system

Abstract

Provide a system. 【Solution means】 A data receiving device, A device that analyzes the format of the received information and checks its integrity, A device that executes a generation model for automatically attaching meta-information to information, A device that categorizes information based on the attached meta-information and stores it in a data store, A device that monitors the change frequency of information and stores and manages information that has not been changed for a certain period, A device that retrains the generation model using a new information set, A device that monitors the inflow of information in real time, automatically detects anomalies, and notifies them, A system including.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern society, as the amount and variety of data increase, enterprises and organizations are required to manage their data efficiently. However, it takes a great deal of time and labor to manually perform data reception, analysis, metadata assignment, categorization, update frequency management, archiving, and re-learning of the generation model for accuracy improvement, and the risk of human error increases. In addition, since there is a lack of an efficient system for consistent management of large-scale datasets, a method for solving these problems is needed.

Means for Solving the Problems

[0005] This invention provides a system comprising data receiving means, integrity verification means, automatic metadata assignment means using a generative model, data classification means based on metadata, update frequency monitoring means, archiving means, and generative model retraining means using new data. This automates a series of data management processes, reducing human error and improving management efficiency. Automatic tagging and efficient classification of data enable rapid data retrieval and access within the database, ultimately comprehensively solving data management challenges for companies and organizations.

[0006] "Data receiving means" refers to a device or function that can receive data in various formats transmitted from an external source and incorporate its contents for internal processing.

[0007] "Consistency verification means" refers to a device or function for analyzing the format and content of received data to detect format errors or data inconsistencies.

[0008] A "generative model" is an algorithm or method that learns patterns and features from data and automatically adds metadata to newly received data.

[0009] "Automatic metadata assignment means" refers to a device or function that mechanically assigns appropriate metadata to data using a generative model.

[0010] "Data classification means" refers to a device or function for organizing and classifying data into specific categories based on assigned metadata.

[0011] "Update frequency monitoring means" refers to a device or function for monitoring the update history of data and identifying data that has not been updated for a certain period of time.

[0012] An "archiving tool" is a device or function for moving infrequently updated data to another storage location and saving it as a backup.

[0013] A "generative model retraining means" is a device or function that performs a retraining process to improve the accuracy of a generative model using a new dataset. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention is a system designed for efficient data management, automating data reception, analysis, automatic metadata assignment, classification, update frequency management, archiving, and retraining of generative models.

[0036] First, the server receives data in various formats from external terminals and users. The received data can be in a wide variety of formats, such as CSV, JSON, and XML. To process this data efficiently, the server analyzes the data format and converts it into a common format suitable for internal processing. Consistency checks to detect data inconsistencies and format errors are also performed at this stage.

[0037] Next, the server runs a generative model to automatically assign metadata to the data. The generative model uses a pre-trained algorithm to analyze the data's features and attach appropriate metadata to the data entries. This automated assignment process streamlines data organization and subsequent processing.

[0038] Based on the assigned metadata, the server classifies the data into specific categories. For example, customer data might be organized into categories such as "VIP customers," "repeat customers," and "new customers" based on purchase history and customer attributes.

[0039] After the data is saved, the server monitors its update frequency. If the data is not updated for a certain period, it is considered "inactive" and archived. This archiving process improves storage efficiency, and necessary information is securely stored as a backup.

[0040] Furthermore, the server retrains the generative model using the newly received data. This improves the accuracy of future data processing, enabling more accurate metadata assignment and classification in subsequent data analyses.

[0041] As a concrete example, when a user uploads newly acquired customer information from their terminal to the server through sales activities, the server quickly analyzes the information and assigns appropriate metadata to each customer. This information is categorized and stored in a database, making it readily accessible to the user when needed. As a result, customer management and marketing activities become more efficient.

[0042] Thus, the system implementing the present invention provides a means to reduce the time and human costs associated with data management, as well as to improve the accuracy of management tasks.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] Users input data using their devices and send it to the server. The data may exist in formats such as CSV, JSON, or XML.

[0046] Step 2:

[0047] The server analyzes the received data and identifies the format of the input data. If the format is different, it converts it to a unified internal format. During this process, it also performs a data integrity check to ensure there are no errors or inconsistencies.

[0048] Step 3:

[0049] The server uses a pre-configured generative model to automatically add metadata to the data. The generative model analyzes the characteristics of the data and adds appropriate tags and attributes. This analysis is based on the data's content and patterns.

[0050] Step 4:

[0051] The server categorizes data based on metadata. For example, customer data is organized into categories such as "VIP customers" and "new customers" according to purchase history and attribute information. This classification process makes subsequent searches and references in the database more efficient.

[0052] Step 5:

[0053] The server is the data storage location and monitors the update frequency of data entries. Data that has not been updated for a certain period is considered "inactive" and moved to a different area of ​​storage as an archive. This process ensures efficient use of storage.

[0054] Step 6:

[0055] The server periodically incorporates new data into the generative model and retrains it. This process improves the accuracy of subsequent data processing. Since learning progresses each time new data is added, improvements in tagging and classification accuracy can be expected.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] In modern information management, receiving, organizing, and storing vast amounts of information is essential. However, the manual processes involved in information analysis, classification, and storage are time-consuming and costly in terms of human resources, necessitating efficient management. Furthermore, the depletion of storage space due to outdated information and the oversight of important information are also challenges. Overcoming these obstacles and achieving smooth and accurate information management is crucial.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes means for receiving information, means for analyzing the type of the received information and verifying its consistency, and means for executing an algorithm for automatically assigning characteristic information to the information. This enables efficient and accurate analysis, classification, and storage of information.

[0061] "Information" is a general term for data expressed in digital format, encompassing a variety of forms and contents.

[0062] "Means" refers to the methods or devices used to achieve a specific objective.

[0063] "Reception" refers to the action or process of taking in information from the outside.

[0064] "Type" refers to the form or structure of information, and it forms the basis for interpreting data.

[0065] "Analysis" refers to the process of examining information in detail to understand and interpret its structure and meaning.

[0066] "Consistency" refers to a state where information is coherent and free from contradictions.

[0067] "Characteristic information" refers to labels and tags that represent the characteristics and attributes of information, and is used for understanding and classifying information.

[0068] An "algorithm" is a procedure or computational method for solving a specific problem.

[0069] Classification is the process of grouping information according to common characteristics or criteria.

[0070] "Memory space" refers to physical or virtual space used to store information.

[0071] "Update frequency" is an indicator that shows how often information is changed or modified.

[0072] "Tracking" refers to monitoring and recording changes and statuses of information.

[0073] "Period" refers to the length of time that a particular activity or state continues.

[0074] "Storage" refers to the act of continuously preserving information over a long period of time.

[0075] An "information set" refers to the whole collection of multiple related pieces of information.

[0076] "Retraining" is the process by which an existing model incorporates new information to improve its performance.

[0077] The embodiment of this invention aims to streamline the reception, analysis, automatic assignment, classification, storage, and retraining of information in a data management system. This system operates primarily on a server and is designed using the following technical elements.

[0078] First, the server uses HTTPS as its communication protocol to securely receive information. This makes it possible to securely retrieve information sent from external terminals and users.

[0079] The received information is parsed using a data parser on the server to determine its data type. This parsing process utilizes parsing tools such as Pandas to convert information in different formats into standard data frames. After conversion, a consistency check is performed, and if inconsistencies are detected, they are logged and the user is notified.

[0080] Next, the server runs a generative AI model to add feature information to the data. Here, a pre-trained language model is used as the AI ​​model. The generative AI model, with a specific prompt, analyzes the features of the data and adds appropriate feature information, thereby streamlining the data organization process. An example of a prompt is, "Classify new customer information into VIP customers, repeat customers, and others."

[0081] The server then classifies the information using the K-means clustering algorithm. The classified information is managed in memory. This allows users to quickly access specific information.

[0082] To track update frequency, a scheduling tool (e.g., a Cron job) is used on the server to perform archiving, moving information that hasn't been updated for a specific period to a storage server. This allows the system to utilize storage efficiently, and important information is stored securely.

[0083] Finally, the server retrains the generated AI model based on the newly accumulated information. This process improves the model's performance by inputting new sets of information. Through this series of processes, users can reduce the effort required for information management while enabling more accurate information processing.

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

[0085] Step 1:

[0086] The server receives data from external terminals and users. Input is, for example, data files in CSV or JSON format. The server uses HTTPS to receive data and ensure security. Output is stored internally as the received raw data.

[0087] Step 2:

[0088] The server parses the format of the received data. The input here is securely stored raw data. The server uses a data parser tool to identify the format and converts the data into a standard dataframe format using the Pandas library. The output is data formatted into a common format.

[0089] Step 3:

[0090] The server performs consistency checks on data in a common format. The input is the formatted data. The server verifies the data integrity, logs any inconsistencies found, and notifies the user. The output is either data that has been verified as consistent or a data log where inconsistencies have been recorded.

[0091] Step 4:

[0092] The server runs a generative AI model and adds feature information to the data. The input is data with confirmed consistency. The server invokes a pre-trained AI model and performs data analysis based on specific prompt statements. The output is data with added feature information.

[0093] Step 5:

[0094] The server classifies data based on feature information. The input is data to which feature information has been added. The server uses the K-means clustering algorithm to classify the data into multiple categories. The output is a dataset classified by category.

[0095] Step 6:

[0096] The server monitors the update frequency of classified data. The input is data classified by category. The server uses a scheduling tool to periodically check the update frequency and identify data that has not been updated for a certain period. The output is a record of whether or not the data has been updated.

[0097] Step 7:

[0098] The server archives data that has not been updated. The input is data identified as not having been updated. The server moves this data to storage for long-term retention. The output is the archived data.

[0099] Step 8:

[0100] The server retrains the generative AI model using new data. The input is the latest data set. The server feeds the new data into the AI ​​model and improves the model's accuracy through retraining. The output is the AI ​​model with improved accuracy.

[0101] (Application Example 1)

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

[0103] In data centers, it is extremely difficult for administrators to efficiently organize vast amounts of information, detect anomalies in real time, and respond quickly using traditional manual methods. Therefore, there is a need for a system that not only automates data classification and storage, but also improves the efficiency and speed of anomaly detection.

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

[0105] In this invention, the server includes a data receiving device, a device for analyzing the format of the received information and verifying its integrity, and a device for executing a generative model for automatically adding metadata to the information. This enables real-time monitoring of information inflow and automatic detection and notification of anomalies, thereby improving data management efficiency and the speed of anomaly response.

[0106] A "data receiving device" is a device that receives data in various formats from external information sources and supplies it to a server.

[0107] A "device for analyzing format and verifying integrity" is a device that analyzes the format of received information to detect consistency and errors.

[0108] A "device that executes a generative model for automatically adding metadata" is a device that uses a generative model to analyze the characteristics of information and add appropriate metadata.

[0109] A "device for categorizing information and storing it in a data store" is a device that classifies information into specific categories based on metadata and efficiently stores the data.

[0110] A "device for monitoring change frequency and storing and managing information" is a device that monitors the frequency of changes to information and securely stores information that has not been updated for a certain period of time.

[0111] A "generative model retraining device" is a device that retrains a generative model using new information data to improve the accuracy of future information processing.

[0112] A "device that monitors information inflow in real time and automatically detects and notifies of anomalies" is a device that detects anomalies in real time when information continues to flow in and notifies the administrator.

[0113] The server is equipped with a data receiving device for receiving data in various formats from external terminals. This device receives formatted data such as CSV, JSON, and XML, analyzes the format, and verifies its integrity. Since the verified data is difficult to manage as is, a metadata addition device using a generative AI model performs feature analysis, and appropriate metadata is automatically added.

[0114] Next, the server's information categorization device classifies the information into specific categories based on the assigned metadata and efficiently stores it in the data store. This speeds up information retrieval and access. This data store is managed by a device that monitors the frequency of changes, and information that has not changed for a certain period is archived to optimize storage.

[0115] Furthermore, each time new information data is added, the system retrains the generative model, improving its accuracy based on this data. This makes it possible to perform more accurate analysis in future data processing.

[0116] As a concrete example, energy usage in a data center is monitored in real time, and when usage exceeds a certain threshold, a device that monitors the inflow of information in real time and automatically detects anomalies notifies the administrator's terminal with an alert. This enables a rapid response.

[0117] An example of a prompt message might be, "How can I detect and notify of anomalies in an application that needs to view data in real time?" The hardware used includes data center server infrastructure and administrator smartphones, while the software includes Python, Flask, and Tensorflow®. This system automates complex data management processes and streamlines management tasks.

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

[0119] Step 1:

[0120] The server receives various data formats (CSV, JSON, XML, etc.) from external terminals. These data files are provided as input, and the format of the received data is specified as output. The server recognizes these formats and prepares the data to be sent to the next processing step.

