system

Abstract

We provide the system. [Solution] A means of obtaining messages from multiple communication media, A means for analyzing the aforementioned message using speech recognition, image-to-text recognition, and natural language processing, A means for determining the importance and urgency of the message based on the analysis results, Means for organizing and classifying the messages based on their importance and urgency, Means for notifying a display device of organized and classified messages, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, due to the diversification of communication tools, it has become common for users to receive messages from multiple platforms. However, it is cumbersome to manage these messages individually, and there is a possibility of missing important and urgent information. For this reason, there is a demand for an efficient means of centrally managing messages obtained from multiple communication media and sorting / classifying them based on importance and urgency.

Means for Solving the Problems

[0005] This invention provides a means for determining the importance and urgency of messages by acquiring messages from multiple communication media and analyzing them using speech recognition, image-to-text recognition, and natural language processing. Furthermore, it solves the aforementioned problems by constructing a system that organizes and classifies messages based on these determination results and notifies the user of the organized messages. In addition, by collecting user feedback and incorporating a learning function to improve the accuracy of analysis and organization, it enables flexible responses to meet the needs of users.

[0006] "Communication medium" is a general term for means and devices used to send and receive data such as voice, text, and images.

[0007] A "message" refers to a unit of information or data that is sent or received through a communication medium.

[0008] "Speech recognition" is a technology that analyzes audio data and converts it into text; it is the process of understanding human speech as digital data.

[0009] "Image character recognition" is a technology that detects characters contained within an image and extracts them as text data.

[0010] "Natural language processing" is a technology that uses computers to understand and manipulate human language, and includes text analysis and generation.

[0011] "Importance" is a criterion for evaluating how valuable the information contained in a message is to the user.

[0012] "Urgency" is a criterion that indicates how quickly a message should be addressed.

[0013] "Judgment" is the act of making an evaluation based on analyzed information, according to specific criteria.

[0014] "Organization" refers to arranging information in an orderly manner based on certain criteria.

[0015] "Classification" refers to the act of grouping things with common characteristics.

[0016] "Notification" is an act of presenting specific information to a user and is a means to draw the user's attention.

[0017] "Feedback" is opinions or evaluations provided by users and contributes to the improvement of the system.

[0018] "Learning function" refers to the ability to automatically improve the system by utilizing past data and feedback.

Brief Description of Drawings

[0019] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing apparatus and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing apparatus and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing apparatus and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing apparatus and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10]Shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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.

[0023] 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.

[0024] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0025] 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).

[0026] 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."

[0027] [First Embodiment]

[0028] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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".

[0040] This invention relates to a system for centrally managing messages from multiple communication media and organizing and classifying them based on importance and urgency. This allows users to easily manage messages and respond quickly without missing important information.

[0041] At the heart of this system is a program on the server, which operates as follows: The server periodically retrieves messages from various communication media, such as email services, chat applications, voice messaging applications, and image sharing platforms. This retrieval uses a secure data retrieval method, which is carried out via the service's API or a dedicated access authentication protocol.

[0042] The acquired messages are first stored on the server and analyzed using speech recognition, image-to-text recognition, and natural language processing. During this analysis, speech messages are converted to text, and text information extracted from images is also converted to text. Subsequently, natural language processing techniques are used to scrutinize the message content, extract key phrases, and perform contextual understanding.

[0043] The analyzed message information is evaluated by the server based on importance and urgency. This evaluation criterion reflects pre-defined rules and trend analysis based on historical data. The evaluated messages are organized and categorized, and the results are notified to the user.

[0044] Notifications are handled by the device. The device receives organized message information sent from the server and relays it to the user. In particular, high-priority messages are immediately pushed, allowing users to quickly access important information.

[0045] As a concrete example, even while a user is on holiday, the server collects and analyzes work-related emails and chat messages that the user has registered. For instance, if an urgent work request arrives, the server classifies the message by priority and urgency and notifies the user via their device. Upon receiving this notification, the user can take appropriate action as needed.

[0046] Thus, the present invention significantly reduces the user's information processing burden and enables efficient communication by efficiently managing multiple messages.

[0047] The following describes the processing flow.

[0048] Step 1:

[0049] The server periodically collects new messages using APIs from various communication media, including email and chat applications, and accesses them securely through authentication.

[0050] Step 2:

[0051] The server temporarily stores the collected messages and then performs speech recognition processing. Speech messages are converted to text, and image messages have text data extracted using OCR technology.

[0052] Step 3:

[0053] The server applies natural language processing techniques to the converted and extracted text data to extract important keywords and understand the context.

[0054] Step 4:

[0055] The server evaluates the importance and urgency of messages based on the analysis results. This evaluation takes into account the presence of specific keywords and source information.

[0056] Step 5:

[0057] The server categorizes messages according to their priority based on their assessed importance and urgency.

[0058] Step 6:

[0059] The server sends the classified messages to the terminal and prepares to notify the user.

[0060] Step 7:

[0061] The device sends push notifications to the user based on the received message information. This is especially important for high-priority messages.

[0062] Step 8:

[0063] Users check notifications and respond to messages as needed. This allows users to instantly grasp important information.

[0064] (Example 1)

[0065] 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."

[0066] In modern society, the vast amount of information exchanged through digital communication channels requires proper management for individuals and organizations. In particular, there is a need for efficient organization of information based on its importance and urgency, enabling rapid decision-making. However, manually analyzing and managing the enormous amount of information received from multiple communication platforms is time-consuming and laborious, and often carries the risk of overlooking crucial information.

[0067] 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.

[0068] In this invention, the server includes means for acquiring information from multiple digital communication means, means for analyzing the information using voice data conversion, image data conversion, and natural language analysis, and means for evaluating the importance and urgency of the information based on the analysis results. This enables users to efficiently manage information received through various communication means and respond quickly to information of high importance and urgency.

[0069] "Digital communication means" refers to electronic media used to send and receive data over the internet, and includes email services, chat applications, voice messaging systems, and image sharing platforms.

[0070] "Information" refers to messages and data that a server obtains from digital communication means, and includes data in text, audio, and image formats.

[0071] "Audio data conversion" refers to the technology that converts audio information into text format. This converts messages acquired via audio into a format that is easier to analyze.

[0072] "Image data conversion" refers to the technology of converting text and content within an image into text format. This converts the information contained in the image into a format that can be analyzed.

[0073] "Natural language analysis" refers to a technology that automatically understands the content of acquired text data and extracts key phrases and determines context.

[0074] "Importance" refers to an evaluation criterion that indicates how much value or meaning information holds for the user. It is determined based on business priorities and other factors.

[0075] "Urgency" refers to an evaluation criterion that indicates how quickly a response to the information needs to be made. It is based on how imminent the event requiring immediate attention is.

[0076] "Evaluation" refers to the process of quantifying or hierarchizing the importance and urgency of information obtained through natural language analysis.

[0077] To implement this invention, a system is constructed in which the server, terminal, and user elements cooperate to function.

[0078] The server functions as the core of this system. The server periodically retrieves messages from multiple digital communication methods registered by the user. This is done using APIs and dedicated access authentication protocols provided by each communication method. For example, data is securely retrieved using APIs from email services and messaging apps. The retrieved information is then analyzed by the server using speech-to-text conversion, image data conversion, and natural language processing. Speech messages are converted to text using speech-to-text technology, and text information is extracted from image data using OCR (optical character recognition) technology. Natural language processing techniques are then applied to the analyzed text to understand the context of the message and identify key phrases.

[0079] The terminal is responsible for receiving organized and evaluated messages sent from the server and notifying the user. In particular, a system is in place to quickly push notifications to users for information deemed highly important or urgent. Such notifications are transmitted to the user via display devices such as smartphones and personal computers.

[0080] Users can check notifications received through their devices and take action based on the information as needed. This creates an environment where vast amounts of information can be managed efficiently and important information can be responded to quickly.

[0081] As a concrete example, if a user receives work-related messages during their holidays, the server analyzes them and, if it determines they are of high importance or urgency, immediately notifies the user via their device. Upon receiving this notification, the user can quickly take the necessary action.

[0082] An example of a prompt using a generative AI model is: "Based on the analyzed message, evaluate the importance and urgency of the information, and notify the terminal of the results so that the user can respond quickly." This prompt makes it easy for the server to understand and execute the series of analysis, evaluation, and notification processes it should perform.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The server retrieves messages from the digital communication methods registered by the user. Inputs include raw data from email, chat, voice messages, and image sharing platforms. This data is retrieved using the APIs and authentication protocols of each platform. As output, the recorded message data is stored in the server's database.

[0086] Step 2:

[0087] The server analyzes the stored message data. The input is the message data obtained in step 1. The server uses speech data conversion technology to convert speech messages into text and image data conversion technology to extract characters from images as text. In this process, natural language processing technology is used to analyze the context and extract key phrases. The output is the analyzed text data.

[0088] Step 3:

[0089] The server evaluates the importance and urgency of each message based on the analyzed text data. The input is the analysis results from step 2. The evaluation is performed based on pre-configured rules and machine learning models, and importance and urgency scores are assigned. The output is the evaluated message data, which includes the importance and urgency tags assigned to each message.

[0090] Step 4:

[0091] The server organizes the evaluated message data and classifies it based on importance and urgency. The input is the output of step 3. The classified message data is then sorted to prioritize those requiring real-time notification. The output is the message data prepared for notification.

[0092] Step 5:

[0093] The device receives organized message data and notifies the user. The input is the output of step 4. The device sends push notifications for messages deemed particularly important or urgent. This allows the user to check the information immediately. The output is a notification to the user, which is displayed on the user's device.

[0094] (Application Example 1)

[0095] 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."

[0096] Modern commercial facilities are required to respond quickly to a wide range of customer inquiries and requests. However, traditional communication methods are insufficient because the sheer volume of information can lead to important messages being overlooked. Furthermore, appropriately prioritizing information and efficiently responding to customer inquiries is a challenging task.

[0097] 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.

[0098] In this invention, the server includes means for acquiring messages from multiple communication media, means for analyzing them using speech recognition, image-to-text recognition, and natural language processing, and means for determining importance and urgency based on the analysis results. This enables workers in commercial facilities to quickly grasp important information and efficiently handle customer interactions.

[0099] "Communication media" refers to various means of transmitting information, including formats such as email, chat, and voice.

[0100] "Speech recognition" is a technology that converts speech data into text data, allowing for the extraction of textual information from speech.

[0101] "Image character recognition" is a technology that detects characters contained within an image and extracts them as text data.

[0102] "Natural language processing" is a technology that uses computers to understand, analyze, and process human language appropriately.

[0103] "Importance" is an indicator that shows the value and priority of information, and serves as a criterion for determining whether action is necessary.

[0104] "Urgency" is an indicator that shows how quickly information should be processed.

[0105] A "display device" is a device used to visually present organized and categorized information to a user.

[0106] A "commercial facility" is a physical place intended for commercial transactions, a place where goods and services are provided to customers.

[0107] "Worker" refers to a person in charge of interacting with customers within a commercial facility.

[0108] "Customer service" refers to the activities of responding to customer requests and questions in commercial facilities and providing appropriate service.

[0109] In the system that implements this application, the server is responsible for collecting source information from multiple communication media, and securely acquires data through APIs and dedicated access authentication protocols to ensure that all information is obtained without omission. As for the software, a Python-based Flask application functions as the server, and natural language processing is enabled by utilizing the OpenAI® API. Google® Cloud Speech-to-Text is used for speech recognition, and the Google Cloud Vision API is used for image-to-text recognition.

[0110] The server converts the acquired messages into text through speech recognition and image-to-text recognition. Next, it analyzes the messages using natural language processing techniques and determines their importance and urgency based on that analysis. During this analysis process, key phrases are extracted, and the message is understood in context.

[0111] The terminal receives organized and categorized messages from the server and notifies the user via a display device. For information of high importance and urgency, push notifications are sent immediately, enabling users to respond quickly.

[0112] As a concrete example, in a commercial facility, if a customer makes an urgent inquiry, the server determines the message to be of high priority and immediately notifies the staff. This system allows staff within the commercial facility to respond efficiently without missing important information, thereby improving customer satisfaction.

[0113] An example of a prompt for a generative AI model could be: "When a new product arrives, tell me how to notify the staff of that information as a top priority."

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The server periodically retrieves messages from multiple communication channels. Inputs include data provided by email and chat application APIs, while output is the raw message data retrieved. A specific access authentication protocol is used to establish a secure connection and ensure that all messages are retrieved.

[0117] Step 2:

[0118] The server parses the acquired messages. The input is the message data acquired in the previous step; voice messages are converted to text using Google Cloud Speech-to-Text, and text information within images is transcribed using the Google Cloud Vision API. The output is the transcribed message.

[0119] Step 3:

[0120] The server analyzes transcribed messages using natural language processing and evaluates their importance and urgency. The input is transcribed messages, and key phrases and contextual understanding are performed using the OpenAI API. The output is the importance and urgency score for each message.

