system

Abstract

We provide the system. [Solution] A means for acquiring audio data and converting said audio data into text data using speech recognition technology, A means for extracting important information from text data using natural language processing technology and automatically generating meeting minutes, A means for generating follow-up tasks based on the generated meeting minutes and assigning those tasks to personnel based on pre-defined rules, A means of monitoring task progress in conjunction with an external task management system, 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, the method 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 a business environment, as the frequency of meetings increases, manual creation of meeting minutes and management of follow-up tasks become burdens, leading to problems such as delays in decision-making and stagnation of business progress. In such an environment, in order to improve the efficiency of meetings and the accuracy of follow-up, means for automating these business processes and reducing the burden are necessary.

Means for Solving the Problems

[0005] This invention provides a means for acquiring audio data and converting it into text data in real time using external speech recognition technology. It also provides a means for extracting important information from the text data using natural language processing technology and automatically generating meeting minutes, thereby reducing the burden of creating meeting minutes. Furthermore, it provides a means for automatically generating follow-up tasks based on the generated meeting minutes and automatically assigning them to appropriate personnel based on pre-set rules. The aim is to improve the accuracy of follow-up and increase work productivity. The invention also includes a means for monitoring task progress in conjunction with an external task management system, thereby improving the efficiency of task management.

[0006] "Audio data" refers to information recorded in digital format from audio sources such as meetings and conversations.

[0007] "Speech recognition technology" is a technology that converts the natural language spoken by humans into text that can be understood by computers.

[0008] "Text data" refers to digital data expressed as character information, stored in a format that can be processed by a computer.

[0009] "Natural language processing technology" is a technology that allows computers to analyze and understand human language, with the aim of grasping the meaning and structure of text data.

[0010] Meeting minutes are documents that record the content of a meeting and summarize important topics, decisions, and statements made.

[0011] "Follow-up tasks" are specific actions or tasks that arise as a result of a meeting or project, and should be carried out by the person in charge.

[0012] A "person in charge" is an individual or group responsible for a specific task or project and tasked with carrying it out.

[0013] A "task management system" is a digital platform or tool that helps plan, execute, track, and complete tasks in a project or business.

[0014] "Progress status" refers to information that indicates the current state or progress of a task or project, specifically how much of it has been completed.

[0015] "Rules" are a set of rules and guidelines for managing tasks and processes, and serve as standards for efficiently carrying out work. [Brief explanation of the drawing]

[0016] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11]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 the 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 the emotion engine is combined.

Mode for Carrying Out the Invention

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc.

[0020] 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.

[0021] 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.

[0022] 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).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] The system of this invention aims to improve the efficiency of meetings by utilizing speech recognition technology and natural language processing technology, and is implemented as follows.

[0038] When the meeting begins, (the user) captures audio using an audio input device installed in the meeting room. This audio data is connected to (the terminal) in real time and sent to (the server) in streaming format. (The server) sends the received audio data to an external speech recognition service, which converts the audio into text data.

[0039] Next, the server analyzes the text data using natural language processing technology to extract important topics and decisions. Based on this information, the server automatically generates meeting minutes, which are then provided to the user after the meeting. This process ensures that what was said during the meeting is accurately recorded and can be used as a document for later reference.

[0040] Furthermore, the server analyzes the generated meeting minutes and extracts necessary follow-up tasks. These tasks are automatically assigned to the appropriate personnel based on pre-configured rules, eliminating the need for users to manually assign tasks and improving work efficiency. The terminal integrates with the task management system to monitor the progress of each task. This allows for real-time monitoring of project and operational progress, enabling immediate detection of delays and problems.

[0041] As a concrete example, suppose a meeting discusses the launch plan for the next product. The (server) transcribes the meeting audio into text, recording important points regarding the product launch as meeting minutes. Subsequently, necessary follow-up tasks, such as preparing marketing activities and conducting internal training on the new product, are automatically generated and assigned to the responsible parties. The (user) can check these tasks and track their progress through a dedicated (terminal) or device. In this way, work proceeds smoothly and productivity is improved.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The user starts a meeting and captures the meeting audio through an audio input device. The audio data is transmitted to the terminal in real time.

[0045] Step 2:

[0046] The (terminal) transfers the received audio data to the (server) in streaming format. The (server) sends this audio data to an external speech recognition service and begins the process of converting it into text data.

[0047] Step 3:

[0048] The server inputs the converted text data into a natural language processing (NLP) engine, which analyzes the content of the statements within the text data. This extracts important topics, decisions, action items, etc.

[0049] Step 4:

[0050] The server automatically generates meeting minutes using the extracted information. The minutes are summarized and compiled into a document containing the key points.

[0051] Step 5:

[0052] After the meeting ends, the server extracts follow-up tasks from the generated meeting minutes and automatically creates a task list. This list includes specific action items required by the assigned person.

[0053] Step 6:

[0054] The server refers to pre-configured rules and assigns each task to the appropriate person. This assignment information is reflected in the project management system in real time.

[0055] Step 7:

[0056] The terminal seamlessly integrates with external task management systems to monitor the progress of each person in charge. This allows for real-time checking of task completion status and incomplete tasks.