[0121] Step 2:

[0122] The server analyzes the format of the received data and verifies its integrity. Data files are provided as input, and format consistency and error information are obtained as output. By checking the data format and for any defects, quality assurance is performed before proceeding to subsequent processing.

[0123] Step 3:

[0124] The server automatically adds metadata to the data using a generative AI model. Analyzed data is provided as input, and the output is data with added metadata. The generative AI model performs feature analysis to add appropriate metadata to the data.

[0125] Step 4:

[0126] The server categorizes information into specific categories based on metadata and stores it in the data store. Data with metadata is provided as input, and the categorized data is stored as output. This enables efficient data retrieval and utilization.

[0127] Step 5:

[0128] The server monitors the frequency of changes to stored data and archives data that has not been updated for a certain period. Update information for stored data is provided as input, and a list of archived data is obtained as output. This maintains storage efficiency.

[0129] Step 6:

[0130] The server retrains the generative model based on the new data. New data is provided as input, and an improved generative model is obtained as output. This will increase the accuracy of future data processing and enable more precise analysis.

[0131] Step 7:

[0132] The server monitors the inflow of information, such as energy usage in the data center, in real time and sends an alert to the administrator's terminal if an anomaly is detected. Usage data is provided as input, and the notification content is sent to the terminal as output. This enables a rapid response.

[0133] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0134] This invention improves the accuracy of data organization and analysis by incorporating an emotion engine into a data management system to recognize user emotions. The system automates data reception, analysis, automatic metadata assignment, emotion analysis, data classification, update frequency management, archiving, and retraining of generative models.

[0135] First, the user inputs new data into the system via a terminal. During this process, the emotion engine recognizes the user's emotions in real time based on their voice, facial expressions, input speed, and other factors. This emotion information is then sent to the data server as metadata.

[0136] The server analyzes the received data, ensuring format consistency and verifying integrity. Furthermore, it uses a built-in generative model to add metadata and user sentiment data to the data, improving the accuracy of the information.

[0137] Based on the assigned metadata and sentiment data, the server categorizes the data. For example, in the case of customer data, customers that the sentiment engine determines to have a high purchase intent are classified as "priority customers" and distinguished from regular customers.

[0138] Once the data is integrated, the server monitors its update frequency. Data that hasn't been updated for a certain period is automatically archived, but even then, sentiment data trends are taken into consideration, and special processing may be applied.

[0139] Furthermore, the server retrains the generative model using newly received data and sentiment information. As a result, the model's ability to adapt to changes in sentiment improves, leading to even greater accuracy in subsequent data processing.

[0140] As a concrete example, suppose a user submits a complaint through an inquiry form, and dissatisfaction or stress is recognized. Through this information, the server identifies that customer as a "customer who needs improvement" and adjusts the priority of follow-up. In this way, it becomes possible to improve the quality of customer service and customer satisfaction.

[0141] With the above configuration, the system implementing the present invention integrates emotion-based data management and achieves a higher level of data analysis and management compared to conventional data management systems.

[0142] The following describes the processing flow.

[0143] Step 1:

[0144] Users input data using their devices, and during this process, voice, facial expressions, and other information are collected in real time by the device's emotion engine. The emotion engine analyzes this data to generate the user's emotional data.

[0145] Step 2:

[0146] The device sends data entered by the user and emotional data analyzed by the emotion engine to the server. This data may be in various formats such as CSV or JSON.

[0147] Step 3:

[0148] The server analyzes the received data and converts it into a standardized format. During this process, it verifies data integrity and detects inconsistencies and errors.

[0149] Step 4:

[0150] The server uses a built-in generative model to automatically add metadata to the data. In this process, a pre-trained algorithm adds tags and attributes based on the data's features.

[0151] Step 5:

[0152] The server considers the attached metadata and sentiment data obtained from the user to classify the data into specific categories. For example, customers with high purchase intent are classified as "priority customers," while those with low intent are classified as "regular customers."

[0153] Step 6:

[0154] The server monitors the update frequency of stored data. Data that has not been updated for a certain period is automatically archived, but if special processing based on sentiment data is required at this time, a re-verification is performed.

[0155] Step 7:

[0156] The server retrains its generative model using newly received data. This retraining process also includes sentiment data, aiming to improve accuracy in subsequent data processing.

[0157] In this way, a system is built that significantly improves the efficiency and accuracy of data management by automating the data input, sentiment analysis, and data management processes.

[0158] (Example 2)

[0159] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0160] Modern data management systems face challenges in accuracy and efficiency because it is difficult to consider user emotions when organizing and analyzing data. Furthermore, there is a growing desire to achieve more comprehensive and precise data management by utilizing emotional information in data updates and classification.

[0161] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0162] In this invention, the server includes means for receiving data, means for analyzing the format of the received data and verifying its integrity, and means for executing a generative model for automatically adding metadata and sentiment data to the data. This enables advanced data management and analysis that reflects the user's sentiment.

[0163] A "means of receiving data" refers to a module that receives input data from the user and incorporates it into the system.

[0164] "Means for analyzing the format of received data and verifying its integrity" refers to a processing device that analyzes the format of input data and checks whether the data is correct and consistent.

[0165] "Means for executing a generative model for automatically adding metadata and sentiment data" refers to an algorithm for automatically generating and adding additional information related to data and user sentiment information.

[0166] "A means of classifying data and storing it in a database" refers to a system for classifying analyzed data into specific categories and storing them in a database that can be used for long-term storage.

[0167] "A means of monitoring update frequency and archiving data that has not been updated for a certain period based on sentiment data" refers to the process of checking the frequency of data changes, and if the data has not been updated for a certain period, considering sentiment information, and moving and saving the data to a separate storage location.

[0168] "Methods for retraining generative models" refer to learning algorithms that readjust the parameters of a generative model based on newly collected data and sentiment information to improve its performance.

[0169] This data management system begins with the user inputting new data through a terminal. The terminal is equipped with voice recognition software and a facial expression analysis system, which uses an emotion engine to analyze the user's voice, facial expressions, input speed, etc. This emotion engine uses an emotion recognition algorithm to recognize the user's emotions in real time and generates the results as emotion data.

[0170] The server receives data and sentiment data sent from the user. It then uses dedicated software to analyze the data format and verify its consistency. Next, the server uses a generative AI model to automatically add metadata and sentiment data to the received data. This generative model is built on deep learning algorithms and effectively extracts information from the dataset.

[0171] The server then categorizes the data based on the assigned metadata and sentiment data. For example, in the case of customer data, it can identify customers with high purchase intent and classify them as "priority customers." This classification is stored in a database and is easily accessible.

[0172] Furthermore, the server monitors the frequency of data updates and archives data that has not been updated for a certain period, taking sentiment data into consideration. This process enables the system to achieve efficient storage management. At the same time, the server retrains its generative model based on newly received data and sentiment information, improving the accuracy of the algorithm.

[0173] For example, when a user submits a complaint through an inquiry form, the system can recognize dissatisfaction and stress as emotional data and treat them as high-priority triage items. This speeds up customer support responses and contributes to improved customer satisfaction.

[0174] An example of a prompt message is, "Process the voice-inputted complaint information, determine the customer's emotions through sentiment analysis, and prioritize their response." By using this prompt, the system can perform emotion-based data management in response to user requests.

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] The user uses a device to input new data. This input data may include text, audio, and images. The device uses sensors to capture the user's voice, facial expressions, and input speed during data entry, and analyzes this data with an emotion engine. This process extracts emotion data from the input data and formats it as metadata.

[0178] Step 2:

[0179] The server receives input data and metadata sent from the terminal. The server analyzes the data format and converts it to the correct format. During the analysis process, a generative AI model is used to analyze the data structure and verify its consistency. Once the format is correctly prepared, the data is ready to be processed internally as structured data.

[0180] Step 3:

[0181] The server runs a generative AI model, adding multiple layers of metadata, including sentiment data, to the input data. When tagging the data, the server retrains the generative model using historical datasets. This tagging process allows the data to acquire additional labels to highlight specific information. The generated metadata improves the accuracy of the data and may also be used as prompts.

[0182] Step 4:

[0183] The server categorizes data based on the assigned metadata and sentiment data. Specifically, it measures user purchase intent based on the analyzed sentiment data and creates lists labeled as priority customers, etc. This classification process forms the basis for formulating optimal management strategies.

[0184] Step 5:

[0185] The server has the function of storing classified data in a database and monitoring the update frequency. During this process, the server checks the sentiment data of data that has not been updated for a certain period and makes a decision on whether to archive it. Data deemed to have important sentiment is retained for special processing rather than being archived.

[0186] Step 6:

[0187] The server retrains its generative AI model based on newly received datasets and sentiment data. This retraining process uses a feedback loop derived from the new inputs to improve the accuracy of sentiment recognition and metadata assignment, thereby enhancing its ability to process data for the next generation.

[0188] (Application Example 2)

[0189] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0190] Current data management systems struggle to organize and classify data while considering user emotions. This often results in an inability to provide information and responses that meet user needs. In particular, consumer electronics require appropriate responses that reflect the user's emotions, but current technology is insufficient to achieve this.

[0191] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0192] In this invention, the server includes means for receiving data, means for analyzing the format of the received data and verifying its integrity, means for executing a generative model for automatically attaching metadata to the data, means for recognizing emotions from user input information, means for classifying data based on the user's emotion data and the attached metadata and storing it in an information set, means for monitoring the data update frequency and archiving data that has not been updated for a certain period of time, and means for retraining the generative model using a new dataset. This enables advanced data management based on user emotions and appropriate responses to the emotions of users in consumer electronic devices.

[0193] "Data receiving means" refers to a device or method that acquires data from an external source and converts it into a format usable within the system.

[0194] "Emotion recognition means" refers to a technology or device for detecting and identifying emotions from data such as the user's voice, facial expressions, and input speed.

[0195] A "generative model" is a computational model used to generate appropriate metadata and tags in response to input data, and is learned through machine learning and AI technologies.

[0196] Metadata is supplementary information added to classify or organize data, making it easier to understand and search for.

[0197] An "information collection" is a database or storage device where classified data is stored, and it serves as the foundation for proper information management.

[0198] "Retraining" is the process of training an existing generative model again with a newly acquired dataset to improve the model's accuracy and adaptability.

[0199] In the system for implementing this invention, the user first inputs data via a terminal. The terminal is equipped with emotion recognition means, which detects the user's emotions from data such as voice, facial expressions, and input speed. The emotion data is attached as metadata and sent to the server along with the data.

[0200] The server analyzes the format of the received data, verifies its integrity, and then automatically adds metadata to the data using a generative model. Python and other machine learning libraries can be used as the generative AI model. Based on the added metadata and user sentiment data, the server classifies and stores the data as an information set. This process enables data management tailored to the user's sentiment.

[0201] Furthermore, the server improves the accuracy of data processing by retraining the generative model using a new dataset. Cloud services such as Google Cloud Platform and AWS can be used for retraining.

[0202] As a concrete example, suppose a child returns home from school and says to their device, "Today's homework was difficult." The server senses the child's stress level from this statement and suggests, through consumer electronics, "Maybe you should take a break and listen to your favorite music." In this way, it becomes possible to provide appropriate responses that reflect the user's emotions.

[0203] An example of a prompt statement might be, "Develop an application for a consumer robot that reads the emotions of the user when they speak and takes appropriate action." Based on this prompt statement, it is possible to create a flow for generating an AI model for emotion recognition and processing the data.

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

[0205] Step 1:

[0206] The user inputs data into the device. The input data is recorded on the device as audio or text. At this point, emotion recognition is activated, analyzing emotions from voice tone and input speed. The input data and analyzed emotions are compiled as metadata.

[0207] Step 2:

[0208] The terminal sends metadata and data to the server. The server analyzes the format of the received data and verifies its consistency. Here, it checks for inconsistencies in the data and standardizes it to a specific format. It also checks the sentiment information recorded as metadata and converts it into a format that can be used by the generative model.

[0209] Step 3:

[0210] The server executes a generative model and automatically adds new metadata to the data. The generative AI model generates prompt statements in response to the input information and processes the information to organize and expand it. This model adds metadata in a format that incorporates user sentiment information, thereby increasing the value of the data.

[0211] Step 4:

[0212] Based on the generated metadata, the server classifies and stores the data as an information collection. In this process, the data is divided into appropriate categories according to the metadata and assigned sentiment information. This makes it easy to search and retrieve information within the database.

[0213] Step 5:

[0214] The server monitors the frequency of data updates, and data that has not been updated for a certain period is archived. During this process, sentiment data is taken into consideration, and archiving is adjusted based on specific criteria. Furthermore, the generative model is retrained using new datasets to prepare for improved accuracy in future data processing.

[0215] Step 6:

[0216] The retrained generative model is used for subsequent data processing, improving its accuracy and adaptability. This allows the server to perform more sophisticated sentiment analysis and metadata assignment during subsequent user input, thereby improving the user experience.

