

[0531] This invention is a system that automates the process from receiving transaction data to analyzing it, detecting anomalies, analyzing root causes, formulating countermeasures, and protecting security and privacy. Specific embodiments of this system are described below.

[0532] System Configuration

[0533] The system of the present invention includes a server, an external system, and a smart device. The server uses a cloud service such as AWS or GCP, and uses MySQL or MongoDB as the database. The generative AI model uses TensorFlow or PyTorch, and the data is encrypted using the AES encryption protocol.

[0534] Program processing

[0535] 1. Data Receipt

[0536] The server receives real-time transaction data from external systems, such as e-commerce sites and financial institutions, and temporarily stores the data in data storage.

[0537] 2. Data cleansing

[0538] The server cleanses the data it receives, which includes deleting duplicate data, removing unnecessary information, and standardizing data formats.

[0539] 3. Real-time analysis

[0540] The server analyzes the cleansed data in real time to detect anomalies, using generative AI models to analyze data patterns and trends and identify abnormal data.

[0541] 4. Root Cause Analysis

[0542] The server identifies the specific cause of the detected anomaly, analyzing it based on information such as time, location, and related transaction details.

[0543] 5. Report Generation

[0544] The server generates a report summarizing details of the anomaly, its cause, and recommended countermeasures, and this report is sent to smart devices such as smartphones and tablets.

[0545] 6. Providing advice

[0546] Users can pose questions to the generative AI model about a specific problem, and the server will provide personalized advice on that question, including solutions and troubleshooting tips.

[0547] 7. Security and Privacy Protection

[0548] The servers use strong encryption protocols for all data storage and processing and enforce access controls to ensure the security of user data.

[0549] Specific examples

[0550] For example, when an online shopping site uses the system of the present invention to monitor transaction data, the system operates as follows.

[0551] 1. Data Receipt

[0552] The server receives order data and user behavior data from an online shopping site in real time. For example, transaction data is sent when a customer purchases a product.

[0553] 2. Data cleansing

[0554] The server performs cleansing to remove duplicate order data and data with inconsistent formats, thereby improving the accuracy of the analysis.

[0555] 3. Real-time analysis

[0556] The server uses generative AI models to analyze the data in real time, detecting, for example, unusual purchase frequencies or unusual patterns in the sales of certain products.

[0557] 4. Root Cause Analysis

[0558] The server identifies a problem with inventory data in a particular product category as the cause of the detected anomaly.

[0559] 5. Report Generation

[0560] The server generates a report summarizing details of the anomaly, its cause, and recommended countermeasures, and notifies the system administrator of the online shopping site.

[0561] 6. Providing advice

[0562] When a user asks, "I'd like more details and solutions about abnormal data occurring in a specific product category," the server recommends, "Recheck the data in your inventory system and correct it if necessary."

[0563] Prompt Sentence Examples

[0564] Question: "Is there anything unusual about my latest transaction?"

[0565] Q: "What unusual activity occurred in trading in April?"

[0566] As described above, the system of the present invention can quickly and accurately detect anomalies and provide appropriate countermeasures, thereby increasing the security of user data.

[0567] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0568] Step 1:

[0569] The server receives transaction data from external systems in real time. The input here is various transaction data sent from the external systems, and the output is transaction data temporarily stored in data storage.

[0570] Step 2:

[0571] The server cleanses the received data by deleting duplicate data, removing unnecessary information, and standardizing data formats. The input here is the transaction data saved in step 1, and the output is the cleansed transaction data.

[0572] Step 3:

[0573] The server uses a generative AI model to perform real-time analysis of the cleansed data and detect anomalies. Specifically, it analyzes data patterns and trends to detect anomalous data. The input here is the cleansed transaction data obtained in step 2, and the output is the detected anomalous data.

[0574] Step 4:

[0575] The server identifies the specific cause of the detected anomaly by analyzing the time, location, and details of the related transaction to identify the cause of the anomaly. The input here is the anomaly data detected in step 3, and the output is information about the cause of the identified anomaly.

[0576] Step 5:

[0577] The server generates a report based on the anomaly and its cause and notifies the smart device. The report contains details of the anomaly, its cause, and recommended countermeasures. The input here is the anomaly cause information identified in step 4, and the output is the generated report.

[0578] Step 6:

[0579] When a user sends a question about a specific problem to the server as a prompt, the server uses a generative AI model to provide personalized advice. Specifically, the server generates an appropriate response to the user's question. The input here is the prompt from the user, and the output is the generated advice.

[0580] Step 7:

[0581] The server uses the AES encryption protocol to store and process user data and enforces access control to protect security and privacy. Specifically, it encrypts and decrypts data and manages access rights. The input here is the data to be stored and the access request, and the output is the encrypted data and the result of the access control.

[0582] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0583] The present invention is a system that provides users with a better interactive experience by combining the reception and analysis of transaction data, anomaly detection, root cause analysis, countermeasure planning, and security and privacy protection, as well as an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0584] Overall flow

[0585] 1. Data Receipt

[0586] The server receives transaction data in real time from external systems. Specifically, it retrieves data from databases such as e-commerce sites via HTTP requests or APIs and temporarily stores it in data storage.

[0587] 2. Data cleansing

[0588] The server cleanses the data it receives. Specifically, it checks the data format and structure, and deletes unnecessary and duplicated information. It also standardizes the data format of necessary information to improve the accuracy of analysis.

[0589] 3. Real-time analysis

[0590] The server then uses generative AI models to analyze the cleansed data in real time, detecting anomalous data or errors that deviate from normal patterns.

[0591] 4. Root Cause Analysis

[0592] To identify the cause of the detected anomaly, the server collects and analyzes relevant data (such as the circumstances surrounding the anomaly and other transaction data).

[0593] 5. Report Generation

[0594] The server generates a detailed report based on the root cause analysis results, including details of the anomaly, its cause, and recommended actions to take. The generated report is saved in PDF or dashboard format and provided to the user.

[0595] 6. Emotion recognition

[0596] The emotion engine analyzes the text entered by the user through the user interface and recognizes the emotion. The emotion engine uses natural language processing to identify emotions (joy, anger, sadness, surprise, etc.) from the user's input text.

[0597] 7. Personalized advice

[0598] The server takes into account the user's emotions and personalizes the advice it provides. For example, if a user types "I'm having trouble with too many errors," the emotion engine will recognize "stress" and provide advice with corresponding support and encouraging messages.

[0599] 8. Security and Privacy Protection

[0600] The server will implement strong security and privacy protection for all data processing and storage. Specifically, data will be encrypted and strict access control will be set to ensure the safety of user data.

[0601] Specific examples

[0602] For example, a case will be described in which an e-commerce site uses the system of the present invention to monitor transaction data.

[0603] 1. Data Receipt

[0604] The server receives order data and user behavior data from the e-commerce site in real time. The order data includes information such as product name, price, and purchase date and time.

[0605] 2. Data cleansing

[0606] The server cleanses the data it receives, removes duplicate order data, and standardizes the data format, thereby improving the efficiency and accuracy of the analysis process.

[0607] 3. Real-time analysis

[0608] The server uses generative AI models to analyze data in real time, for example to detect unusually high purchase frequency of a particular product or an abnormal number of transactions.

[0609] 4. Root Cause Analysis

[0610] The server examines the relevant transaction data and system logs to determine the cause of the identified anomaly, and determines that the cause is, for example, a data discrepancy in an inventory system.

[0611] 5. Report Generation

[0612] The server generates a report detailing the anomaly, its cause, and recommended actions to take, which is output in PDF format and sent to the e-commerce site's system administrator.

[0613] 6. Emotion recognition

[0614] The emotion engine analyzes feedback and inquiries from system administrators to recognize their emotions. For example, it can identify the emotion of stress from feedback such as "the frequency of errors is too high."

[0615] 7. Personalized advice

[0616] The server will provide specific advice based on the recognized emotion, for example, providing a support message along with detailed guidance on "how to improve your workflow to resolve this issue."

[0617] 8. Security and Privacy Protection

[0618] The servers encrypt all communications and data storage and implement strict access controls to prevent unauthorized access to user data and confidential information.

[0619] In this way, the present invention reduces the burden on system personnel and improves the quality of the system and the user experience. By combining it with an emotion engine, responses to users become more flexible and effective.

[0620] The processing flow will be explained below.

[0621] Step 1:

[0622] The server receives transaction data from external systems. Specifically, the data is obtained in real time through HTTP requests or API calls and temporarily stored in data storage. This process is performed by setting up a listener for receiving data, and when data arrives, the listener generates an event and receives the data stream.

[0623] Step 2:

[0624] The server cleanses the data it receives. Specifically, it checks the data format and structure, removes unnecessary information and duplicate records, standardizes the data format, and corrects inconsistent data, preparing the cleansed data for analysis.

[0625] Step 3:

[0626] The server sends the cleansed data to the analytics engine, which begins real-time analysis by feeding the data into a generative AI model and running algorithms to detect anomalous data or errors that deviate from normal patterns.

[0627] Step 4:

[0628] The server logs any detected anomalies, adding details such as the time and location of the anomaly and the transaction ID to the anomaly log for future reference by administrators.

[0629] Step 5:

[0630] The server performs root cause analysis of the anomaly. Specifically, it collects and analyzes the circumstances surrounding the anomaly and related transaction data to identify the cause of the anomaly. For example, it identifies unusual purchasing patterns in a particular product category or data discrepancies in an inventory system.

[0631] Step 6:

[0632] The server generates a detailed report based on the results of the root cause analysis, summarizing the details of the anomaly, its cause, and recommended actions to take, and saves it in PDF or dashboard format.

[0633] Step 7:

[0634] When a user requests a report, the server provides it: the user requests a report through an interface (web browser or application), the server finds the saved report, and sends it to the user.

[0635] Step 8:

[0636] The emotion engine analyzes the text entered by the user through the user interface and recognizes the emotion. Specifically, the emotion engine uses natural language processing to identify emotions (joy, anger, sadness, surprise, etc.) from the user's text input and records them in a database.

[0637] Step 9:

[0638] The server personalizes the advice it provides based on the results of emotion recognition. Specifically, it takes the user's emotions into account and generates solutions with appropriate support and encouraging messages. For example, if the user enters "I'm having trouble with too many errors," the emotion engine will recognize "stress" and provide warm-hearted advice accordingly.

[0639] Step 10:

[0640] The servers implement strong security and privacy protection for all data processing and storage. Specifically, data is encrypted and strict access control is set up to ensure the safety of user data. A monitoring system is also in place to respond immediately to any signs of unauthorized access.

[0641] Example 2

[0642] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0643] While conventional data analysis systems receive, cleanse, analyze, and detect anomalies in real time, they lack clear cause analysis of detected anomalies and provide countermeasures that take user sentiment into account. In terms of security and privacy protection, the safety of user data is also not sufficiently ensured, which is a problem.

[0644] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving data from an external system in real time, a means for cleansing the received data, a means for detecting anomalies based on the preprocessed data, a means for identifying the cause of the detected anomaly, a means for generating a report based on the anomaly and its cause, a means for recognizing emotions from a user's input, a means for providing personalized advice based on the recognized emotions, and a means for protecting the security and privacy of user data. This makes it possible to detect anomalies and analyze their causes, present countermeasures that take user emotions into consideration, and ensure the safety of user data.

[0645] "Means of receiving data in real time from external systems" refers to the processes and technologies for obtaining data in real time through external databases or application program interfaces (APIs).

[0646] "Means of cleansing received data" refers to the process of removing unnecessary information from the data and standardizing the data structure in order to improve the accuracy and consistency of the data obtained.

[0647] "Anomaly detection methods based on pre-processed data" refers to algorithms and techniques that use cleansed data to analyze the data for anomalous patterns or deviations.

[0648] "Means for identifying the cause of a detected abnormality" refers to the technology and process for conducting a detailed analysis of the background and factors that caused the abnormality and identifying them.

[0649] "Means for generating reports based on anomalies and their causes" refers to technologies and processes that organize information about detected anomalies and their causes, and automatically generate reports that can be presented to users in an easy-to-understand manner.

[0650] "Means for recognizing emotions from user input" refers to natural language processing techniques that analyze the text and feedback entered by users into the system and identify the emotions contained therein.

[0651] "Means for providing personalized advice based on perceived emotions" refers to algorithms or technologies that take into account a user's emotional state to provide advice or support messages that are appropriate for that user.

[0652] "Measures to protect the security and privacy of user data" refers to encryption technologies and access control policies to protect users' personal information and prevent unauthorized access or information leaks.

[0653] The present invention is a system that provides users with a better interactive experience by combining the reception and analysis of transaction data, anomaly detection, root cause analysis, countermeasure planning, and security and privacy protection, as well as an emotion engine that recognizes user emotions. A detailed embodiment of this system will now be described.

[0654] Hardware and Software Configuration

[0655] The server plays the central role in the system. Data is received in real time from external systems and stored on the server. This data reception process uses HTTP requests and APIs. The data is stored in, for example, an S3 bucket on Amazon Web Services (AWS) or Google Cloud Storage.

[0656] Data cleansing is performed by a program installed on a server, written in a programming language such as Python or Java, that performs, among other things, data normalization and the elimination of duplicate data.

[0657] Real-time analysis for anomaly detection uses generative AI models, trained using deep learning frameworks such as TensorFlow and PyTorch, which are then analyzed by a server in real time to detect unusual data patterns and errors.

[0658] The server also handles root cause analysis, which involves collecting relevant data and using statistical methods and AI models to identify the cause of an anomaly.

[0659] The generated reports can be provided to the user in PDF format or via a web-based dashboard, which can be emailed or uploaded to a dashboard.