[0057] Step 8:

[0058] The user uses their device to review the generated meeting minutes and follow up on the progress of their assigned tasks. This information is used to improve work efficiency and inform future decision-making processes.

[0059] (Example 1)

[0060] 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."

[0061] In business and project meetings, accurately and efficiently recording discussions, effectively extracting key points, and smoothly managing follow-up tasks are major challenges in improving operational efficiency and productivity. Traditional methods primarily involved manual recording and task allocation, which were time-consuming, labor-intensive, and prone to human error. Furthermore, real-time monitoring of progress was difficult, leading to problems such as project delays and the inability to detect problems early.

[0062] 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.

[0063] In this invention, the server includes means for acquiring audio information and converting the audio information into text information using speech recognition technology; means for extracting important information from the text information using natural language processing technology and automatically generating a record document; and means for generating tracking tasks based on the generated record document and assigning the tasks to personnel based on pre-set rules. As a result, the content of each meeting is accurately recorded in real time, important agenda items and decisions are automatically extracted, and follow-up tasks based on them are quickly assigned to personnel, significantly improving work efficiency.

[0064] "Voice information" refers to digital data related to human voices acquired through voice input devices.

[0065] "Speech recognition technology" is a technical means for converting acquired speech information into linguistic information.

[0066] "Textual information" refers to digital data in text format that is obtained by converting audio information using speech recognition technology.

[0067] "Natural language processing technology" refers to the technical means by which computers understand, analyze, and process the meaning of human natural language.

[0068] "Important information" refers to information that should be given particular importance in a meeting, such as agenda items and decisions, which is extracted using natural language processing technology.

[0069] A "record document" is a text document that is automatically generated based on important information.

[0070] "Follow-up tasks" are tasks and action items that need to be done after a meeting, generated from the recorded documents.

[0071] "Pre-established rules" are predetermined standards or rules used for assigning and managing tracking tasks.

[0072] An "external work management system" is a computer system or software used to manage tracking tasks and monitoring their progress.

[0073] A "network" is a communication system used to transmit information.

[0074] "Access" refers to the act of referencing or manipulating record documents or tracking operations.

[0075] This invention is essentially a system that acquires speech as digital data and analyzes it using natural language processing technology. A specific embodiment of this system is shown below.

[0076] Capture and transmission of audio data

[0077] Users capture speech in real time during meetings using an audio input device installed in the conference room. The audio input device includes a microphone and an audio signal processor. This device also has the function of converting the received audio signals into digital audio information.

[0078] Speech-to-text conversion

[0079] The terminal transmits the acquired audio information to the server in streaming format. The server uses external speech recognition technology to convert the audio information into text. This process often utilizes commercially available speech recognition services.

[0080] Extraction of important information and generation of meeting minutes

[0081] The server analyzes textual information using natural language processing software and extracts important information. Based on the extracted information, it automatically generates a record document. The generated record document is stored via cloud storage and can be accessed by users over the network.

[0082] Generation and management of follow-up tasks

[0083] The server generates tracking tasks from the generated record documents, which are then integrated with external work management software and assigned to the responsible personnel. The terminals function to allow users to monitor these tracking tasks in real time.

[0084] For example, in a meeting about a new product launch, the server transcribes the audio into text and generates a document containing important information such as product specifications and launch plans. Subsequently, follow-up tasks such as creating a marketing plan are automatically generated and assigned to the appropriate person.

[0085] An example of a prompt message might be: "Transcribe the audio of the next meeting in real time, extract the important points, and create meeting minutes. Also, generate necessary follow-up tasks, automatically assign them to the respective personnel, and monitor their progress." In this way, the present invention aims to improve business efficiency by automating the entire process from acquiring audio information to transcribing it into text, extracting information, and managing the work.

[0086] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0087] Step 1:

[0088] The user captures the audio during the meeting in real time using an audio input device installed in the meeting room. The input is an analog audio signal, which is captured by a microphone. This device outputs the audio signal as digital audio information and improves its quality through a noise reduction filter. The digital audio data is then transmitted to the terminal.

[0089] Step 2:

[0090] The terminal receives digital audio data from the user and sends it to the server in streaming format. The input is digital audio data, and the output is data packets to be sent to the server. It utilizes a data transfer protocol and is optimized to maintain low latency during transmission.

[0091] Step 3:

[0092] The server converts received audio data into text information using speech recognition technology. The input is streamed digital audio data, and the output is text data. The server calls a commercially available speech recognition service and uses a language model to convert the audio to text. This process performs highly accurate speech identification and speaker tagging.

[0093] Step 4:

[0094] The server analyzes the converted text information using natural language processing techniques and extracts important information. The input is text data, and the output is a list of important information. The natural language processing engine identifies specific terms and phrases and automatically prioritizes agenda items and decisions for meetings.

[0095] Step 5:

[0096] The server automatically generates record documents based on the extracted key information. The input is a list of key information, and the output is a record document. The record document is generated using a standardized template and stored in the cloud for later access by the user.

[0097] Step 6:

[0098] The server analyzes the recorded documents and generates tracking tasks. The input is the recorded documents, and the output is a list of tracking tasks. The server uses pre-configured rules to assign the work tasks to the appropriate personnel.