[0217] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0218] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0219] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0220] [Second Embodiment]

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

[0222] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0223] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0224] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0225] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0226] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0227] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0228] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0229] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0230] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0231] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0232] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0233] This invention is a system designed for efficient data management, automating data reception, analysis, automatic metadata assignment, classification, update frequency management, archiving, and retraining of generative models.

[0234] First, the server receives data in various formats from external terminals and users. The received data can be in a wide variety of formats, such as CSV, JSON, and XML. To process this data efficiently, the server analyzes the data format and converts it into a common format suitable for internal processing. Consistency checks to detect data inconsistencies and format errors are also performed at this stage.

[0235] Next, the server runs a generative model to automatically assign metadata to the data. The generative model uses a pre-trained algorithm to analyze the data's features and attach appropriate metadata to the data entries. This automated assignment process streamlines data organization and subsequent processing.

[0236] Based on the assigned metadata, the server classifies the data into specific categories. For example, customer data might be organized into categories such as "VIP customers," "repeat customers," and "new customers" based on purchase history and customer attributes.

[0237] After the data is saved, the server monitors its update frequency. If the data is not updated for a certain period, it is considered "inactive" and archived. This archiving process improves storage efficiency, and necessary information is securely stored as a backup.

[0238] Furthermore, the server retrains the generative model using the newly received data. This improves the accuracy of future data processing, enabling more accurate metadata assignment and classification in subsequent data analyses.

[0239] As a concrete example, when a user uploads newly acquired customer information from their terminal to the server through sales activities, the server quickly analyzes the information and assigns appropriate metadata to each customer. This information is categorized and stored in a database, making it readily accessible to the user when needed. As a result, customer management and marketing activities become more efficient.

[0240] Thus, the system implementing the present invention provides a means to reduce the time and human costs associated with data management, as well as to improve the accuracy of management tasks.

[0241] The following describes the processing flow.

[0242] Step 1:

[0243] Users input data using their devices and send it to the server. The data may exist in formats such as CSV, JSON, or XML.

[0244] Step 2:

[0245] The server analyzes the received data and identifies the format of the input data. If the format is different, it converts it to a unified internal format. During this process, it also performs a data integrity check to ensure there are no errors or inconsistencies.

[0246] Step 3:

[0247] The server uses a pre-configured generative model to automatically add metadata to the data. The generative model analyzes the characteristics of the data and adds appropriate tags and attributes. This analysis is based on the data's content and patterns.

[0248] Step 4:

[0249] The server categorizes data based on metadata. For example, customer data is organized into categories such as "VIP customers" and "new customers" according to purchase history and attribute information. This classification process makes subsequent searches and references in the database more efficient.

[0250] Step 5:

[0251] The server is the data storage location and monitors the update frequency of data entries. Data that has not been updated for a certain period is considered "inactive" and moved to a different area of ​​storage as an archive. This process ensures efficient use of storage.

[0252] Step 6:

[0253] The server periodically incorporates new data into the generative model and retrains it. This process improves the accuracy of subsequent data processing. Since learning progresses each time new data is added, improvements in tagging and classification accuracy can be expected.

[0254] (Example 1)

[0255] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0256] In modern information management, receiving, organizing, and storing vast amounts of information is essential. However, the manual processes involved in information analysis, classification, and storage are time-consuming and costly in terms of human resources, necessitating efficient management. Furthermore, the depletion of storage space due to outdated information and the oversight of important information are also challenges. Overcoming these obstacles and achieving smooth and accurate information management is crucial.

[0257] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0258] In this invention, the server includes means for receiving information, means for analyzing the type of the received information and verifying its consistency, and means for executing an algorithm for automatically assigning characteristic information to the information. This enables efficient and accurate analysis, classification, and storage of information.

[0259] "Information" is a general term for data expressed in digital format, encompassing a variety of forms and contents.

[0260] "Means" refers to the methods or devices used to achieve a specific objective.

[0261] "Reception" refers to the action or process of taking in information from the outside.

[0262] "Type" refers to the form or structure of information, and it forms the basis for interpreting data.

[0263] "Analysis" refers to the process of examining information in detail to understand and interpret its structure and meaning.

[0264] "Consistency" refers to a state where information is coherent and free from contradictions.

[0265] "Characteristic information" refers to labels and tags that represent the characteristics and attributes of information, and is used for understanding and classifying information.

[0266] An "algorithm" is a procedure or computational method for solving a specific problem.

[0267] Classification is the process of grouping information according to common characteristics or criteria.

[0268] "Memory space" refers to physical or virtual space used to store information.

[0269] "Update frequency" is an indicator that shows how often information is changed or modified.

[0270] "Tracking" refers to monitoring and recording changes and statuses of information.

[0271] "Period" refers to the length of time that a particular activity or state continues.

[0272] "Storage" refers to the act of continuously preserving information over a long period of time.

[0273] An "information set" refers to the whole collection of multiple related pieces of information.

[0274] "Retraining" is the process by which an existing model incorporates new information to improve its performance.

[0275] The embodiment of this invention aims to streamline the reception, analysis, automatic assignment, classification, storage, and retraining of information in a data management system. This system operates primarily on a server and is designed using the following technical elements.

[0276] First, the server uses HTTPS as its communication protocol to securely receive information. This makes it possible to securely retrieve information sent from external terminals and users.

[0277] The received information is parsed using a data parser on the server to determine its data type. This parsing process utilizes parsing tools such as Pandas to convert information in different formats into standard data frames. After conversion, a consistency check is performed, and if inconsistencies are detected, they are logged and the user is notified.

[0278] Next, the server runs a generative AI model to add feature information to the data. Here, a pre-trained language model is used as the AI ​​model. The generative AI model, with a specific prompt, analyzes the features of the data and adds appropriate feature information, thereby streamlining the data organization process. An example of a prompt is, "Classify new customer information into VIP customers, repeat customers, and others."

[0279] The server then classifies the information using the K-means clustering algorithm. The classified information is managed in memory. This allows users to quickly access specific information.

[0280] To track update frequency, a scheduling tool (e.g., a Cron job) is used on the server to perform archiving, moving information that hasn't been updated for a specific period to a storage server. This allows the system to utilize storage efficiently, and important information is stored securely.

[0281] Finally, the server retrains the generative AI model based on the accumulated new information. In this process, the performance of the model is improved by feeding a new set of information into it. Through this series of processes, users can perform more accurate information processing while reducing the effort of information management.

[0282] The flow of the specific process in Example 1 will be described using FIG. 11.

[0283] Step 1:

[0284] The server receives data from external terminals or users. The input is, for example, a data file in CSV or JSON format. The server uses HTTPS to receive the data and ensure security. The output is stored internally as the received raw data.

[0285] Step 2:

[0286] The server analyzes the format of the received data. The input here is the raw data stored securely. The server uses a data parser tool to identify the format and convert the data into a standard data frame format using the Pandas library. The output is data formatted in a common format.

[0287] Step 3:

[0288] The server performs a consistency check on the data in the common format. The input is the formatted data. The server conducts a data consistency check and, if an inconsistency is found, records it in a log and notifies the user. The output is either data with confirmed consistency or a data log with recorded inconsistencies.

[0289] Step 4:

[0290] The server runs a generative AI model and adds feature information to the data. The input is data with confirmed consistency. The server invokes a pre-trained AI model and performs data analysis based on specific prompt statements. The output is data with added feature information.

[0291] Step 5:

[0292] The server classifies data based on feature information. The input is data to which feature information has been added. The server uses the K-means clustering algorithm to classify the data into multiple categories. The output is a dataset classified by category.

[0293] Step 6:

[0294] The server monitors the update frequency of classified data. The input is data classified by category. The server uses a scheduling tool to periodically check the update frequency and identify data that has not been updated for a certain period. The output is a record of whether or not the data has been updated.

[0295] Step 7:

[0296] The server archives data that has not been updated. The input is data identified as not having been updated. The server moves this data to storage for long-term retention. The output is the archived data.

[0297] Step 8:

[0298] The server retrains the generative AI model using new data. The input is the latest data set. The server feeds the new data into the AI ​​model and improves the model's accuracy through retraining. The output is the AI ​​model with improved accuracy.

[0299] (Application Example 1)

[0300] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0301] In a data center, it is very difficult for an administrator to efficiently organize a huge amount of information and detect anomalies in real time and respond quickly by means of conventional manual management. Therefore, there is a need for a system that not only improves the efficiency of data automatic classification and storage but also enhances the efficiency and speed in anomaly detection.

[0302] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0303] In this invention, the server includes a data receiving device, a device for analyzing the format of the received information and confirming its integrity, and a device for executing a generation model for automatically attaching meta information to the information. As a result, by monitoring the inflow of information in real time, automatically detecting anomalies, and notifying them, it becomes possible to improve data management efficiency and the speed of anomaly response.

[0304] The "data receiving device" is a device that receives various forms of data from an external information source and supplies it to the server.

[0305] The "device for analyzing the format and confirming the integrity" is a device that analyzes the format of the received information to detect consistency and errors.

[0306] The "device for executing a generation model for automatically attaching meta information" is a device that analyzes the characteristics of information using the generation model and adds appropriate meta information.

[0307] The "device for categorizing information and storing it in a data store" is a device that classifies information into specific categories based on meta information and stores data efficiently.

[0308] A "device for monitoring change frequency and storing and managing information" is a device that monitors the frequency of changes to information and securely stores information that has not been updated for a certain period of time.

[0309] A "generative model retraining device" is a device that retrains a generative model using new information data to improve the accuracy of future information processing.

[0310] A "device that monitors information inflow in real time and automatically detects and notifies of anomalies" is a device that detects anomalies in real time when information continues to flow in and notifies the administrator.

[0311] The server is equipped with a data receiving device for receiving data in various formats from external terminals. This device receives formatted data such as CSV, JSON, and XML, analyzes the format, and verifies its integrity. Since the verified data is difficult to manage as is, a metadata addition device using a generative AI model performs feature analysis, and appropriate metadata is automatically added.

[0312] Next, the server's information categorization device classifies the information into specific categories based on the assigned metadata and efficiently stores it in the data store. This speeds up information retrieval and access. This data store is managed by a device that monitors the frequency of changes, and information that has not changed for a certain period is archived to optimize storage.

[0313] Furthermore, each time new information data is added, the system retrains the generative model, improving its accuracy based on this data. This makes it possible to perform more accurate analysis in future data processing.

[0314] As a concrete example, energy usage in a data center is monitored in real time, and when usage exceeds a certain threshold, a device that monitors the inflow of information in real time and automatically detects anomalies notifies the administrator's terminal with an alert. This enables a rapid response.

[0315] An example of a prompt might be, "How can I detect and notify of anomalies in an application that needs to view data in real time?" The hardware used would include data center server infrastructure and administrator smartphones, while the software would utilize Python, Flask, TensorFlow, and other technologies. This system automates complex data management processes and streamlines management tasks.

[0316] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0317] Step 1:

[0318] The server receives various data formats (CSV, JSON, XML, etc.) from external terminals. These data files are provided as input, and the format of the received data is specified as output. The server recognizes these formats and prepares the data to be sent to the next processing step.

[0319] Step 2:

[0320] The server analyzes the format of the received data and verifies its integrity. Data files are provided as input, and format consistency and error information are obtained as output. By checking the data format and for any defects, quality assurance is performed before proceeding to subsequent processing.

[0321] Step 3:

[0322] The server automatically adds metadata to the data using a generative AI model. Analyzed data is provided as input, and the output is data with added metadata. The generative AI model performs feature analysis to add appropriate metadata to the data.

[0323] Step 4:

[0324] The server categorizes information into specific categories based on metadata and stores it in the data store. Data with metadata is provided as input, and the categorized data is stored as output. This enables efficient data retrieval and utilization.

[0325] Step 5:

[0326] The server monitors the frequency of changes to stored data and archives data that has not been updated for a certain period. Update information for stored data is provided as input, and a list of archived data is obtained as output. This maintains storage efficiency.

[0327] Step 6:

[0328] The server retrains the generative model based on the new data. New data is provided as input, and an improved generative model is obtained as output. This will increase the accuracy of future data processing and enable more precise analysis.

[0329] Step 7:

[0330] The server monitors the inflow of information, such as energy usage in the data center, in real time and sends an alert to the administrator's terminal if an anomaly is detected. Usage data is provided as input, and the notification content is sent to the terminal as output. This enables a rapid response.

[0331] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0332] This invention improves the accuracy of data organization and analysis by incorporating an emotion engine into a data management system to recognize user emotions. The system automates data reception, analysis, automatic metadata assignment, emotion analysis, data classification, update frequency management, archiving, and retraining of generative models.