[0121] Step 4:

[0122] The server organizes and categorizes messages based on their importance and urgency. The input is the score evaluated in the previous step, which is used to determine the priority of responses. The output is a prioritized list of messages.

[0123] Step 5:

[0124] The device receives organized messages from the server and notifies the user. The input is an organized and categorized list of messages, and the output is notification information for the user. The device immediately sends push notifications to the user, quickly conveying important information.

[0125] Step 6:

[0126] The user responds to customer inquiries based on the notifications received. The input is notification information from the device, enabling immediate responses to high-priority customer inquiries. The output is the user's response action.

[0127] 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.

[0128] This invention relates to a system for centrally managing messages acquired from multiple communication media, determining their importance and urgency while taking user emotions into consideration, and organizing and classifying them. For this purpose, it is equipped with advanced analytical functions incorporating an emotion engine.

[0129] The server first retrieves messages through various communication media. This retrieval uses a secure method that involves authentication via the media's API. The retrieved messages are temporarily stored on the server, and then voice messages are converted to text using speech recognition technology, and image messages have their text data extracted using OCR technology.

[0130] Next, the server uses natural language processing technology to analyze the text data, and the emotion engine detects the user's emotions. These emotions are analyzed in conjunction with the message's context and keywords, and are reflected in determining its specific importance and urgency. The emotion engine can, for example, adjust the message to draw attention even to messages that should be given a low importance rating if the user is feeling stressed.

[0131] The analyzed information is indexed by the server, and messages are automatically organized and classified based on their evaluation. This organized message information is then sent to the terminal according to priority, and users are notified.

[0132] As a concrete example, consider a situation where a user is checking personal emails during work breaks. In this case, the server determines that the user is highly stressed because they are focused on their work. Taking this emotional data into account, the server reduces unnecessary notifications and only pushes notifications for highly urgent messages. As a result, the user can respond quickly to important information without being distracted.

[0133] Furthermore, by collecting user feedback, the server applies machine learning algorithms to improve the accuracy of analysis and organization based on the accumulated data. As a result, the system can adapt more closely to user characteristics and preferences over time, enabling it to manage messages increasingly effectively.

[0134] The following describes the processing flow.

[0135] Step 1:

[0136] The server retrieves messages using APIs from multiple communication channels. During this process, data is collected securely through the authentication protocols of each service.

[0137] Step 2:

[0138] The server temporarily stores the acquired messages in a database and uses a speech recognition engine to convert the voice messages into text. It also applies OCR technology to extract text from images.

[0139] Step 3:

[0140] The server uses natural language processing to analyze the text data and gain a detailed understanding of each message's content. This process includes keyword extraction and content summarization.

[0141] Step 4:

[0142] The server uses an emotion engine to estimate the user's emotional state. This analysis is based on the message content and the user's past emotional data, taking into account the user's psychological state.

[0143] Step 5:

[0144] The server integrates the analyzed content and sentiment information to assess the importance and urgency of the message. The evaluation criteria are dynamically adjusted and optimized as needed.

[0145] Step 6:

[0146] The server classifies messages based on their evaluation and organizes them by priority. This organized information is then properly indexed, enabling efficient access.

[0147] Step 7:

[0148] The organized message information is sent from the server to the terminal. The terminal then prepares a notification for the user based on the received information and delivers it as a push notification.

[0149] Step 8:

[0150] Users check notifications from their devices and respond to messages as needed. The user's response history is fed back to the server, and the system uses this information for future processing.

[0151] Step 9:

[0152] The server records user feedback and reactions as training data and runs machine learning to improve the accuracy of sentiment detection and message analysis. As a result, the system evolves over time to better adapt to user needs.

[0153] (Example 2)

[0154] 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".

[0155] In modern information and communication technology, there is a need to effectively manage the vast amount of information flowing in from multiple means of information transmission, and to efficiently organize and classify only the information that is truly important and urgent to the user. Furthermore, it is difficult to flexibly adjust the priority of information according to the user's emotions and circumstances. Providing an information management system that solves these problems is a challenge.

[0156] 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.

[0157] In this invention, the server includes means for acquiring information from multiple information transmission means, means for analyzing the information using speech recognition technology, character recognition technology, and information analysis technology, and means for detecting emotions considering the context of the information using an emotion analysis function, and adjusting the priority and speed based on that. This makes it possible to automatically organize and classify information that is important and relevant to the user and notify them at the appropriate time.

[0158] "Means of information transmission" refer to means of sending and receiving information to and from each other, such as email, social media, and messaging platforms.

[0159] "Speech recognition technology" is a technology that analyzes speech as a digital signal and converts it into corresponding text data.

[0160] "Character recognition technology" is a technology that identifies characters within an image and converts that character information into text data.

[0161] "Information analysis technology" refers to techniques that analyze information, including natural language processing and sentiment analysis, to extract meaning and emotions.

[0162] The "emotion analysis function" is a feature that detects emotions and tone contained in text data and adjusts the priority and speed of data based on that.

[0163] "Priority" is an indicator of the importance of information and is used to determine the priority of information processing and notification.

[0164] "Rapidity" is an indicator of the urgency of information and is used to determine how quickly information should be processed.

[0165] "Organization and classification" is the process of systematically organizing acquired information based on specific criteria and classifying it into categories according to its relevance and priority.

[0166] "Indexing" is the process of listing information based on specific keywords or attributes and storing it in a database in a searchable format.

[0167] The "learning function" is a feature used to improve the accuracy of system analysis and organization by utilizing user feedback and past data.

[0168] This invention provides a process for an information management system in which a server acquires information through multiple information transmission means and manages it efficiently. The server first acquires information from email, social media, and messaging platforms using APIs for the information transmission means. This information is temporarily recorded in the server's database.

[0169] Next, the server analyzes the information using speech recognition, character recognition, and information analysis technologies. For voice messages, speech recognition technology is used to convert them into text data. For example, a general-purpose speech recognition engine can be used for speech recognition. For image messages, character recognition technology is used to extract text data. Specifically, optical character recognition (OCR) technology is used to read characters within images.

[0170] Furthermore, the server uses sentiment analysis capabilities to detect the sentiment of the information. The analysis employs a natural language processing engine that considers keywords and context. This allows the context of the information to be evaluated, and its priority and speed of processing are determined.

[0171] The analyzed information is organized and categorized according to priority and urgency. This allows users to receive information that is most relevant to their current situation and emotional state.

[0172] As a concrete example, this system works by having the server notify users only of high-priority messages when they are feeling stressed at work. This feature allows users to focus on important information.

[0173] An example of a prompt used with a generative AI model is as follows: "Explain the effectiveness of a system for determining the priority of important emails while under high stress at work." This prompt allows the generative AI model to explain the system's effectiveness and benefits in more detail.

[0174] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0175] Step 1:

[0176] The server retrieves information from email, social media, and messaging platforms using APIs for various communication methods. This step involves an API authentication process to obtain an authentication token and securely collect information. The input consists of messages from multiple communication methods, and the output is message data stored in a database within the server.

[0177] Step 2:

[0178] The server converts voice messages into text data using speech recognition technology. This process involves receiving an audio file as input, passing it through a speech recognition engine, and outputting the resulting text. Specifically, it performs digital signal processing to convert voice messages into text format.

[0179] Step 3:

[0180] The server applies character recognition (OCR) technology to image messages to extract text data. The input is an image file, and OCR technology is used to analyze the characters within the image, obtaining the corresponding text as output. For example, it can identify handwritten characters or printed text and extract character data.

[0181] Step 4:

[0182] The server analyzes text data using natural language processing techniques. In this step, the input text data is passed through the analysis engine to extract keywords, understand the context, and identify important information. The output is the analysis result used to determine importance and urgency.

[0183] Step 5:

[0184] The server uses sentiment analysis functionality to detect emotions contained in text data. It analyzes emotional patterns in the input text data, identifying the user's emotions (e.g., stress, joy), and outputs sentiment analysis information. This information is then used for subsequent priority adjustments.

[0185] Step 6:

[0186] The server determines the priority and urgency of information based on the analysis results and sentiment analysis information. The input consists of text analysis results and sentiment analysis information. The server evaluates the importance of the information according to pre-defined criteria and outputs the results. Based on these results, the next steps of organization and classification are performed.

[0187] Step 7:

[0188] The server organizes and appropriately classifies information based on priority and urgency. The input is determined importance information; the server determines which category the information belongs to and outputs an organized dataset. This process allows users to easily identify information that requires immediate attention.

[0189] Step 8:

[0190] The server sends organized and categorized information to the terminal and notifies the user. The input is organized information data, and by sending this to the user's terminal, the output is a user notification. This notification allows the user to respond quickly to important and urgent information.

[0191] (Application Example 2)

[0192] 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 device 14 will be referred to as the "terminal."

[0193] As virtual stores receive a growing number of diverse customer inquiries and feedback, it becomes difficult to respond to all of them quickly and accurately. In particular, urgent inquiries and negative feedback require priority, but current systems struggle to efficiently prioritize and respond appropriately. This raises concerns about decreased customer satisfaction and an increased burden on support staff.

[0194] 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.

[0195] In this invention, the server includes means for acquiring messages from multiple information transmission devices, means for analyzing the messages using voice analysis, image character extraction, and natural language processing, means for determining the priority and urgency of the messages based on the analysis results, means for collecting customer inquiries and opinions and determining response priority through sentiment analysis, and means for notifying display means of the organized and classified messages. This makes it possible to efficiently determine priorities and respond quickly to important inquiries.

[0196] An "information transmission device" is a device used to send and receive digital messages and data, and serves as the source of messages.

[0197] "Voice analysis" is a technology that converts acquired voice messages into text and then analyzes their content.

[0198] "Image-to-text extraction" is a technology that identifies character information from image data and extracts it as text.

[0199] "Natural language processing" is a technology used to understand meaning from text and analyze intentions and emotions.

[0200] "Priority" is an indicator that shows the level of importance of the message that needs to be processed.

[0201] "Urgency" is an indicator that shows the degree to which a quick response to a message is required.

[0202] "Sentiment analysis" is a technology that understands the emotions contained in a message and determines a course of action based on the results.

[0203] A "display means" is a device that visually outputs the analyzed message and presents the information to the user.

[0204] This invention is a message management system centered around a server. The server securely collects messages from multiple information transmission devices and then generates text data using speech analysis and image-to-text extraction technologies. Specifically, speech messages are converted into text using IBM Watson® Speech to Text, and text information is extracted from image data using Google OCR.

[0205] Next, the server uses natural language processing to analyze the text content and identifies the sentiment and intent of the message using Google Natural Language API and Azure® Text Analytics. At this stage, the server determines the priority and urgency of the message based on the analysis results, and then, after detecting the customer's emotions through sentiment analysis, determines the priority of the response. In particular, messages that are highly urgent and of emotional importance receive priority notifications.

[0206] The server organizes messages according to priority and urgency, and notifies the user's terminal display of the results. This allows users to quickly recognize important information and take appropriate action. For example, if there are many customer inquiries during the Christmas sales period, the server can analyze their sentiment and prioritize notifying the support team of those that are urgent or cause the most dissatisfaction.

[0207] Ultimately, the system continuously collects user feedback and applies machine learning algorithms (such as TENSORFLOW® and Scikit-learn) to improve the accuracy of analysis and organization. This enables more effective message management over time.

[0208] Examples of prompt statements are as follows:

[0209] "Analyze the following customer message and infer its sentiment. Then, determine its importance and urgency, and set a priority for action. Message: 'I am very unhappy because the item I ordered has not arrived. If this continues, I will consider canceling the order.'"

[0210] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0211] Step 1:

[0212] The server collects messages using APIs for various information transmission devices. The input is raw message data obtained through API calls, and the output is a digital copy of the message stored on the server. This data includes messages in voice, image, and text formats.

[0213] Step 2:

[0214] The server uses a speech analysis program to convert speech messages into text. The input is speech data, which is processed using the IBM Watson Speech to Text service, resulting in text data as output. In this process, the recorded speech content is extracted as textual information.

[0215] Step 3:

[0216] The server analyzes image messages using an image text extraction program. The input is image data, and text information is extracted via Google OCR, resulting in the output being text data within the image. This process visualizes reviews and descriptions within the image.

[0217] Step 4:

[0218] The server analyzes text content using a natural language processing program. The input is text data, and the Google Natural Language API recognizes sentiment and subject matter, providing a sentiment rating and semantic information for the message as output. This clarifies the message's intent and emotions.

[0219] Step 5:

[0220] The server determines priority and urgency based on the analyzed data. The input is sentiment analysis results, which are calculated using a rule-based algorithm. The output is the message priority rank and urgency score. This allows for an assessment of which messages require immediate attention.

[0221] Step 6:

[0222] The server classifies and organizes messages based on priority and urgency. Inputs are priority rank and urgency score, which are stored in a data structure using a categorization algorithm, generating an organized message list as output. This ensures messages are sorted in a way that prioritizes response efficiency.