[0099] Step 7:

[0100] The terminal integrates with an external work management system to manage tracking tasks, allowing users to monitor work progress. Inputs are the tracking tasks and their progress, and output is a progress dashboard that users can view. Real-time updates enable quick detection of work delays and problems.

[0101] (Application Example 1)

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

[0103] In family communication, the inefficiency of managing family schedules and dividing tasks is a challenge, leading to confusion and forgetfulness. Furthermore, there is a lack of tools to automatically extract necessary information from everyday conversations and organize and manage it as schedules and tasks.

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

[0105] In this invention, the server includes means for acquiring voice information and converting said voice information into text information using voice recognition technology, means for extracting important information from said text information using natural language processing technology and automatically generating a recorded document, and means for acquiring voice conversations within the home and organizing and managing personal schedules and tasks. This makes it possible to efficiently organize necessary information from communication within the home and automate schedule management and task allocation.

[0106] "Auditory information" refers to acoustic signals that are recorded or transmitted by physical or electrical means from human speech.

[0107] "Speech recognition technology" is a technology that analyzes acquired speech information and formally converts its content into text information.

[0108] "Textual information" refers to the string of characters that constitutes information converted by speech recognition technology, and is information expressed as natural language.

[0109] "Natural language processing technology" is a technology that understands human language and extracts important information by performing syntactic and semantic analysis.

[0110] A "record document" is a document automatically generated based on extracted important information, and it organizes and records the content of the conversation.

[0111] A "tracking task" is an item that indicates subsequent activities generated from the record document, and is assigned to the person in charge according to pre-established rules.

[0112] A "progress management system" is a system for monitoring the progress of assigned tasks and updating information in a timely manner.

[0113] "Voice conversations within the home" refers to conversations that take place between family members at home, and the content of these conversations is related to schedule management and task sharing.

[0114] "Schedule management" is the act of organizing and recording the future activities and events of each individual member.

[0115] "Task sharing" refers to the act of appropriately assigning various household activities to individual members and managing them to ensure they are carried out efficiently.

[0116] The system for implementing this invention acquires voice information and supports family communication by utilizing voice recognition technology and natural language processing technology. Its specific form is described below.

[0117] First, hardware equipped with a microphone installed in the home collects voice information. This hardware can, for example, be a microphone built into a mobile device or home appliance. The collected voice information is transmitted to a server in real time.

[0118] The server uses the "Google® Speech Recognition API" as its speech recognition library to convert speech information into text. The converted text is then analyzed by the natural language processing engine "spaCy" and extracted as important information and tracking tasks. This organizes the content of the conversation into a recorded document.

[0119] The extracted tracking tasks are integrated with a progress management system to automate scheduling and task allocation for each family member. Assignments are made to assigned personnel based on pre-defined family rules, and the server monitors task progress in conjunction with the progress management system (e.g., Google Calendar or Todoist) and updates information in a timely manner.

[0120] For example, if someone says in a morning conversation, "Let's weed the garden this weekend," the server analyzes this, adds the plan to the family's shared calendar, and sets a reminder the day before, such as "Prepare the necessary tools."

[0121] It is possible to utilize generative AI models and prompt statements; for example, using prompt statements such as "Generate text to extract tasks from family communications" can make system automation more efficient.

[0122] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0123] Step 1:

[0124] The user engages in voice conversations within their home, and this voice information is captured through a microphone. The input is the user's voice, and the output is an analog voice signal collected by the microphone. The microphone converts this analog signal into digital audio data.

[0125] Step 2:

[0126] The converted digital audio data is transmitted to the server in real time. The server receives this digital audio data as input and generates data packets as output, sending them to the next processing step. Digital data streaming takes place.

[0127] Step 3:

[0128] The server uses the Google Speech Recognition API to convert digital audio data into text. The input is streamed audio data, and the output is text-formatted character information. This step involves analysis using speech recognition technology.

[0129] Step 4:

[0130] The server uses spaCy to perform natural language processing on the converted text information and extract important points and tasks. It receives text information as input and generates an output of extracted important points and a list of scheduled tasks. Contextual analysis and keyword extraction are performed in this step.

[0131] Step 5:

[0132] The server automatically assigns schedule management and task sharing to family members based on the extracted tracking tasks. It receives a task list and established family rules as input and generates a task list assigned to the appropriate member as output. This step involves rule-based task assignment.

[0133] Step 6:

[0134] The server works in conjunction with the progress management system to monitor task progress and update information. Inputs are tasks assigned to members and their progress, while output is an updated progress report. This step involves status checks and database updates.

[0135] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0136] The system of the present invention combines standard meeting management functions with an emotion engine that recognizes user emotions, thereby enabling more detailed understanding and follow-up of meetings.

[0137] When the meeting begins, the user captures the meeting audio through a voice input device. This audio data is transmitted in real time to the server by the terminal. The server uses speech recognition technology to convert the audio data into text data, and then uses natural language processing technology to extract important information from the text data and automatically generate meeting minutes.