[0333] First, the user inputs new data into the system via a terminal. During this process, the emotion engine recognizes the user's emotions in real time based on their voice, facial expressions, input speed, and other factors. This emotion information is then sent to the data server as metadata.

[0334] The server analyzes the received data, ensuring format consistency and verifying integrity. Furthermore, it uses a built-in generative model to add metadata and user sentiment data to the data, improving the accuracy of the information.

[0335] Based on the assigned metadata and sentiment data, the server categorizes the data. For example, in the case of customer data, customers that the sentiment engine determines to have a high purchase intent are classified as "priority customers" and distinguished from regular customers.

[0336] Once the data is integrated, the server monitors its update frequency. Data that hasn't been updated for a certain period is automatically archived, but even then, sentiment data trends are taken into consideration, and special processing may be applied.

[0337] Furthermore, the server retrains the generative model using newly received data and sentiment information. As a result, the model's ability to adapt to changes in sentiment improves, leading to even greater accuracy in subsequent data processing.

[0338] As a concrete example, suppose a user submits a complaint through an inquiry form, and dissatisfaction or stress is recognized. Through this information, the server identifies that customer as a "customer who needs improvement" and adjusts the priority of follow-up. In this way, it becomes possible to improve the quality of customer service and customer satisfaction.

[0339] With the above configuration, the system implementing the present invention integrates emotion-based data management and achieves a higher level of data analysis and management compared to conventional data management systems.

[0340] The following describes the processing flow.

[0341] Step 1:

[0342] Users input data using their devices, and during this process, voice, facial expressions, and other information are collected in real time by the device's emotion engine. The emotion engine analyzes this data to generate the user's emotional data.

[0343] Step 2:

[0344] The device sends data entered by the user and emotional data analyzed by the emotion engine to the server. This data may be in various formats such as CSV or JSON.

[0345] Step 3:

[0346] The server analyzes the received data and converts it into a standardized format. During this process, it verifies data integrity and detects inconsistencies and errors.

[0347] Step 4:

[0348] The server uses a built-in generative model to automatically add metadata to the data. In this process, a pre-trained algorithm adds tags and attributes based on the data's features.

[0349] Step 5:

[0350] The server considers the attached metadata and sentiment data obtained from the user to classify the data into specific categories. For example, customers with high purchase intent are classified as "priority customers," while those with low intent are classified as "regular customers."

[0351] Step 6:

[0352] The server monitors the update frequency of stored data. Data that has not been updated for a certain period is automatically archived, but if special processing based on sentiment data is required at this time, a re-verification is performed.

[0353] Step 7:

[0354] The server retrains its generative model using newly received data. This retraining process also includes sentiment data, aiming to improve accuracy in subsequent data processing.

[0355] In this way, a system is built that significantly improves the efficiency and accuracy of data management by automating the data input, sentiment analysis, and data management processes.

[0356] (Example 2)

[0357] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0358] Modern data management systems face challenges in accuracy and efficiency because it is difficult to consider user emotions when organizing and analyzing data. Furthermore, there is a growing desire to achieve more comprehensive and precise data management by utilizing emotional information in data updates and classification.

[0359] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0360] In this invention, the server includes means for receiving data, means for analyzing the format of the received data and verifying its integrity, and means for executing a generative model for automatically adding metadata and sentiment data to the data. This enables advanced data management and analysis that reflects the user's sentiment.

[0361] A "means of receiving data" refers to a module that receives input data from the user and incorporates it into the system.

[0362] "Means for analyzing the format of received data and verifying its integrity" refers to a processing device that analyzes the format of input data and checks whether the data is correct and consistent.

[0363] "Means for executing a generative model for automatically adding metadata and sentiment data" refers to an algorithm for automatically generating and adding additional information related to data and user sentiment information.

[0364] "A means of classifying data and storing it in a database" refers to a system for classifying analyzed data into specific categories and storing them in a database that can be used for long-term storage.

[0365] "A means of monitoring update frequency and archiving data that has not been updated for a certain period based on sentiment data" refers to the process of checking the frequency of data changes, and if the data has not been updated for a certain period, considering sentiment information, and moving and saving the data to a separate storage location.

[0366] "Methods for retraining generative models" refer to learning algorithms that readjust the parameters of a generative model based on newly collected data and sentiment information to improve its performance.

[0367] This data management system begins with the user inputting new data through a terminal. The terminal is equipped with voice recognition software and a facial expression analysis system, which uses an emotion engine to analyze the user's voice, facial expressions, input speed, etc. This emotion engine uses an emotion recognition algorithm to recognize the user's emotions in real time and generates the results as emotion data.

[0368] The server receives data and sentiment data sent from the user. It then uses dedicated software to analyze the data format and verify its consistency. Next, the server uses a generative AI model to automatically add metadata and sentiment data to the received data. This generative model is built on deep learning algorithms and effectively extracts information from the dataset.

[0369] The server then categorizes the data based on the assigned metadata and sentiment data. For example, in the case of customer data, it can identify customers with high purchase intent and classify them as "priority customers." This classification is stored in a database and is easily accessible.

[0370] Furthermore, the server monitors the frequency of data updates and archives data that has not been updated for a certain period, taking sentiment data into consideration. This process enables the system to achieve efficient storage management. At the same time, the server retrains its generative model based on newly received data and sentiment information, improving the accuracy of the algorithm.

[0371] For example, when a user submits a complaint through an inquiry form, the system can recognize dissatisfaction and stress as emotional data and treat them as high-priority triage items. This speeds up customer support responses and contributes to improved customer satisfaction.

[0372] An example of a prompt message is, "Process the voice-inputted complaint information, determine the customer's emotions through sentiment analysis, and prioritize their response." By using this prompt, the system can perform emotion-based data management in response to user requests.

[0373] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0374] Step 1:

[0375] The user uses a device to input new data. This input data may include text, audio, and images. The device uses sensors to capture the user's voice, facial expressions, and input speed during data entry, and analyzes this data with an emotion engine. This process extracts emotion data from the input data and formats it as metadata.

[0376] Step 2:

[0377] The server receives input data and metadata sent from the terminal. The server analyzes the data format and converts it to the correct format. During the analysis process, a generative AI model is used to analyze the data structure and verify its consistency. Once the format is correctly prepared, the data is ready to be processed internally as structured data.

[0378] Step 3:

[0379] The server runs a generative AI model, adding multiple layers of metadata, including sentiment data, to the input data. When tagging the data, the server retrains the generative model using historical datasets. This tagging process allows the data to acquire additional labels to highlight specific information. The generated metadata improves the accuracy of the data and may also be used as prompts.

[0380] Step 4:

[0381] The server categorizes data based on the assigned metadata and sentiment data. Specifically, it measures user purchase intent based on the analyzed sentiment data and creates lists labeled as priority customers, etc. This classification process forms the basis for formulating optimal management strategies.

[0382] Step 5:

[0383] The server has the function of storing classified data in a database and monitoring the update frequency. During this process, the server checks the sentiment data of data that has not been updated for a certain period and makes a decision on whether to archive it. Data deemed to have important sentiment is retained for special processing rather than being archived.

[0384] Step 6:

[0385] The server retrains its generative AI model based on newly received datasets and sentiment data. This retraining process uses a feedback loop derived from the new inputs to improve the accuracy of sentiment recognition and metadata assignment, thereby enhancing its ability to process data for the next generation.

[0386] (Application Example 2)

[0387] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0388] Current data management systems struggle to organize and classify data while considering user emotions. This often results in an inability to provide information and responses that meet user needs. In particular, consumer electronics require appropriate responses that reflect the user's emotions, but current technology is insufficient to achieve this.

[0389] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0390] In this invention, the server includes means for receiving data, means for analyzing the format of the received data and verifying its integrity, means for executing a generative model for automatically attaching metadata to the data, means for recognizing emotions from user input information, means for classifying data based on the user's emotion data and the attached metadata and storing it in an information set, means for monitoring the data update frequency and archiving data that has not been updated for a certain period of time, and means for retraining the generative model using a new dataset. This enables advanced data management based on user emotions and appropriate responses to the emotions of users in consumer electronic devices.

[0391] "Data receiving means" refers to a device or method that acquires data from an external source and converts it into a format usable within the system.

[0392] "Emotion recognition means" refers to a technology or device for detecting and identifying emotions from data such as the user's voice, facial expressions, and input speed.

[0393] A "generative model" is a computational model used to generate appropriate metadata and tags in response to input data, and is learned through machine learning and AI technologies.

[0394] Metadata is supplementary information added to classify or organize data, making it easier to understand and search for.

[0395] An "information collection" is a database or storage device where classified data is stored, and it serves as the foundation for proper information management.

[0396] "Retraining" is the process of training an existing generative model again with a newly acquired dataset to improve the model's accuracy and adaptability.

[0397] In the system for implementing this invention, the user first inputs data via a terminal. The terminal is equipped with emotion recognition means, which detects the user's emotions from data such as voice, facial expressions, and input speed. The emotion data is attached as metadata and sent to the server along with the data.

[0398] The server analyzes the format of the received data, verifies its integrity, and then automatically adds metadata to the data using a generative model. Python and other machine learning libraries can be used as the generative AI model. Based on the added metadata and user sentiment data, the server classifies and stores the data as an information set. This process enables data management tailored to the user's sentiment.

[0399] Furthermore, the server improves the accuracy of data processing by retraining the generative model using a new dataset. Cloud services such as Google Cloud Platform and AWS can be used for retraining.

[0400] As a concrete example, suppose a child returns home from school and says to their device, "Today's homework was difficult." The server senses the child's stress level from this statement and suggests, through consumer electronics, "Maybe you should take a break and listen to your favorite music." In this way, it becomes possible to provide appropriate responses that reflect the user's emotions.

[0401] An example of a prompt statement might be, "Develop an application for a consumer robot that reads the emotions of the user when they speak and takes appropriate action." Based on this prompt statement, it is possible to create a flow for generating an AI model for emotion recognition and processing the data.

[0402] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0403] Step 1:

[0404] The user inputs data into the device. The input data is recorded on the device as audio or text. At this point, emotion recognition is activated, analyzing emotions from voice tone and input speed. The input data and analyzed emotions are compiled as metadata.

[0405] Step 2:

[0406] The terminal sends metadata and data to the server. The server analyzes the format of the received data and verifies its consistency. Here, it checks for inconsistencies in the data and standardizes it to a specific format. It also checks the sentiment information recorded as metadata and converts it into a format that can be used by the generative model.

[0407] Step 3:

[0408] The server executes a generative model and automatically adds new metadata to the data. The generative AI model generates prompt statements in response to the input information and processes the information to organize and expand it. This model adds metadata in a format that incorporates user sentiment information, thereby increasing the value of the data.

[0409] Step 4:

[0410] Based on the generated metadata, the server classifies and stores the data as an information collection. In this process, the data is divided into appropriate categories according to the metadata and assigned sentiment information. This makes it easy to search and retrieve information within the database.

[0411] Step 5:

[0412] The server monitors the frequency of data updates, and data that has not been updated for a certain period is archived. During this process, sentiment data is taken into consideration, and archiving is adjusted based on specific criteria. Furthermore, the generative model is retrained using new datasets to prepare for improved accuracy in future data processing.

[0413] Step 6:

[0414] The retrained generative model is used for subsequent data processing, improving its accuracy and adaptability. This allows the server to perform more sophisticated sentiment analysis and metadata assignment during subsequent user input, thereby improving the user experience.

[0415] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0416] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0417] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0418] [Third Embodiment]

[0419] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0420] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0421] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0422] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0423] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0424] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0425] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0426] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0427] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0428] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0429] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0430] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0431] This invention is a system designed for efficient data management, automating data reception, analysis, automatic metadata assignment, classification, update frequency management, archiving, and retraining of generative models.

[0432] First, the server receives data in various formats from external terminals and users. The received data can be in a wide variety of formats, such as CSV, JSON, and XML. To process this data efficiently, the server analyzes the data format and converts it into a common format suitable for internal processing. Consistency checks to detect data inconsistencies and format errors are also performed at this stage.

[0433] Next, the server runs a generative model to automatically assign metadata to the data. The generative model uses a pre-trained algorithm to analyze the data's features and attach appropriate metadata to the data entries. This automated assignment process streamlines data organization and subsequent processing.

[0434] Based on the assigned metadata, the server classifies the data into specific categories. For example, customer data might be organized into categories such as "VIP customers," "repeat customers," and "new customers" based on purchase history and customer attributes.

[0435] After the data is saved, the server monitors its update frequency. If the data is not updated for a certain period, it is considered "inactive" and archived. This archiving process improves storage efficiency, and necessary information is securely stored as a backup.

[0436] Furthermore, the server retrains the generative model using the newly received data. This improves the accuracy of future data processing, enabling more accurate metadata assignment and classification in subsequent data analyses.