[0223] Step 7:

[0224] The server sends organized messages to the terminal for display via a notification system. The input is an organized list of messages, and the terminal's API is used to generate notifications, which are then displayed on the user's terminal as output. This allows the user to visually identify messages that require priority attention.

[0225] Step 8:

[0226] The underlying system collects user feedback and uses machine learning algorithms to further improve the accuracy of analysis and organization. The input is user feedback data, which is trained using TensorFlow or Scikit-learn, resulting in an improved model as output. As a result, the system evolves over time, managing messages with greater accuracy.

[0227] 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.

[0228] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0229] 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.

[0230] [Second Embodiment]

[0231] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0232] 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.

[0233] 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).

[0234] 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.

[0235] 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.

[0236] 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).

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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".

[0243] This invention relates to a system for centrally managing messages from multiple communication media and organizing and classifying them based on importance and urgency. This allows users to easily manage messages and respond quickly without missing important information.

[0244] At the heart of this system is a program on the server, which operates as follows: The server periodically retrieves messages from various communication media, such as email services, chat applications, voice messaging applications, and image sharing platforms. This retrieval uses a secure data retrieval method, which is carried out via the service's API or a dedicated access authentication protocol.

[0245] The acquired messages are first stored on the server and analyzed using speech recognition, image-to-text recognition, and natural language processing. During this analysis, speech messages are converted to text, and text information extracted from images is also converted to text. Subsequently, natural language processing techniques are used to scrutinize the message content, extract key phrases, and perform contextual understanding.

[0246] The analyzed message information is evaluated by the server based on importance and urgency. This evaluation criterion reflects pre-defined rules and trend analysis based on historical data. The evaluated messages are organized and categorized, and the results are notified to the user.

[0247] Notifications are handled by the device. The device receives organized message information sent from the server and relays it to the user. In particular, high-priority messages are immediately pushed, allowing users to quickly access important information.

[0248] As a concrete example, even while a user is on holiday, the server collects and analyzes work-related emails and chat messages that the user has registered. For instance, if an urgent work request arrives, the server classifies the message by priority and urgency and notifies the user via their device. Upon receiving this notification, the user can take appropriate action as needed.

[0249] Thus, the present invention significantly reduces the user's information processing burden and enables efficient communication by efficiently managing multiple messages.

[0250] The following describes the processing flow.

[0251] Step 1:

[0252] The server periodically collects new messages using APIs from various communication media, including email and chat applications, and accesses them securely through authentication.

[0253] Step 2:

[0254] The server temporarily stores the collected messages and then performs speech recognition processing. Speech messages are converted to text, and image messages have text data extracted using OCR technology.

[0255] Step 3:

[0256] The server applies natural language processing techniques to the converted and extracted text data to extract important keywords and understand the context.

[0257] Step 4:

[0258] The server evaluates the importance and urgency of messages based on the analysis results. This evaluation takes into account the presence of specific keywords and source information.

[0259] Step 5:

[0260] The server categorizes messages according to their priority based on their assessed importance and urgency.

[0261] Step 6:

[0262] The server sends the classified messages to the terminal and prepares to notify the user.

[0263] Step 7:

[0264] The device sends push notifications to the user based on the received message information. This is especially important for high-priority messages.

[0265] Step 8:

[0266] Users check notifications and respond to messages as needed. This allows users to instantly grasp important information.

[0267] (Example 1)

[0268] 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."

[0269] In modern society, the vast amount of information exchanged through digital communication channels requires proper management for individuals and organizations. In particular, there is a need for efficient organization of information based on its importance and urgency, enabling rapid decision-making. However, manually analyzing and managing the enormous amount of information received from multiple communication platforms is time-consuming and laborious, and often carries the risk of overlooking crucial information.

[0270] 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.

[0271] In this invention, the server includes means for acquiring information from multiple digital communication means, means for analyzing the information using voice data conversion, image data conversion, and natural language analysis, and means for evaluating the importance and urgency of the information based on the analysis results. This enables users to efficiently manage information received through various communication means and respond quickly to information of high importance and urgency.

[0272] "Digital communication means" refers to electronic media used to send and receive data over the internet, and includes email services, chat applications, voice messaging systems, and image sharing platforms.

[0273] "Information" refers to messages and data that a server obtains from digital communication means, and includes data in text, audio, and image formats.

[0274] "Audio data conversion" refers to the technology that converts audio information into text format. This converts messages acquired via audio into a format that is easier to analyze.

[0275] "Image data conversion" refers to the technology of converting text and content within an image into text format. This converts the information contained in the image into a format that can be analyzed.

[0276] "Natural language analysis" refers to a technology that automatically understands the content of acquired text data and extracts key phrases and determines context.

[0277] "Importance" refers to an evaluation criterion that indicates how much value or meaning information holds for the user. It is determined based on business priorities and other factors.

[0278] "Urgency" refers to an evaluation criterion that indicates how quickly a response to the information needs to be made. It is based on how imminent the event requiring immediate attention is.

[0279] "Evaluation" refers to the process of quantifying or hierarchizing the importance and urgency of information obtained through natural language analysis.

[0280] To implement this invention, a system is constructed in which the server, terminal, and user elements cooperate to function.

[0281] The server functions as the core of this system. The server periodically acquires messages from multiple digital communication means registered by the user. As the acquisition method, APIs provided by each communication means or a dedicated access authentication protocol is used. For example, APIs of mail services and messaging apps are used to securely acquire data. The information thus acquired is analyzed by the server using voice data conversion, image data conversion, and natural language analysis. Voice messages are texturized by speech-to-text technology, and character information is extracted from image information using OCR (Optical Character Recognition) technology. Then, natural language processing technology is applied to the analyzed text to understand the context of the message and identify key phrases.

[0282] The terminal receives the sorted and evaluated messages sent from the server and plays the role of notifying the user. In particular, for information evaluated as having high importance or urgency, a mechanism for quickly pushing notifications to the user is established. Such notifications are transmitted to the user via a display device such as a smartphone or a personal computer.

[0283] The user can check the notifications received through the terminal and take actions based on the information as needed. This builds an environment where a vast amount of information can be efficiently managed and quick responses can be made to important information.

[0284] As a specific example, regarding work-related messages received by the user during holidays, if the server analyzes them and determines that they have high importance or urgency, it immediately notifies the user through the terminal. Upon receiving this notification, the user can quickly take the necessary actions.

[0285] As an example of a prompt sentence using a generative AI model, there is "Based on the analyzed message, evaluate the importance and urgency of the information and notify the terminal of the results so that the user can respond quickly." With this prompt sentence, the series of analysis, evaluation, and notification processes performed by the server can be easily understood and executed.

[0286] The flow of the specific process in Example 1 will be described using FIG. 11.

[0287] Step 1:

[0288] The server obtains a message from the digital communication means registered by the user. The inputs include mails, chats, voice messages, and raw data from image sharing platforms. These data are obtained using the APIs and authentication protocols of their respective platforms. As output, the recorded message data is saved in the server's database.

[0289] Step 2:

[0290] The server analyzes the saved message data. The input is the message data obtained in Step 1. The server uses voice data conversion technology to convert voice messages into text, and also uses image data conversion technology to extract the characters in the image as text. In this process, natural language processing technology is used to analyze the context and extract key phrases. The output is the analyzed text data.

[0291] Step 3:

[0292] Based on the analyzed text data, the server evaluates the importance and urgency of each message. The input is the analysis result of Step 2. The evaluation is carried out based on pre-set rules or machine learning models, and scores for importance and urgency are given. The output is the evaluated message data, which includes tags for importance and urgency assigned to each message.

[0293] Step 4:

[0294] The server organizes the evaluated message data and classifies it based on importance and urgency. The input is the output of step 3. The classified message data is then sorted to prioritize those requiring real-time notification. The output is the message data prepared for notification.

[0295] Step 5:

[0296] The device receives organized message data and notifies the user. The input is the output of step 4. The device sends push notifications for messages deemed particularly important or urgent. This allows the user to check the information immediately. The output is a notification to the user, which is displayed on the user's device.

[0297] (Application Example 1)

[0298] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0299] Modern commercial facilities are required to respond quickly to a wide range of customer inquiries and requests. However, traditional communication methods are insufficient because the sheer volume of information can lead to important messages being overlooked. Furthermore, appropriately prioritizing information and efficiently responding to customer inquiries is a challenging task.

[0300] 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.

[0301] In this invention, the server includes means for acquiring messages from multiple communication media, means for analyzing them using speech recognition, image-to-text recognition, and natural language processing, and means for determining importance and urgency based on the analysis results. This enables workers in commercial facilities to quickly grasp important information and efficiently handle customer interactions.

[0302] "Communication medium" refers to various means for transmitting information, including forms such as email, chat, and voice.

[0303] "Speech recognition" is a technology that converts speech data into text data and can extract character information from speech.

[0304] "Image character recognition" is a technology that detects characters contained in an image and extracts them as text data.

[0305] "Natural language processing" refers to technologies that enable a computer to understand, analyze, and appropriately process human language.

[0306] "Importance" is an indicator that shows the value or priority of information and serves as a criterion for determining the necessity of response.

[0307] "Urgency" is an indicator that shows how quickly information should be processed in terms of time.

[0308] "Display device" is a device for visually presenting organized and classified information to a user.

[0309] "Commercial facility" is a physical location for commercial transactions and a place for providing goods and services to customers.

[0310] "Operator" refers to the person in charge of dealing with customers within a commercial facility.

[0311] "Customer service" refers to activities that respond to customer requests and questions in a commercial facility and provide appropriate services.

[0312] In the system that implements this application, the server is responsible for collecting source information from multiple communication media, and securely acquires data through APIs and dedicated access authentication protocols to ensure that all information is obtained without omission. As for the software, a Python-based Flask application functions as the server, and natural language processing is enabled by utilizing the OpenAI API. Google Cloud Speech-to-Text is used for speech recognition, and the Google Cloud Vision API is used for image-to-text recognition.

[0313] The server converts the acquired messages into text through speech recognition and image-to-text recognition. Next, it analyzes the messages using natural language processing techniques and determines their importance and urgency based on that analysis. During this analysis process, key phrases are extracted, and the message is understood in context.

[0314] The terminal receives organized and categorized messages from the server and notifies the user via a display device. For information of high importance and urgency, push notifications are sent immediately, enabling users to respond quickly.

[0315] As a concrete example, in a commercial facility, if a customer makes an urgent inquiry, the server determines the message to be of high priority and immediately notifies the staff. This system allows staff within the commercial facility to respond efficiently without missing important information, thereby improving customer satisfaction.

[0316] An example of a prompt for a generative AI model could be: "When a new product arrives, tell me how to notify the staff of that information as a top priority."

[0317] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0318] Step 1:

[0319] The server periodically retrieves messages from multiple communication channels. Inputs include data provided by email and chat application APIs, while output is the raw message data retrieved. A specific access authentication protocol is used to establish a secure connection and ensure that all messages are retrieved.

[0320] Step 2:

[0321] The server parses the acquired messages. The input is the message data acquired in the previous step; voice messages are converted to text using Google Cloud Speech-to-Text, and text information within images is transcribed using the Google Cloud Vision API. The output is the transcribed message.

[0322] Step 3:

[0323] The server analyzes transcribed messages using natural language processing and evaluates their importance and urgency. The input is transcribed messages, and key phrases and contextual understanding are performed using the OpenAI API. The output is the importance and urgency score for each message.

[0324] Step 4:

[0325] The server organizes and categorizes messages based on their importance and urgency. The input is the score evaluated in the previous step, which is used to determine the priority of responses. The output is a prioritized list of messages.

[0326] Step 5:

[0327] The device receives organized messages from the server and notifies the user. The input is an organized and categorized list of messages, and the output is notification information for the user. The device immediately sends push notifications to the user, quickly conveying important information.

[0328] Step 6:

[0329] The user responds to customer inquiries based on the notifications received. The input is notification information from the device, enabling immediate responses to high-priority customer inquiries. The output is the user's response action.

[0330] 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.

[0331] This invention relates to a system for centrally managing messages acquired from multiple communication media, determining their importance and urgency while taking user emotions into consideration, and organizing and classifying them. For this purpose, it is equipped with advanced analytical functions incorporating an emotion engine.

[0332] The server first retrieves messages through various communication media. This retrieval uses a secure method that involves authentication via the media's API. The retrieved messages are temporarily stored on the server, and then voice messages are converted to text using speech recognition technology, and image messages have their text data extracted using OCR technology.

[0333] Next, the server uses natural language processing technology to analyze the text data, and the emotion engine detects the user's emotions. These emotions are analyzed in conjunction with the message's context and keywords, and are reflected in determining its specific importance and urgency. The emotion engine can, for example, adjust the message to draw attention even to messages that should be given a low importance rating if the user is feeling stressed.

[0334] The analyzed information is indexed by the server, and messages are automatically organized and classified based on their evaluation. This organized message information is then sent to the terminal according to priority, and users are notified.