[0660] The emotion engine is responsible for recognizing user emotions. This engine uses natural language processing (NLP) technology to extract emotions from the text entered by the user. NLP tools such as Google Cloud Natural Language API and IBM Watson are used for this.

[0661] Personalized advice based on emotion recognition is generated by the server, which implements an algorithm that takes into account the recognized emotions and provides appropriate advice and support messages to the user.

[0662] Security and privacy are ensured through data encryption and strict access control, using SSL / TLS for communication encryption and AWS IAM policies for access control.

[0663] Specific examples

[0664] For example, consider the case where an e-commerce site uses the system of the present invention to monitor transaction data.

[0665] 1. Data Receipt

[0666] The server receives order data and user behavior data from the e-commerce site in real time. The order data includes information such as product name, price, and purchase date and time.

[0667] 2. Data cleansing

[0668] The server cleanses the data it receives, removes duplicate order data, and standardizes the data format, thereby improving the efficiency and accuracy of the analysis process.

[0669] 3. Real-time analysis

[0670] The server uses generative AI models to analyze the data in real time, for example to detect unusually high purchase frequency of a particular product or an unusual number of transactions.

[0671] 4. Root Cause Analysis

[0672] The server examines the relevant transaction data and system logs to determine the cause of the identified anomaly, and determines that the cause is, for example, a data discrepancy in an inventory system.

[0673] 5. Report Generation

[0674] The server generates a report summarizing the details of the anomaly, its cause, and recommended countermeasures, which is output in PDF format and sent to the e-commerce site's system administrator.

[0675] 6. Emotion recognition

[0676] The emotion engine analyzes feedback and inquiries from system administrators to recognize their emotions. For example, it can identify the emotion of stress from feedback such as "the frequency of errors is too high."

[0677] 7. Personalized advice

[0678] The server will then provide specific advice based on the perceived emotion, for example providing a support message along with detailed guidance on "how to improve your workflow to resolve this issue."

[0679] 8. Security and Privacy Protection

[0680] The servers encrypt all communications and data storage and implement strict access controls to prevent unauthorized access to user data and confidential information.

[0681] Prompt Sentence Examples

[0682] Can you please elaborate on the anomaly detection algorithms for transaction data in this system, specifically the generative AI model used and its training data?

[0683] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0684] Step 1: Data Reception

[0685] The server receives transaction data from external systems. Inputs include HTTP requests from e-commerce sites, order data obtained via APIs, and user behavior data. Specifically, the server uses Amazon Web Services (AWS) or Google Cloud Platform (GCP) to store the data in its own storage in real time.

[0686] Input: Transaction data from external systems (e.g., order data, user behavior data)

[0687] Output: Temporarily stored transaction data

[0688] Step 2: Data cleansing

[0689] The server cleanses the data it receives. It checks the format and structure of the data and removes unnecessary and duplicated data. This is done using programming languages ​​such as Python and Java, applying regular expressions and data conversion scripts. If some data is missing, it also performs missing value imputation.

[0690] Input: Temporarily stored transaction data

[0691] Output: Cleansed data

[0692] Step 3: Real-time analysis

[0693] The server performs real-time analysis on the cleansed data using generative AI models implemented using frameworks such as TensorFlow and PyTorch. The server detects abnormal data patterns and errors and generates alerts and notifications.

[0694] Input: Cleansed data

[0695] Output: Anomaly detection results and notifications

[0696] Step 4: Root Cause Analysis

[0697] The server performs a detailed analysis of the cause of the detected anomaly. It collects relevant data (such as the circumstances surrounding the anomaly and other transaction data) and uses statistical techniques and additional AI models to identify the cause. Specifically, it analyzes whether the anomalous transaction is linked to a specific promotion code or system log.

[0698] Input: Anomaly detection results and associated data

[0699] Output: Cause identification and details

[0700] Step 5: Generate a report

[0701] The server generates a detailed report based on the results of the root cause analysis. The report includes details of the anomaly, its cause, and recommended actions to take. The generated report is saved in PDF or web dashboard format and provided to the user. Specifically, the generated PDF can be sent by email or uploaded to the dashboard.

[0702] Input: Cause identification and details

[0703] Output: Detailed report

[0704] Step 6: Emotion Recognition

[0705] The emotion engine analyzes the text entered by the user through the user interface and recognizes the emotion. It uses Google Cloud Natural Language API and IBM Watson to extract emotions (joy, anger, sadness, surprise, etc.) from the text.

[0706] Input: User-entered text

[0707] Output: Recognized emotion

[0708] Step 7: Personalized advice

[0709] The server considers the user's emotions and personalizes the advice it provides. For example, if a user types "I'm having trouble with too many errors," the emotion engine will recognize "stress" and generate appropriate advice or encouraging messages.

[0710] Input: Recognized emotion

[0711] Output: Personalized advice

[0712] Step 8: Protecting security and privacy

[0713] The server implements strong security and privacy protection for all data processing and storage. Specifically, SSL / TLS is used for data encryption and strict access control is set to ensure the safety of user data. This is achieved using AWS IAM policies, etc.

[0714] Input: All user data

[0715] Output: Securely stored and processed user data

[0716] (Application example 2)

[0717] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0718] While traditional transaction monitoring systems are equipped with basic functions such as anomaly detection, cause identification, and user advice provision, they lack the ability to recognize user emotions and provide personalized advice based on those emotions. This makes it difficult to improve user experience or quickly resolve problems. Furthermore, robust measures are required from the perspective of security and privacy protection, but these measures are often not adequately provided.

[0719] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving data from an external system in real time, means for cleansing the received data, means for detecting anomalies based on the preprocessed data, means for identifying the cause of the detected anomaly, means for generating a report based on the anomaly and its cause, means for providing advice to the user regarding a specific problem, means for analyzing user feedback via a user interface and recognizing emotions, means for personalizing advice based on the recognized emotions, and means for protecting the security and privacy of user data. This makes it possible to provide advice that takes user emotions into consideration and to enhance security and privacy protection.

[0720] An "external system" refers to an external information processing device such as a server, database, or application that provides transaction data in real time.

[0721] "Means of receiving data" refers to a mechanism that uses an interface or protocol, such as an HTTP request or API, to obtain data from an external system.

[0722] "Data cleansing methods" refers to the process of removing unnecessary information and redundant data from received data and preparing the necessary data in an appropriate format.

[0723] "Means for detecting anomalies" refers to algorithms or systems that analyze and identify anomalous data that deviates from normal patterns in pre-processed data.

[0724] "Means for identifying the cause" refers to the mechanisms and methods for analyzing and identifying the factors behind the detected abnormality.

[0725] "Means for generating reports" refers to the process of creating and providing a report to the user that includes details of the anomaly, its cause, and recommended actions to take.

[0726] "Advice methods" refer to methods that provide users with appropriate solutions or guidance for specific problems.

[0727] "User interface" refers to the screens and input devices that allow a user to interact with a system, providing feedback and receiving information.

[0728] "Emotion recognition means" refers to natural language processing techniques and models for analyzing and identifying emotions from user feedback and input text.

[0729] "Means of personalizing advice" refers to the process of providing relevant and tailored advice based on perceived user sentiment.

[0730] "Security and privacy measures" refers to encryption technologies and access control mechanisms to ensure the security of user data and protect privacy.

[0731] This invention includes a system that provides real-time monitoring of transaction data in electronic payment services, anomaly detection, cause analysis, emotion recognition, and personalized advice. The overall flow of the system and the hardware and software used are described below.

[0732] Hardware and Software

[0733] The server receives transaction data and performs analysis and anomaly detection. The specific software and hardware used includes Python, scikit-learn, TensorFlow, Transformers, and Cryptography libraries.

[0734] Data Receipt

[0735] The server receives transaction data in real time from external systems. Specifically, it retrieves data from external databases and applications via HTTP requests or APIs and temporarily stores it in data storage.

[0736] Data Cleansing

[0737] The server cleanses the received data. Using Pandas, it checks the data format and structure, and removes unnecessary and duplicated data. It also standardizes the data format of necessary information to improve the accuracy of analysis.

[0738] Real-time analytics and anomaly detection

[0739] The server uses the Isolation Forest algorithm to detect anomalies in real time based on the cleansed data, a process that involves analyzing pre-processed data and identifying anomalies.

[0740] Root Cause Analysis and Report Generation

[0741] The server collects and analyzes relevant data to identify the cause of the detected anomaly. Based on the results, it generates a report containing details of the anomaly, its cause, and recommended actions to take. The generated report is saved in PDF or dashboard format and provided to the user.

[0742] Emotion Recognition and Personalized Advice

[0743] The server receives user feedback through the user interface and recognizes emotions using Transformers' natural language processing model. For example, from feedback such as "I'm having trouble with the frequency of errors," it identifies the emotion "stress." It then provides specific, personalized advice based on the recognized emotion. This makes the advice the user receives more appropriate and effective.

[0744] Security and Privacy Protection

[0745] The server implements strong security and privacy protection for all data processing and storage, specifically encrypting data using the Cryptography library and setting strict access control.

[0746] Specific examples

[0747] For example, if an e-commerce site uses the system of the present invention to monitor transaction data, it can receive order data and user behavior data in real time and detect anomalies. If an anomaly occurs, a detailed report is generated and an administrator is notified. Furthermore, emotions are recognized based on the administrator's feedback, and appropriate advice is provided.

[0748] Prompt Sentence Examples

[0749] User feedback: "I've been having a lot of payment errors lately."

[0750] Prompt: "Analyze feedback statements that are likely to cause users anger."

[0751] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0752] Step 1:

[0753] The server receives transaction data in real time from external systems via HTTP requests or APIs. The input is the transaction data obtained from the external system, and the output is the received data that is temporarily stored. This received data consists of various transactions (e.g., product purchase data, payment data, etc.).

[0754] Step 2:

[0755] The server uses the Pandas library to cleanse the incoming data by removing duplicates and unnecessary fields and converting the data into a uniform format. The input is the temporarily stored incoming data, and the output is a cleansed, consistent dataset. This cleansing improves the accuracy of the data for analysis.

[0756] Step 3:

[0757] The server uses the Isolation Forest algorithm to detect anomalies in real time based on the cleansed data. The input is the cleansed dataset, and the output is the identification of anomalous data. Specifically, transaction data is converted into a feature vector and classified as anomalous or normal.

[0758] Step 4:

[0759] The server collects and analyzes related transaction data and system logs to identify the cause of the detected anomaly. The input is the anomaly data and related complementary data, and the output is the analysis result of the anomaly's cause. The server uses machine learning models and statistical methods in this analysis process.

[0760] Step 5:

[0761] The server generates a report that summarizes the details of the anomaly, its cause, and recommended countermeasures. The input is the cause analysis result, and the output is a report in PDF or dashboard format. This report details the specific content of the anomaly, the scope of its impact, and the countermeasures.

[0762] Step 6:

[0763] The server receives user feedback through the user interface and recognizes emotions using Transformers' natural language processing model. The input is the user's feedback text, and the output is the recognized emotion (e.g., anger, sadness, joy, etc.). As a specific example, the server identifies the emotion "stress" from the feedback, "I've been having trouble with a lot of payment errors lately."

[0764] Step 7:

[0765] The server then personalizes and provides advice to users based on the recognized emotions. The input is the recognized user's emotions and the analysis results of transaction data, and the output is a personalized advice message. For example, if stressful emotions are recognized, advice is generated that includes a link to a support guide that explains the solution in detail.

[0766] Step 8:

[0767] The server uses the Cryptography library to encrypt all data during processing and storage, and sets strict access control. All transaction data and analysis data are input, and the output is encrypted and secure data. This protects user security and privacy.

[0768] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0769] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0770] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0771] [Third embodiment]

[0772] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0773] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0774] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0775] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0776] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0777] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0778] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0779] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0780] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0781] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0782] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0783] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0784] The present invention provides a system that automates the process from receiving transaction data to analyzing it, detecting anomalies, analyzing root causes, formulating countermeasures, and protecting security and privacy. Specific embodiments of the system are described below.

[0785] Overall flow

[0786] 1. Data Receipt

[0787] The server receives transaction data in real time from external systems, such as e-commerce site databases and applications. The received data is temporarily stored in data storage.

[0788] 2. Data cleansing

[0789] The server cleanses the data it receives, which includes removing duplicate records, standardizing data formats, and filtering out unnecessary information.

[0790] 3. Real-time analysis

[0791] The server analyzes the cleansed data in real time to detect anomalies, using generative AI models to analyze the data for patterns and trends and spot data that is out of the ordinary.

[0792] 4. Root Cause Analysis

[0793] The server identifies the specific cause of the detected anomaly using information such as the time and location of the anomaly and details of the associated transaction.

[0794] 5. Report Generation

[0795] The server generates a report based on the root cause analysis results and provides it to the user, containing details of the anomaly, its cause, and recommended actions to take.

[0796] 6. Providing advice

[0797] Users can pose questions to the generative AI model about a specific problem, and the server will provide personalized advice on the question, including solutions and troubleshooting tips.

[0798] 7. Security and Privacy Protection

[0799] The servers use strong encryption protocols and enforce access controls to ensure the security of user data when storing and processing data.

[0800] Specific examples

[0801] For example, a case will be described in which an e-commerce site uses the system of the present invention to monitor transaction data.

[0802] 1. Data Receipt

[0803] The server receives order data and user behavior data from the e-commerce site in real time. For example, transaction data is sent when a customer purchases a product.

[0804] 2. Data cleansing

[0805] The server performs cleansing to remove duplicate order data and data with inconsistent formats, thereby improving the accuracy of analysis.

[0806] 3. Real-time analysis

[0807] The server uses generative AI models to analyze the data in real time, detecting, for example, unusual purchase frequencies or unusual patterns in the sales of certain products.