[0437] As a concrete example, when a user uploads newly acquired customer information from their terminal to the server through sales activities, the server quickly analyzes the information and assigns appropriate metadata to each customer. This information is categorized and stored in a database, making it readily accessible to the user when needed. As a result, customer management and marketing activities become more efficient.

[0438] Thus, the system implementing the present invention provides a means to reduce the time and human costs associated with data management, as well as to improve the accuracy of management tasks.

[0439] The following describes the processing flow.

[0440] Step 1:

[0441] Users input data using their devices and send it to the server. The data may exist in formats such as CSV, JSON, or XML.

[0442] Step 2:

[0443] The server analyzes the received data and identifies the format of the input data. If the format is different, it converts it to a unified internal format. During this process, it also performs a data integrity check to ensure there are no errors or inconsistencies.

[0444] Step 3:

[0445] The server uses a pre-configured generative model to automatically add metadata to the data. The generative model analyzes the characteristics of the data and adds appropriate tags and attributes. This analysis is based on the data's content and patterns.

[0446] Step 4:

[0447] The server categorizes data based on metadata. For example, customer data is organized into categories such as "VIP customers" and "new customers" according to purchase history and attribute information. This classification process makes subsequent searches and references in the database more efficient.

[0448] Step 5:

[0449] The server is the data storage location and monitors the update frequency of data entries. Data that has not been updated for a certain period is considered "inactive" and moved to a different area of ​​storage as an archive. This process ensures efficient use of storage.

[0450] Step 6:

[0451] The server periodically incorporates new data into the generative model and retrains it. This process improves the accuracy of subsequent data processing. Since learning progresses each time new data is added, improvements in tagging and classification accuracy can be expected.

[0452] (Example 1)

[0453] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0454] In modern information management, receiving, organizing, and storing vast amounts of information is essential. However, the manual processes involved in information analysis, classification, and storage are time-consuming and costly in terms of human resources, necessitating efficient management. Furthermore, the depletion of storage space due to outdated information and the oversight of important information are also challenges. Overcoming these obstacles and achieving smooth and accurate information management is crucial.

[0455] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0456] In this invention, the server includes means for receiving information, means for analyzing the type of the received information and verifying its consistency, and means for executing an algorithm for automatically assigning characteristic information to the information. This enables efficient and accurate analysis, classification, and storage of information.

[0457] "Information" is a general term for data expressed in digital format, encompassing a variety of forms and contents.

[0458] "Means" refers to the methods or devices used to achieve a specific objective.

[0459] "Reception" refers to the action or process of taking in information from the outside.

[0460] "Type" refers to the form or structure of information, and it forms the basis for interpreting data.

[0461] "Analysis" refers to the process of examining information in detail to understand and interpret its structure and meaning.

[0462] "Consistency" refers to a state where information is coherent and free from contradictions.

[0463] "Characteristic information" refers to labels and tags that represent the characteristics and attributes of information, and is used for understanding and classifying information.

[0464] An "algorithm" is a procedure or computational method for solving a specific problem.

[0465] Classification is the process of grouping information according to common characteristics or criteria.

[0466] "Memory space" refers to physical or virtual space used to store information.

[0467] "Update frequency" is an indicator that shows how often information is changed or modified.

[0468] "Tracking" refers to monitoring and recording changes and statuses of information.

[0469] "Period" refers to the length of time that a particular activity or state continues.

[0470] "Storage" refers to the act of continuously preserving information over a long period of time.

[0471] An "information set" refers to the whole collection of multiple related pieces of information.

[0472] "Retraining" is the process by which an existing model incorporates new information to improve its performance.

[0473] The embodiment of this invention aims to streamline the reception, analysis, automatic assignment, classification, storage, and retraining of information in a data management system. This system operates primarily on a server and is designed using the following technical elements.

[0474] First, the server uses HTTPS as its communication protocol to securely receive information. This makes it possible to securely retrieve information sent from external terminals and users.

[0475] The received information is parsed using a data parser on the server to determine its data type. This parsing process utilizes parsing tools such as Pandas to convert information in different formats into standard data frames. After conversion, a consistency check is performed, and if inconsistencies are detected, they are logged and the user is notified.

[0476] Next, the server runs a generative AI model to add feature information to the data. Here, a pre-trained language model is used as the AI ​​model. The generative AI model, with a specific prompt, analyzes the features of the data and adds appropriate feature information, thereby streamlining the data organization process. An example of a prompt is, "Classify new customer information into VIP customers, repeat customers, and others."

[0477] The server then classifies the information using the K-means clustering algorithm. The classified information is managed in memory. This allows users to quickly access specific information.

[0478] To track update frequency, a scheduling tool (e.g., a Cron job) is used on the server to perform archiving, moving information that hasn't been updated for a specific period to a storage server. This allows the system to utilize storage efficiently, and important information is stored securely.

[0479] Finally, the server retrains the generated AI model based on the newly accumulated information. This process improves the model's performance by inputting new sets of information. Through this series of processes, users can reduce the effort required for information management while enabling more accurate information processing.

[0480] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0481] Step 1:

[0482] The server receives data from external terminals and users. Input is, for example, data files in CSV or JSON format. The server uses HTTPS to receive data and ensure security. Output is stored internally as the received raw data.

[0483] Step 2:

[0484] The server parses the format of the received data. The input here is securely stored raw data. The server uses a data parser tool to identify the format and converts the data into a standard dataframe format using the Pandas library. The output is data formatted into a common format.

[0485] Step 3:

[0486] The server performs consistency checks on data in a common format. The input is the formatted data. The server verifies the data integrity, logs any inconsistencies found, and notifies the user. The output is either data that has been verified as consistent or a data log where inconsistencies have been recorded.

[0487] Step 4:

[0488] The server runs a generative AI model and adds feature information to the data. The input is data with confirmed consistency. The server invokes a pre-trained AI model and performs data analysis based on specific prompt statements. The output is data with added feature information.

[0489] Step 5:

[0490] The server classifies data based on feature information. The input is data to which feature information has been added. The server uses the K-means clustering algorithm to classify the data into multiple categories. The output is a dataset classified by category.

[0491] Step 6:

[0492] The server monitors the update frequency of classified data. The input is data classified by category. The server uses a scheduling tool to periodically check the update frequency and identify data that has not been updated for a certain period. The output is a record of whether or not the data has been updated.

[0493] Step 7:

[0494] The server archives data that has not been updated. The input is data identified as not having been updated. The server moves this data to storage for long-term retention. The output is the archived data.

[0495] Step 8:

[0496] The server retrains the generative AI model using new data. The input is the latest data set. The server feeds the new data into the AI ​​model and improves the model's accuracy through retraining. The output is the AI ​​model with improved accuracy.

[0497] (Application Example 1)

[0498] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0499] In data centers, it is extremely difficult for administrators to efficiently organize vast amounts of information, detect anomalies in real time, and respond quickly using traditional manual methods. Therefore, there is a need for a system that not only automates data classification and storage, but also improves the efficiency and speed of anomaly detection.

[0500] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0501] In this invention, the server includes a data receiving device, a device for analyzing the format of the received information and verifying its integrity, and a device for executing a generative model for automatically adding metadata to the information. This enables real-time monitoring of information inflow and automatic detection and notification of anomalies, thereby improving data management efficiency and the speed of anomaly response.

[0502] A "data receiving device" is a device that receives data in various formats from external information sources and supplies it to a server.

[0503] A "device for analyzing format and verifying integrity" is a device that analyzes the format of received information to detect consistency and errors.

[0504] A "device that executes a generative model for automatically adding metadata" is a device that uses a generative model to analyze the characteristics of information and add appropriate metadata.

[0505] A "device for categorizing information and storing it in a data store" is a device that classifies information into specific categories based on metadata and efficiently stores the data.

[0506] A "device for monitoring change frequency and storing and managing information" is a device that monitors the frequency of changes to information and securely stores information that has not been updated for a certain period of time.

[0507] A "generative model retraining device" is a device that retrains a generative model using new information data to improve the accuracy of future information processing.

[0508] A "device that monitors information inflow in real time and automatically detects and notifies of anomalies" is a device that detects anomalies in real time when information continues to flow in and notifies the administrator.

[0509] The server is equipped with a data receiving device for receiving data in various formats from external terminals. This device receives formatted data such as CSV, JSON, and XML, analyzes the format, and verifies its integrity. Since the verified data is difficult to manage as is, a metadata addition device using a generative AI model performs feature analysis, and appropriate metadata is automatically added.

[0510] Next, the server's information categorization device classifies the information into specific categories based on the assigned metadata and efficiently stores it in the data store. This speeds up information retrieval and access. This data store is managed by a device that monitors the frequency of changes, and information that has not changed for a certain period is archived to optimize storage.

[0511] Furthermore, each time new information data is added, the system retrains the generative model, improving its accuracy based on this data. This makes it possible to perform more accurate analysis in future data processing.

[0512] As a concrete example, energy usage in a data center is monitored in real time, and when usage exceeds a certain threshold, a device that monitors the inflow of information in real time and automatically detects anomalies notifies the administrator's terminal with an alert. This enables a rapid response.

[0513] An example of a prompt might be, "How can I detect and notify of anomalies in an application that needs to view data in real time?" The hardware used would include data center server infrastructure and administrator smartphones, while the software would utilize Python, Flask, TensorFlow, and other technologies. This system automates complex data management processes and streamlines management tasks.

[0514] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0515] Step 1:

[0516] The server receives various data formats (CSV, JSON, XML, etc.) from external terminals. These data files are provided as input, and the format of the received data is specified as output. The server recognizes these formats and prepares the data to be sent to the next processing step.

[0517] Step 2:

[0518] The server analyzes the format of the received data and verifies its integrity. Data files are provided as input, and format consistency and error information are obtained as output. By checking the data format and for any defects, quality assurance is performed before proceeding to subsequent processing.

[0519] Step 3:

[0520] The server automatically adds metadata to the data using a generative AI model. Analyzed data is provided as input, and the output is data with added metadata. The generative AI model performs feature analysis to add appropriate metadata to the data.

[0521] Step 4:

[0522] The server categorizes information into specific categories based on metadata and stores it in the data store. Data with metadata is provided as input, and the categorized data is stored as output. This enables efficient data retrieval and utilization.

[0523] Step 5:

[0524] The server monitors the frequency of changes to stored data and archives data that has not been updated for a certain period. Update information for stored data is provided as input, and a list of archived data is obtained as output. This maintains storage efficiency.

[0525] Step 6:

[0526] The server retrains the generative model based on the new data. New data is provided as input, and an improved generative model is obtained as output. This will increase the accuracy of future data processing and enable more precise analysis.

[0527] Step 7:

[0528] The server monitors the inflow of information, such as energy usage in the data center, in real time and sends an alert to the administrator's terminal if an anomaly is detected. Usage data is provided as input, and the notification content is sent to the terminal as output. This enables a rapid response.

[0529] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0530] This invention improves the accuracy of data organization and analysis by incorporating an emotion engine into a data management system to recognize user emotions. The system automates data reception, analysis, automatic metadata assignment, emotion analysis, data classification, update frequency management, archiving, and retraining of generative models.

[0531] First, the user inputs new data into the system via a terminal. During this process, the emotion engine recognizes the user's emotions in real time based on their voice, facial expressions, input speed, and other factors. This emotion information is then sent to the data server as metadata.

[0532] The server analyzes the received data, ensuring format consistency and verifying integrity. Furthermore, it uses a built-in generative model to add metadata and user sentiment data to the data, improving the accuracy of the information.

[0533] Based on the assigned metadata and sentiment data, the server categorizes the data. For example, in the case of customer data, customers that the sentiment engine determines to have a high purchase intent are classified as "priority customers" and distinguished from regular customers.

[0534] Once the data is integrated, the server monitors its update frequency. Data that hasn't been updated for a certain period is automatically archived, but even then, sentiment data trends are taken into consideration, and special processing may be applied.

[0535] Furthermore, the server retrains the generative model using newly received data and sentiment information. As a result, the model's ability to adapt to changes in sentiment improves, leading to even greater accuracy in subsequent data processing.

[0536] As a concrete example, suppose a user submits a complaint through an inquiry form, and dissatisfaction or stress is recognized. Through this information, the server identifies that customer as a "customer who needs improvement" and adjusts the priority of follow-up. In this way, it becomes possible to improve the quality of customer service and customer satisfaction.

[0537] With the above configuration, the system implementing the present invention integrates emotion-based data management and achieves a higher level of data analysis and management compared to conventional data management systems.

[0538] The following describes the processing flow.

[0539] Step 1:

[0540] Users input data using their devices, and during this process, voice, facial expressions, and other information are collected in real time by the device's emotion engine. The emotion engine analyzes this data to generate the user's emotional data.

[0541] Step 2:

[0542] The device sends data entered by the user and emotional data analyzed by the emotion engine to the server. This data may be in various formats such as CSV or JSON.