[0335] As a concrete example, consider a situation where a user is checking personal emails during work breaks. In this case, the server determines that the user is highly stressed because they are focused on their work. Taking this emotional data into account, the server reduces unnecessary notifications and only pushes notifications for highly urgent messages. As a result, the user can respond quickly to important information without being distracted.

[0336] Furthermore, by collecting user feedback, the server applies machine learning algorithms to improve the accuracy of analysis and organization based on the accumulated data. As a result, the system can adapt more closely to user characteristics and preferences over time, enabling it to manage messages increasingly effectively.

[0337] The following describes the processing flow.

[0338] Step 1:

[0339] The server retrieves messages using APIs from multiple communication channels. During this process, data is collected securely through the authentication protocols of each service.

[0340] Step 2:

[0341] The server temporarily stores the acquired messages in a database and uses a speech recognition engine to convert the voice messages into text. It also applies OCR technology to extract text from images.

[0342] Step 3:

[0343] The server uses natural language processing to analyze the text data and gain a detailed understanding of each message's content. This process includes keyword extraction and content summarization.

[0344] Step 4:

[0345] The server uses an emotion engine to estimate the user's emotional state. This analysis is based on the message content and the user's past emotional data, taking into account the user's psychological state.

[0346] Step 5:

[0347] The server integrates the analyzed content and sentiment information to assess the importance and urgency of the message. The evaluation criteria are dynamically adjusted and optimized as needed.

[0348] Step 6:

[0349] The server classifies messages based on their evaluation and organizes them by priority. This organized information is then properly indexed, enabling efficient access.

[0350] Step 7:

[0351] The organized message information is sent from the server to the terminal. The terminal then prepares a notification for the user based on the received information and delivers it as a push notification.

[0352] Step 8:

[0353] Users check notifications from their devices and respond to messages as needed. The user's response history is fed back to the server, and the system uses this information for future processing.

[0354] Step 9:

[0355] The server records user feedback and reactions as training data and runs machine learning to improve the accuracy of sentiment detection and message analysis. As a result, the system evolves over time to better adapt to user needs.

[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] In modern information and communication technology, there is a need to effectively manage the vast amount of information flowing in from multiple means of information transmission, and to efficiently organize and classify only the information that is truly important and urgent to the user. Furthermore, it is difficult to flexibly adjust the priority of information according to the user's emotions and circumstances. Providing an information management system that solves these problems is a challenge.

[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 acquiring information from multiple information transmission means, means for analyzing the information using speech recognition technology, character recognition technology, and information analysis technology, and means for detecting emotions considering the context of the information using an emotion analysis function, and adjusting the priority and speed based on that. This makes it possible to automatically organize and classify information that is important and relevant to the user and notify them at the appropriate time.

[0361] "Means of information transmission" refer to means of sending and receiving information to and from each other, such as email, social media, and messaging platforms.

[0362] "Speech recognition technology" is a technology that analyzes speech as a digital signal and converts it into corresponding text data.

[0363] "Character recognition technology" is a technology that identifies characters within an image and converts that character information into text data.

[0364] "Information analysis technology" refers to techniques that analyze information, including natural language processing and sentiment analysis, to extract meaning and emotions.

[0365] The "emotion analysis function" is a feature that detects emotions and tone contained in text data and adjusts the priority and speed of data based on that.

[0366] "Priority" is an indicator of the importance of information and is used to determine the priority of information processing and notification.

[0367] "Rapidity" is an indicator of the urgency of information and is used to determine how quickly information should be processed.

[0368] "Organization and classification" is the process of systematically organizing acquired information based on specific criteria and classifying it into categories according to its relevance and priority.

[0369] "Indexing" is the process of listing information based on specific keywords or attributes and storing it in a database in a searchable format.

[0370] The "learning function" is a feature used to improve the accuracy of system analysis and organization by utilizing user feedback and past data.

[0371] This invention provides a process for an information management system in which a server acquires information through multiple information transmission means and manages it efficiently. The server first acquires information from email, social media, and messaging platforms using APIs for the information transmission means. This information is temporarily recorded in the server's database.

[0372] Next, the server analyzes the information using speech recognition, character recognition, and information analysis technologies. For voice messages, speech recognition technology is used to convert them into text data. For example, a general-purpose speech recognition engine can be used for speech recognition. For image messages, character recognition technology is used to extract text data. Specifically, optical character recognition (OCR) technology is used to read characters within images.

[0373] Furthermore, the server uses sentiment analysis capabilities to detect the sentiment of the information. The analysis employs a natural language processing engine that considers keywords and context. This allows the context of the information to be evaluated, and its priority and speed of processing are determined.

[0374] The analyzed information is organized and categorized according to priority and urgency. This allows users to receive information that is most relevant to their current situation and emotional state.

[0375] As a concrete example, this system works by having the server notify users only of high-priority messages when they are feeling stressed at work. This feature allows users to focus on important information.

[0376] An example of a prompt used with a generative AI model is as follows: "Explain the effectiveness of a system for determining the priority of important emails while under high stress at work." This prompt allows the generative AI model to explain the system's effectiveness and benefits in more detail.

[0377] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0378] Step 1:

[0379] The server retrieves information from email, social media, and messaging platforms using APIs for various communication methods. This step involves an API authentication process to obtain an authentication token and securely collect information. The input consists of messages from multiple communication methods, and the output is message data stored in a database within the server.

[0380] Step 2:

[0381] The server converts voice messages into text data using speech recognition technology. This process involves receiving an audio file as input, passing it through a speech recognition engine, and outputting the resulting text. Specifically, it performs digital signal processing to convert voice messages into text format.

[0382] Step 3:

[0383] The server applies character recognition (OCR) technology to image messages to extract text data. The input is an image file, and OCR technology is used to analyze the characters within the image, obtaining the corresponding text as output. For example, it can identify handwritten characters or printed text and extract character data.

[0384] Step 4:

[0385] The server analyzes text data using natural language processing techniques. In this step, the input text data is passed through the analysis engine to extract keywords, understand the context, and identify important information. The output is the analysis result used to determine importance and urgency.

[0386] Step 5:

[0387] The server uses sentiment analysis functionality to detect emotions contained in text data. By analyzing the emotional patterns in the input text data and identifying the user's emotions (e.g., stress, joy), it obtains sentiment analysis information as output. This information is then used for subsequent priority adjustments.

[0388] Step 6:

[0389] The server determines the priority and urgency of information based on the analysis results and sentiment analysis information. The input consists of text analysis results and sentiment analysis information. The server evaluates the importance of the information according to pre-defined criteria and outputs the results. Based on these results, the next steps of organization and classification are performed.

[0390] Step 7:

[0391] The server organizes and appropriately classifies information based on priority and urgency. The input is determined importance information; the server determines which category the information belongs to and outputs an organized dataset. This process allows users to easily identify information that requires immediate attention.

[0392] Step 8:

[0393] The server sends organized and categorized information to the terminal and notifies the user. The input is organized information data, and by sending this to the user's terminal, the output is a user notification. This notification allows the user to respond quickly to important and urgent information.

[0394] (Application Example 2)

[0395] 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."

[0396] As virtual stores receive a growing number of diverse customer inquiries and feedback, it becomes difficult to respond to all of them quickly and accurately. In particular, urgent inquiries and negative feedback require priority, but current systems struggle to efficiently prioritize and respond appropriately. This raises concerns about decreased customer satisfaction and an increased burden on support staff.

[0397] 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.

[0398] In this invention, the server includes means for acquiring messages from multiple information transmission devices, means for analyzing the messages using voice analysis, image character extraction, and natural language processing, means for determining the priority and urgency of the messages based on the analysis results, means for collecting customer inquiries and opinions and determining response priority through sentiment analysis, and means for notifying display means of the organized and classified messages. This makes it possible to efficiently determine priorities and respond quickly to important inquiries.

[0399] An "information transmission device" is a device used to send and receive digital messages and data, and serves as the source of messages.

[0400] "Voice analysis" is a technology that converts acquired voice messages into text and then analyzes their content.

[0401] "Image-to-text extraction" is a technology that identifies character information from image data and extracts it as text.

[0402] "Natural language processing" is a technology used to understand meaning from text and analyze intentions and emotions.

[0403] "Priority" is an indicator that shows the level of importance of the message that needs to be processed.

[0404] "Urgency" is an indicator that shows the degree to which a quick response to a message is required.

[0405] "Sentiment analysis" is a technology that understands the emotions contained in a message and determines a course of action based on the results.

[0406] A "display means" is a device that visually outputs the analyzed message and presents the information to the user.

[0407] This invention is a message management system centered around a server. The server securely collects messages from multiple information transmission devices and then generates text data using speech analysis and image-to-text extraction technologies. Specifically, speech messages are converted to text using IBM Watson Speech to Text, and text information is extracted from image data using Google OCR.

[0408] Next, the server uses natural language processing to analyze the text content and identifies the sentiment and intent of the message using the Google Natural Language API and Azure Text Analytics. At this stage, the server determines the priority and urgency of the message based on the analysis results, and then detects the customer's emotions through sentiment analysis to determine the priority of the response. In particular, messages that are highly urgent and emotionally important receive priority notifications.

[0409] The server organizes messages according to priority and urgency, and notifies the user's terminal display of the results. This allows users to quickly recognize important information and take appropriate action. For example, if there are many customer inquiries during the Christmas sales period, the server can analyze their sentiment and prioritize notifying the support team of those that are urgent or cause the most dissatisfaction.

[0410] Ultimately, the system continuously collects user feedback and applies machine learning algorithms (such as TensorFlow and Scikit-learn) to improve the accuracy of analysis and organization. This enables more effective message management over time.

[0411] Examples of prompt statements are as follows:

[0412] "Analyze the following customer message and infer its sentiment. Then, determine its importance and urgency, and set a priority for action. Message: 'I am very unhappy because the item I ordered has not arrived. If this continues, I will consider canceling the order.'"

[0413] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0414] Step 1:

[0415] The server collects messages using APIs for various information transmission devices. The input is raw message data obtained through API calls, and the output is a digital copy of the message stored on the server. This data includes messages in voice, image, and text formats.

[0416] Step 2:

[0417] The server uses a speech analysis program to convert speech messages into text. The input is speech data, which is processed using the IBM Watson Speech to Text service, resulting in text data as output. In this process, the recorded speech content is extracted as textual information.

[0418] Step 3:

[0419] The server analyzes image messages using an image text extraction program. The input is image data, and text information is extracted via Google OCR, resulting in the output being text data within the image. This process visualizes reviews and descriptions within the image.

[0420] Step 4:

[0421] The server analyzes text content using a natural language processing program. The input is text data, and the Google Natural Language API recognizes sentiment and subject matter, providing a sentiment rating and semantic information for the message as output. This clarifies the message's intent and emotions.

[0422] Step 5:

[0423] The server determines priority and urgency based on the analyzed data. The input is sentiment analysis results, which are calculated using a rule-based algorithm. The output is the message priority rank and urgency score. This allows for an assessment of which messages require immediate attention.

[0424] Step 6:

[0425] The server classifies and organizes messages based on priority and urgency. Inputs are priority rank and urgency score, which are stored in a data structure using a categorization algorithm, generating an organized message list as output. This ensures messages are sorted in a way that prioritizes response efficiency.

[0426] Step 7:

[0427] The server sends organized messages to the terminal for display via a notification system. The input is an organized list of messages, and the terminal's API is used to generate notifications, which are then displayed on the user's terminal as output. This allows the user to visually identify messages that require priority attention.

[0428] Step 8:

[0429] The underlying system collects user feedback and uses machine learning algorithms to further improve the accuracy of analysis and organization. The input is user feedback data, which is trained using TensorFlow or Scikit-learn, resulting in an improved model as output. As a result, the system evolves over time, managing messages with greater accuracy.

[0430] 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.

[0431] 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.

[0432] 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.

[0433] [Third Embodiment]

[0434] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0435] 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.

[0436] 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).

[0437] 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.

[0438] 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.

[0439] 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).

[0440] 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.

[0441] 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.

[0442] 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.

[0443] 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.

[0444] 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.

[0445] 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".

[0446] This invention relates to a system for centrally managing messages from multiple communication media and organizing and classifying them based on importance and urgency. This allows users to easily manage messages and respond quickly without missing important information.

[0447] At the heart of this system is a program on the server, which operates as follows: The server periodically retrieves messages from various communication media, such as email services, chat applications, voice messaging applications, and image sharing platforms. This retrieval uses a secure data retrieval method, which is carried out via the service's API or a dedicated access authentication protocol.

[0448] The acquired messages are first stored on the server and analyzed using speech recognition, image-to-text recognition, and natural language processing. During this analysis, speech messages are converted to text, and text information extracted from images is also converted to text. Subsequently, natural language processing techniques are used to scrutinize the message content, extract key phrases, and perform contextual understanding.

[0449] The analyzed message information is evaluated by the server based on importance and urgency. This evaluation criterion reflects pre-defined rules and trend analysis based on historical data. The evaluated messages are organized and categorized, and the results are notified to the user.