[0138] Furthermore, in this invention, an emotion engine installed in the server analyzes the voice data and identifies the user's emotional state. This allows for an understanding of the tone and emotions of speakers during a meeting, and by recording this information in the meeting minutes, it improves the understanding of the meeting's context.

[0139] The emotional information obtained by the emotion engine is also reflected in the generation of follow-up tasks. The server automatically adjusts task priorities according to the emotional state. For example, when a high-priority issue is discussed, it is assigned to the person in charge as a high-urgency task. This approach allows for improved work efficiency and accurate task management by utilizing emotional information.

[0140] For example, if a marketing strategy is discussed during a meeting and some speakers express feelings of caution or concern, that sentiment data is reflected in the meeting minutes. The server can then use the sentiment engine's results to generate a follow-up task to schedule an urgent meeting and assign it preferentially to the marketing team. This allows important emotional nuances from meetings to be utilized in work and enables a swift response.

[0141] The following describes the processing flow.

[0142] Step 1:

[0143] When the user starts a meeting, the audio of the meeting is captured using the voice input device. The audio data is captured on the device in real time.

[0144] Step 2:

[0145] The (terminal) sends the acquired audio data to the (server) in streaming format. The (server) uses speech recognition technology to convert the audio data into text data.

[0146] Step 3:

[0147] The server feeds the converted text data into a natural language processing engine to extract important topics and decisions. This analysis then generates a meeting summary.

[0148] Step 4:

[0149] The server, using its built-in emotion engine, analyzes the user's emotional state from the audio data and identifies the speaker's tone and emotions.

[0150] Step 5:

[0151] The server automatically generates meeting minutes based on the extracted information, taking into account the sentiment data identified by the sentiment engine. The sentiment information is recorded as part of the meeting minutes.

[0152] Step 6:

[0153] Based on meeting minutes, the server generates follow-up tasks. By using sentiment information to automatically adjust the urgency and priority of tasks, important tasks are quickly assigned to the appropriate personnel.

[0154] Step 7:

[0155] The terminal works in conjunction with a task management system to assign generated tasks in real time and monitor the progress of each task.

[0156] Step 8:

[0157] The user reviews meeting minutes and sentiment information from their device and follows up on the progress of assigned tasks. They take prompt action and provide additional communication as needed.

[0158] (Example 2)

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

[0160] Even with automated conversion of audio data from meetings to text data, traditional systems process information without considering participants' emotions or tone of voice. This makes it difficult to prioritize follow-up tasks that reflect these nuances, resulting in challenges to operational efficiency and response speed.

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

[0162] In this invention, the server includes a speech recognition means for acquiring audio data and converting it into text data, a means for extracting important information from the text data using natural language processing technology and automatically generating meeting minutes, and a means for identifying emotional states using sentiment analysis technology and reflecting them in the meeting minutes. This makes it possible to prioritize follow-up tasks that incorporate the emotional nuances of meetings, enabling more efficient work and faster responses.

[0163] "Speech recognition technology" is a technology that analyzes audio data and converts it into text data, and is a means of understanding human spoken language in a digital format.

[0164] "Natural language processing technology" is a technology that allows computers to understand and analyze human language, and is a technology for extracting meaning from text data.

[0165] "Sentiment analysis technology" is a technique that identifies the emotional state and tone of a statement based on text or audio data, and is a means of classifying emotional nuances as numerical values ​​or categories.

[0166] Meeting minutes are documents that summarize the content of statements and discussions during a meeting and are used for later reference and record-keeping.

[0167] A "follow-up task" is an action item generated to support work processes, based on the meeting results and minutes, outlining the next steps to take and necessary procedures.

[0168] "Priority adjustment" is the process of determining the order in which follow-up tasks are performed based on specific criteria (e.g., importance, urgency).

[0169] The system of the present invention aims to improve voice input processing in meeting management by integrating speech recognition and natural language processing technologies to efficiently generate meeting minutes and further improve follow-up tasks through sentiment analysis.

[0170] First, the user acquires the meeting audio using a voice input device (e.g., a smartphone or a dedicated voice capture device). This device captures the meeting speeches in real time and converts them into a digital format.

[0171] Next, the device sends this audio data to a server via the internet. The server implements an external speech recognition service (e.g., a cloud-based speech recognition API) as speech recognition technology, and the audio data is converted into text data here. The speech service uses different speech models to identify the speaker and efficiently converts it into text.

[0172] The server then processes the text data, uses natural language processing technology (e.g., natural language understanding APIs) to extract key points from the meeting, and automatically generates meeting minutes. This documents a summary of the meeting, making it easy to refer to later.

[0173] Furthermore, the server's sentiment analysis engine analyzes text and audio data to identify the emotional state of participants. This sentiment information is not only reflected in the meeting minutes but is also used as a crucial factor in determining the priority of follow-up tasks. Based on this information, the server works in conjunction with the task management system to assign tasks to the appropriate personnel, thereby streamlining operations.

[0174] For example, if emotional discussions about a new strategy arise during a marketing meeting, the emotions identified through sentiment analysis will be prioritized by the server for subsequent follow-up meetings. This ensures that important nuances from the meeting are efficiently utilized.