[0543] Step 3:

[0544] The server analyzes the received data and converts it into a standardized format. During this process, it verifies data integrity and detects inconsistencies and errors.

[0545] Step 4:

[0546] The server uses a built-in generative model to automatically add metadata to the data. In this process, a pre-trained algorithm adds tags and attributes based on the data's features.

[0547] Step 5:

[0548] The server considers the attached metadata and sentiment data obtained from the user to classify the data into specific categories. For example, customers with high purchase intent are classified as "priority customers," while those with low intent are classified as "regular customers."

[0549] Step 6:

[0550] The server monitors the update frequency of stored data. Data that has not been updated for a certain period is automatically archived, but if special processing based on sentiment data is required at this time, a re-verification is performed.

[0551] Step 7:

[0552] The server retrains its generative model using newly received data. This retraining process also includes sentiment data, aiming to improve accuracy in subsequent data processing.

[0553] In this way, a system is built that significantly improves the efficiency and accuracy of data management by automating the data input, sentiment analysis, and data management processes.

[0554] (Example 2)

[0555] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0556] Modern data management systems face challenges in accuracy and efficiency because it is difficult to consider user emotions when organizing and analyzing data. Furthermore, there is a growing desire to achieve more comprehensive and precise data management by utilizing emotional information in data updates and classification.

[0557] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0558] In this invention, the server includes means for receiving data, means for analyzing the format of the received data and verifying its integrity, and means for executing a generative model for automatically adding metadata and sentiment data to the data. This enables advanced data management and analysis that reflects the user's sentiment.

[0559] A "means of receiving data" refers to a module that receives input data from the user and incorporates it into the system.

[0560] "Means for analyzing the format of received data and verifying its integrity" refers to a processing device that analyzes the format of input data and checks whether the data is correct and consistent.

[0561] "Means for executing a generative model for automatically adding metadata and sentiment data" refers to an algorithm for automatically generating and adding additional information related to data and user sentiment information.

[0562] "A means of classifying data and storing it in a database" refers to a system for classifying analyzed data into specific categories and storing them in a database that can be used for long-term storage.

[0563] "A means of monitoring update frequency and archiving data that has not been updated for a certain period based on sentiment data" refers to the process of checking the frequency of data changes, and if the data has not been updated for a certain period, considering sentiment information, and moving and saving the data to a separate storage location.

[0564] "Methods for retraining generative models" refer to learning algorithms that readjust the parameters of a generative model based on newly collected data and sentiment information to improve its performance.

[0565] This data management system begins with the user inputting new data through a terminal. The terminal is equipped with voice recognition software and a facial expression analysis system, which uses an emotion engine to analyze the user's voice, facial expressions, input speed, etc. This emotion engine uses an emotion recognition algorithm to recognize the user's emotions in real time and generates the results as emotion data.

[0566] The server receives data and sentiment data sent from the user. It then uses dedicated software to analyze the data format and verify its consistency. Next, the server uses a generative AI model to automatically add metadata and sentiment data to the received data. This generative model is built on deep learning algorithms and effectively extracts information from the dataset.

[0567] The server then categorizes the data based on the assigned metadata and sentiment data. For example, in the case of customer data, it can identify customers with high purchase intent and classify them as "priority customers." This classification is stored in a database and is easily accessible.

[0568] Furthermore, the server monitors the frequency of data updates and archives data that has not been updated for a certain period, taking sentiment data into consideration. This process enables the system to achieve efficient storage management. At the same time, the server retrains its generative model based on newly received data and sentiment information, improving the accuracy of the algorithm.

[0569] For example, when a user submits a complaint through an inquiry form, the system can recognize dissatisfaction and stress as emotional data and treat them as high-priority triage items. This speeds up customer support responses and contributes to improved customer satisfaction.

[0570] An example of a prompt message is, "Process the voice-inputted complaint information, determine the customer's emotions through sentiment analysis, and prioritize their response." By using this prompt, the system can perform emotion-based data management in response to user requests.

[0571] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0572] Step 1:

[0573] The user uses a device to input new data. This input data may include text, audio, and images. The device uses sensors to capture the user's voice, facial expressions, and input speed during data entry, and analyzes this data with an emotion engine. This process extracts emotion data from the input data and formats it as metadata.

[0574] Step 2:

[0575] The server receives input data and metadata sent from the terminal. The server analyzes the data format and converts it to the correct format. During the analysis process, a generative AI model is used to analyze the data structure and verify its consistency. Once the format is correctly prepared, the data is ready to be processed internally as structured data.

[0576] Step 3:

[0577] The server runs a generative AI model, adding multiple layers of metadata, including sentiment data, to the input data. When tagging the data, the server retrains the generative model using historical datasets. This tagging process allows the data to acquire additional labels to highlight specific information. The generated metadata improves the accuracy of the data and may also be used as prompts.

[0578] Step 4:

[0579] The server categorizes data based on the assigned metadata and sentiment data. Specifically, it measures user purchase intent based on the analyzed sentiment data and creates lists labeled as priority customers, etc. This classification process forms the basis for formulating optimal management strategies.

[0580] Step 5:

[0581] The server has the function of storing classified data in a database and monitoring the update frequency. During this process, the server checks the sentiment data of data that has not been updated for a certain period and makes a decision on whether to archive it. Data deemed to have important sentiment is retained for special processing rather than being archived.

[0582] Step 6:

[0583] The server retrains its generative AI model based on newly received datasets and sentiment data. This retraining process uses a feedback loop derived from the new inputs to improve the accuracy of sentiment recognition and metadata assignment, thereby enhancing its ability to process data for the next generation.

[0584] (Application Example 2)

[0585] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0586] Current data management systems struggle to organize and classify data while considering user emotions. This often results in an inability to provide information and responses that meet user needs. In particular, consumer electronics require appropriate responses that reflect the user's emotions, but current technology is insufficient to achieve this.

[0587] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0588] In this invention, the server includes means for receiving data, means for analyzing the format of the received data and verifying its integrity, means for executing a generative model for automatically attaching metadata to the data, means for recognizing emotions from user input information, means for classifying data based on the user's emotion data and the attached metadata and storing it in an information set, means for monitoring the data update frequency and archiving data that has not been updated for a certain period of time, and means for retraining the generative model using a new dataset. This enables advanced data management based on user emotions and appropriate responses to the emotions of users in consumer electronic devices.

[0589] "Data receiving means" refers to a device or method that acquires data from an external source and converts it into a format usable within the system.

[0590] "Emotion recognition means" refers to a technology or device for detecting and identifying emotions from data such as the user's voice, facial expressions, and input speed.

[0591] A "generative model" is a computational model used to generate appropriate metadata and tags in response to input data, and is learned through machine learning and AI technologies.

[0592] Metadata is supplementary information added to classify or organize data, making it easier to understand and search for.

[0593] An "information collection" is a database or storage device where classified data is stored, and it serves as the foundation for proper information management.

[0594] "Retraining" is the process of training an existing generative model again with a newly acquired dataset to improve the model's accuracy and adaptability.

[0595] In the system for implementing this invention, the user first inputs data via a terminal. The terminal is equipped with emotion recognition means, which detects the user's emotions from data such as voice, facial expressions, and input speed. The emotion data is attached as metadata and sent to the server along with the data.

[0596] The server analyzes the format of the received data, verifies its integrity, and then automatically adds metadata to the data using a generative model. Python and other machine learning libraries can be used as the generative AI model. Based on the added metadata and user sentiment data, the server classifies and stores the data as an information set. This process enables data management tailored to the user's sentiment.

[0597] Furthermore, the server improves the accuracy of data processing by retraining the generative model using a new dataset. Cloud services such as Google Cloud Platform and AWS can be used for retraining.

[0598] As a concrete example, suppose a child returns home from school and says to their device, "Today's homework was difficult." The server senses the child's stress level from this statement and suggests, through consumer electronics, "Maybe you should take a break and listen to your favorite music." In this way, it becomes possible to provide appropriate responses that reflect the user's emotions.

[0599] An example of a prompt statement might be, "Develop an application for a consumer robot that reads the emotions of the user when they speak and takes appropriate action." Based on this prompt statement, it is possible to create a flow for generating an AI model for emotion recognition and processing the data.

[0600] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0601] Step 1:

[0602] The user inputs data into the device. The input data is recorded on the device as audio or text. At this point, emotion recognition is activated, analyzing emotions from voice tone and input speed. The input data and analyzed emotions are compiled as metadata.

[0603] Step 2:

[0604] The terminal sends metadata and data to the server. The server analyzes the format of the received data and verifies its consistency. Here, it checks for inconsistencies in the data and standardizes it to a specific format. It also checks the sentiment information recorded as metadata and converts it into a format that can be used by the generative model.

[0605] Step 3:

[0606] The server executes a generative model and automatically adds new metadata to the data. The generative AI model generates prompt statements in response to the input information and processes the information to organize and expand it. This model adds metadata in a format that incorporates user sentiment information, thereby increasing the value of the data.

[0607] Step 4:

[0608] Based on the generated metadata, the server classifies and stores the data as an information collection. In this process, the data is divided into appropriate categories according to the metadata and assigned sentiment information. This makes it easy to search and retrieve information within the database.

[0609] Step 5:

[0610] The server monitors the frequency of data updates, and data that has not been updated for a certain period is archived. During this process, sentiment data is taken into consideration, and archiving is adjusted based on specific criteria. Furthermore, the generative model is retrained using new datasets to prepare for improved accuracy in future data processing.

[0611] Step 6:

[0612] The retrained generative model is used for subsequent data processing, improving its accuracy and adaptability. This allows the server to perform more sophisticated sentiment analysis and metadata assignment during subsequent user input, thereby improving the user experience.

[0613] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0614] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0615] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0616] [Fourth Embodiment]

[0617] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0618] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0619] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0620] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0621] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0622] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0623] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0624] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0625] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0626] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0627] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0628] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0629] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0630] This invention is a system designed for efficient data management, automating data reception, analysis, automatic metadata assignment, classification, update frequency management, archiving, and retraining of generative models.

[0631] First, the server receives data in various formats from external terminals and users. The received data can be in a wide variety of formats, such as CSV, JSON, and XML. To process this data efficiently, the server analyzes the data format and converts it into a common format suitable for internal processing. Consistency checks to detect data inconsistencies and format errors are also performed at this stage.

[0632] Next, the server runs a generative model to automatically assign metadata to the data. The generative model uses a pre-trained algorithm to analyze the data's features and attach appropriate metadata to the data entries. This automated assignment process streamlines data organization and subsequent processing.

[0633] Based on the assigned metadata, the server classifies the data into specific categories. For example, customer data might be organized into categories such as "VIP customers," "repeat customers," and "new customers" based on purchase history and customer attributes.

[0634] After the data is saved, the server monitors its update frequency. If the data is not updated for a certain period, it is considered "inactive" and archived. This archiving process improves storage efficiency, and necessary information is securely stored as a backup.

[0635] Furthermore, the server retrains the generative model using the newly received data. This improves the accuracy of future data processing, enabling more accurate metadata assignment and classification in subsequent data analyses.

[0636] As a concrete example, when a user uploads newly acquired customer information from their terminal to the server through sales activities, the server quickly analyzes the information and assigns appropriate metadata to each customer. This information is categorized and stored in a database, making it readily accessible to the user when needed. As a result, customer management and marketing activities become more efficient.

[0637] Thus, the system implementing the present invention provides a means to reduce the time and human costs associated with data management, as well as to improve the accuracy of management tasks.

[0638] The following describes the processing flow.

[0639] Step 1:

[0640] Users input data using their devices and send it to the server. The data may exist in formats such as CSV, JSON, or XML.

[0641] Step 2:

[0642] The server analyzes the received data and identifies the format of the input data. If the format is different, it converts it to a unified internal format. During this process, it also performs a data integrity check to ensure there are no errors or inconsistencies.

[0643] Step 3:

[0644] The server uses a pre-configured generative model to automatically add metadata to the data. The generative model analyzes the characteristics of the data and adds appropriate tags and attributes. This analysis is based on the data's content and patterns.

[0645] Step 4:

[0646] The server categorizes data based on metadata. For example, customer data is organized into categories such as "VIP customers" and "new customers" according to purchase history and attribute information. This classification process makes subsequent searches and references in the database more efficient.

[0647] Step 5:

[0648] The server is the data storage location and monitors the update frequency of data entries. Data that has not been updated for a certain period is considered "inactive" and moved to a different area of ​​storage as an archive. This process ensures efficient use of storage.

[0649] Step 6:

[0650] The server periodically incorporates new data into the generative model and retrains it. This process improves the accuracy of subsequent data processing. Since learning progresses each time new data is added, improvements in tagging and classification accuracy can be expected.