[0450] Notifications are handled by the device. The device receives organized message information sent from the server and relays it to the user. In particular, high-priority messages are immediately pushed, allowing users to quickly access important information.

[0451] As a concrete example, even while a user is on holiday, the server collects and analyzes work-related emails and chat messages that the user has registered. For instance, if an urgent work request arrives, the server classifies the message by priority and urgency and notifies the user via their device. Upon receiving this notification, the user can take appropriate action as needed.

[0452] Thus, the present invention significantly reduces the user's information processing burden and enables efficient communication by efficiently managing multiple messages.

[0453] The following describes the processing flow.

[0454] Step 1:

[0455] The server periodically collects new messages using APIs from various communication media, including email and chat applications, and accesses them securely through authentication.

[0456] Step 2:

[0457] The server temporarily stores the collected messages and then performs speech recognition processing. Speech messages are converted to text, and image messages have text data extracted using OCR technology.

[0458] Step 3:

[0459] The server applies natural language processing techniques to the converted and extracted text data to extract important keywords and understand the context.

[0460] Step 4:

[0461] The server evaluates the importance and urgency of messages based on the analysis results. This evaluation takes into account the presence of specific keywords and source information.

[0462] Step 5:

[0463] The server categorizes messages according to their priority based on their assessed importance and urgency.

[0464] Step 6:

[0465] The server sends the classified messages to the terminal and prepares to notify the user.

[0466] Step 7:

[0467] The device sends push notifications to the user based on the received message information. This is especially important for high-priority messages.

[0468] Step 8:

[0469] Users check notifications and respond to messages as needed. This allows users to instantly grasp important information.

[0470] (Example 1)

[0471] 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."

[0472] In modern society, the vast amount of information exchanged through digital communication channels requires proper management for individuals and organizations. In particular, there is a need for efficient organization of information based on its importance and urgency, enabling rapid decision-making. However, manually analyzing and managing the enormous amount of information received from multiple communication platforms is time-consuming and laborious, and often carries the risk of overlooking crucial information.

[0473] 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.

[0474] In this invention, the server includes means for acquiring information from multiple digital communication means, means for analyzing the information using voice data conversion, image data conversion, and natural language analysis, and means for evaluating the importance and urgency of the information based on the analysis results. This enables users to efficiently manage information received through various communication means and respond quickly to information of high importance and urgency.

[0475] "Digital communication means" refers to electronic media used to send and receive data over the internet, and includes email services, chat applications, voice messaging systems, and image sharing platforms.

[0476] "Information" refers to messages and data that a server obtains from digital communication means, and includes data in text, audio, and image formats.

[0477] "Audio data conversion" refers to the technology that converts audio information into text format. This converts messages acquired via audio into a format that is easier to analyze.

[0478] "Image data conversion" refers to the technology of converting text and content within an image into text format. This converts the information contained in the image into a format that can be analyzed.

[0479] "Natural language analysis" refers to a technology that automatically understands the content of acquired text data and extracts key phrases and determines context.

[0480] "Importance" refers to an evaluation criterion that indicates how much value or meaning information holds for the user. It is determined based on business priorities and other factors.

[0481] "Urgency" refers to an evaluation criterion that indicates how quickly a response to the information needs to be made. It is based on how imminent the event requiring immediate attention is.

[0482] "Evaluation" refers to the process of quantifying or hierarchizing the importance and urgency of information obtained through natural language analysis.

[0483] To implement this invention, a system is constructed in which the server, terminal, and user elements cooperate to function.

[0484] The server functions as the core of this system. The server periodically retrieves messages from multiple digital communication methods registered by the user. This is done using APIs and dedicated access authentication protocols provided by each communication method. For example, data is securely retrieved using APIs from email services and messaging apps. The retrieved information is then analyzed by the server using speech-to-text conversion, image data conversion, and natural language processing. Speech messages are converted to text using speech-to-text technology, and text information is extracted from image data using OCR (optical character recognition) technology. Natural language processing techniques are then applied to the analyzed text to understand the context of the message and identify key phrases.

[0485] The terminal is responsible for receiving organized and evaluated messages sent from the server and notifying the user. In particular, a system is in place to quickly push notifications to users for information deemed highly important or urgent. Such notifications are transmitted to the user via display devices such as smartphones and personal computers.

[0486] Users can check notifications received through their devices and take action based on the information as needed. This creates an environment where vast amounts of information can be managed efficiently and important information can be responded to quickly.

[0487] As a concrete example, if a user receives work-related messages during their holidays, the server analyzes them and, if it determines they are of high importance or urgency, immediately notifies the user via their device. Upon receiving this notification, the user can quickly take the necessary action.

[0488] An example of a prompt using a generative AI model is: "Based on the analyzed message, evaluate the importance and urgency of the information, and notify the terminal of the results so that the user can respond quickly." This prompt makes it easy for the server to understand and execute the series of analysis, evaluation, and notification processes it should perform.

[0489] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0490] Step 1:

[0491] The server retrieves messages from the digital communication methods registered by the user. Inputs include raw data from email, chat, voice messages, and image sharing platforms. This data is retrieved using the APIs and authentication protocols of each platform. As output, the recorded message data is stored in the server's database.

[0492] Step 2:

[0493] The server analyzes the stored message data. The input is the message data obtained in step 1. The server uses speech data conversion technology to convert speech messages into text and image data conversion technology to extract characters from images as text. In this process, natural language processing technology is used to analyze the context and extract key phrases. The output is the analyzed text data.

[0494] Step 3:

[0495] The server evaluates the importance and urgency of each message based on the analyzed text data. The input is the analysis results from step 2. The evaluation is performed based on pre-configured rules and machine learning models, and importance and urgency scores are assigned. The output is the evaluated message data, which includes the importance and urgency tags assigned to each message.

[0496] Step 4:

[0497] The server organizes the evaluated message data and classifies it based on importance and urgency. The input is the output of step 3. The classified message data is then sorted to prioritize those that require real-time notification. The output is the message data prepared for notification.

[0498] Step 5:

[0499] The device receives organized message data and notifies the user. The input is the output of step 4. The device sends push notifications for messages deemed particularly important or urgent. This allows the user to check the information immediately. The output is a notification to the user, which is displayed on the user's device.

[0500] (Application Example 1)

[0501] 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."

[0502] Modern commercial facilities are required to respond quickly to a wide range of customer inquiries and requests. However, traditional communication methods are insufficient because the sheer volume of information can lead to important messages being overlooked. Furthermore, appropriately prioritizing information and efficiently responding to customer inquiries is a challenging task.

[0503] 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.

[0504] In this invention, the server includes means for acquiring messages from multiple communication media, means for analyzing them using speech recognition, image-to-text recognition, and natural language processing, and means for determining importance and urgency based on the analysis results. This enables workers in commercial facilities to quickly grasp important information and efficiently handle customer interactions.

[0505] "Communication media" refers to various means of transmitting information, including formats such as email, chat, and voice.

[0506] "Speech recognition" is a technology that converts speech data into text data, allowing for the extraction of textual information from speech.

[0507] "Image character recognition" is a technology that detects characters contained within an image and extracts them as text data.

[0508] "Natural language processing" is a technology that uses computers to understand, analyze, and process human language appropriately.

[0509] "Importance" is an indicator that shows the value and priority of information, and serves as a criterion for determining whether action is necessary.

[0510] "Urgency" is an indicator that shows how quickly information should be processed.

[0511] A "display device" is a device used to visually present organized and categorized information to a user.

[0512] A "commercial facility" is a physical place intended for commercial transactions, a place where goods and services are provided to customers.

[0513] "Worker" refers to a person in charge of interacting with customers within a commercial facility.

[0514] "Customer service" refers to the activities of responding to customer requests and questions in commercial facilities and providing appropriate service.

[0515] In the system that implements this application, the server is responsible for collecting source information from multiple communication media, and securely acquires data through APIs and dedicated access authentication protocols to ensure that all information is obtained without omission. As for the software, a Python-based Flask application functions as the server, and natural language processing is enabled by utilizing the OpenAI API. Google Cloud Speech-to-Text is used for speech recognition, and the Google Cloud Vision API is used for image-to-text recognition.

[0516] The server converts the acquired messages into text through speech recognition and image-to-text recognition. Next, it analyzes the messages using natural language processing techniques and determines their importance and urgency based on that analysis. During this analysis process, key phrases are extracted, and the message is understood in context.

[0517] The terminal receives organized and categorized messages from the server and notifies the user via a display device. For information of high importance and urgency, push notifications are sent immediately, enabling users to respond quickly.

[0518] As a concrete example, in a commercial facility, if a customer makes an urgent inquiry, the server determines the message to be of high priority and immediately notifies the staff. This system allows staff within the commercial facility to respond efficiently without missing important information, thereby improving customer satisfaction.

[0519] An example of a prompt for a generative AI model could be: "When a new product arrives, tell me how to notify the staff of that information as a top priority."

[0520] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0521] Step 1:

[0522] The server periodically retrieves messages from multiple communication channels. Inputs include data provided by email and chat application APIs, while output is the raw message data retrieved. A specific access authentication protocol is used to establish a secure connection and ensure that all messages are retrieved.

[0523] Step 2:

[0524] The server parses the acquired messages. The input is the message data acquired in the previous step; voice messages are converted to text using Google Cloud Speech-to-Text, and text information within images is transcribed using the Google Cloud Vision API. The output is the transcribed message.

[0525] Step 3:

[0526] The server analyzes transcribed messages using natural language processing and evaluates their importance and urgency. The input is transcribed messages, and key phrases and contextual understanding are performed using the OpenAI API. The output is the importance and urgency score for each message.

[0527] Step 4:

[0528] The server organizes and categorizes messages based on their importance and urgency. The input is the score evaluated in the previous step, which is used to determine the priority of responses. The output is a prioritized list of messages.

[0529] Step 5:

[0530] The device receives organized messages from the server and notifies the user. The input is an organized and categorized list of messages, and the output is notification information for the user. The device immediately sends push notifications to the user, quickly conveying important information.

[0531] Step 6:

[0532] The user responds to customer inquiries based on the notifications received. The input is notification information from the device, enabling immediate responses to high-priority customer inquiries. The output is the user's response action.

[0533] 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.

[0534] This invention relates to a system for centrally managing messages acquired from multiple communication media, determining their importance and urgency while taking user emotions into consideration, and organizing and classifying them. For this purpose, it is equipped with advanced analytical functions incorporating an emotion engine.

[0535] The server first retrieves messages through various communication media. This retrieval uses a secure method that involves authentication via the media's API. The retrieved messages are temporarily stored on the server, and then voice messages are converted to text using speech recognition technology, and image messages have their text data extracted using OCR technology.

[0536] Next, the server uses natural language processing technology to analyze the text data, and the emotion engine detects the user's emotions. These emotions are analyzed in conjunction with the message's context and keywords, and are reflected in determining its specific importance and urgency. The emotion engine can, for example, adjust the message to draw attention even to messages that should be given a low importance rating if the user is feeling stressed.

[0537] The analyzed information is indexed by the server, and messages are automatically organized and classified based on their evaluation. This organized message information is then sent to the terminal according to priority, and users are notified.

[0538] As a concrete example, consider a situation where a user is checking personal emails during work breaks. In this case, the server determines that the user is highly stressed because they are focused on their work. Taking this emotional data into account, the server reduces unnecessary notifications and only pushes notifications for highly urgent messages. As a result, the user can respond quickly to important information without being distracted.

[0539] Furthermore, by collecting user feedback, the server applies machine learning algorithms to improve the accuracy of analysis and organization based on the accumulated data. As a result, the system can adapt more closely to user characteristics and preferences over time, enabling it to manage messages increasingly effectively.

[0540] The following describes the processing flow.

[0541] Step 1:

[0542] The server retrieves messages using APIs from multiple communication channels. During this process, data is collected securely through the authentication protocols of each service.

[0543] Step 2:

[0544] The server temporarily stores the acquired messages in a database and uses a speech recognition engine to convert the voice messages into text. It also applies OCR technology to extract text from images.

[0545] Step 3:

[0546] The server uses natural language processing to analyze the text data and gain a detailed understanding of each message's content. This process includes keyword extraction and content summarization.

[0547] Step 4:

[0548] The server uses an emotion engine to estimate the user's emotional state. This analysis is based on the message content and the user's past emotional data, taking into account the user's psychological state.

[0549] Step 5:

[0550] The server integrates the analyzed content and sentiment information to assess the importance and urgency of the message. The evaluation criteria are dynamically adjusted and optimized as needed.

[0551] Step 6:

[0552] The server classifies messages based on their evaluation and organizes them by priority. This organized information is then properly indexed, enabling efficient access.

[0553] Step 7:

[0554] The organized message information is sent from the server to the terminal. The terminal then prepares a notification for the user based on the received information and delivers it as a push notification.

[0555] Step 8:

[0556] Users check notifications from their devices and respond to messages as needed. The user's response history is fed back to the server, and the system uses this information for future processing.