[0175] An example of a prompt using a generative AI model is: "We have audio data of a new product announcement from a meeting. Based on this data, extract the emotions, summarize the key points as meeting minutes, and generate follow-up tasks based on that information."

[0176] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0177] Step 1:

[0178] The user captures audio using an audio input device at the start of the meeting. The input at this stage is the raw audio signal acquired through the meeting's microphone. This audio signal is transmitted to the terminal as digital audio data. The terminal performs noise reduction processing to improve the quality of the audio data.

[0179] Step 2:

[0180] The terminal sends noise-reduced audio data to the server. The input is audio data processed in digital format. The server passes this audio data to an external speech recognition service to convert it into text data. The output is the converted string data. This conversion uses acoustic and language models to enable highly accurate text conversion.

[0181] Step 3:

[0182] The server processes the received text data through a natural language processing engine. The input is a draft of meeting minutes in text format. The natural language processing engine extracts important keywords and topics from this data and generates a summary. The output is an automatically generated meeting minute containing essential information. During this process, the importance and frequency of keywords are analyzed, and the information is organized.

[0183] Step 4:

[0184] The server then sends text data to the sentiment analysis engine. The input is meeting minutes with key points organized. The sentiment analysis engine identifies the emotional tone of each statement from these minutes. The output is meeting minutes data with emotional states assigned to it. Here, sentiment scoring of statements is performed using dictionary-based or machine learning models.

[0185] Step 5:

[0186] The server generates follow-up tasks based on sentiment-analyzed meeting minutes. The input for this process is meeting minutes with sentiment fields added. The server sets the urgency and priority of tasks according to the sentiment state and assigns them to the most suitable person. The output is the assigned follow-up task, which is then integrated with the business management system. This operation involves task re-evaluation and system integration based on sentiment scores.

[0187] (Application Example 2)

[0188] 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."

[0189] In modern family communication, effectively understanding family conversations and providing appropriate advice that takes emotions into account is a challenging task. Conventional conversation support technologies often fail to adequately capture emotional nuances, resulting in insufficient support. To address these challenges, there is a need for a system that can effectively support decision-making and problem-solving within families.

[0190] 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.

[0191] In this invention, the server includes means for inputting acoustic data and converting said acoustic data into text data using acoustic recognition technology, means for extracting important information from the text data and automatically generating a record using text processing technology, and means for identifying the speaker's emotional state using emotion analysis technology and recording the result in the record. This enables real-time understanding of conversations within the home and provides effective communication support through helpful advice and task management that takes emotions into account.

[0192] "Audio data" refers to data that represents sound in digital format and is the subject of conversion into text data using speech recognition technology.

[0193] "Acoustic recognition technology" is a technology that analyzes input acoustic data and converts it into linguistic data.

[0194] "Text data" refers to text-based data generated using acoustic recognition technology, which is used for further analysis and processing.

[0195] "Text processing technology" refers to techniques for extracting semantic information from text data and identifying important points.

[0196] A "record" is a document that includes text data and emotional information generated from audio data, and accurately represents the content of a conversation.

[0197] "Emotion analysis technology" is a technology that determines the emotional state of a speaker based on acoustic data and text data.

[0198] The "speaker" is the entity that produced the sound that forms the basis of the audio data.

[0199] A "task management platform" is an external system used to manage and monitor the progress and completion status of generated tasks.

[0200] "Priority" is an indicator used to set an order for multiple tasks or items based on their importance and urgency.

[0201] Embodiments of this invention include a system comprising a communication support robot placed in the home. The user captures the audio of a conversation through an acoustic input device, and this acoustic data is transmitted in real time to a server by the terminal. The server converts the acoustic data into text data using acoustic recognition technology, and further extracts important information from the text data using text processing technology, automatically generating it as a record.

[0202] Furthermore, emotion analysis technology installed on the server analyzes the acoustic data to identify the speaker's emotional state. The obtained emotional information is incorporated into the record, and the priority of follow-up tasks is adjusted based on this. The generated tasks are sent to an external task management platform, where their progress is monitored.

[0203] As a concrete example, when a family is discussing holiday plans, a robot can analyze the speakers' excitement and anticipation and create a record summarizing the plans. As a result, the server can provide helpful advice to the user and set up follow-up tasks as needed. In this case, an example of a prompt to the generating AI model would be, "Detect emotional arousal from this conversation and generate tasks that require suggestions."

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

[0205] Step 1:

[0206] The user captures the audio of the conversation through an acoustic input device. This acoustic data is collected by the terminal and sent to a server. The input is real-time acoustic data, and the output is the transmission of acoustic data to the server. Specifically, a microphone is used to record the audio of the conversation as digital data.

[0207] Step 2:

[0208] The server uses acoustic recognition technology to convert the received acoustic data into text data. This process employs an acoustic recognition algorithm. The input is acoustic data, and the output is the converted text data. Specifically, the process involves converting speech to text using a speech recognition API.

[0209] Step 3:

[0210] The server analyzes the converted text data using text processing techniques and extracts important information. The input is the previously obtained text data, and the output is a record summarizing the important information. Specifically, this involves extracting important keywords and phrases using a natural language processing library.