[0651] (Example 1)

[0652] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0653] In modern information management, receiving, organizing, and storing vast amounts of information is essential. However, the manual processes involved in information analysis, classification, and storage are time-consuming and costly in terms of human resources, necessitating efficient management. Furthermore, the depletion of storage space due to outdated information and the oversight of important information are also challenges. Overcoming these obstacles and achieving smooth and accurate information management is crucial.

[0654] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0655] In this invention, the server includes means for receiving information, means for analyzing the type of the received information and verifying its consistency, and means for executing an algorithm for automatically assigning characteristic information to the information. This enables efficient and accurate analysis, classification, and storage of information.

[0656] "Information" is a general term for data expressed in digital format, encompassing a variety of forms and contents.

[0657] "Means" refers to the methods or devices used to achieve a specific objective.

[0658] "Reception" refers to the action or process of taking in information from the outside.

[0659] "Type" refers to the form or structure of information, and it forms the basis for interpreting data.

[0660] "Analysis" refers to the process of examining information in detail to understand and interpret its structure and meaning.

[0661] "Consistency" refers to a state where information is coherent and free from contradictions.

[0662] "Characteristic information" refers to labels and tags that represent the characteristics and attributes of information, and is used for understanding and classifying information.

[0663] An "algorithm" is a procedure or computational method for solving a specific problem.

[0664] Classification is the process of grouping information according to common characteristics or criteria.

[0665] "Memory space" refers to physical or virtual space used to store information.

[0666] "Update frequency" is an indicator that shows how often information is changed or modified.

[0667] "Tracking" refers to monitoring and recording changes and statuses of information.

[0668] "Period" refers to the length of time that a particular activity or state continues.

[0669] "Storage" refers to the act of continuously preserving information over a long period of time.

[0670] An "information set" refers to the whole collection of multiple related pieces of information.

[0671] "Retraining" is the process by which an existing model incorporates new information to improve its performance.

[0672] The embodiment of this invention aims to streamline the reception, analysis, automatic assignment, classification, storage, and retraining of information in a data management system. This system operates primarily on a server and is designed using the following technical elements.

[0673] First, the server uses HTTPS as its communication protocol to securely receive information. This makes it possible to securely retrieve information sent from external terminals and users.

[0674] The received information is parsed using a data parser on the server to determine its data type. This parsing process utilizes parsing tools such as Pandas to convert information in different formats into standard data frames. After conversion, a consistency check is performed, and if inconsistencies are detected, they are logged and the user is notified.

[0675] Next, the server runs a generative AI model to add feature information to the data. Here, a pre-trained language model is used as the AI ​​model. The generative AI model, with a specific prompt, analyzes the features of the data and adds appropriate feature information, thereby streamlining the data organization process. An example of a prompt is, "Classify new customer information into VIP customers, repeat customers, and others."

[0676] The server then classifies the information using the K-means clustering algorithm. The classified information is managed in memory. This allows users to quickly access specific information.

[0677] To track update frequency, a scheduling tool (e.g., a Cron job) is used on the server to perform archiving, moving information that hasn't been updated for a specific period to a storage server. This allows the system to utilize storage efficiently, and important information is stored securely.

[0678] Finally, the server retrains the generated AI model based on the newly accumulated information. This process improves the model's performance by inputting new sets of information. Through this series of processes, users can reduce the effort required for information management while enabling more accurate information processing.

[0679] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0680] Step 1:

[0681] The server receives data from external terminals and users. Input is, for example, data files in CSV or JSON format. The server uses HTTPS to receive data and ensure security. Output is stored internally as the received raw data.

[0682] Step 2:

[0683] The server parses the format of the received data. The input here is securely stored raw data. The server uses a data parser tool to identify the format and converts the data into a standard dataframe format using the Pandas library. The output is data formatted into a common format.

[0684] Step 3:

[0685] The server performs consistency checks on data in a common format. The input is the formatted data. The server verifies the data integrity, logs any inconsistencies found, and notifies the user. The output is either data that has been verified as consistent or a data log where inconsistencies have been recorded.

[0686] Step 4:

[0687] The server runs a generative AI model and adds feature information to the data. The input is data with confirmed consistency. The server invokes a pre-trained AI model and performs data analysis based on specific prompt statements. The output is data with added feature information.

[0688] Step 5:

[0689] The server classifies data based on feature information. The input is data to which feature information has been added. The server uses the K-means clustering algorithm to classify the data into multiple categories. The output is a dataset classified by category.

[0690] Step 6:

[0691] The server monitors the update frequency of classified data. The input is data classified by category. The server uses a scheduling tool to periodically check the update frequency and identify data that has not been updated for a certain period. The output is a record of whether or not the data has been updated.

[0692] Step 7:

[0693] The server archives data that has not been updated. The input is data identified as not having been updated. The server moves this data to storage for long-term retention. The output is the archived data.

[0694] Step 8:

[0695] The server retrains the generative AI model using new data. The input is the latest data set. The server feeds the new data into the AI ​​model and improves the model's accuracy through retraining. The output is the AI ​​model with improved accuracy.

[0696] (Application Example 1)

[0697] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0698] In data centers, it is extremely difficult for administrators to efficiently organize vast amounts of information, detect anomalies in real time, and respond quickly using traditional manual methods. Therefore, there is a need for a system that not only automates data classification and storage, but also improves the efficiency and speed of anomaly detection.

[0699] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0700] In this invention, the server includes a data receiving device, a device for analyzing the format of the received information and verifying its integrity, and a device for executing a generative model for automatically adding metadata to the information. This enables real-time monitoring of information inflow and automatic detection and notification of anomalies, thereby improving data management efficiency and the speed of anomaly response.

[0701] A "data receiving device" is a device that receives data in various formats from external information sources and supplies it to a server.

[0702] A "device for analyzing format and verifying integrity" is a device that analyzes the format of received information to detect consistency and errors.

[0703] A "device that executes a generative model for automatically adding metadata" is a device that uses a generative model to analyze the characteristics of information and add appropriate metadata.

[0704] A "device for categorizing information and storing it in a data store" is a device that classifies information into specific categories based on metadata and efficiently stores the data.

[0705] A "device for monitoring change frequency and storing and managing information" is a device that monitors the frequency of changes to information and securely stores information that has not been updated for a certain period of time.

[0706] A "generative model retraining device" is a device that retrains a generative model using new information data to improve the accuracy of future information processing.

[0707] A "device that monitors information inflow in real time and automatically detects and notifies of anomalies" is a device that detects anomalies in real time when information continues to flow in and notifies the administrator.

[0708] The server is equipped with a data receiving device for receiving data in various formats from external terminals. This device receives formatted data such as CSV, JSON, and XML, analyzes the format, and verifies its integrity. Since the verified data is difficult to manage as is, a metadata addition device using a generative AI model performs feature analysis, and appropriate metadata is automatically added.

[0709] Next, the server's information categorization device classifies the information into specific categories based on the assigned metadata and efficiently stores it in the data store. This speeds up information retrieval and access. This data store is managed by a device that monitors the frequency of changes, and information that has not changed for a certain period is archived to optimize storage.

[0710] Furthermore, each time new information data is added, the system retrains the generative model, improving its accuracy based on this data. This makes it possible to perform more accurate analysis in future data processing.

[0711] As a concrete example, energy usage in a data center is monitored in real time, and when usage exceeds a certain threshold, a device that monitors the inflow of information in real time and automatically detects anomalies notifies the administrator's terminal with an alert. This enables a rapid response.

[0712] An example of a prompt might be, "How can I detect and notify of anomalies in an application that needs to view data in real time?" The hardware used would include data center server infrastructure and administrator smartphones, while the software would utilize Python, Flask, TensorFlow, and other technologies. This system automates complex data management processes and streamlines management tasks.

[0713] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0714] Step 1:

[0715] The server receives various data formats (CSV, JSON, XML, etc.) from external terminals. These data files are provided as input, and the format of the received data is specified as output. The server recognizes these formats and prepares the data to be sent to the next processing step.

[0716] Step 2:

[0717] The server analyzes the format of the received data and verifies its integrity. Data files are provided as input, and format consistency and error information are obtained as output. By checking the data format and for any defects, quality assurance is performed before proceeding to subsequent processing.

[0718] Step 3:

[0719] The server automatically adds metadata to the data using a generative AI model. Analyzed data is provided as input, and the output is data with added metadata. The generative AI model performs feature analysis to add appropriate metadata to the data.

[0720] Step 4:

[0721] The server categorizes information into specific categories based on metadata and stores it in the data store. Data with metadata is provided as input, and the categorized data is stored as output. This enables efficient data retrieval and utilization.

[0722] Step 5:

[0723] The server monitors the frequency of changes to stored data and archives data that has not been updated for a certain period. Update information for stored data is provided as input, and a list of archived data is obtained as output. This maintains storage efficiency.

[0724] Step 6:

[0725] The server retrains the generative model based on the new data. New data is provided as input, and an improved generative model is obtained as output. This will increase the accuracy of future data processing and enable more precise analysis.

[0726] Step 7:

[0727] The server monitors the inflow of information, such as energy usage in the data center, in real time and sends an alert to the administrator's terminal if an anomaly is detected. Usage data is provided as input, and the notification content is sent to the terminal as output. This enables a rapid response.

[0728] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0729] This invention improves the accuracy of data organization and analysis by incorporating an emotion engine into a data management system to recognize user emotions. The system automates data reception, analysis, automatic metadata assignment, emotion analysis, data classification, update frequency management, archiving, and retraining of generative models.

[0730] First, the user inputs new data into the system via a terminal. During this process, the emotion engine recognizes the user's emotions in real time based on their voice, facial expressions, input speed, and other factors. This emotion information is then sent to the data server as metadata.

[0731] The server analyzes the received data, ensuring format consistency and verifying integrity. Furthermore, it uses a built-in generative model to add metadata and user sentiment data to the data, improving the accuracy of the information.

[0732] Based on the assigned metadata and sentiment data, the server categorizes the data. For example, in the case of customer data, customers that the sentiment engine determines to have a high purchase intent are classified as "priority customers" and distinguished from regular customers.

[0733] Once the data is integrated, the server monitors its update frequency. Data that hasn't been updated for a certain period is automatically archived, but even then, sentiment data trends are taken into consideration, and special processing may be applied.

[0734] Furthermore, the server retrains the generative model using newly received data and sentiment information. As a result, the model's ability to adapt to changes in sentiment improves, leading to even greater accuracy in subsequent data processing.

[0735] As a concrete example, suppose a user submits a complaint through an inquiry form, and dissatisfaction or stress is recognized. Through this information, the server identifies that customer as a "customer who needs improvement" and adjusts the priority of follow-up. In this way, it becomes possible to improve the quality of customer service and customer satisfaction.

[0736] With the above configuration, the system implementing the present invention integrates emotion-based data management and achieves a higher level of data analysis and management compared to conventional data management systems.

[0737] The following describes the processing flow.

[0738] Step 1:

[0739] Users input data using their devices, and during this process, voice, facial expressions, and other information are collected in real time by the device's emotion engine. The emotion engine analyzes this data to generate the user's emotional data.

[0740] Step 2:

[0741] The device sends data entered by the user and emotional data analyzed by the emotion engine to the server. This data may be in various formats such as CSV or JSON.

[0742] Step 3:

[0743] The server analyzes the received data and converts it into a standardized format. During this process, it verifies data integrity and detects inconsistencies and errors.

[0744] Step 4:

[0745] The server uses a built-in generative model to automatically add metadata to the data. In this process, a pre-trained algorithm adds tags and attributes based on the data's features.

[0746] Step 5:

[0747] The server considers the attached metadata and sentiment data obtained from the user to classify the data into specific categories. For example, customers with high purchase intent are classified as "priority customers," while those with low intent are classified as "regular customers."

[0748] Step 6:

[0749] The server monitors the update frequency of stored data. Data that has not been updated for a certain period is automatically archived, but if special processing based on sentiment data is required at this time, a re-verification is performed.

[0750] Step 7:

[0751] The server retrains its generative model using newly received data. This retraining process also includes sentiment data, aiming to improve accuracy in subsequent data processing.

[0752] In this way, a system is built that significantly improves the efficiency and accuracy of data management by automating the data input, sentiment analysis, and data management processes.

[0753] (Example 2)

[0754] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0755] Modern data management systems face challenges in accuracy and efficiency because it is difficult to consider user emotions when organizing and analyzing data. Furthermore, there is a growing desire to achieve more comprehensive and precise data management by utilizing emotional information in data updates and classification.

[0756] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0757] In this invention, the server includes means for receiving data, means for analyzing the format of the received data and verifying its integrity, and means for executing a generative model for automatically adding metadata and sentiment data to the data. This enables advanced data management and analysis that reflects the user's sentiment.

[0758] A "means of receiving data" refers to a module that receives input data from the user and incorporates it into the system.

[0759] "Means for analyzing the format of received data and verifying its integrity" refers to a processing device that analyzes the format of input data and checks whether the data is correct and consistent.