[0557] Step 9:

[0558] The server records user feedback and reactions as training data and runs machine learning to improve the accuracy of sentiment detection and message analysis. As a result, the system evolves over time to better adapt to user needs.

[0559] (Example 2)

[0560] 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."

[0561] In modern information and communication technology, there is a need to effectively manage the vast amount of information flowing in from multiple means of information transmission, and to efficiently organize and classify only the information that is truly important and urgent to the user. Furthermore, it is difficult to flexibly adjust the priority of information according to the user's emotions and circumstances. Providing an information management system that solves these problems is a challenge.

[0562] 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.

[0563] In this invention, the server includes means for acquiring information from multiple information transmission means, means for analyzing the information using speech recognition technology, character recognition technology, and information analysis technology, and means for detecting emotions considering the context of the information using an emotion analysis function, and adjusting the priority and speed based on that. This makes it possible to automatically organize and classify information that is important and relevant to the user and notify them at the appropriate time.

[0564] "Means of information transmission" refer to means of sending and receiving information to and from each other, such as email, social media, and messaging platforms.

[0565] "Speech recognition technology" is a technology that analyzes speech as a digital signal and converts it into corresponding text data.

[0566] "Character recognition technology" is a technology that identifies characters within an image and converts that character information into text data.

[0567] "Information analysis technology" refers to techniques that analyze information, including natural language processing and sentiment analysis, to extract meaning and emotions.

[0568] The "emotion analysis function" is a feature that detects emotions and tone contained in text data and adjusts the priority and speed of data based on that.

[0569] "Priority" is an indicator of the importance of information and is used to determine the priority of information processing and notification.

[0570] "Rapidity" is an indicator of the urgency of information and is used to determine how quickly information should be processed.

[0571] "Organization and classification" is the process of systematically organizing acquired information based on specific criteria and classifying it into categories according to its relevance and priority.

[0572] "Indexing" is the process of listing information based on specific keywords or attributes and storing it in a database in a searchable format.

[0573] The "learning function" is a feature used to improve the accuracy of system analysis and organization by utilizing user feedback and past data.

[0574] This invention provides a process for an information management system in which a server acquires information through multiple information transmission means and manages it efficiently. The server first acquires information from email, social media, and messaging platforms using APIs for the information transmission means. This information is temporarily recorded in the server's database.

[0575] Next, the server analyzes the information using speech recognition, character recognition, and information analysis technologies. For voice messages, speech recognition technology is used to convert them into text data. For example, a general-purpose speech recognition engine can be used for speech recognition. For image messages, character recognition technology is used to extract text data. Specifically, optical character recognition (OCR) technology is used to read characters within images.

[0576] Furthermore, the server uses sentiment analysis capabilities to detect the sentiment of the information. The analysis employs a natural language processing engine that considers keywords and context. This allows the context of the information to be evaluated, and its priority and speed of processing are determined.

[0577] The analyzed information is organized and categorized according to priority and urgency. This allows users to receive information that is most relevant to their current situation and emotional state.

[0578] As a concrete example, this system works by having the server notify users only of high-priority messages when they are feeling stressed at work. This feature allows users to focus on important information.

[0579] An example of a prompt used with a generative AI model is as follows: "Explain the effectiveness of a system for determining the priority of important emails while under high stress at work." This prompt allows the generative AI model to explain the system's effectiveness and benefits in more detail.

[0580] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0581] Step 1:

[0582] The server retrieves information from email, social media, and messaging platforms using APIs for various communication methods. This step involves an API authentication process to obtain an authentication token and securely collect information. The input consists of messages from multiple communication methods, and the output is message data stored in a database within the server.

[0583] Step 2:

[0584] The server converts voice messages into text data using speech recognition technology. This process involves receiving an audio file as input, passing it through a speech recognition engine, and outputting the resulting text. Specifically, it performs digital signal processing to convert voice messages into text format.

[0585] Step 3:

[0586] The server applies character recognition (OCR) technology to image messages to extract text data. The input is an image file, and OCR technology is used to analyze the characters within the image, obtaining the corresponding text as output. For example, it can identify handwritten characters or printed text and extract character data.

[0587] Step 4:

[0588] The server analyzes text data using natural language processing techniques. In this step, the input text data is passed through the analysis engine to extract keywords, understand the context, and identify important information. The output is the analysis result used to determine importance and urgency.

[0589] Step 5:

[0590] The server uses sentiment analysis functionality to detect emotions contained in text data. It analyzes emotional patterns in the input text data, identifying the user's emotions (e.g., stress, joy), and outputs sentiment analysis information. This information is then used for subsequent priority adjustments.

[0591] Step 6:

[0592] The server determines the priority and urgency of information based on the analysis results and sentiment analysis information. The input consists of text analysis results and sentiment analysis information. The server evaluates the importance of the information according to pre-defined criteria and outputs the results. Based on these results, the next steps of organization and classification are performed.

[0593] Step 7:

[0594] The server organizes and appropriately classifies information based on priority and urgency. The input is determined importance information; the server determines which category the information belongs to and outputs an organized dataset. This process allows users to easily identify information that requires immediate attention.

[0595] Step 8:

[0596] The server sends organized and categorized information to the terminal and notifies the user. The input is organized information data, and by sending this to the user's terminal, the output is a user notification. This notification allows the user to respond quickly to important and urgent information.

[0597] (Application Example 2)

[0598] 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."

[0599] As virtual stores receive a growing number of diverse customer inquiries and feedback, it becomes difficult to respond to all of them quickly and accurately. In particular, urgent inquiries and negative feedback require priority, but current systems struggle to efficiently prioritize and respond appropriately. This raises concerns about decreased customer satisfaction and an increased burden on support staff.

[0600] 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.

[0601] In this invention, the server includes means for acquiring messages from multiple information transmission devices, means for analyzing the messages using voice analysis, image character extraction, and natural language processing, means for determining the priority and urgency of the messages based on the analysis results, means for collecting customer inquiries and opinions and determining response priority through sentiment analysis, and means for notifying display means of the organized and classified messages. This makes it possible to efficiently determine priorities and respond quickly to important inquiries.

[0602] An "information transmission device" is a device used to send and receive digital messages and data, and serves as the source of messages.

[0603] "Voice analysis" is a technology that converts acquired voice messages into text and then analyzes their content.

[0604] "Image-to-text extraction" is a technology that identifies character information from image data and extracts it as text.

[0605] "Natural language processing" is a technology used to understand meaning from text and analyze intentions and emotions.

[0606] "Priority" is an indicator that shows the level of importance of the message that needs to be processed.

[0607] "Urgency" is an indicator that shows the degree to which a quick response to a message is required.

[0608] "Sentiment analysis" is a technology that understands the emotions contained in a message and determines a course of action based on the results.

[0609] A "display means" is a device that visually outputs the analyzed message and presents the information to the user.

[0610] This invention is a message management system centered around a server. The server securely collects messages from multiple information transmission devices and then generates text data using speech analysis and image-to-text extraction technologies. Specifically, speech messages are converted to text using IBM Watson Speech to Text, and text information is extracted from image data using Google OCR.

[0611] Next, the server uses natural language processing to analyze the text content and identifies the sentiment and intent of the message using the Google Natural Language API and Azure Text Analytics. At this stage, the server determines the priority and urgency of the message based on the analysis results, and then detects the customer's emotions through sentiment analysis to determine the priority of the response. In particular, messages that are highly urgent and emotionally important receive priority notifications.

[0612] The server organizes messages according to priority and urgency, and notifies the user's terminal display of the results. This allows users to quickly recognize important information and take appropriate action. For example, if there are many customer inquiries during the Christmas sales period, the server can analyze their sentiment and prioritize notifying the support team of those that are urgent or cause the most dissatisfaction.

[0613] Ultimately, the system continuously collects user feedback and applies machine learning algorithms (such as TensorFlow and Scikit-learn) to improve the accuracy of analysis and organization. This enables more effective message management over time.

[0614] Examples of prompt statements are as follows:

[0615] "Analyze the following customer message and infer its sentiment. Then, determine its importance and urgency, and set a priority for action. Message: 'I am very unhappy because the item I ordered has not arrived. If this continues, I will consider canceling the order.'"

[0616] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0617] Step 1:

[0618] The server collects messages using APIs for various information transmission devices. The input is raw message data obtained through API calls, and the output is a digital copy of the message stored on the server. This data includes messages in voice, image, and text formats.

[0619] Step 2:

[0620] The server uses a speech analysis program to convert speech messages into text. The input is speech data, which is processed using the IBM Watson Speech to Text service, resulting in text data as output. In this process, the recorded speech content is extracted as textual information.

[0621] Step 3:

[0622] The server analyzes image messages using an image text extraction program. The input is image data, and text information is extracted via Google OCR, resulting in the output being text data within the image. This process visualizes reviews and descriptions within the image.

[0623] Step 4:

[0624] The server analyzes text content using a natural language processing program. The input is text data, and the Google Natural Language API recognizes sentiment and subject matter, providing a sentiment rating and semantic information for the message as output. This clarifies the message's intent and emotions.

[0625] Step 5:

[0626] The server determines priority and urgency based on the analyzed data. The input is sentiment analysis results, which are calculated using a rule-based algorithm. The output is the message priority rank and urgency score. This allows for an assessment of which messages require immediate attention.

[0627] Step 6:

[0628] The server classifies and organizes messages based on priority and urgency. Inputs are priority rank and urgency score, which are stored in a data structure using a categorization algorithm, generating an organized message list as output. This ensures messages are sorted in a way that prioritizes response efficiency.

[0629] Step 7:

[0630] The server sends organized messages to the terminal for display via a notification system. The input is an organized list of messages, and the terminal's API is used to generate notifications, which are then displayed on the user's terminal as output. This allows the user to visually identify messages that require priority attention.

[0631] Step 8:

[0632] The underlying system collects user feedback and uses machine learning algorithms to further improve the accuracy of analysis and organization. The input is user feedback data, which is trained using TensorFlow or Scikit-learn, resulting in an improved model as output. As a result, the system evolves over time, managing messages with greater accuracy.

[0633] 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.

[0634] 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.

[0635] 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.

[0636] [Fourth Embodiment]

[0637] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0638] 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.

[0639] 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).

[0640] 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.

[0641] 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.

[0642] 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).

[0643] 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.

[0644] 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.

[0645] 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.

[0646] 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.

[0647] 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.

[0648] 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.

[0649] 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".

[0650] This invention relates to a system for centrally managing messages from multiple communication media and organizing and classifying them based on importance and urgency. This allows users to easily manage messages and respond quickly without missing important information.

[0651] At the heart of this system is a program on the server, which operates as follows: The server periodically retrieves messages from various communication media, such as email services, chat applications, voice messaging applications, and image sharing platforms. This retrieval uses a secure data retrieval method, which is carried out via the service's API or a dedicated access authentication protocol.

[0652] The acquired messages are first stored on the server and analyzed using speech recognition, image-to-text recognition, and natural language processing. During this analysis, speech messages are converted to text, and text information extracted from images is also converted to text. Subsequently, natural language processing techniques are used to scrutinize the message content, extract key phrases, and perform contextual understanding.

[0653] The analyzed message information is evaluated by the server based on importance and urgency. This evaluation criterion reflects pre-defined rules and trend analysis based on historical data. The evaluated messages are organized and categorized, and the results are notified to the user.

[0654] Notifications are handled by the device. The device receives organized message information sent from the server and relays it to the user. In particular, high-priority messages are immediately pushed, allowing users to quickly access important information.

[0655] As a concrete example, even while a user is on holiday, the server collects and analyzes work-related emails and chat messages that the user has registered. For instance, if an urgent work request arrives, the server classifies the message by priority and urgency and notifies the user via their device. Upon receiving this notification, the user can take appropriate action as needed.

[0656] Thus, the present invention significantly reduces the user's information processing burden and enables efficient communication by efficiently managing multiple messages.

[0657] The following describes the processing flow.

[0658] Step 1:

[0659] The server periodically collects new messages using APIs from various communication media, including email and chat applications, and accesses them securely through authentication.

[0660] Step 2:

[0661] The server temporarily stores the collected messages and then performs speech recognition processing. Speech messages are converted to text, and image messages have text data extracted using OCR technology.

[0662] Step 3:

[0663] The server applies natural language processing techniques to the converted and extracted text data to extract important keywords and understand the context.

[0664] Step 4:

[0665] The server evaluates the importance and urgency of messages based on the analysis results. This evaluation takes into account the presence of specific keywords and source information.

[0666] Step 5:

[0667] The server categorizes messages according to their priority based on their assessed importance and urgency.

[0668] Step 6:

[0669] The server sends the classified messages to the terminal and prepares to notify the user.

[0670] Step 7:

[0671] The device sends push notifications to the user based on the received message information. This is especially important for high-priority messages.

[0672] Step 8:

[0673] Users check notifications and respond to messages as needed. This allows users to instantly grasp important information.

[0674] (Example 1)

[0675] 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".