[0808] 4. Root Cause Analysis

[0809] The server identifies a problem with inventory data in a particular product category as the cause of the detected anomaly.

[0810] 5. Report Generation

[0811] The server generates a report detailing the anomaly, its cause, and recommended countermeasures, and provides it to the e-commerce site's system administrator.

[0812] 6. Providing advice

[0813] When a user asks, "I would like to know more details about the abnormal data occurring in a specific product category and what to do about it," the server will recommend, "Recheck the data in your inventory system and correct it if necessary."

[0814] 7. Security and Privacy Protection

[0815] The server encrypts all communications and stored data and implements appropriate access controls to ensure data security.

[0816] In this way, the present invention can significantly reduce the man-hours required by system personnel and improve the quality of the system. By automating specific processes, it becomes possible to quickly and accurately detect and respond to abnormalities.

[0817] The processing flow will be explained below.

[0818] Step 1:

[0819] The server receives transaction data from external systems. Specifically, it retrieves data in real time from e-commerce sites and other systems using HTTP requests or APIs, and temporarily stores it in data storage.

[0820] Step 2:

[0821] The data received by the server is cleansed. Specifically, the data format and structure are checked, unnecessary and duplicate data is deleted, and only the necessary information is retained. This work also includes standardizing the data format and correcting inconsistent data.

[0822] Step 3:

[0823] The server sends the cleansed data to the analysis engine. Specifically, the cleansed data is passed to the generative AI model in real time, and analysis begins.

[0824] Step 4:

[0825] The server uses the generative AI model to analyze the data in real time. Specifically, the analysis engine learns patterns and trends in the data and detects anomalous data or errors that deviate from normal patterns.

[0826] Step 5:

[0827] The server logs any detected anomalies. Specifically, each time an anomaly is detected, details about it (such as time, location, and transaction ID) are added to the anomaly log.

[0828] Step 6:

[0829] The server performs root cause analysis of the anomaly. Specifically, it collects related data (the situation at the time the anomaly occurred and other transaction data) and analyzes the cause to identify the cause of the anomaly.

[0830] Step 7:

[0831] The server generates a report based on the results of the root cause analysis, summarizing the details of the anomaly, its cause, and recommended actions to take, and saves it in PDF or dashboard format.

[0832] Step 8:

[0833] When a user requests a report, the server provides it: the user requests a report through an interface (web browser or application), the server finds the saved report, and sends it to the user.

[0834] Step 9:

[0835] When a user inputs a question about a specific anomaly into the generative AI model, the server analyzes the question and generates appropriate advice. Specifically, it analyzes the question and generates an answer using relevant data and past case studies, and provides it to the user.

[0836] Step 10:

[0837] The server will implement strong security and privacy protections for all data processing and storage, including encrypting data and setting strict access controls to ensure that only a limited number of users can access the data.

[0838] Example 1

[0839] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0840] In conventional transaction data analysis systems, the process from receiving data to detecting anomalies, identifying causes, and proposing countermeasures is often done manually, which is time-consuming and labor-intensive. Security and privacy protections are often inadequate, raising concerns about data safety. Furthermore, it is difficult to detect anomalies in real time or provide specific advice to users regarding specific problems.

[0841] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0842] In this invention, the server includes means for receiving data from an external system in real time, means for cleansing the received data, and means for detecting anomalies using a generative AI model based on the preprocessed data. This enables real-time analysis of transaction data. The server also includes means for identifying specific causes of detected anomalies, means for generating reports based on the anomalies and their causes, means for providing advice to users regarding specific issues based on prompts, means for protecting the security and privacy of user data, means for storing the preprocessed data in storage, and means for implementing access control for the stored data. This enables efficient analysis of transaction data, anomaly detection, cause analysis, proposal of appropriate countermeasures, and secure data management.

[0843] "External System" refers to any other system or database to which transaction data can be transmitted in real time.

[0844] "Data receiving means" refers to a device or program that has the function of receiving transaction data from an external system in real time.

[0845] "Cleansing means" refers to a device or program that has the function of deleting duplicate records from received data, standardizing data formats, and filtering out unnecessary information.

[0846] "Pre-processed data" refers to data after it has been processed by a cleansing tool.

[0847] A "generative AI model" is a model that uses machine learning and deep learning algorithms to analyze patterns and trends in data and detect anomalies.

[0848] "Anomaly detection means" refers to a device or program that has the function of detecting anomalies using a generative AI model based on preprocessed data.

[0849] "Cause identification means" refers to a device or program with analytical capabilities to identify the specific cause of a detected abnormality.

[0850] "Report generation means" refers to a device or program that has the function of generating a report based on anomalies and their causes and providing the information to the user.

[0851] A "prompt" refers to a question that a user inputs into a generative AI model to obtain specific information.

[0852] The "advice providing means" refers to a device or program that has the function of providing personalized advice to a user regarding a specific problem based on a prompt sentence.

[0853] "Security and privacy measures" refers to devices and programs that use strong encryption protocols and access control when storing and processing user data.

[0854] "Data Storage" refers to storage systems and cloud storage for temporary or long-term storage of received and pre-processed data.

[0855] "Access control" refers to authentication and authorization functions for managing access rights to data and preventing unauthorized access.

[0856] This invention is a system that consistently performs processes from receiving transaction data to analyzing it, detecting anomalies, identifying causes, generating reports, providing advice, and protecting security and privacy. This system is equipped with functions for receiving real-time data from external systems, data cleansing, detecting anomalies using a generative AI model, identifying causes, generating reports, and providing advice based on prompts. It also has powerful security and privacy protection functions for storing data and controlling access.

[0857] This system operates mainly around the server. Each function is explained in detail below.

[0858] Data Receipt

[0859] The server receives transaction data in real time from external systems (e.g., e-commerce sites or databases for various applications). The received data is temporarily stored in data storage (e.g., cloud storage), making it easy to access the data in the next processing step.

[0860] Data Cleansing

[0861] The server cleanses the data it receives. This process includes removing duplicate records, standardizing data formats, and filtering out unnecessary information. Data processing libraries such as Python's Pandas and Dask can be used for data cleansing.

[0862] Real-time analytics

[0863] The server uses generative AI models (e.g., TensorFlow or PyTorch) to analyze the cleansed data in real time. The generative AI models analyze the data for patterns and trends and detect anomalies. If an anomaly is detected, the information is passed on to subsequent processes.

[0864] Root Cause Analysis

[0865] The server identifies the specific cause of the anomaly, for example by analyzing the time, location, and related transaction details of the detected anomaly. Root cause analysis can be performed using database queries or log analysis tools.

[0866] Report Generation

[0867] The server generates a report based on the results of the root cause analysis. The report includes details of the anomaly, its cause, and recommended actions. The generated report is saved in PDF or HTML format and provided to the user.

[0868] Providing advice

[0869] The user sends a prompt to the server, such as "I would like to know more about the abnormal data occurring in a specific product category and what to do about it." The server then uses a generative AI model based on the prompt to provide personalized advice. For example, the server might recommend, "Recheck the data in your inventory system and correct it if necessary."

[0870] Security and privacy protection

[0871] The server uses strong encryption protocols (e.g., AES-256) for storing and processing data and applies access controls, including access logging and authentication and authorization mechanisms, to ensure the security of user data.

[0872] Specific examples

[0873] For example, let us consider a case where an e-commerce site uses the system of the present invention to monitor transaction data. Order data and user behavior data from the e-commerce site are sent to a server in real time, which receives and stores them in data storage. After data cleansing and anomalies are detected using a generative AI model, a root cause analysis is performed to generate a report summarizing the causes of the anomaly and countermeasures, which is then provided to the user. When the user sends a prompt requesting advice, the server uses the generative AI model to provide appropriate advice.

[0874] In this way, the system enables efficient analysis of transaction data, anomaly detection, cause analysis, appropriate countermeasure proposals, and secure data management.

[0875] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0876] Step 1: Data Reception

[0877] The server receives transaction data from external systems in real time. Input data is order data and user behavior data sent from the database of the e-commerce site or application. The server temporarily stores this data in data storage, allowing the data to be used efficiently in the next step.

[0878] Step 2: Data cleansing

[0879] The server cleanses the temporarily stored transaction data. The input data is the raw data received in the previous step. Specific operations include deleting duplicate records, standardizing data formats, and filtering out unnecessary information. For example, these operations are performed using the Python Pandas library. The output data is cleansed, consistent data.

[0880] Step 3: Real-time analysis

[0881] The server applies a generative AI model to the cleansed data to detect anomalies in real time. The input data is the data cleansed in step 2. The server uses a generative AI model (e.g., TensorFlow or PyTorch) to analyze the data for patterns and trends and detect anomalies. The output data is the anomaly detection results, which include a list of anomalous patterns and values.

[0882] Step 4: Root Cause Analysis

[0883] The server identifies the specific cause of the detected anomaly. The input data is the anomaly detection result obtained in step 3. The server analyzes the cause based on the time of the anomaly occurrence, location, and detailed information about the related transaction. For example, it extracts detailed information from the database using SQL queries or log analysis tools. The output data is the cause of the anomaly and its details.

[0884] Step 5: Generate a report

[0885] The server generates a report based on the results of the root cause analysis. The input data are the anomaly causes and their details obtained in step 4. The report contains details of the anomaly, its cause, and recommended actions. Specifically, the report is generated as a PDF or HTML file and saved on the server. The output data is the generated report, which is ready to be provided to the user.

[0886] Step 6: Providing advice

[0887] The user poses a question to the server based on a prompt about a specific problem. The input data is the prompt sent by the user (e.g., "I would like to know more about the abnormal data occurring in a specific product category and what to do about it"). The server uses a generative AI model to generate personalized advice corresponding to the prompt. The output data is the advice provided to the user. For example, it might recommend, "Recheck the data in your inventory system and correct it if necessary."

[0888] Step 7: Protecting security and privacy

[0889] The server uses a strong encryption protocol (e.g., AES-256) to store and process data and implements access control. Input data is all data stored within the server. The server records access logs and sets authorization to ensure the safety of user data. Output data is encrypted and secure. This prevents unauthorized access or leakage of data.

[0890] (Application example 1)

[0891] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0892] Conventional technologies require a lot of manual work to receive and analyze transaction data, detect anomalies, identify the cause, and develop countermeasures, which can easily lead to human error. Furthermore, there was no system in place to respond quickly and appropriately after an anomaly was detected, resulting in insufficient security and privacy protection for user data. Therefore, there was a need for a system that could detect anomalies in real time and provide appropriate countermeasures to improve the safety of user data.

[0893] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0894] In this invention, the server includes means for receiving data from an external system in real time, means for cleansing the received data, means for detecting anomalies based on the preprocessed data, means for identifying the cause of the detected anomaly, means for generating a report based on the anomaly and its cause, means for providing advice to the user regarding the specific problem, means for protecting the security and privacy of the user data, means for linking with a smart device to notify the user of the generated report, means for generating a prompt message and providing advice to the user based on the anomaly detection result, and means for ensuring the portability and security of data using an encryption protocol. This enables rapid and accurate anomaly detection and provision of appropriate countermeasures, and further enhances the security of user data.

[0895] "External system" refers to other computer systems or networks that send and receive data.

[0896] "Means for receiving data" refers to a hardware or software part that has the function of obtaining data from an external system in real time.

[0897] "Means for cleansing data" refers to a function for purifying received data and eliminating duplicate data and unnecessary information.

[0898] "Means for detecting anomalies" refers to the part that has the functionality to identify unusual patterns or values ​​based on preprocessed data.

[0899] "Means for identifying the cause" refers to the function for analyzing and identifying the reason why an abnormality occurred.

[0900] "Means for generating reports" refers to a function for creating a report summarizing details and causes of anomalies and recommended actions to be taken.

[0901] "Means for providing advice" refers to a function that provides appropriate advice to users on specific issues.

[0902] "Security and privacy measures" refers to features designed to protect user data from unauthorized access and leaks.

[0903] "Means of collaboration with smart devices to notify users of generated reports" refers to the function for sending reports to devices such as users' smartphones and tablets.

[0904] "Means for generating prompt sentences and providing advice" refers to the function for generating appropriate responses to questions from users based on the results of anomaly detection.

[0905] "Means for ensuring data portability and security using cryptographic protocols" refers to functions that use strong cryptographic technology to ensure the security of data during transport and storage.

[0906] This invention is a system that automates the process from receiving transaction data to analyzing it, detecting anomalies, analyzing root causes, formulating countermeasures, and protecting security and privacy. Specific embodiments of this system are described below.

[0907] System Configuration

[0908] The system of the present invention includes a server, an external system, and a smart device. The server uses a cloud service such as AWS or GCP, and uses MySQL or MongoDB as the database. The generative AI model uses TensorFlow or PyTorch, and the data is encrypted using the AES encryption protocol.

[0909] Program processing

[0910] 1. Data Receipt

[0911] The server receives real-time transaction data from external systems, such as e-commerce sites and financial institutions, and temporarily stores the data in data storage.

[0912] 2. Data cleansing

[0913] The server cleanses the data it receives, which includes deleting duplicate data, removing unnecessary information, and standardizing data formats.

[0914] 3. Real-time analysis

[0915] The server analyzes the cleansed data in real time to detect anomalies, using generative AI models to analyze data patterns and trends and identify abnormal data.

[0916] 4. Root Cause Analysis

[0917] The server identifies the specific cause of the detected anomaly, analyzing it based on information such as time, location, and related transaction details.

[0918] 5. Report Generation

[0919] The server generates a report summarizing details of the anomaly, its cause, and recommended countermeasures, and this report is sent to smart devices such as smartphones and tablets.

[0920] 6. Providing advice

[0921] Users can pose questions to the generative AI model about a specific problem, and the server will provide personalized advice on that question, including solutions and troubleshooting tips.