[0211] Step 4:

[0212] The server uses emotion analysis technology to analyze the speaker's emotional state from acoustic data. The input is acoustic data, and the output is identified emotion information. In this process, the emotion analysis engine determines the emotion based on the tone and content of the speech.

[0213] Step 5:

[0214] The server integrates the collected emotional information and important points, incorporates them into the record, and adjusts the priority of follow-up tasks. The input is emotional information and important points, and the output is prioritized tasks. Specifically, task management is performed based on an algorithm set according to the urgency of the tasks.

[0215] Step 6:

[0216] Finally, the generated tasks are sent to an external task management platform for progress monitoring. The input is prioritized task information, and the output is the task monitoring status. Specifically, progress is tracked via a task management API.

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

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

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

[0220] [Second Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0233] The system of this invention aims to improve the efficiency of meetings by utilizing speech recognition technology and natural language processing technology, and is implemented as follows.

[0234] When the meeting begins, (the user) captures audio using an audio input device installed in the meeting room. This audio data is connected to (the terminal) in real time and sent to (the server) in streaming format. (The server) sends the received audio data to an external speech recognition service, which converts the audio into text data.

[0235] Next, the server analyzes the text data using natural language processing technology to extract important topics and decisions. Based on this information, the server automatically generates meeting minutes, which are then provided to the user after the meeting. This process ensures that what was said during the meeting is accurately recorded and can be used as a document for later reference.

[0236] Furthermore, the server analyzes the generated meeting minutes and extracts necessary follow-up tasks. These tasks are automatically assigned to the appropriate personnel based on pre-configured rules, eliminating the need for users to manually assign tasks and improving work efficiency. The terminal integrates with the task management system to monitor the progress of each task. This allows for real-time monitoring of project and operational progress, enabling immediate detection of delays and problems.

[0237] As a concrete example, suppose a meeting discusses the launch plan for the next product. The (server) transcribes the meeting audio into text, recording important points regarding the product launch as meeting minutes. Subsequently, necessary follow-up tasks, such as preparing marketing activities and conducting internal training on the new product, are automatically generated and assigned to the responsible parties. The (user) can check these tasks and track their progress through a dedicated (terminal) or device. In this way, work proceeds smoothly and productivity is improved.

[0238] The following describes the processing flow.

[0239] Step 1:

[0240] The user starts a meeting and captures the meeting audio through an audio input device. The audio data is transmitted to the terminal in real time.

[0241] Step 2:

[0242] The (terminal) transfers the received audio data to the (server) in streaming format. The (server) sends this audio data to an external speech recognition service and begins the process of converting it into text data.

[0243] Step 3:

[0244] The server inputs the converted text data into a natural language processing (NLP) engine, which analyzes the content of the statements within the text data. This extracts important topics, decisions, action items, etc.

[0245] Step 4:

[0246] The server automatically generates meeting minutes using the extracted information. The minutes are summarized and compiled into a document containing the key points.

[0247] Step 5:

[0248] After the meeting ends, the server extracts follow-up tasks from the generated meeting minutes and automatically creates a task list. This list includes specific action items required by the assigned person.

[0249] Step 6:

[0250] The server refers to pre-configured rules and assigns each task to the appropriate person. This assignment information is reflected in the project management system in real time.

[0251] Step 7:

[0252] The terminal seamlessly integrates with external task management systems to monitor the progress of each person in charge. This allows for real-time checking of task completion status and incomplete tasks.

[0253] Step 8:

[0254] The user uses their device to review the generated meeting minutes and follow up on the progress of their assigned tasks. This information is used to improve work efficiency and inform future decision-making processes.

[0255] (Example 1)

[0256] 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."

[0257] In business and project meetings, accurately and efficiently recording discussions, effectively extracting key points, and smoothly managing follow-up tasks are major challenges in improving operational efficiency and productivity. Traditional methods primarily involved manual recording and task allocation, which were time-consuming, labor-intensive, and prone to human error. Furthermore, real-time monitoring of progress was difficult, leading to problems such as project delays and the inability to detect problems early.

[0258] 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.

[0259] In this invention, the server includes means for acquiring audio information and converting the audio information into text information using speech recognition technology; means for extracting important information from the text information using natural language processing technology and automatically generating a record document; and means for generating tracking tasks based on the generated record document and assigning the tasks to personnel based on pre-set rules. As a result, the content of each meeting is accurately recorded in real time, important agenda items and decisions are automatically extracted, and follow-up tasks based on them are quickly assigned to personnel, significantly improving work efficiency.

[0260] "Voice information" refers to digital data related to human voices acquired through voice input devices.

[0261] "Speech recognition technology" is a technical means for converting acquired speech information into linguistic information.

[0262] "Textual information" refers to digital data in text format that is obtained by converting audio information using speech recognition technology.

[0263] "Natural language processing technology" refers to the technical means by which computers understand, analyze, and process the meaning of human natural language.

[0264] "Important information" refers to information that should be given particular importance in a meeting, such as agenda items and decisions, which is extracted using natural language processing technology.

[0265] A "record document" is a text document that is automatically generated based on important information.

[0266] "Follow-up tasks" are tasks and action items that need to be done after a meeting, generated from the recorded documents.