[0676] In modern society, the vast amount of information exchanged through digital communication channels requires proper management for individuals and organizations. In particular, there is a need for efficient organization of information based on its importance and urgency, enabling rapid decision-making. However, manually analyzing and managing the enormous amount of information received from multiple communication platforms is time-consuming and laborious, and often carries the risk of overlooking crucial information.

[0677] 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.

[0678] In this invention, the server includes means for acquiring information from multiple digital communication means, means for analyzing the information using voice data conversion, image data conversion, and natural language analysis, and means for evaluating the importance and urgency of the information based on the analysis results. This enables users to efficiently manage information received through various communication means and respond quickly to information of high importance and urgency.

[0679] "Digital communication means" refers to electronic media used to send and receive data over the internet, and includes email services, chat applications, voice messaging systems, and image sharing platforms.

[0680] "Information" refers to messages and data that a server obtains from digital communication means, and includes data in text, audio, and image formats.

[0681] "Audio data conversion" refers to the technology that converts audio information into text format. This converts messages acquired via audio into a format that is easier to analyze.

[0682] "Image data conversion" refers to the technology of converting text and content within an image into text format. This converts the information contained in the image into a format that can be analyzed.

[0683] "Natural language analysis" refers to a technology that automatically understands the content of acquired text data and extracts key phrases and determines context.

[0684] "Importance" refers to an evaluation criterion that indicates how much value or meaning information holds for the user. It is determined based on business priorities and other factors.

[0685] "Urgency" refers to an evaluation criterion that indicates how quickly a response to the information needs to be made. It is based on how imminent the event requiring immediate attention is.

[0686] "Evaluation" refers to the process of quantifying or hierarchizing the importance and urgency of information obtained through natural language analysis.

[0687] To implement this invention, a system is constructed in which the server, terminal, and user elements cooperate to function.

[0688] The server functions as the core of this system. The server periodically retrieves messages from multiple digital communication methods registered by the user. This is done using APIs and dedicated access authentication protocols provided by each communication method. For example, data is securely retrieved using APIs from email services and messaging apps. The retrieved information is then analyzed by the server using speech-to-text conversion, image data conversion, and natural language processing. Speech messages are converted to text using speech-to-text technology, and text information is extracted from image data using OCR (optical character recognition) technology. Natural language processing techniques are then applied to the analyzed text to understand the context of the message and identify key phrases.

[0689] The terminal is responsible for receiving organized and evaluated messages sent from the server and notifying the user. In particular, a system is in place to quickly push notifications to users for information deemed highly important or urgent. Such notifications are transmitted to the user via display devices such as smartphones and personal computers.

[0690] Users can check notifications received through their devices and take action based on the information as needed. This creates an environment where vast amounts of information can be managed efficiently and important information can be responded to quickly.

[0691] As a concrete example, if a user receives work-related messages during their holidays, the server analyzes them and, if it determines they are of high importance or urgency, immediately notifies the user via their device. Upon receiving this notification, the user can quickly take the necessary action.

[0692] An example of a prompt using a generative AI model is: "Based on the analyzed message, evaluate the importance and urgency of the information, and notify the terminal of the results so that the user can respond quickly." This prompt makes it easy for the server to understand and execute the series of analysis, evaluation, and notification processes it should perform.

[0693] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0694] Step 1:

[0695] The server retrieves messages from the digital communication methods registered by the user. Inputs include raw data from email, chat, voice messages, and image sharing platforms. This data is retrieved using the APIs and authentication protocols of each platform. As output, the recorded message data is stored in the server's database.

[0696] Step 2:

[0697] The server analyzes the stored message data. The input is the message data obtained in step 1. The server uses speech data conversion technology to convert speech messages into text and image data conversion technology to extract characters from images as text. In this process, natural language processing technology is used to analyze the context and extract key phrases. The output is the analyzed text data.

[0698] Step 3:

[0699] The server evaluates the importance and urgency of each message based on the analyzed text data. The input is the analysis results from step 2. The evaluation is performed based on pre-configured rules and machine learning models, and importance and urgency scores are assigned. The output is the evaluated message data, which includes the importance and urgency tags assigned to each message.

[0700] Step 4:

[0701] The server organizes the evaluated message data and classifies it based on importance and urgency. The input is the output of step 3. The classified message data is then sorted to prioritize those requiring real-time notification. The output is the message data prepared for notification.

[0702] Step 5:

[0703] The device receives organized message data and notifies the user. The input is the output of step 4. The device sends push notifications for messages deemed particularly important or urgent. This allows the user to check the information immediately. The output is a notification to the user, which is displayed on the user's device.

[0704] (Application Example 1)

[0705] 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".

[0706] Modern commercial facilities are required to respond quickly to a wide range of customer inquiries and requests. However, traditional communication methods are insufficient because the sheer volume of information can lead to important messages being overlooked. Furthermore, appropriately prioritizing information and efficiently responding to customer inquiries is a challenging task.

[0707] 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.

[0708] In this invention, the server includes means for acquiring messages from multiple communication media, means for analyzing them using speech recognition, image-to-text recognition, and natural language processing, and means for determining importance and urgency based on the analysis results. This enables workers in commercial facilities to quickly grasp important information and efficiently handle customer interactions.

[0709] "Communication media" refers to various means of transmitting information, including formats such as email, chat, and voice.

[0710] "Speech recognition" is a technology that converts speech data into text data, allowing for the extraction of textual information from speech.

[0711] "Image character recognition" is a technology that detects characters contained within an image and extracts them as text data.

[0712] "Natural language processing" is a technology that uses computers to understand, analyze, and process human language appropriately.

[0713] "Importance" is an indicator that shows the value and priority of information, and serves as a criterion for determining whether action is necessary.

[0714] "Urgency" is an indicator that shows how quickly information should be processed.

[0715] A "display device" is a device used to visually present organized and categorized information to a user.

[0716] A "commercial facility" is a physical place intended for commercial transactions, a place where goods and services are provided to customers.

[0717] "Worker" refers to a person in charge of interacting with customers within a commercial facility.

[0718] "Customer service" refers to the activities of responding to customer requests and questions in commercial facilities and providing appropriate service.

[0719] In the system that implements this application, the server is responsible for collecting source information from multiple communication media, and securely acquires data through APIs and dedicated access authentication protocols to ensure that all information is obtained without omission. As for the software, a Python-based Flask application functions as the server, and natural language processing is enabled by utilizing the OpenAI API. Google Cloud Speech-to-Text is used for speech recognition, and the Google Cloud Vision API is used for image-to-text recognition.

[0720] The server converts the acquired messages into text through speech recognition and image-to-text recognition. Next, it analyzes the messages using natural language processing techniques and determines their importance and urgency based on that analysis. During this analysis process, key phrases are extracted, and the message is understood in context.

[0721] The terminal receives organized and categorized messages from the server and notifies the user via a display device. For information of high importance and urgency, push notifications are sent immediately, enabling users to respond quickly.

[0722] As a concrete example, in a commercial facility, if a customer makes an urgent inquiry, the server determines the message to be of high priority and immediately notifies the staff. This system allows staff within the commercial facility to respond efficiently without missing important information, thereby improving customer satisfaction.

[0723] An example of a prompt for a generative AI model could be: "When a new product arrives, tell me how to notify the staff of that information as a top priority."

[0724] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0725] Step 1:

[0726] The server periodically retrieves messages from multiple communication channels. Inputs include data provided by email and chat application APIs, while output is the raw message data retrieved. A specific access authentication protocol is used to establish a secure connection and ensure that all messages are retrieved.

[0727] Step 2:

[0728] The server parses the acquired messages. The input is the message data acquired in the previous step; voice messages are converted to text using Google Cloud Speech-to-Text, and text information within images is transcribed using the Google Cloud Vision API. The output is the transcribed message.

[0729] Step 3:

[0730] The server analyzes transcribed messages using natural language processing and evaluates their importance and urgency. The input is transcribed messages, and key phrases and contextual understanding are performed using the OpenAI API. The output is the importance and urgency score for each message.

[0731] Step 4:

[0732] The server organizes and categorizes messages based on their importance and urgency. The input is the score evaluated in the previous step, which is used to determine the priority of responses. The output is a prioritized list of messages.

[0733] Step 5:

[0734] The device receives organized messages from the server and notifies the user. The input is an organized and categorized list of messages, and the output is notification information for the user. The device immediately sends push notifications to the user, quickly conveying important information.

[0735] Step 6:

[0736] The user responds to customer inquiries based on the notifications received. The input is notification information from the device, enabling immediate responses to high-priority customer inquiries. The output is the user's response action.

[0737] 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.

[0738] This invention relates to a system for centrally managing messages acquired from multiple communication media, determining their importance and urgency while taking user emotions into consideration, and organizing and classifying them. For this purpose, it is equipped with advanced analytical functions incorporating an emotion engine.

[0739] The server first retrieves messages through various communication media. This retrieval uses a secure method that involves authentication via the media's API. The retrieved messages are temporarily stored on the server, and then voice messages are converted to text using speech recognition technology, and image messages have their text data extracted using OCR technology.

[0740] Next, the server uses natural language processing technology to analyze the text data, and the emotion engine detects the user's emotions. These emotions are analyzed in conjunction with the message's context and keywords, and are reflected in determining its specific importance and urgency. The emotion engine can, for example, adjust the message to draw attention even to messages that should be given a low importance rating if the user is feeling stressed.

[0741] The analyzed information is indexed by the server, and messages are automatically organized and classified based on their evaluation. This organized message information is then sent to the terminal according to priority, and users are notified.

[0742] As a concrete example, consider a situation where a user is checking personal emails during work breaks. In this case, the server determines that the user is highly stressed because they are focused on their work. Taking this emotional data into account, the server reduces unnecessary notifications and only pushes notifications for highly urgent messages. As a result, the user can respond quickly to important information without being distracted.

[0743] Furthermore, by collecting user feedback, the server applies machine learning algorithms to improve the accuracy of analysis and organization based on the accumulated data. As a result, the system can adapt more closely to user characteristics and preferences over time, enabling it to manage messages increasingly effectively.

[0744] The following describes the processing flow.

[0745] Step 1:

[0746] The server retrieves messages using APIs from multiple communication channels. During this process, data is collected securely through the authentication protocols of each service.

[0747] Step 2:

[0748] The server temporarily stores the acquired messages in a database and uses a speech recognition engine to convert the voice messages into text. It also applies OCR technology to extract text from images.

[0749] Step 3:

[0750] The server uses natural language processing to analyze the text data and gain a detailed understanding of each message's content. This process includes keyword extraction and content summarization.

[0751] Step 4:

[0752] The server uses an emotion engine to estimate the user's emotional state. This analysis is based on the message content and the user's past emotional data, taking into account the user's psychological state.

[0753] Step 5:

[0754] The server integrates the analyzed content and sentiment information to assess the importance and urgency of the message. The evaluation criteria are dynamically adjusted and optimized as needed.

[0755] Step 6:

[0756] The server classifies messages based on their evaluation and organizes them by priority. This organized information is then properly indexed, enabling efficient access.

[0757] Step 7:

[0758] The organized message information is sent from the server to the terminal. The terminal then prepares a notification for the user based on the received information and delivers it as a push notification.

[0759] Step 8:

[0760] Users check notifications from their devices and respond to messages as needed. The user's response history is fed back to the server, and the system uses this information for future processing.

[0761] Step 9:

[0762] The server records user feedback and reactions as training data and runs machine learning to improve the accuracy of sentiment detection and message analysis. As a result, the system evolves over time to better adapt to user needs.

[0763] (Example 2)

[0764] 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".

[0765] In modern information and communication technology, there is a need to effectively manage the vast amount of information flowing in from multiple means of information transmission, and to efficiently organize and classify only the information that is truly important and urgent to the user. Furthermore, it is difficult to flexibly adjust the priority of information according to the user's emotions and circumstances. Providing an information management system that solves these problems is a challenge.

[0766] 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.

[0767] In this invention, the server includes means for acquiring information from multiple information transmission means, means for analyzing the information using speech recognition technology, character recognition technology, and information analysis technology, and means for detecting emotions considering the context of the information using an emotion analysis function, and adjusting the priority and speed based on that. This makes it possible to automatically organize and classify information that is important and relevant to the user and notify them at the appropriate time.

[0768] "Means of information transmission" refer to means of sending and receiving information to and from each other, such as email, social media, and messaging platforms.

[0769] "Speech recognition technology" is a technology that analyzes speech as a digital signal and converts it into corresponding text data.

[0770] "Character recognition technology" is a technology that identifies characters within an image and converts that character information into text data.

[0771] "Information analysis technology" refers to techniques that analyze information, including natural language processing and sentiment analysis, to extract meaning and emotions.

[0772] The "emotion analysis function" is a feature that detects emotions and tone contained in text data and adjusts the priority and speed of data based on that.

[0773] "Priority" is an indicator of the importance of information and is used to determine the priority of information processing and notification.

[0774] "Rapidity" is an indicator of the urgency of information and is used to determine how quickly information should be processed.