[0922] 7. Security and Privacy Protection

[0923] The servers use strong encryption protocols for all data storage and processing and enforce access controls to ensure the security of user data.

[0924] Specific examples

[0925] For example, when an online shopping site uses the system of the present invention to monitor transaction data, the system operates as follows.

[0926] 1. Data Receipt

[0927] The server receives order data and user behavior data from an online shopping site in real time. For example, transaction data is sent when a customer purchases a product.

[0928] 2. Data cleansing

[0929] The server performs cleansing to remove duplicate order data and data with inconsistent formats, thereby improving the accuracy of the analysis.

[0930] 3. Real-time analysis

[0931] The server uses generative AI models to analyze the data in real time, detecting, for example, unusual purchase frequencies or unusual patterns in the sales of certain products.

[0932] 4. Root Cause Analysis

[0933] The server identifies a problem with inventory data in a particular product category as the cause of the detected anomaly.

[0934] 5. Report Generation

[0935] The server generates a report summarizing details of the anomaly, its cause, and recommended countermeasures, and notifies the system administrator of the online shopping site.

[0936] 6. Providing advice

[0937] When a user asks, "I'd like more details and solutions about abnormal data occurring in a specific product category," the server recommends, "Recheck the data in your inventory system and correct it if necessary."

[0938] Prompt Sentence Examples

[0939] Question: "Is there anything unusual about my latest transaction?"

[0940] Q: "What unusual activity occurred in trading in April?"

[0941] As described above, the system of the present invention can quickly and accurately detect anomalies and provide appropriate countermeasures, thereby increasing the security of user data.

[0942] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0943] Step 1:

[0944] The server receives transaction data from external systems in real time. The input here is various transaction data sent from the external systems, and the output is transaction data temporarily stored in data storage.

[0945] Step 2:

[0946] The server cleanses the received data by deleting duplicate data, removing unnecessary information, and standardizing data formats. The input here is the transaction data saved in step 1, and the output is the cleansed transaction data.

[0947] Step 3:

[0948] The server uses a generative AI model to perform real-time analysis of the cleansed data and detect anomalies. Specifically, it analyzes data patterns and trends to detect anomalous data. The input here is the cleansed transaction data obtained in step 2, and the output is the detected anomalous data.

[0949] Step 4:

[0950] The server identifies the specific cause of the detected anomaly by analyzing the time, location, and details of the related transaction to identify the cause of the anomaly. The input here is the anomaly data detected in step 3, and the output is information about the cause of the identified anomaly.

[0951] Step 5:

[0952] The server generates a report based on the anomaly and its cause and notifies the smart device. The report contains details of the anomaly, its cause, and recommended countermeasures. The input here is the anomaly cause information identified in step 4, and the output is the generated report.

[0953] Step 6:

[0954] When a user sends a question about a specific problem to the server as a prompt, the server uses a generative AI model to provide personalized advice. Specifically, the server generates an appropriate response to the user's question. The input here is the prompt from the user, and the output is the generated advice.

[0955] Step 7:

[0956] The server uses the AES encryption protocol to store and process user data and enforces access control to protect security and privacy. Specifically, it encrypts and decrypts data and manages access rights. The input here is the data to be stored and the access request, and the output is the encrypted data and the result of the access control.

[0957] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0958] The present invention is a system that provides users with a better interactive experience by combining the reception and analysis of transaction data, anomaly detection, root cause analysis, countermeasure planning, and security and privacy protection, as well as an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0959] Overall flow

[0960] 1. Data Receipt

[0961] The server receives transaction data in real time from external systems. Specifically, it retrieves data from databases such as e-commerce sites via HTTP requests or APIs and temporarily stores it in data storage.

[0962] 2. Data cleansing

[0963] The server cleanses the data it receives. Specifically, it checks the data format and structure, and deletes unnecessary and duplicated information. It also standardizes the data format of necessary information to improve the accuracy of analysis.

[0964] 3. Real-time analysis

[0965] The server then uses generative AI models to analyze the cleansed data in real time, detecting anomalous data or errors that deviate from normal patterns.

[0966] 4. Root Cause Analysis

[0967] To identify the cause of the detected anomaly, the server collects and analyzes relevant data (such as the circumstances surrounding the anomaly and other transaction data).

[0968] 5. Report Generation

[0969] The server generates a detailed report based on the root cause analysis results, including details of the anomaly, its cause, and recommended actions to take. The generated report is saved in PDF or dashboard format and provided to the user.

[0970] 6. Emotion recognition

[0971] The emotion engine analyzes the text entered by the user through the user interface and recognizes the emotion. The emotion engine uses natural language processing to identify emotions (joy, anger, sadness, surprise, etc.) from the user's input text.

[0972] 7. Personalized advice

[0973] The server takes into account the user's emotions and personalizes the advice it provides. For example, if a user types "I'm having trouble with too many errors," the emotion engine will recognize "stress" and provide advice with corresponding support and encouraging messages.

[0974] 8. Security and Privacy Protection

[0975] The server will implement strong security and privacy protection for all data processing and storage. Specifically, data will be encrypted and strict access control will be set to ensure the safety of user data.

[0976] Specific examples

[0977] For example, a case will be described in which an e-commerce site uses the system of the present invention to monitor transaction data.

[0978] 1. Data Receipt

[0979] The server receives order data and user behavior data from the e-commerce site in real time. The order data includes information such as product name, price, and purchase date and time.

[0980] 2. Data cleansing

[0981] The server cleanses the data it receives, removes duplicate order data, and standardizes the data format, thereby improving the efficiency and accuracy of the analysis process.

[0982] 3. Real-time analysis

[0983] The server uses generative AI models to analyze data in real time, for example to detect unusually high purchase frequency of a particular product or an abnormal number of transactions.

[0984] 4. Root Cause Analysis

[0985] The server examines the relevant transaction data and system logs to determine the cause of the identified anomaly, and determines that the cause is, for example, a data discrepancy in an inventory system.

[0986] 5. Report Generation

[0987] The server generates a report detailing the anomaly, its cause, and recommended actions to take, which is output in PDF format and sent to the e-commerce site's system administrator.

[0988] 6. Emotion recognition

[0989] The emotion engine analyzes feedback and inquiries from system administrators to recognize their emotions. For example, it can identify the emotion of stress from feedback such as "the frequency of errors is too high."

[0990] 7. Personalized advice

[0991] The server will provide specific advice based on the recognized emotion, for example, providing a support message along with detailed guidance on "how to improve your workflow to resolve this issue."

[0992] 8. Security and Privacy Protection

[0993] The servers encrypt all communications and data storage and implement strict access controls to prevent unauthorized access to user data and confidential information.

[0994] In this way, the present invention reduces the burden on system personnel and improves the quality of the system and the user experience. By combining it with an emotion engine, responses to users become more flexible and effective.

[0995] The processing flow will be explained below.

[0996] Step 1:

[0997] The server receives transaction data from external systems. Specifically, the data is obtained in real time through HTTP requests or API calls and temporarily stored in data storage. This process is performed by setting up a listener for receiving data, and when data arrives, the listener generates an event and receives the data stream.

[0998] Step 2:

[0999] The server cleanses the data it receives. Specifically, it checks the data format and structure, removes unnecessary information and duplicate records, standardizes the data format, and corrects inconsistent data, preparing the cleansed data for analysis.

[1000] Step 3:

[1001] The server sends the cleansed data to the analytics engine, which begins real-time analysis by feeding the data into a generative AI model and running algorithms to detect anomalous data or errors that deviate from normal patterns.

[1002] Step 4:

[1003] The server logs any detected anomalies, adding details such as the time and location of the anomaly and the transaction ID to the anomaly log for future reference by administrators.

[1004] Step 5:

[1005] The server performs root cause analysis of the anomaly. Specifically, it collects and analyzes the circumstances surrounding the anomaly and related transaction data to identify the cause of the anomaly. For example, it identifies unusual purchasing patterns in a particular product category or data discrepancies in an inventory system.

[1006] Step 6:

[1007] The server generates a detailed report based on the results of the root cause analysis, summarizing the details of the anomaly, its cause, and recommended actions to take, and saves it in PDF or dashboard format.

[1008] Step 7:

[1009] When a user requests a report, the server provides it: the user requests a report through an interface (web browser or application), the server finds the saved report, and sends it to the user.

[1010] Step 8:

[1011] The emotion engine analyzes the text entered by the user through the user interface and recognizes the emotion. Specifically, the emotion engine uses natural language processing to identify emotions (joy, anger, sadness, surprise, etc.) from the user's text input and records them in a database.

[1012] Step 9:

[1013] The server personalizes the advice it provides based on the results of emotion recognition. Specifically, it takes the user's emotions into account and generates solutions with appropriate support and encouraging messages. For example, if the user enters "I'm having trouble with too many errors," the emotion engine will recognize "stress" and provide warm-hearted advice accordingly.

[1014] Step 10:

[1015] The servers implement strong security and privacy protection for all data processing and storage. Specifically, data is encrypted and strict access control is set up to ensure the safety of user data. A monitoring system is also in place to respond immediately to any signs of unauthorized access.

[1016] Example 2

[1017] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1018] While conventional data analysis systems receive, cleanse, analyze, and detect anomalies in real time, they lack clear cause analysis of detected anomalies and provide countermeasures that take user sentiment into account. In terms of security and privacy protection, the safety of user data is also not sufficiently ensured, which is a problem.

[1019] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving data from an external system in real time, a means for cleansing the received data, a means for detecting anomalies based on the preprocessed data, a means for identifying the cause of the detected anomaly, a means for generating a report based on the anomaly and its cause, a means for recognizing emotions from a user's input, a means for providing personalized advice based on the recognized emotions, and a means for protecting the security and privacy of user data. This makes it possible to detect anomalies and analyze their causes, present countermeasures that take user emotions into consideration, and ensure the safety of user data.

[1020] "Means of receiving data in real time from external systems" refers to the processes and technologies for obtaining data in real time through external databases or application program interfaces (APIs).

[1021] "Means of cleansing received data" refers to the process of removing unnecessary information from the data and standardizing the data structure in order to improve the accuracy and consistency of the data obtained.

[1022] "Anomaly detection methods based on pre-processed data" refers to algorithms and techniques that use cleansed data to analyze the data for anomalous patterns or deviations.

[1023] "Means for identifying the cause of a detected abnormality" refers to the technology and process for conducting a detailed analysis of the background and factors that caused the abnormality and identifying them.

[1024] "Means for generating reports based on anomalies and their causes" refers to technologies and processes that organize information about detected anomalies and their causes, and automatically generate reports that can be presented to users in an easy-to-understand manner.

[1025] "Means for recognizing emotions from user input" refers to natural language processing techniques that analyze the text and feedback entered by users into the system and identify the emotions contained therein.

[1026] "Means for providing personalized advice based on perceived emotions" refers to algorithms or technologies that take into account a user's emotional state to provide advice or support messages that are appropriate for that user.

[1027] "Measures to protect the security and privacy of user data" refers to encryption technologies and access control policies to protect users' personal information and prevent unauthorized access or information leaks.

[1028] The present invention is a system that provides users with a better interactive experience by combining the reception and analysis of transaction data, anomaly detection, root cause analysis, countermeasure planning, and security and privacy protection, as well as an emotion engine that recognizes user emotions. A detailed embodiment of this system will now be described.

[1029] Hardware and Software Configuration

[1030] The server plays the central role in the system. Data is received in real time from external systems and stored on the server. This data reception process uses HTTP requests and APIs. The data is stored in, for example, an S3 bucket on Amazon Web Services (AWS) or Google Cloud Storage.

[1031] Data cleansing is performed by a program installed on a server, written in a programming language such as Python or Java, that performs, among other things, data normalization and the elimination of duplicate data.

[1032] Real-time analysis for anomaly detection uses generative AI models, trained using deep learning frameworks such as TensorFlow and PyTorch, which are then analyzed by a server in real time to detect unusual data patterns and errors.

[1033] The server also handles root cause analysis, which involves collecting relevant data and using statistical methods and AI models to identify the cause of an anomaly.

[1034] The generated reports can be provided to the user in PDF format or via a web-based dashboard, which can be emailed or uploaded to a dashboard.

[1035] The emotion engine is responsible for recognizing user emotions. This engine uses natural language processing (NLP) technology to extract emotions from the text entered by the user. NLP tools such as Google Cloud Natural Language API and IBM Watson are used for this.

[1036] Personalized advice based on emotion recognition is generated by the server, which implements an algorithm that takes into account the recognized emotions and provides appropriate advice and support messages to the user.

[1037] Security and privacy are ensured through data encryption and strict access control, using SSL / TLS for communication encryption and AWS IAM policies for access control.

[1038] Specific examples

[1039] For example, consider the case where an e-commerce site uses the system of the present invention to monitor transaction data.

[1040] 1. Data Receipt

[1041] The server receives order data and user behavior data from the e-commerce site in real time. The order data includes information such as product name, price, and purchase date and time.

[1042] 2. Data cleansing

[1043] The server cleanses the data it receives, removes duplicate order data, and standardizes the data format, thereby improving the efficiency and accuracy of the analysis process.

[1044] 3. Real-time analysis

[1045] The server uses generative AI models to analyze the data in real time, for example to detect unusually high purchase frequency of a particular product or an unusual number of transactions.

[1046] 4. Root Cause Analysis

[1047] The server examines the relevant transaction data and system logs to determine the cause of the identified anomaly, and determines that the cause is, for example, a data discrepancy in an inventory system.

[1048] 5. Report Generation

[1049] The server generates a report summarizing the details of the anomaly, its cause, and recommended countermeasures, which is output in PDF format and sent to the e-commerce site's system administrator.