[0760] "Means for executing a generative model for automatically adding metadata and sentiment data" refers to an algorithm for automatically generating and adding additional information related to data and user sentiment information.

[0761] "A means of classifying data and storing it in a database" refers to a system for classifying analyzed data into specific categories and storing them in a database that can be used for long-term storage.

[0762] "A means of monitoring update frequency and archiving data that has not been updated for a certain period based on sentiment data" refers to the process of checking the frequency of data changes, and if the data has not been updated for a certain period, considering sentiment information, and moving and saving the data to a separate storage location.

[0763] "Methods for retraining generative models" refer to learning algorithms that readjust the parameters of a generative model based on newly collected data and sentiment information to improve its performance.

[0764] This data management system begins with the user inputting new data through a terminal. The terminal is equipped with voice recognition software and a facial expression analysis system, which uses an emotion engine to analyze the user's voice, facial expressions, input speed, etc. This emotion engine uses an emotion recognition algorithm to recognize the user's emotions in real time and generates the results as emotion data.

[0765] The server receives data and sentiment data sent from the user. It then uses dedicated software to analyze the data format and verify its consistency. Next, the server uses a generative AI model to automatically add metadata and sentiment data to the received data. This generative model is built on deep learning algorithms and effectively extracts information from the dataset.

[0766] The server then categorizes the data based on the assigned metadata and sentiment data. For example, in the case of customer data, it can identify customers with high purchase intent and classify them as "priority customers." This classification is stored in a database and is easily accessible.

[0767] Furthermore, the server monitors the frequency of data updates and archives data that has not been updated for a certain period, taking sentiment data into consideration. This process enables the system to achieve efficient storage management. At the same time, the server retrains its generative model based on newly received data and sentiment information, improving the accuracy of the algorithm.

[0768] For example, when a user submits a complaint through an inquiry form, the system can recognize dissatisfaction and stress as emotional data and treat them as high-priority triage items. This speeds up customer support responses and contributes to improved customer satisfaction.

[0769] An example of a prompt message is, "Process the voice-inputted complaint information, determine the customer's emotions through sentiment analysis, and prioritize their response." By using this prompt, the system can perform emotion-based data management in response to user requests.

[0770] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0771] Step 1:

[0772] The user uses a device to input new data. This input data may include text, audio, and images. The device uses sensors to capture the user's voice, facial expressions, and input speed during data entry, and analyzes this data with an emotion engine. This process extracts emotion data from the input data and formats it as metadata.

[0773] Step 2:

[0774] The server receives input data and metadata sent from the terminal. The server analyzes the data format and converts it to the correct format. During the analysis process, a generative AI model is used to analyze the data structure and verify its consistency. Once the format is correctly prepared, the data is ready to be processed internally as structured data.

[0775] Step 3:

[0776] The server runs a generative AI model, adding multiple layers of metadata, including sentiment data, to the input data. When tagging the data, the server retrains the generative model using historical datasets. This tagging process allows the data to acquire additional labels to highlight specific information. The generated metadata improves the accuracy of the data and may also be used as prompts.

[0777] Step 4:

[0778] The server categorizes data based on the assigned metadata and sentiment data. Specifically, it measures user purchase intent based on the analyzed sentiment data and creates lists labeled as priority customers, etc. This classification process forms the basis for formulating optimal management strategies.

[0779] Step 5:

[0780] The server has the function of storing classified data in a database and monitoring the update frequency. During this process, the server checks the sentiment data of data that has not been updated for a certain period and makes a decision on whether to archive it. Data deemed to have important sentiment is retained for special processing rather than being archived.

[0781] Step 6:

[0782] The server retrains its generative AI model based on newly received datasets and sentiment data. This retraining process uses a feedback loop derived from the new inputs to improve the accuracy of sentiment recognition and metadata assignment, thereby enhancing its ability to process data for the next generation.

[0783] (Application Example 2)

[0784] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0785] Current data management systems struggle to organize and classify data while considering user emotions. This often results in an inability to provide information and responses that meet user needs. In particular, consumer electronics require appropriate responses that reflect the user's emotions, but current technology is insufficient to achieve this.

[0786] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0787] In this invention, the server includes means for receiving data, means for analyzing the format of the received data and verifying its integrity, means for executing a generative model for automatically attaching metadata to the data, means for recognizing emotions from user input information, means for classifying data based on the user's emotion data and the attached metadata and storing it in an information set, means for monitoring the data update frequency and archiving data that has not been updated for a certain period of time, and means for retraining the generative model using a new dataset. This enables advanced data management based on user emotions and appropriate responses to the emotions of users in consumer electronic devices.

[0788] "Data receiving means" refers to a device or method that acquires data from an external source and converts it into a format usable within the system.

[0789] "Emotion recognition means" refers to a technology or device for detecting and identifying emotions from data such as the user's voice, facial expressions, and input speed.

[0790] A "generative model" is a computational model used to generate appropriate metadata and tags in response to input data, and is learned through machine learning and AI technologies.

[0791] Metadata is supplementary information added to classify or organize data, making it easier to understand and search for.

[0792] An "information collection" is a database or storage device where classified data is stored, and it serves as the foundation for proper information management.

[0793] "Retraining" is the process of training an existing generative model again with a newly acquired dataset to improve the model's accuracy and adaptability.

[0794] In the system for implementing this invention, the user first inputs data via a terminal. The terminal is equipped with emotion recognition means, which detects the user's emotions from data such as voice, facial expressions, and input speed. The emotion data is attached as metadata and sent to the server along with the data.

[0795] The server analyzes the format of the received data, verifies its integrity, and then automatically adds metadata to the data using a generative model. Python and other machine learning libraries can be used as the generative AI model. Based on the added metadata and user sentiment data, the server classifies and stores the data as an information set. This process enables data management tailored to the user's sentiment.

[0796] Furthermore, the server improves the accuracy of data processing by retraining the generative model using a new dataset. Cloud services such as Google Cloud Platform and AWS can be used for retraining.

[0797] As a concrete example, suppose a child returns home from school and says to their device, "Today's homework was difficult." The server senses the child's stress level from this statement and suggests, through consumer electronics, "Maybe you should take a break and listen to your favorite music." In this way, it becomes possible to provide appropriate responses that reflect the user's emotions.

[0798] An example of a prompt statement might be, "Develop an application for a consumer robot that reads the emotions of the user when they speak and takes appropriate action." Based on this prompt statement, it is possible to create a flow for generating an AI model for emotion recognition and processing the data.

[0799] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0800] Step 1:

[0801] The user inputs data into the device. The input data is recorded on the device as audio or text. At this point, emotion recognition is activated, analyzing emotions from voice tone and input speed. The input data and analyzed emotions are compiled as metadata.

[0802] Step 2:

[0803] The terminal sends metadata and data to the server. The server analyzes the format of the received data and verifies its consistency. Here, it checks for inconsistencies in the data and standardizes it to a specific format. It also checks the sentiment information recorded as metadata and converts it into a format that can be used by the generative model.

[0804] Step 3:

[0805] The server executes a generative model and automatically adds new metadata to the data. The generative AI model generates prompt statements in response to the input information and processes the information to organize and expand it. This model adds metadata in a format that incorporates user sentiment information, thereby increasing the value of the data.

[0806] Step 4:

[0807] Based on the generated metadata, the server classifies and stores the data as an information collection. In this process, the data is divided into appropriate categories according to the metadata and assigned sentiment information. This makes it easy to search and retrieve information within the database.

[0808] Step 5:

[0809] The server monitors the frequency of data updates, and data that has not been updated for a certain period is archived. During this process, sentiment data is taken into consideration, and archiving is adjusted based on specific criteria. Furthermore, the generative model is retrained using new datasets to prepare for improved accuracy in future data processing.

[0810] Step 6:

[0811] The retrained generative model is used for subsequent data processing, improving its accuracy and adaptability. This allows the server to perform more sophisticated sentiment analysis and metadata assignment during subsequent user input, thereby improving the user experience.

[0812] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0813] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0814] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0815] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0816] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0817] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0818] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0819] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0820] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0821] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0822] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0823] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0824] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0825] 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.

[0826] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0827] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0828] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0829] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0830] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0831] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0832] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0833] The following is further disclosed regarding the embodiments described above.

[0834] (Claim 1)

[0835] Data receiving means,

[0836] A means to analyze the format of the received data and verify its integrity,

[0837] A means of executing a generative model for automatically adding metadata to data,

[0838] A means of classifying data based on assigned metadata and storing it in a database,

[0839] A means of monitoring the update frequency of data and archiving data that has not been updated for a certain period of time,

[0840] A method for retraining a generative model using a new dataset,

[0841] A system that includes this.

[0842] (Claim 2)

[0843] The system according to claim 1, wherein when metadata is added to data, a generative model adds tags with high accuracy based on past datasets.

[0844] (Claim 3)

[0845] The system according to claim 1, which classifies data into specific categories based on pre-set criteria in data classification.

[0846] "Example 1"

[0847] (Claim 1)

[0848] Means of receiving information,

[0849] A means to analyze the type of received information and verify its consistency,

[0850] A means of executing an algorithm for automatically assigning characteristic information to information,

[0851] A means for classifying information based on assigned characteristic information and storing it in a memory area,

[0852] A means of tracking the frequency of information updates and accumulating information that has not been updated for a specific period of time,

[0853] A means of retraining an algorithm using a new set of information,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The system according to claim 1, wherein when assigning characteristic information to information, the algorithm performs high-precision identification based on a past information set.

[0857] (Claim 3)

[0858] The system according to claim 1, which classifies information into specific types based on pre-set criteria in the classification of information.

[0859] "Application Example 1"

[0860] (Claim 1)

[0861] Data receiving device,

[0862] A device that analyzes the format of received information and verifies its integrity,

[0863] A device that executes a generative model for automatically adding metadata to information,

[0864] A device that categorizes information based on assigned metadata and stores it in a data store,

[0865] A device that monitors the frequency of information changes and stores and manages information that has not been changed for a certain period of time,

[0866] A device for retraining a generative model using a new information set,

[0867] A device that monitors the inflow of information in real time, automatically detects and notifies of anomalies,

[0868] A system that includes this.

[0869] (Claim 2)

[0870] The system according to claim 1, wherein when metadata is added to information, a generative model assigns labels with high accuracy based on a past set of information.

[0871] (Claim 3)

[0872] The system according to claim 1, which classifies information into specific categories based on pre-set criteria in the classification of information.

[0873] "Example 2 of combining an emotion engine"

[0874] (Claim 1)

[0875] A means for receiving data,

[0876] A means to analyze the format of the received data and verify its integrity,

[0877] A means for executing a generative model to automatically add metadata and sentiment data to data,

[0878] A means of classifying data based on assigned metadata and sentiment data and storing it in a database,

[0879] A means of monitoring the update frequency of data and archiving data that has not been updated for a certain period based on sentiment data,

[0880] A method for retraining a generative model using newly received data and sentiment information,

[0881] A system that includes this.

[0882] (Claim 2)

[0883] The system according to claim 1, wherein when metadata and sentiment data are attached to data, a generative model is used to tag the data with high accuracy based on past datasets and sentiment information.

[0884] (Claim 3)

[0885] The system according to claim 1, which classifies data into specific categories based on pre-set criteria and sentiment data in data classification.

[0886] "Application example 2 when combining with an emotional engine"

[0887] (Claim 1)

[0888] Data receiving means,

[0889] A means to analyze the format of the received data and verify its integrity,

[0890] A means of executing a generative model for automatically adding metadata to data,

[0891] An emotion recognition method that recognizes emotions from user input information,

[0892] A means of classifying data based on user sentiment data and assigned metadata, and storing it in an information collection,

[0893] A means of monitoring the update frequency of data and archiving data that has not been updated for a certain period of time,

[0894] A method for retraining a generative model using a new dataset,

[0895] A system that includes this.

[0896] (Claim 2)

[0897] The system according to claim 1, which performs information analysis based on the user's emotions and presents an appropriate response.

[0898] (Claim 3)

[0899] The system according to claim 1, applicable to consumer electronics and providing guidance in response to the user's emotions. [Explanation of Symbols]

[0900] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Data receiving device, A device that analyzes the format of received information and verifies its integrity, A device that executes a generative model for automatically adding metadata to information, A device that categorizes information based on assigned metadata and stores it in a data store, A device that monitors the frequency of information changes and stores and manages information that has not been changed for a certain period of time, A device for retraining a generative model using a new information set, A device that monitors the inflow of information in real time, automatically detects and notifies of anomalies, A system that includes this.

2. The system according to claim 1, wherein when metadata is added to information, a generative model assigns labels with high accuracy based on past information sets.

3. The system according to claim 1, which classifies information into specific categories based on pre-set criteria in the classification of information.

Images