[0775] "Organization and classification" is the process of systematically organizing acquired information based on specific criteria and classifying it into categories according to its relevance and priority.

[0776] "Indexing" is the process of listing information based on specific keywords or attributes and storing it in a database in a searchable format.

[0777] The "learning function" is a feature used to improve the accuracy of system analysis and organization by utilizing user feedback and past data.

[0778] This invention provides a process for an information management system in which a server acquires information through multiple information transmission means and manages it efficiently. The server first acquires information from email, social media, and messaging platforms using APIs for the information transmission means. This information is temporarily recorded in the server's database.

[0779] Next, the server analyzes the information using speech recognition, character recognition, and information analysis technologies. For voice messages, speech recognition technology is used to convert them into text data. For example, a general-purpose speech recognition engine can be used for speech recognition. For image messages, character recognition technology is used to extract text data. Specifically, optical character recognition (OCR) technology is used to read characters within images.

[0780] Furthermore, the server uses sentiment analysis capabilities to detect the sentiment of the information. The analysis employs a natural language processing engine that considers keywords and context. This allows the context of the information to be evaluated, and its priority and speed of processing are determined.

[0781] The analyzed information is organized and categorized according to priority and urgency. This allows users to receive information that is most relevant to their current situation and emotional state.

[0782] As a concrete example, this system works by having the server notify users only of high-priority messages when they are feeling stressed at work. This feature allows users to focus on important information.

[0783] An example of a prompt used with a generative AI model is as follows: "Explain the effectiveness of a system for determining the priority of important emails while under high stress at work." This prompt allows the generative AI model to explain the system's effectiveness and benefits in more detail.

[0784] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0785] Step 1:

[0786] The server retrieves information from email, social media, and messaging platforms using APIs for various communication methods. This step involves an API authentication process to obtain an authentication token and securely collect information. The input consists of messages from multiple communication methods, and the output is message data stored in a database within the server.

[0787] Step 2:

[0788] The server converts voice messages into text data using speech recognition technology. This process involves receiving an audio file as input, passing it through a speech recognition engine, and outputting the resulting text. Specifically, it performs digital signal processing to convert voice messages into text format.

[0789] Step 3:

[0790] The server applies character recognition (OCR) technology to image messages to extract text data. The input is an image file, and OCR technology is used to analyze the characters within the image, obtaining the corresponding text as output. For example, it can identify handwritten characters or printed text and extract character data.

[0791] Step 4:

[0792] The server analyzes text data using natural language processing techniques. In this step, the input text data is passed through the analysis engine to extract keywords, understand the context, and identify important information. The output is the analysis result used to determine importance and urgency.

[0793] Step 5:

[0794] The server uses sentiment analysis functionality to detect emotions contained in text data. It analyzes emotional patterns in the input text data, identifying the user's emotions (e.g., stress, joy), and outputs sentiment analysis information. This information is then used for subsequent priority adjustments.

[0795] Step 6:

[0796] The server determines the priority and urgency of information based on the analysis results and sentiment analysis information. The input consists of text analysis results and sentiment analysis information. The server evaluates the importance of the information according to pre-defined criteria and outputs the results. Based on these results, the next steps of organization and classification are performed.

[0797] Step 7:

[0798] The server organizes and appropriately classifies information based on priority and urgency. The input is determined importance information; the server determines which category the information belongs to and outputs an organized dataset. This process allows users to easily identify information that requires immediate attention.

[0799] Step 8:

[0800] The server sends organized and categorized information to the terminal and notifies the user. The input is organized information data, and by sending this to the user's terminal, the output is a user notification. This notification allows the user to respond quickly to important and urgent information.

[0801] (Application Example 2)

[0802] 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".

[0803] As virtual stores receive a growing number of diverse customer inquiries and feedback, it becomes difficult to respond to all of them quickly and accurately. In particular, urgent inquiries and negative feedback require priority, but current systems struggle to efficiently prioritize and respond appropriately. This raises concerns about decreased customer satisfaction and an increased burden on support staff.

[0804] 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.

[0805] In this invention, the server includes means for acquiring messages from multiple information transmission devices, means for analyzing the messages using voice analysis, image character extraction, and natural language processing, means for determining the priority and urgency of the messages based on the analysis results, means for collecting customer inquiries and opinions and determining response priority through sentiment analysis, and means for notifying display means of the organized and classified messages. This makes it possible to efficiently determine priorities and respond quickly to important inquiries.

[0806] An "information transmission device" is a device used to send and receive digital messages and data, and serves as the source of messages.

[0807] "Voice analysis" is a technology that converts acquired voice messages into text and then analyzes their content.

[0808] "Image-to-text extraction" is a technology that identifies character information from image data and extracts it as text.

[0809] "Natural language processing" is a technology used to understand meaning from text and analyze intentions and emotions.

[0810] "Priority" is an indicator that shows the level of importance of the message that needs to be processed.

[0811] "Urgency" is an indicator that shows the degree to which a quick response to a message is required.

[0812] "Sentiment analysis" is a technology that understands the emotions contained in a message and determines a course of action based on the results.

[0813] A "display means" is a device that visually outputs the analyzed message and presents the information to the user.

[0814] This invention is a message management system centered around a server. The server securely collects messages from multiple information transmission devices and then generates text data using speech analysis and image-to-text extraction technologies. Specifically, speech messages are converted to text using IBM Watson Speech to Text, and text information is extracted from image data using Google OCR.

[0815] Next, the server uses natural language processing to analyze the text content and identifies the sentiment and intent of the message using the Google Natural Language API and Azure Text Analytics. At this stage, the server determines the priority and urgency of the message based on the analysis results, and then detects the customer's emotions through sentiment analysis to determine the priority of the response. In particular, messages that are highly urgent and emotionally important receive priority notifications.

[0816] The server organizes messages according to priority and urgency, and notifies the user's terminal display of the results. This allows users to quickly recognize important information and take appropriate action. For example, if there are many customer inquiries during the Christmas sales period, the server can analyze their sentiment and prioritize notifying the support team of those that are urgent or cause the most dissatisfaction.

[0817] Ultimately, the system continuously collects user feedback and applies machine learning algorithms (such as TensorFlow and Scikit-learn) to improve the accuracy of analysis and organization. This enables more effective message management over time.

[0818] Examples of prompt statements are as follows:

[0819] "Analyze the following customer message and infer its sentiment. Then, determine its importance and urgency, and set a priority for action. Message: 'I am very unhappy because the item I ordered has not arrived. If this continues, I will consider canceling the order.'"

[0820] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0821] Step 1:

[0822] The server collects messages using APIs for various information transmission devices. The input is raw message data obtained through API calls, and the output is a digital copy of the message stored on the server. This data includes messages in voice, image, and text formats.

[0823] Step 2:

[0824] The server uses a speech analysis program to convert speech messages into text. The input is speech data, which is processed using the IBM Watson Speech to Text service, resulting in text data as output. In this process, the recorded speech content is extracted as textual information.

[0825] Step 3:

[0826] The server analyzes image messages using an image text extraction program. The input is image data, and text information is extracted via Google OCR, resulting in the output being text data within the image. This process visualizes reviews and descriptions within the image.

[0827] Step 4:

[0828] The server analyzes text content using a natural language processing program. The input is text data, and the Google Natural Language API recognizes sentiment and subject matter, providing a sentiment rating and semantic information for the message as output. This clarifies the message's intent and emotions.

[0829] Step 5:

[0830] The server determines priority and urgency based on the analyzed data. The input is sentiment analysis results, which are calculated using a rule-based algorithm. The output is the message priority rank and urgency score. This allows for an assessment of which messages require immediate attention.

[0831] Step 6:

[0832] The server classifies and organizes messages based on priority and urgency. Inputs are priority rank and urgency score, which are stored in a data structure using a categorization algorithm, generating an organized message list as output. This ensures messages are sorted in a way that prioritizes response efficiency.

[0833] Step 7:

[0834] The server sends organized messages to the terminal for display via a notification system. The input is an organized list of messages, and the terminal's API is used to generate notifications, which are then displayed on the user's terminal as output. This allows the user to visually identify messages that require priority attention.

[0835] Step 8:

[0836] The underlying system collects user feedback and uses machine learning algorithms to further improve the accuracy of analysis and organization. The input is user feedback data, which is trained using TensorFlow or Scikit-learn, resulting in an improved model as output. As a result, the system evolves over time, managing messages with greater accuracy.

[0837] 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.

[0838] 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.

[0839] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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."

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0858] The following is further disclosed regarding the embodiments described above.

[0859] (Claim 1)

[0860] A means of obtaining messages from multiple communication media,

[0861] A means for analyzing the aforementioned message using speech recognition, image-to-text recognition, and natural language processing,

[0862] A means for determining the importance and urgency of the message based on the analysis results,

[0863] Means for organizing and classifying the messages based on their importance and urgency,

[0864] Means for notifying a display device of organized and classified messages,

[0865] A system that includes this.

[0866] (Claim 2)

[0867] The system according to claim 1, further comprising means for indexing messages based on the analysis results and storing them in a database.

[0868] (Claim 3)

[0869] The system according to claim 1, which has a learning function that collects user feedback and improves the accuracy of the analysis and organization.

[0870] "Example 1"

[0871] (Claim 1)

[0872] A means of acquiring information from multiple digital communication methods,

[0873] The means for analyzing the aforementioned information using audio data conversion, image data conversion, and natural language analysis,

[0874] A means for evaluating the importance and urgency of the information based on the analysis results,

[0875] Means for organizing and classifying the information based on its importance and urgency,

[0876] A means for displaying organized and classified information on a display device,

[0877] An information processing system that includes this.

[0878] (Claim 2)

[0879] The information processing system according to claim 1, further comprising means for indexing the analyzed information and recording it in a data storage device.

[0880] (Claim 3)

[0881] The information processing system according to claim 1, which has a learning algorithm that collects opinions from users and improves the accuracy of the analysis and organization.

[0882] "Application Example 1"

[0883] (Claim 1)

[0884] A means of obtaining messages from multiple communication media,

[0885] A means for analyzing the aforementioned message using speech recognition, image-to-text recognition, and natural language processing,

[0886] A means for determining the importance and urgency of the message based on the analysis results,

[0887] Means for organizing and classifying the messages based on their importance and urgency,

[0888] Means for notifying a display device of organized and classified messages,

[0889] With the aim of improving the efficiency of worker support within commercial facilities, a means of prioritizing customer service is provided,

[0890] A system that includes this.

[0891] (Claim 2)

[0892] The system according to claim 1, further comprising means for indexing messages based on the analysis results and storing them in a database.

[0893] (Claim 3)

[0894] The system according to claim 1, which has a learning function that collects user feedback and improves the accuracy of the analysis and organization.

[0895] "Example 2 of combining an emotion engine"

[0896] (Claim 1)

[0897] A means of acquiring information from multiple means of information transmission,

[0898] Means for analyzing the aforementioned information using speech recognition technology, character recognition technology, and information analysis technology,

[0899] A means for determining the priority and speed of the information based on the analysis results,

[0900] Means for organizing and classifying the information based on the aforementioned priority and speed,

[0901] Means for notifying a display device of organized and classified information,

[0902] A means for detecting emotions considering the context of information using an emotion analysis function, and adjusting the priority and speed based on that,

[0903] A system that includes this.

[0904] (Claim 2)

[0905] The system according to claim 1, further comprising means for indexing information based on the analysis results and storing it in a storage device.

[0906] (Claim 3)

[0907] The system according to claim 1, which has a learning function for collecting user feedback and improving the accuracy of the analysis and organization.

[0908] "Application example 2 when combining with an emotional engine"

[0909] (Claim 1)

[0910] A means of obtaining messages from multiple information transmission devices,

[0911] A means for analyzing the aforementioned message using speech analysis, image-to-text extraction, and natural language processing,

[0912] A means for determining the priority and urgency of the message based on the analysis results,

[0913] Means for organizing and classifying the messages based on the aforementioned priority and urgency,

[0914] A means of collecting customer inquiries and opinions and determining response priorities through sentiment analysis,

[0915] A means for notifying a display means of organized and classified messages,

[0916] A system that includes this.

[0917] (Claim 2)

[0918] The system according to claim 1, further comprising means for indexing messages based on the analysis results and storing them in a storage device.

[0919] (Claim 3)

[0920] The system according to claim 1, which has a learning function to collect opinions from users and improve the accuracy of the analysis and organization described above. [Explanation of Symbols]

[0921] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of obtaining messages from multiple communication media, A means for analyzing the aforementioned message using speech recognition, image-to-text recognition, and natural language processing, A means for determining the importance and urgency of the message based on the analysis results, Means for organizing and classifying the messages based on their importance and urgency, Means for notifying a display device of organized and classified messages, A system that includes this.

2. The system according to claim 1, further comprising means for indexing messages based on the analysis results and storing them in a database.

3. The system according to claim 1, which has a learning function that collects user feedback and improves the accuracy of the analysis and organization.

Images