[1050] 6. Emotion recognition

[1051] The emotion engine analyzes feedback and inquiries from system administrators to recognize their emotions. For example, it can identify the emotion of stress from feedback such as "the frequency of errors is too high."

[1052] 7. Personalized advice

[1053] The server will then provide specific advice based on the perceived emotion, for example providing a support message along with detailed guidance on "how to improve your workflow to resolve this issue."

[1054] 8. Security and Privacy Protection

[1055] The servers encrypt all communications and data storage and implement strict access controls to prevent unauthorized access to user data and confidential information.

[1056] Prompt Sentence Examples

[1057] Can you please elaborate on the anomaly detection algorithms for transaction data in this system, specifically the generative AI model used and its training data?

[1058] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1059] Step 1: Data Reception

[1060] The server receives transaction data from external systems. Inputs include HTTP requests from e-commerce sites, order data obtained via APIs, and user behavior data. Specifically, the server uses Amazon Web Services (AWS) or Google Cloud Platform (GCP) to store the data in its own storage in real time.

[1061] Input: Transaction data from external systems (e.g., order data, user behavior data)

[1062] Output: Temporarily stored transaction data

[1063] Step 2: Data cleansing

[1064] The server cleanses the data it receives. It checks the format and structure of the data and removes unnecessary and duplicated data. This is done using programming languages ​​such as Python and Java, applying regular expressions and data conversion scripts. If some data is missing, it also performs missing value imputation.

[1065] Input: Temporarily stored transaction data

[1066] Output: Cleansed data

[1067] Step 3: Real-time analysis

[1068] The server performs real-time analysis on the cleansed data using generative AI models implemented using frameworks such as TensorFlow and PyTorch. The server detects abnormal data patterns and errors and generates alerts and notifications.

[1069] Input: Cleansed data

[1070] Output: Anomaly detection results and notifications

[1071] Step 4: Root Cause Analysis

[1072] The server performs a detailed analysis of the cause of the detected anomaly. It collects relevant data (such as the circumstances surrounding the anomaly and other transaction data) and uses statistical techniques and additional AI models to identify the cause. Specifically, it analyzes whether the anomalous transaction is linked to a specific promotion code or system log.

[1073] Input: Anomaly detection results and associated data

[1074] Output: Cause identification and details

[1075] Step 5: Generate a report

[1076] The server generates a detailed report based on the results of the root cause analysis. The report includes details of the anomaly, its cause, and recommended actions to take. The generated report is saved in PDF or web dashboard format and provided to the user. Specifically, the generated PDF can be sent by email or uploaded to the dashboard.

[1077] Input: Cause identification and details

[1078] Output: Detailed report

[1079] Step 6: Emotion Recognition

[1080] The emotion engine analyzes the text entered by the user through the user interface and recognizes the emotion. It uses Google Cloud Natural Language API and IBM Watson to extract emotions (joy, anger, sadness, surprise, etc.) from the text.

[1081] Input: User-entered text

[1082] Output: Recognized emotion

[1083] Step 7: Personalized advice

[1084] The server considers the user's emotions and personalizes the advice it provides. For example, if a user types "I'm having trouble with too many errors," the emotion engine will recognize "stress" and generate appropriate advice or encouraging messages.

[1085] Input: Recognized emotion

[1086] Output: Personalized advice

[1087] Step 8: Protecting security and privacy

[1088] The server implements strong security and privacy protection for all data processing and storage. Specifically, SSL / TLS is used for data encryption and strict access control is set to ensure the safety of user data. This is achieved using AWS IAM policies, etc.

[1089] Input: All user data

[1090] Output: Securely stored and processed user data

[1091] (Application example 2)

[1092] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1093] While traditional transaction monitoring systems are equipped with basic functions such as anomaly detection, cause identification, and user advice provision, they lack the ability to recognize user emotions and provide personalized advice based on those emotions. This makes it difficult to improve user experience or quickly resolve problems. Furthermore, robust measures are required from the perspective of security and privacy protection, but these measures are often not adequately provided.

[1094] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving data from an external system in real time, means for cleansing the received data, means for detecting anomalies based on the preprocessed data, means for identifying the cause of the detected anomaly, means for generating a report based on the anomaly and its cause, means for providing advice to the user regarding a specific problem, means for analyzing user feedback via a user interface and recognizing emotions, means for personalizing advice based on the recognized emotions, and means for protecting the security and privacy of user data. This makes it possible to provide advice that takes user emotions into consideration and to enhance security and privacy protection.

[1095] An "external system" refers to an external information processing device such as a server, database, or application that provides transaction data in real time.

[1096] "Means of receiving data" refers to a mechanism that uses an interface or protocol, such as an HTTP request or API, to obtain data from an external system.

[1097] "Data cleansing methods" refers to the process of removing unnecessary information and redundant data from received data and preparing the necessary data in an appropriate format.

[1098] "Means for detecting anomalies" refers to algorithms or systems that analyze and identify anomalous data that deviates from normal patterns in pre-processed data.

[1099] "Means for identifying the cause" refers to the mechanisms and methods for analyzing and identifying the factors behind the detected abnormality.

[1100] "Means for generating reports" refers to the process of creating and providing a report to the user that includes details of the anomaly, its cause, and recommended actions to take.

[1101] "Advice methods" refer to methods that provide users with appropriate solutions or guidance for specific problems.

[1102] "User interface" refers to the screens and input devices that allow a user to interact with a system, providing feedback and receiving information.

[1103] "Emotion recognition means" refers to natural language processing techniques and models for analyzing and identifying emotions from user feedback and input text.

[1104] "Means of personalizing advice" refers to the process of providing relevant and tailored advice based on perceived user sentiment.

[1105] "Security and privacy measures" refers to encryption technologies and access control mechanisms to ensure the security of user data and protect privacy.

[1106] This invention includes a system that provides real-time monitoring of transaction data in electronic payment services, anomaly detection, cause analysis, emotion recognition, and personalized advice. The overall flow of the system and the hardware and software used are described below.

[1107] Hardware and Software

[1108] The server receives transaction data and performs analysis and anomaly detection. The specific software and hardware used includes Python, scikit-learn, TensorFlow, Transformers, and Cryptography libraries.

[1109] Data Receipt

[1110] The server receives transaction data in real time from external systems. Specifically, it retrieves data from external databases and applications via HTTP requests or APIs and temporarily stores it in data storage.

[1111] Data Cleansing

[1112] The server cleanses the received data. Using Pandas, it checks the data format and structure, and removes unnecessary and duplicated data. It also standardizes the data format of necessary information to improve the accuracy of analysis.

[1113] Real-time analytics and anomaly detection

[1114] The server uses the Isolation Forest algorithm to detect anomalies in real time based on the cleansed data, a process that involves analyzing pre-processed data and identifying anomalies.

[1115] Root Cause Analysis and Report Generation

[1116] The server collects and analyzes relevant data to identify the cause of the detected anomaly. Based on the results, it generates a report containing details of the anomaly, its cause, and recommended actions to take. The generated report is saved in PDF or dashboard format and provided to the user.

[1117] Emotion Recognition and Personalized Advice

[1118] The server receives user feedback through the user interface and recognizes emotions using Transformers' natural language processing model. For example, from feedback such as "I'm having trouble with the frequency of errors," it identifies the emotion "stress." It then provides specific, personalized advice based on the recognized emotion. This makes the advice the user receives more appropriate and effective.

[1119] Security and Privacy Protection

[1120] The server implements strong security and privacy protection for all data processing and storage, specifically encrypting data using the Cryptography library and setting strict access control.

[1121] Specific examples

[1122] For example, if an e-commerce site uses the system of the present invention to monitor transaction data, it can receive order data and user behavior data in real time and detect anomalies. If an anomaly occurs, a detailed report is generated and an administrator is notified. Furthermore, emotions are recognized based on the administrator's feedback, and appropriate advice is provided.

[1123] Prompt Sentence Examples

[1124] User feedback: "I've been having a lot of payment errors lately."

[1125] Prompt: "Analyze feedback statements that are likely to cause users anger."

[1126] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1127] Step 1:

[1128] The server receives transaction data in real time from external systems via HTTP requests or APIs. The input is the transaction data obtained from the external system, and the output is the received data that is temporarily stored. This received data consists of various transactions (e.g., product purchase data, payment data, etc.).

[1129] Step 2:

[1130] The server uses the Pandas library to cleanse the incoming data by removing duplicates and unnecessary fields and converting the data into a uniform format. The input is the temporarily stored incoming data, and the output is a cleansed, consistent dataset. This cleansing improves the accuracy of the data for analysis.

[1131] Step 3:

[1132] The server uses the Isolation Forest algorithm to detect anomalies in real time based on the cleansed data. The input is the cleansed dataset, and the output is the identification of anomalous data. Specifically, transaction data is converted into a feature vector and classified as anomalous or normal.

[1133] Step 4:

[1134] The server collects and analyzes related transaction data and system logs to identify the cause of the detected anomaly. The input is the anomaly data and related complementary data, and the output is the analysis result of the anomaly's cause. The server uses machine learning models and statistical methods in this analysis process.

[1135] Step 5:

[1136] The server generates a report that summarizes the details of the anomaly, its cause, and recommended countermeasures. The input is the cause analysis result, and the output is a report in PDF or dashboard format. This report details the specific content of the anomaly, the scope of its impact, and the countermeasures.

[1137] Step 6:

[1138] The server receives user feedback through the user interface and recognizes emotions using Transformers' natural language processing model. The input is the user's feedback text, and the output is the recognized emotion (e.g., anger, sadness, joy, etc.). As a specific example, the server identifies the emotion "stress" from the feedback, "I've been having trouble with a lot of payment errors lately."

[1139] Step 7:

[1140] The server then personalizes and provides advice to users based on the recognized emotions. The input is the recognized user's emotions and the analysis results of transaction data, and the output is a personalized advice message. For example, if stressful emotions are recognized, advice is generated that includes a link to a support guide that explains the solution in detail.

[1141] Step 8:

[1142] The server uses the Cryptography library to encrypt all data during processing and storage, and sets strict access control. All transaction data and analysis data are input, and the output is encrypted and secure data. This protects user security and privacy.

[1143] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1144] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1145] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1146] [Fourth embodiment]

[1147] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1148] 7, a 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.

[1149] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1150] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1151] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1153] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1154] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1155] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1156] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1157] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1158] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1159] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1160] The present invention provides a system that automates the process from receiving transaction data to analyzing it, detecting anomalies, analyzing root causes, formulating countermeasures, and protecting security and privacy. Specific embodiments of the system are described below.

[1161] Overall flow

[1162] 1. Data Receipt

[1163] The server receives transaction data in real time from external systems, such as e-commerce site databases and applications. The received data is temporarily stored in data storage.

[1164] 2. Data cleansing

[1165] The server cleanses the data it receives, which includes removing duplicate records, standardizing data formats, and filtering out unnecessary information.

[1166] 3. Real-time analysis

[1167] The server analyzes the cleansed data in real time to detect anomalies, using generative AI models to analyze the data for patterns and trends and spot data that is out of the ordinary.

[1168] 4. Root Cause Analysis

[1169] The server identifies the specific cause of the detected anomaly using information such as the time and location of the anomaly and details of the associated transaction.

[1170] 5. Report Generation

[1171] The server generates a report based on the root cause analysis results and provides it to the user, containing details of the anomaly, its cause, and recommended actions to take.

[1172] 6. Providing advice

[1173] Users can pose questions to the generative AI model about a specific problem, and the server will provide personalized advice on the question, including solutions and troubleshooting tips.

[1174] 7. Security and Privacy Protection

[1175] The servers use strong encryption protocols and enforce access controls to ensure the security of user data when storing and processing data.

[1176] Specific examples

[1177] For example, a case will be described in which an e-commerce site uses the system of the present invention to monitor transaction data.

[1178] 1. Data Receipt

[1179] The server receives order data and user behavior data from the e-commerce site in real time. For example, transaction data is sent when a customer purchases a product.

[1180] 2. Data cleansing

[1181] The server performs cleansing to remove duplicate order data and data with inconsistent formats, thereby improving the accuracy of analysis.

[1182] 3. Real-time analysis

[1183] The server uses generative AI models to analyze the data in real time, detecting, for example, unusual purchase frequencies or unusual patterns in the sales of certain products.

[1184] 4. Root Cause Analysis

[1185] The server identifies a problem with inventory data in a particular product category as the cause of the detected anomaly.

[1186] 5. Report Generation

[1187] The server generates a report detailing the anomaly, its cause, and recommended countermeasures, and provides it to the e-commerce site's system administrator.

[1188] 6. Providing advice

[1189] When a user asks, "I would like to know more details about the abnormal data occurring in a specific product category and what to do about it," the server will recommend, "Recheck the data in your inventory system and correct it if necessary."

[1190] 7. Security and Privacy Protection

[1191] The server encrypts all communications and stored data and implements appropriate access controls to ensure data security.

[1192] In this way, the present invention can significantly reduce the man-hours required by system personnel and improve the quality of the system. By automating specific processes, it becomes possible to quickly and accurately detect and respond to abnormalities.

[1193] The processing flow will be explained below.

[1194] Step 1:

[1195] The server receives transaction data from external systems. Specifically, it retrieves data in real time from e-commerce sites and other systems using HTTP requests or APIs, and temporarily stores it in data storage.

[1196] Step 2:

[1197] The data received by the server is cleansed. Specifically, the data format and structure are checked, unnecessary and duplicate data is deleted, and only the necessary information is retained. This work also includes standardizing the data format and correcting inconsistent data.

[1198] Step 3:

[1199] The server sends the cleansed data to the analysis engine. Specifically, the cleansed data is passed to the generative AI model in real time, and analysis begins.