[0267] "Pre-established rules" are predetermined standards or rules used for assigning and managing tracking tasks.

[0268] An "external work management system" is a computer system or software used to manage tracking tasks and monitoring their progress.

[0269] A "network" is a communication system used to transmit information.

[0270] "Access" refers to the act of referencing or manipulating record documents or tracking operations.

[0271] This invention is essentially a system that acquires speech as digital data and analyzes it using natural language processing technology. A specific embodiment of this system is shown below.

[0272] Capture and transmission of audio data

[0273] Users capture speech in real time during meetings using an audio input device installed in the conference room. The audio input device includes a microphone and an audio signal processor. This device also has the function of converting the received audio signals into digital audio information.

[0274] Speech-to-text conversion

[0275] The terminal transmits the acquired audio information to the server in streaming format. The server uses external speech recognition technology to convert the audio information into text. This process often utilizes commercially available speech recognition services.

[0276] Extraction of important information and generation of meeting minutes

[0277] The server analyzes textual information using natural language processing software and extracts important information. Based on the extracted information, it automatically generates a record document. The generated record document is stored via cloud storage and can be accessed by users over the network.

[0278] Generation and management of follow-up tasks

[0279] The server generates tracking tasks from the generated record documents, which are then integrated with external work management software and assigned to the responsible personnel. The terminals function to allow users to monitor these tracking tasks in real time.

[0280] For example, in a meeting about a new product launch, the server transcribes the audio into text and generates a document containing important information such as product specifications and launch plans. Subsequently, follow-up tasks such as creating a marketing plan are automatically generated and assigned to the appropriate person.

[0281] As an example of a prompt sentence, an instruction such as "Please perform real-time transcription of the audio of the next meeting, extract important matters, and create a meeting minutes. Also, generate necessary follow-up tasks and automatically assign them to respective responsible persons and monitor the progress." can be considered. Thus, the present invention aims to improve business efficiency by automating the processes from the acquisition of audio information to text conversion, information extraction, and work management in a consistent manner.

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

[0283] Step 1:

[0284] The user uses an audio input device installed in the meeting room to capture the audio during the meeting in real time. The input is an analog audio signal, which is captured by a microphone. This device outputs the audio signal as digital audio information and improves the quality through a noise reduction filter. Then, the digital audio data is transmitted to the terminal.

[0285] Step 2:

[0286] The terminal transmits the digital audio data received from the user to the server in a streaming format. The input is digital audio data, and the output is data packets for transmission to the server. It is optimized to maintain low latency during the transmission using a data transfer protocol.

[0287] Step 3:

[0288] The server converts the received audio data into character information using speech recognition technology. The input is the streamed digital audio data, and the output is character data. The server calls a commercially available speech recognition service and uses a language model to convert the audio to text. In this process, high-precision speech recognition and speaker tagging are performed.

[0289] Step 4:

[0290] The server analyzes the converted text information using natural language processing techniques and extracts important information. The input is text data, and the output is a list of important information. The natural language processing engine identifies specific terms and phrases and automatically prioritizes agenda items and decisions for meetings.

[0291] Step 5:

[0292] The server automatically generates record documents based on the extracted key information. The input is a list of key information, and the output is a record document. The record document is generated using a standardized template and stored in the cloud for later access by the user.

[0293] Step 6:

[0294] The server analyzes the recorded documents and generates tracking tasks. The input is the recorded documents, and the output is a list of tracking tasks. The server uses pre-configured rules to assign the work tasks to the appropriate personnel.

[0295] Step 7:

[0296] The terminal integrates with an external work management system to manage tracking tasks, allowing users to monitor work progress. Inputs are the tracking tasks and their progress, and output is a progress dashboard that users can view. Real-time updates enable quick detection of work delays and problems.

[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] In family communication, the inefficiency of managing family schedules and dividing tasks is a challenge, leading to confusion and forgetfulness. Furthermore, there is a lack of tools to automatically extract necessary information from everyday conversations and organize and manage it as schedules and tasks.

[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 voice information and converting said voice information into text information using voice recognition technology, means for extracting important information from said text information using natural language processing technology and automatically generating a recorded document, and means for acquiring voice conversations within the home and organizing and managing personal schedules and tasks. This makes it possible to efficiently organize necessary information from communication within the home and automate schedule management and task allocation.

[0302] "Auditory information" refers to acoustic signals that are recorded or transmitted by physical or electrical means from human speech.

[0303] "Speech recognition technology" is a technology that analyzes acquired speech information and formally converts its content into text information.

[0304] "Textual information" refers to the string of characters that constitutes information converted by speech recognition technology, and is information expressed as natural language.

[0305] "Natural language processing technology" is a technology that understands human language and extracts important information by performing syntactic and semantic analysis.

[0306] A "record document" is a document automatically generated based on extracted important information, and it organizes and records the content of the conversation.

[0307] A "tracking task" is an item that indicates subsequent activities generated from the record document, and is assigned to the person in charge according to pre-established rules.

[0308] The "progress management system" is a system for monitoring the progress of assigned tasks and updating information in a timely manner.