[1200] Step 4:

[1201] The server uses the generative AI model to analyze the data in real time. Specifically, the analysis engine learns patterns and trends in the data and detects anomalous data or errors that deviate from normal patterns.

[1202] Step 5:

[1203] The server logs any detected anomalies. Specifically, each time an anomaly is detected, details about it (such as time, location, and transaction ID) are added to the anomaly log.

[1204] Step 6:

[1205] The server performs root cause analysis of the anomaly. Specifically, it collects related data (the situation at the time the anomaly occurred and other transaction data) and analyzes the cause to identify the cause of the anomaly.

[1206] Step 7:

[1207] The server generates a report based on the results of the root cause analysis, summarizing the details of the anomaly, its cause, and recommended actions to take, and saves it in PDF or dashboard format.

[1208] Step 8:

[1209] When a user requests a report, the server provides it: the user requests a report through an interface (web browser or application), the server finds the saved report, and sends it to the user.

[1210] Step 9:

[1211] When a user inputs a question about a specific anomaly into the generative AI model, the server analyzes the question and generates appropriate advice. Specifically, it analyzes the question and generates an answer using relevant data and past case studies, and provides it to the user.

[1212] Step 10:

[1213] The server will implement strong security and privacy protections for all data processing and storage, including encrypting data and setting strict access controls to ensure that only a limited number of users can access the data.

[1214] Example 1

[1215] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1216] In conventional transaction data analysis systems, the process from receiving data to detecting anomalies, identifying causes, and proposing countermeasures is often done manually, which is time-consuming and labor-intensive. Security and privacy protections are often inadequate, raising concerns about data safety. Furthermore, it is difficult to detect anomalies in real time or provide specific advice to users regarding specific problems.

[1217] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1218] In this invention, the server includes means for receiving data from an external system in real time, means for cleansing the received data, and means for detecting anomalies using a generative AI model based on the preprocessed data. This enables real-time analysis of transaction data. The server also includes means for identifying specific causes of detected anomalies, means for generating reports based on the anomalies and their causes, means for providing advice to users regarding specific issues based on prompts, means for protecting the security and privacy of user data, means for storing the preprocessed data in storage, and means for implementing access control for the stored data. This enables efficient analysis of transaction data, anomaly detection, cause analysis, proposal of appropriate countermeasures, and secure data management.

[1219] "External System" refers to any other system or database to which transaction data can be transmitted in real time.

[1220] "Data receiving means" refers to a device or program that has the function of receiving transaction data from an external system in real time.

[1221] "Cleansing means" refers to a device or program that has the function of deleting duplicate records from received data, standardizing data formats, and filtering out unnecessary information.

[1222] "Pre-processed data" refers to data after it has been processed by a cleansing tool.

[1223] A "generative AI model" is a model that uses machine learning and deep learning algorithms to analyze patterns and trends in data and detect anomalies.

[1224] "Anomaly detection means" refers to a device or program that has the function of detecting anomalies using a generative AI model based on preprocessed data.

[1225] "Cause identification means" refers to a device or program with analytical capabilities to identify the specific cause of a detected abnormality.

[1226] "Report generation means" refers to a device or program that has the function of generating a report based on anomalies and their causes and providing the information to the user.

[1227] A "prompt" refers to a question that a user inputs into a generative AI model to obtain specific information.

[1228] The "advice providing means" refers to a device or program that has the function of providing personalized advice to a user regarding a specific problem based on a prompt sentence.

[1229] "Security and privacy measures" refers to devices and programs that use strong encryption protocols and access control when storing and processing user data.

[1230] "Data Storage" refers to storage systems and cloud storage for temporary or long-term storage of received and pre-processed data.

[1231] "Access control" refers to authentication and authorization functions for managing access rights to data and preventing unauthorized access.

[1232] This invention is a system that consistently performs processes from receiving transaction data to analyzing it, detecting anomalies, identifying causes, generating reports, providing advice, and protecting security and privacy. This system is equipped with functions for receiving real-time data from external systems, data cleansing, detecting anomalies using a generative AI model, identifying causes, generating reports, and providing advice based on prompts. It also has powerful security and privacy protection functions for storing data and controlling access.

[1233] This system operates mainly around the server. Each function is explained in detail below.

[1234] Data Receipt

[1235] The server receives transaction data in real time from external systems (e.g., e-commerce sites or databases for various applications). The received data is temporarily stored in data storage (e.g., cloud storage), making it easy to access the data in the next processing step.

[1236] Data Cleansing

[1237] The server cleanses the data it receives. This process includes removing duplicate records, standardizing data formats, and filtering out unnecessary information. Data processing libraries such as Python's Pandas and Dask can be used for data cleansing.

[1238] Real-time analytics

[1239] The server uses generative AI models (e.g., TensorFlow or PyTorch) to analyze the cleansed data in real time. The generative AI models analyze the data for patterns and trends and detect anomalies. If an anomaly is detected, the information is passed on to subsequent processes.

[1240] Root Cause Analysis

[1241] The server identifies the specific cause of the anomaly, for example by analyzing the time, location, and related transaction details of the detected anomaly. Root cause analysis can be performed using database queries or log analysis tools.

[1242] Report Generation

[1243] The server generates a report based on the results of the root cause analysis. The report includes details of the anomaly, its cause, and recommended actions. The generated report is saved in PDF or HTML format and provided to the user.

[1244] Providing advice

[1245] The user sends a prompt to the server, such as "I would like to know more about the abnormal data occurring in a specific product category and what to do about it." The server then uses a generative AI model based on the prompt to provide personalized advice. For example, the server might recommend, "Recheck the data in your inventory system and correct it if necessary."

[1246] Security and privacy protection

[1247] The server uses strong encryption protocols (e.g., AES-256) for storing and processing data and applies access controls, including access logging and authentication and authorization mechanisms, to ensure the security of user data.

[1248] Specific examples

[1249] For example, let us consider a case where an e-commerce site uses the system of the present invention to monitor transaction data. Order data and user behavior data from the e-commerce site are sent to a server in real time, which receives and stores them in data storage. After data cleansing and anomalies are detected using a generative AI model, a root cause analysis is performed to generate a report summarizing the causes of the anomaly and countermeasures, which is then provided to the user. When the user sends a prompt requesting advice, the server uses the generative AI model to provide appropriate advice.

[1250] In this way, the system enables efficient analysis of transaction data, anomaly detection, cause analysis, appropriate countermeasure proposals, and secure data management.

[1251] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1252] Step 1: Data Reception

[1253] The server receives transaction data from external systems in real time. Input data is order data and user behavior data sent from the database of the e-commerce site or application. The server temporarily stores this data in data storage, allowing the data to be used efficiently in the next step.

[1254] Step 2: Data cleansing

[1255] The server cleanses the temporarily stored transaction data. The input data is the raw data received in the previous step. Specific operations include deleting duplicate records, standardizing data formats, and filtering out unnecessary information. For example, these operations are performed using the Python Pandas library. The output data is cleansed, consistent data.

[1256] Step 3: Real-time analysis

[1257] The server applies a generative AI model to the cleansed data to detect anomalies in real time. The input data is the data cleansed in step 2. The server uses a generative AI model (e.g., TensorFlow or PyTorch) to analyze the data for patterns and trends and detect anomalies. The output data is the anomaly detection results, which include a list of anomalous patterns and values.

[1258] Step 4: Root Cause Analysis

[1259] The server identifies the specific cause of the detected anomaly. The input data is the anomaly detection result obtained in step 3. The server analyzes the cause based on the time of the anomaly occurrence, location, and detailed information about the related transaction. For example, it extracts detailed information from the database using SQL queries or log analysis tools. The output data is the cause of the anomaly and its details.

[1260] Step 5: Generate a report

[1261] The server generates a report based on the results of the root cause analysis. The input data are the anomaly causes and their details obtained in step 4. The report contains details of the anomaly, its cause, and recommended actions. Specifically, the report is generated as a PDF or HTML file and saved on the server. The output data is the generated report, which is ready to be provided to the user.

[1262] Step 6: Providing advice

[1263] The user poses a question to the server based on a prompt about a specific problem. The input data is the prompt sent by the user (e.g., "I would like to know more about the abnormal data occurring in a specific product category and what to do about it"). The server uses a generative AI model to generate personalized advice corresponding to the prompt. The output data is the advice provided to the user. For example, it might recommend, "Recheck the data in your inventory system and correct it if necessary."

[1264] Step 7: Protecting security and privacy

[1265] The server uses a strong encryption protocol (e.g., AES-256) to store and process data and implements access control. Input data is all data stored within the server. The server records access logs and sets authorization to ensure the safety of user data. Output data is encrypted and secure. This prevents unauthorized access or leakage of data.

[1266] (Application example 1)

[1267] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1268] Conventional technologies require a lot of manual work to receive and analyze transaction data, detect anomalies, identify the cause, and develop countermeasures, which can easily lead to human error. Furthermore, there was no system in place to respond quickly and appropriately after an anomaly was detected, resulting in insufficient security and privacy protection for user data. Therefore, there was a need for a system that could detect anomalies in real time and provide appropriate countermeasures to improve the safety of user data.

[1269] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1270] In this invention, the server includes means for receiving data from an external system in real time, means for cleansing the received data, means for detecting anomalies based on the preprocessed data, means for identifying the cause of the detected anomaly, means for generating a report based on the anomaly and its cause, means for providing advice to the user regarding the specific problem, means for protecting the security and privacy of the user data, means for linking with a smart device to notify the user of the generated report, means for generating a prompt message and providing advice to the user based on the anomaly detection result, and means for ensuring the portability and security of data using an encryption protocol. This enables rapid and accurate anomaly detection and provision of appropriate countermeasures, and further enhances the security of user data.

[1271] "External system" refers to other computer systems or networks that send and receive data.

[1272] "Means for receiving data" refers to a hardware or software part that has the function of obtaining data from an external system in real time.

[1273] "Means for cleansing data" refers to a function for purifying received data and eliminating duplicate data and unnecessary information.

[1274] "Means for detecting anomalies" refers to the part that has the functionality to identify unusual patterns or values ​​based on preprocessed data.

[1275] "Means for identifying the cause" refers to the function for analyzing and identifying the reason why an abnormality occurred.

[1276] "Means for generating reports" refers to a function for creating a report summarizing details and causes of anomalies and recommended actions to be taken.

[1277] "Means for providing advice" refers to a function that provides appropriate advice to users on specific issues.

[1278] "Security and privacy measures" refers to features designed to protect user data from unauthorized access and leaks.

[1279] "Means of collaboration with smart devices to notify users of generated reports" refers to the function for sending reports to devices such as users' smartphones and tablets.

[1280] "Means for generating prompt sentences and providing advice" refers to the function for generating appropriate responses to questions from users based on the results of anomaly detection.

[1281] "Means for ensuring data portability and security using cryptographic protocols" refers to functions that use strong cryptographic technology to ensure the security of data during transport and storage.

[1282] This invention is a system that automates the process from receiving transaction data to analyzing it, detecting anomalies, analyzing root causes, formulating countermeasures, and protecting security and privacy. Specific embodiments of this system are described below.

[1283] System Configuration

[1284] The system of the present invention includes a server, an external system, and a smart device. The server uses a cloud service such as AWS or GCP, and uses MySQL or MongoDB as the database. The generative AI model uses TensorFlow or PyTorch, and the data is encrypted using the AES encryption protocol.

[1285] Program processing

[1286] 1. Data Receipt

[1287] The server receives real-time transaction data from external systems, such as e-commerce sites and financial institutions, and temporarily stores the data in data storage.

[1288] 2. Data cleansing

[1289] The server cleanses the data it receives, which includes deleting duplicate data, removing unnecessary information, and standardizing data formats.

[1290] 3. Real-time analysis

[1291] The server analyzes the cleansed data in real time to detect anomalies, using generative AI models to analyze data patterns and trends and identify abnormal data.

[1292] 4. Root Cause Analysis

[1293] The server identifies the specific cause of the detected anomaly, analyzing it based on information such as time, location, and related transaction details.

[1294] 5. Report Generation

[1295] The server generates a report summarizing details of the anomaly, its cause, and recommended countermeasures, and this report is sent to smart devices such as smartphones and tablets.

[1296] 6. Providing advice

[1297] Users can pose questions to the generative AI model about a specific problem, and the server will provide personalized advice on that question, including solutions and troubleshooting tips.

[1298] 7. Security and Privacy Protection

[1299] The servers use strong encryption protocols for all data storage and processing and enforce access controls to ensure the security of user data.

[1300] Specific examples

[1301] For example, when an online shopping site uses the system of the present invention to monitor transaction data, the system operates as follows.

[1302] 1. Data Receipt

[1303] The server receives order data and user behavior data from an online shopping site in real time. For example, transaction data is sent when a customer purchases a product.

[1304] 2. Data cleansing

[1305] The server performs cleansing to remove duplicate order data and data with inconsistent formats, thereby improving the accuracy of the analysis.

[1306] 3. Real-time analysis

[1307] The server uses generative AI models to analyze the data in real time, detecting, for example, unusual purchase frequencies or unusual patterns in the sales of certain products.

[1308] 4. Root Cause Analysis

[1309] The server identifies a problem with inventory data in a particular product category as the cause of the detected anomaly.

[1310] 5. Report Generation

[1311] The server generates a report summarizing details of the anomaly, its cause, and recommended countermeasures, and notifies the system administrator of the online shopping site.

[1312] 6. Providing advice

[1313] When a user asks, "I'd like more details and solutions about abnormal data occurring in a specific product category," the server recommends, "Recheck the data in your inventory system and correct it if necessary."

[1314] Prompt Sentence Examples

[1315] Question: "Is there anything unusual about my latest transaction?"

[1316] Q: "What unusual activity occurred in trading in April?"

[1317] As described above, the system of the present invention can quickly and accurately detect anomalies and provide appropriate countermeasures, thereby increasing the security of user data.

[1318] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1319] Step 1:

[1320] The server receives transaction data from external systems in real time. The input here is various transaction data sent from the external systems, and the output is transaction data temporarily stored in data storage.

[1321] Step 2:

[1322] The server cleanses the received data by deleting duplicate data, removing unnecessary information, and standardizing data formats. The input here is the transaction data saved in step 1, and the output is the cleansed transaction data.

[1323] Step 3:

[1324] The server uses a generative AI model to perform real-time analysis of the cleansed data and detect anomalies. Specifically, it analyzes data patterns and trends to detect anomalous data. The input here is the cleansed transaction data obtained in step 2, and the output is the detected anomalous data.

[1325] Step 4:

[1326] The server identifies the specific cause of the detected anomaly by analyzing the time, location, and details of the related transaction to identify the cause of the anomaly. The input here is the anomaly data detected in step 3, and the output is information about the cause of the identified anomaly.

[1327] Step 5:

[1328] The server generates a report based on the anomaly and its cause and notifies the smart device. The report contains details of the anomaly, its cause, and recommended countermeasures. The input here is the anomaly cause information identified in step 4, and the output is the generated report.

[1329] Step 6:

[1330] When a user sends a question about a specific problem to the server as a prompt, the server uses a generative AI model to provide personalized advice. Specifically, the server generates an appropriate response to the user's question. The input here is the prompt from the user, and the output is the generated advice.

[1331] Step 7:

[1332] The server uses the AES encryption protocol to store and process user data and enforces access control to protect security and privacy. Specifically, it encrypts and decrypts data and manages access rights. The input here is the data to be stored and the access request, and the output is the encrypted data and the result of the access control.

[1333] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1334] The present invention is a system that provides users with a better interactive experience by combining the reception and analysis of transaction data, anomaly detection, root cause analysis, countermeasure planning, and security and privacy protection, as well as an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[1335] Overall flow

[1336] 1. Data Receipt

[1337] The server receives transaction data in real time from external systems. Specifically, it retrieves data from databases such as e-commerce sites via HTTP requests or APIs and temporarily stores it in data storage.

[1338] 2. Data cleansing

[1339] The server cleanses the data it receives. Specifically, it checks the data format and structure, and deletes unnecessary and duplicated information. It also standardizes the data format of necessary information to improve the accuracy of analysis.

[1340] 3. Real-time analysis

[1341] The server then uses generative AI models to analyze the cleansed data in real time, detecting anomalous data or errors that deviate from normal patterns.

[1342] 4. Root Cause Analysis

[1343] To identify the cause of the detected anomaly, the server collects and analyzes relevant data (such as the circumstances surrounding the anomaly and other transaction data).

[1344] 5. Report Generation

[1345] The server generates a detailed report based on the root cause analysis results, including details of the anomaly, its cause, and recommended actions to take. The generated report is saved in PDF or dashboard format and provided to the user.

[1346] 6. Emotion recognition

[1347] The emotion engine analyzes the text entered by the user through the user interface and recognizes the emotion. The emotion engine uses natural language processing to identify emotions (joy, anger, sadness, surprise, etc.) from the user's input text.

[1348] 7. Personalized advice

[1349] The server takes into account the user's emotions and personalizes the advice it provides. For example, if a user types "I'm having trouble with too many errors," the emotion engine will recognize "stress" and provide advice with corresponding support and encouraging messages.

[1350] 8. Security and Privacy Protection

[1351] The server will implement strong security and privacy protection for all data processing and storage. Specifically, data will be encrypted and strict access control will be set to ensure the safety of user data.

[1352] Specific examples

[1353] For example, a case will be described in which an e-commerce site uses the system of the present invention to monitor transaction data.

[1354] 1. Data Receipt

[1355] The server receives order data and user behavior data from the e-commerce site in real time. The order data includes information such as product name, price, and purchase date and time.

[1356] 2. Data cleansing

[1357] The server cleanses the data it receives, removes duplicate order data, and standardizes the data format, thereby improving the efficiency and accuracy of the analysis process.

[1358] 3. Real-time analysis

[1359] The server uses generative AI models to analyze data in real time, for example to detect unusually high purchase frequency of a particular product or an abnormal number of transactions.

[1360] 4. Root Cause Analysis

[1361] The server examines the relevant transaction data and system logs to determine the cause of the identified anomaly, and determines that the cause is, for example, a data discrepancy in an inventory system.

[1362] 5. Report Generation

[1363] The server generates a report detailing the anomaly, its cause, and recommended actions to take, which is output in PDF format and sent to the e-commerce site's system administrator.

[1364] 6. Emotion recognition

[1365] The emotion engine analyzes feedback and inquiries from system administrators to recognize their emotions. For example, it can identify the emotion of stress from feedback such as "the frequency of errors is too high."

[1366] 7. Personalized advice

[1367] The server will provide specific advice based on the recognized emotion, for example, providing a support message along with detailed guidance on "how to improve your workflow to resolve this issue."

[1368] 8. Security and Privacy Protection

[1369] The servers encrypt all communications and data storage and implement strict access controls to prevent unauthorized access to user data and confidential information.

[1370] In this way, the present invention reduces the burden on system personnel and improves the quality of the system and the user experience. By combining it with an emotion engine, responses to users become more flexible and effective.

[1371] The processing flow will be explained below.

[1372] Step 1:

[1373] The server receives transaction data from external systems. Specifically, the data is obtained in real time through HTTP requests or API calls and temporarily stored in data storage. This process is performed by setting up a listener for receiving data, and when data arrives, the listener generates an event and receives the data stream.

[1374] Step 2:

[1375] The server cleanses the data it receives. Specifically, it checks the data format and structure, removes unnecessary information and duplicate records, standardizes the data format, and corrects inconsistent data, preparing the cleansed data for analysis.

[1376] Step 3:

[1377] The server sends the cleansed data to the analytics engine, which begins real-time analysis by feeding the data into a generative AI model and running algorithms to detect anomalous data or errors that deviate from normal patterns.

[1378] Step 4:

[1379] The server logs any detected anomalies, adding details such as the time and location of the anomaly and the transaction ID to the anomaly log for future reference by administrators.

[1380] Step 5:

[1381] The server performs root cause analysis of the anomaly. Specifically, it collects and analyzes the circumstances surrounding the anomaly and related transaction data to identify the cause of the anomaly. For example, it identifies unusual purchasing patterns in a particular product category or data discrepancies in an inventory system.

[1382] Step 6:

[1383] The server generates a detailed report based on the results of the root cause analysis, summarizing the details of the anomaly, its cause, and recommended actions to take, and saves it in PDF or dashboard format.

[1384] Step 7:

[1385] When a user requests a report, the server provides it: the user requests a report through an interface (web browser or application), the server finds the saved report, and sends it to the user.

[1386] Step 8:

[1387] The emotion engine analyzes the text entered by the user through the user interface and recognizes the emotion. Specifically, the emotion engine uses natural language processing to identify emotions (joy, anger, sadness, surprise, etc.) from the user's text input and records them in a database.

[1388] Step 9:

[1389] The server personalizes the advice it provides based on the results of emotion recognition. Specifically, it takes the user's emotions into account and generates solutions with appropriate support and encouraging messages. For example, if the user enters "I'm having trouble with too many errors," the emotion engine will recognize "stress" and provide warm-hearted advice accordingly.

[1390] Step 10:

[1391] The servers implement strong security and privacy protection for all data processing and storage. Specifically, data is encrypted and strict access control is set up to ensure the safety of user data. A monitoring system is also in place to respond immediately to any signs of unauthorized access.

[1392] Example 2

[1393] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1394] While conventional data analysis systems receive, cleanse, analyze, and detect anomalies in real time, they lack clear cause analysis of detected anomalies and provide countermeasures that take user sentiment into account. In terms of security and privacy protection, the safety of user data is also not sufficiently ensured, which is a problem.

[1395] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving data from an external system in real time, a means for cleansing the received data, a means for detecting anomalies based on the preprocessed data, a means for identifying the cause of the detected anomaly, a means for generating a report based on the anomaly and its cause, a means for recognizing emotions from a user's input, a means for providing personalized advice based on the recognized emotions, and a means for protecting the security and privacy of user data. This makes it possible to detect anomalies and analyze their causes, present countermeasures that take user emotions into consideration, and ensure the safety of user data.

[1396] "Means of receiving data in real time from external systems" refers to the processes and technologies for obtaining data in real time through external databases or application program interfaces (APIs).

[1397] "Means of cleansing received data" refers to the process of removing unnecessary information from the data and standardizing the data structure in order to improve the accuracy and consistency of the data obtained.

[1398] "Anomaly detection methods based on pre-processed data" refers to algorithms and techniques that use cleansed data to analyze the data for anomalous patterns or deviations.

[1399] "Means for identifying the cause of a detected abnormality" refers to the technology and process for conducting a detailed analysis of the background and factors that caused the abnormality and identifying them.

[1400] "Means for generating reports based on anomalies and their causes" refers to technologies and processes that organize information about detected anomalies and their causes, and automatically generate reports that can be presented to users in an easy-to-understand manner.

[1401] "Means for recognizing emotions from user input" refers to natural language processing techniques that analyze the text and feedback entered by users into the system and identify the emotions contained therein.

[1402] "Means for providing personalized advice based on perceived emotions" refers to algorithms or technologies that take into account a user's emotional state to provide advice or support messages that are appropriate for that user.

[1403] "Measures to protect the security and privacy of user data" refers to encryption technologies and access control policies to protect users' personal information and prevent unauthorized access or information leaks.

[1404] The present invention is a system that provides users with a better interactive experience by combining the reception and analysis of transaction data, anomaly detection, root cause analysis, countermeasure planning, and security and privacy protection, as well as an emotion engine that recognizes user emotions. A detailed embodiment of this system will now be described.

[1405] Hardware and Software Configuration

[1406] The server plays the central role in the system. Data is received in real time from external systems and stored on the server. This data reception process uses HTTP requests and APIs. The data is stored in, for example, an S3 bucket on Amazon Web Services (AWS) or Google Cloud Storage.

[1407] Data cleansing is performed by a program installed on a server, written in a programming language such as Python or Java, that performs, among other things, data normalization and the elimination of duplicate data.

[1408] Real-time analysis for anomaly detection uses generative AI models, trained using deep learning frameworks such as TensorFlow and PyTorch, which are then analyzed by a server in real time to detect unusual data patterns and errors.

[1409] The server also handles root cause analysis, which involves collecting relevant data and using statistical methods and AI models to identify the cause of an anomaly.

[1410] The generated reports can be provided to the user in PDF format or via a web-based dashboard, which can be emailed or uploaded to a dashboard.

[1411] The emotion engine is responsible for recognizing user emotions. This engine uses natural language processing (NLP) technology to extract emotions from the text entered by the user. NLP tools such as Google Cloud Natural Language API and IBM Watson are used for this.

[1412] Personalized advice based on emotion recognition is generated by the server, which implements an algorithm that takes into account the recognized emotions and provides appropriate advice and support messages to the user.

[1413] Security and privacy are ensured through data encryption and strict access control, using SSL / TLS for communication encryption and AWS IAM policies for access control.

[1414] Specific examples

[1415] For example, consider the case where an e-commerce site uses the system of the present invention to monitor transaction data.

[1416] 1. Data Receipt

[1417] The server receives order data and user behavior data from the e-commerce site in real time. The order data includes information such as product name, price, and purchase date and time.

[1418] 2. Data cleansing

[1419] The server cleanses the data it receives, removes duplicate order data, and standardizes the data format, thereby improving the efficiency and accuracy of the analysis process.

[1420] 3. Real-time analysis

[1421] The server uses generative AI models to analyze the data in real time, for example to detect unusually high purchase frequency of a particular product or an unusual number of transactions.

[1422] 4. Root Cause Analysis

[1423] The server examines the relevant transaction data and system logs to determine the cause of the identified anomaly, and determines that the cause is, for example, a data discrepancy in an inventory system.

[1424] 5. Report Generation

[1425] The server generates a report summarizing the details of the anomaly, its cause, and recommended countermeasures, which is output in PDF format and sent to the e-commerce site's system administrator.

[1426] 6. Emotion recognition

[1427] The emotion engine analyzes feedback and inquiries from system administrators to recognize their emotions. For example, it can identify the emotion of stress from feedback such as "the frequency of errors is too high."

[1428] 7. Personalized advice

[1429] The server will then provide specific advice based on the perceived emotion, for example providing a support message along with detailed guidance on "how to improve your workflow to resolve this issue."

[1430] 8. Security and Privacy Protection

[1431] The servers encrypt all communications and data storage and implement strict access controls to prevent unauthorized access to user data and confidential information.

[1432] Prompt Sentence Examples

[1433] Can you please elaborate on the anomaly detection algorithms for transaction data in this system, specifically the generative AI model used and its training data?

[1434] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1435] Step 1: Data Reception

[1436] The server receives transaction data from external systems. Inputs include HTTP requests from e-commerce sites, order data obtained via APIs, and user behavior data. Specifically, the server uses Amazon Web Services (AWS) or Google Cloud Platform (GCP) to store the data in its own storage in real time.

[1437] Input: Transaction data from external systems (e.g., order data, user behavior data)

[1438] Output: Temporarily stored transaction data

[1439] Step 2: Data cleansing

[1440] The server cleanses the data it receives. It checks the format and structure of the data and removes unnecessary and duplicated data. This is done using programming languages ​​such as Python and Java, applying regular expressions and data conversion scripts. If some data is missing, it also performs missing value imputation.

[1441] Input: Temporarily stored transaction data

[1442] Output: Cleansed data

[1443] Step 3: Real-time analysis

[1444] The server performs real-time analysis on the cleansed data using generative AI models implemented using frameworks such as TensorFlow and PyTorch. The server detects abnormal data patterns and errors and generates alerts and notifications.

[1445] Input: Cleansed data

[1446] Output: Anomaly detection results and notifications

[1447] Step 4: Root Cause Analysis

[1448] The server performs a detailed analysis of the cause of the detected anomaly. It collects relevant data (such as the circumstances surrounding the anomaly and other transaction data) and uses statistical techniques and additional AI models to identify the cause. Specifically, it analyzes whether the anomalous transaction is linked to a specific promotion code or system log.

[1449] Input: Anomaly detection results and associated data

[1450] Output: Cause identification and details

[1451] Step 5: Generate a report

[1452] The server generates a detailed report based on the results of the root cause analysis. The report includes details of the anomaly, its cause, and recommended actions to take. The generated report is saved in PDF or web dashboard format and provided to the user. Specifically, the generated PDF can be sent by email or uploaded to the dashboard.

[1453] Input: Cause identification and details

[1454] Output: Detailed report

[1455] Step 6: Emotion Recognition

[1456] The emotion engine analyzes the text entered by the user through the user interface and recognizes the emotion. It uses Google Cloud Natural Language API and IBM Watson to extract emotions (joy, anger, sadness, surprise, etc.) from the text.

[1457] Input: User-entered text

[1458] Output: Recognized emotion

[1459] Step 7: Personalized advice

[1460] The server considers the user's emotions and personalizes the advice it provides. For example, if a user types "I'm having trouble with too many errors," the emotion engine will recognize "stress" and generate appropriate advice or encouraging messages.

[1461] Input: Recognized emotion

[1462] Output: Personalized advice

[1463] Step 8: Protecting security and privacy

[1464] The server implements strong security and privacy protection for all data processing and storage. Specifically, SSL / TLS is used for data encryption and strict access control is set to ensure the safety of user data. This is achieved using AWS IAM policies, etc.

[1465] Input: All user data

[1466] Output: Securely stored and processed user data

[1467] (Application example 2)

[1468] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1469] While traditional transaction monitoring systems are equipped with basic functions such as anomaly detection, cause identification, and user advice provision, they lack the ability to recognize user emotions and provide personalized advice based on those emotions. This makes it difficult to improve user experience or quickly resolve problems. Furthermore, robust measures are required from the perspective of security and privacy protection, but these measures are often not adequately provided.

[1470] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving data from an external system in real time, means for cleansing the received data, means for detecting anomalies based on the preprocessed data, means for identifying the cause of the detected anomaly, means for generating a report based on the anomaly and its cause, means for providing advice to the user regarding a specific problem, means for analyzing user feedback via a user interface and recognizing emotions, means for personalizing advice based on the recognized emotions, and means for protecting the security and privacy of user data. This makes it possible to provide advice that takes user emotions into consideration and to enhance security and privacy protection.

[1471] An "external system" refers to an external information processing device such as a server, database, or application that provides transaction data in real time.

[1472] "Means of receiving data" refers to a mechanism that uses an interface or protocol, such as an HTTP request or API, to obtain data from an external system.

[1473] "Data cleansing methods" refers to the process of removing unnecessary information and redundant data from received data and preparing the necessary data in an appropriate format.

[1474] "Means for detecting anomalies" refers to algorithms or systems that analyze and identify anomalous data that deviates from normal patterns in pre-processed data.

[1475] "Means for identifying the cause" refers to the mechanisms and methods for analyzing and identifying the factors behind the detected abnormality.

[1476] "Means for generating reports" refers to the process of creating and providing a report to the user that includes details of the anomaly, its cause, and recommended actions to take.

[1477] "Advice methods" refer to methods that provide users with appropriate solutions or guidance for specific problems.

[1478] "User interface" refers to the screens and input devices that allow a user to interact with a system, providing feedback and receiving information.

[1479] "Emotion recognition means" refers to natural language processing techniques and models for analyzing and identifying emotions from user feedback and input text.

[1480] "Means of personalizing advice" refers to the process of providing relevant and tailored advice based on perceived user sentiment.

[1481] "Security and privacy measures" refers to encryption technologies and access control mechanisms to ensure the security of user data and protect privacy.

[1482] This invention includes a system that provides real-time monitoring of transaction data in electronic payment services, anomaly detection, cause analysis, emotion recognition, and personalized advice. The overall flow of the system and the hardware and software used are described below.

[1483] Hardware and Software

[1484] The server receives transaction data and performs analysis and anomaly detection. The specific software and hardware used includes Python, scikit-learn, TensorFlow, Transformers, and Cryptography libraries.

[1485] Data Receipt

[1486] The server receives transaction data in real time from external systems. Specifically, it retrieves data from external databases and applications via HTTP requests or APIs and temporarily stores it in data storage.

[1487] Data Cleansing

[1488] The server cleanses the received data. Using Pandas, it checks the data format and structure, and removes unnecessary and duplicated data. It also standardizes the data format of necessary information to improve the accuracy of analysis.

[1489] Real-time analytics and anomaly detection

[1490] The server uses the Isolation Forest algorithm to detect anomalies in real time based on the cleansed data, a process that involves analyzing pre-processed data and identifying anomalies.

[1491] Root Cause Analysis and Report Generation

[1492] The server collects and analyzes relevant data to identify the cause of the detected anomaly. Based on the results, it generates a report containing details of the anomaly, its cause, and recommended actions to take. The generated report is saved in PDF or dashboard format and provided to the user.

[1493] Emotion Recognition and Personalized Advice

[1494] The server receives user feedback through the user interface and recognizes emotions using Transformers' natural language processing model. For example, from feedback such as "I'm having trouble with the frequency of errors," it identifies the emotion "stress." It then provides specific, personalized advice based on the recognized emotion. This makes the advice the user receives more appropriate and effective.

[1495] Security and Privacy Protection

[1496] The server implements strong security and privacy protection for all data processing and storage, specifically encrypting data using the Cryptography library and setting strict access control.

[1497] Specific examples

[1498] For example, if an e-commerce site uses the system of the present invention to monitor transaction data, it can receive order data and user behavior data in real time and detect anomalies. If an anomaly occurs, a detailed report is generated and an administrator is notified. Furthermore, emotions are recognized based on the administrator's feedback, and appropriate advice is provided.

[1499] Prompt Sentence Examples

[1500] User feedback: "I've been having a lot of payment errors lately."

[1501] Prompt: "Analyze feedback statements that are likely to cause users anger."

[1502] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1503] Step 1:

[1504] The server receives transaction data in real time from external systems via HTTP requests or APIs. The input is the transaction data obtained from the external system, and the output is the received data that is temporarily stored. This received data consists of various transactions (e.g., product purchase data, payment data, etc.).

[1505] Step 2:

[1506] The server uses the Pandas library to cleanse the incoming data by removing duplicates and unnecessary fields and converting the data into a uniform format. The input is the temporarily stored incoming data, and the output is a cleansed, consistent dataset. This cleansing improves the accuracy of the data for analysis.

[1507] Step 3:

[1508] The server uses the Isolation Forest algorithm to detect anomalies in real time based on the cleansed data. The input is the cleansed dataset, and the output is the identification of anomalous data. Specifically, transaction data is converted into a feature vector and classified as anomalous or normal.

[1509] Step 4:

[1510] The server collects and analyzes related transaction data and system logs to identify the cause of the detected anomaly. The input is the anomaly data and related complementary data, and the output is the analysis result of the anomaly's cause. The server uses machine learning models and statistical methods in this analysis process.

[1511] Step 5:

[1512] The server generates a report that summarizes the details of the anomaly, its cause, and recommended countermeasures. The input is the cause analysis result, and the output is a report in PDF or dashboard format. This report details the specific content of the anomaly, the scope of its impact, and the countermeasures.

[1513] Step 6:

[1514] The server receives user feedback through the user interface and recognizes emotions using Transformers' natural language processing model. The input is the user's feedback text, and the output is the recognized emotion (e.g., anger, sadness, joy, etc.). As a specific example, the server identifies the emotion "stress" from the feedback, "I've been having trouble with a lot of payment errors lately."

[1515] Step 7:

[1516] The server then personalizes and provides advice to users based on the recognized emotions. The input is the recognized user's emotions and the analysis results of transaction data, and the output is a personalized advice message. For example, if stressful emotions are recognized, advice is generated that includes a link to a support guide that explains the solution in detail.

[1517] Step 8:

[1518] The server uses the Cryptography library to encrypt all data during processing and storage, and sets strict access control. All transaction data and analysis data are input, and the output is encrypted and secure data. This protects user security and privacy.

[1519] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1520] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1521] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1522] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1523] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1524] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1525] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1526] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1527] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1528] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1529] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1530] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1531] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1532] 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.

[1533] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1534] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1535] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1536] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1537] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1538] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1539] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1540] The following is further disclosed regarding the above embodiment.

[1541] (Claim 1)

[1542] a means for receiving data in real time from an external system;

[1543] a means for cleansing the received data;

[1544] a means for detecting anomalies based on the preprocessed data;

[1545] a means for identifying the cause of the detected anomaly; and

[1546] a means for generating a report based on the anomalies and their causes;

[1547] a means of providing users with advice on specific issues;

[1548] A system that includes measures to protect the security and privacy of user data.

[1549] (Claim 2)

[1550] 10. The system of claim 1, further comprising means for analyzing the preprocessed data in real time to detect anomalies.

[1551] (Claim 3)

[1552] 10. The system of claim 1, further comprising means for removing unnecessary fields and duplicate records from the preprocessed data.

[1553] "Example 1"

[1554] (Claim 1)

[1555] a means for receiving data in real time from an external system;

[1556] a means for cleansing the received data;

[1557] A means of detecting anomalies using generative AI models based on preprocessed data; and

[1558] a means of identifying the specific cause of the detected anomaly; and

[1559] a means for generating a report based on the anomalies and their causes;

[1560] a means for providing advice to a user regarding a particular problem based on a prompt;

[1561] measures to protect the security and privacy of user data;

[1562] a means for storing the preprocessed data in storage;

[1563] A means of enforcing access control on stored data

[1564] A system including:

[1565] (Claim 2)

[1566] 10. The system of claim 1, further comprising means for analyzing the preprocessed data in real time and detecting anomalies using the generative AI model.

[1567] (Claim 3)

[1568] 10. The system of claim 1, further comprising means for removing unnecessary fields and duplicate records from the preprocessed data.

[1569] "Application Example 1"

[1570] (Claim 1)

[1571] a means for receiving data in real time from an external system;

[1572] a means for cleansing the received data;

[1573] a means for detecting anomalies based on the preprocessed data;

[1574] a means for identifying the cause of the detected anomaly; and

[1575] a means for generating a report based on the anomalies and their causes;

[1576] a means of providing users with advice on specific issues;

[1577] measures to protect the security and privacy of user data;

[1578] A means of linking with smart devices to notify users of the generated reports;

[1579] A means for generating a prompt sentence and providing advice to a user based on the anomaly detection result;

[1580] A system that includes a means to ensure data portability and security using cryptographic protocols.

[1581] (Claim 2)

[1582] 10. The system of claim 1, further comprising means for analyzing the preprocessed data in real time to detect anomalies.

[1583] (Claim 3)

[1584] 10. The system of claim 1, further comprising means for removing unnecessary fields and duplicate records from the preprocessed data.

[1585] "Example 2: Combining Emotion Engines"

[1586] (Claim 1)

[1587] a means for receiving data in real time from an external system;

[1588] a means for cleansing the received data;

[1589] a means for detecting anomalies based on the preprocessed data;

[1590] a means for identifying the cause of the detected anomaly; and

[1591] a means for generating a report based on the anomalies and their causes;

[1592] a means for recognizing emotions from user input;

[1593] a means for providing personalized advice based on the perceived emotions;

[1594] A system that includes measures to protect the security and privacy of user data.

[1595] (Claim 2)

[1596] 10. The system of claim 1, further comprising means for analyzing the preprocessed data in real time to detect anomalies.

[1597] (Claim 3)

[1598] 10. The system of claim 1, further comprising means for removing unnecessary fields and duplicate records from the preprocessed data.

[1599] "Application example 2 when combining emotion engines"

[1600] (Claim 1)

[1601] a means for receiving data in real time from an external system;

[1602] a means for cleansing the received data;

[1603] a means for detecting anomalies based on the preprocessed data;

[1604] a means for identifying the cause of the detected anomaly; and

[1605] a means for generating a report based on the anomalies and their causes;

[1606] a means of providing users with advice on specific issues;

[1607] A means of analyzing user feedback through the user interface and recognizing emotions;

[1608] a means for personalizing advice based on perceived emotions;

[1609] A system that includes measures to protect the security and privacy of user data.

[1610] (Claim 2)

[1611] 10. The system of claim 1, further comprising means for analyzing the preprocessed data in real time to detect anomalies.

[1612] (Claim 3)

[1613] 10. The system of claim 1, further comprising means for removing unnecessary fields and duplicate records from the preprocessed data. [Explanation of symbols]

[1614] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for receiving data in real time from an external system; a means for cleansing the received data; a means for detecting anomalies based on the preprocessed data; a means for identifying the cause of the detected anomaly; and a means for generating a report based on the anomalies and their causes; a means of providing users with advice on specific issues; A system that includes measures to protect the security and privacy of user data.

2. The system of claim 1 , further comprising means for analyzing the pre-processed data in real time to detect anomalies.

3. The system of claim 1 , further comprising means for removing unnecessary fields and duplicate records from the preprocessed data.

Images