[0309] The "in-home voice conversation" is a conversation conducted among family members within the home, and the content of the conversation is related to schedule management and task sharing.

[0310] "Schedule management" is the act of organizing and recording the future activities and events of individual members.

[0311] "Task sharing" is the act of appropriately assigning various activities conducted within the home to individual members and managing them to be executed efficiently.

[0312] The system for implementing this invention acquires voice information and utilizes voice recognition technology and natural language processing technology to assist in communication within the family. The specific form thereof will be described below.

[0313] First, hardware equipped with a microphone installed within the home collects voice information. This hardware can use, for example, a microphone incorporated in a mobile device or home appliance. The collected voice information is transmitted to the server in real time.

[0314] The server uses the "Google Speech Recognition API" as a voice recognition library to convert the voice information into character information. The converted character information is analyzed by the natural language processing engine "spaCy" and extracted as important matters and tracking tasks. As a result, the content of the conversation is organized as a recorded document.

[0315] The extracted tracking tasks are integrated with a progress management system to automate scheduling and task allocation for each family member. Assignments are made to assigned personnel based on pre-defined family rules, and the server monitors task progress in conjunction with the progress management system (e.g., Google Calendar or Todoist) and updates information in a timely manner.

[0316] For example, if someone says in a morning conversation, "Let's weed the garden this weekend," the server analyzes this, adds the plan to the family's shared calendar, and sets a reminder the day before, such as "Prepare the necessary tools."

[0317] It is possible to utilize generative AI models and prompt statements; for example, using prompt statements such as "Generate text to extract tasks from family communications" can make system automation more efficient.

[0318] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0319] Step 1:

[0320] The user engages in voice conversations within their home, and this voice information is captured through a microphone. The input is the user's voice, and the output is an analog voice signal collected by the microphone. The microphone converts this analog signal into digital audio data.

[0321] Step 2:

[0322] The converted digital audio data is transmitted to the server in real time. The server receives this digital audio data as input and generates data packets as output, sending them to the next processing step. Digital data streaming takes place.

[0323] Step 3:

[0324] The server uses the Google Speech Recognition API to convert digital audio data into text. The input is streamed audio data, and the output is text-formatted character information. This step involves analysis using speech recognition technology.

[0325] Step 4:

[0326] The server uses spaCy to perform natural language processing on the converted text information and extract important points and tasks. It receives text information as input and generates an output of extracted important points and a list of scheduled tasks. Contextual analysis and keyword extraction are performed in this step.

[0327] Step 5:

[0328] The server automatically assigns schedule management and task sharing to family members based on the extracted tracking tasks. It receives a task list and established family rules as input and generates a task list assigned to the appropriate member as output. This step involves rule-based task assignment.

[0329] Step 6:

[0330] The server works in conjunction with the progress management system to monitor task progress and update information. Inputs are tasks assigned to members and their progress, while output is an updated progress report. This step involves status checks and database updates.

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

[0332] The system of the present invention combines standard meeting management functions with an emotion engine that recognizes user emotions, thereby enabling more detailed understanding and follow-up of meetings.

[0333] When the meeting begins, the user captures the meeting audio through a voice input device. This audio data is transmitted in real time to the server by the terminal. The server uses speech recognition technology to convert the audio data into text data, and then uses natural language processing technology to extract important information from the text data and automatically generate meeting minutes.

[0334] Furthermore, in this invention, an emotion engine installed in the server analyzes the voice data and identifies the user's emotional state. This allows for an understanding of the tone and emotions of speakers during a meeting, and by recording this information in the meeting minutes, it improves the understanding of the meeting's context.

[0335] The emotional information obtained by the emotion engine is also reflected in the generation of follow-up tasks. The server automatically adjusts task priorities according to the emotional state. For example, when a high-priority issue is discussed, it is assigned to the person in charge as a high-urgency task. This approach allows for improved work efficiency and accurate task management by utilizing emotional information.

[0336] For example, if a marketing strategy is discussed during a meeting and some speakers express feelings of caution or concern, that sentiment data is reflected in the meeting minutes. The server can then use the sentiment engine's results to generate a follow-up task to schedule an urgent meeting and assign it preferentially to the marketing team. This allows important emotional nuances from meetings to be utilized in work and enables a swift response.

[0337] The following describes the processing flow.

[0338] Step 1:

[0339] When the user starts a meeting, the audio of the meeting is captured using the voice input device. The audio data is captured on the device in real time.

[0340] Step 2:

[0341] The (terminal) sends the acquired audio data to the (server) in streaming format. The (server) uses speech recognition technology to convert the audio data into text data.

[0342] Step 3:

[0343] The server feeds the converted text data into a natural language processing engine to extract important topics and decisions. This analysis then generates a meeting summary.

[0344] Step 4:

[0345] The server, using its built-in emotion engine, analyzes the user's emotional state from the audio data and identifies the speaker's tone and emotions.

[0346] Step 5:

[0347] The server automatically generates meeting minutes based on the extracted information, taking into account the sentiment data identified by the sentiment engine. The sentiment information is recorded as part of the meeting minutes.

[0348] Step 6:

[0349] Based on meeting minutes, the server generates follow-up tasks. By using sentiment information to automatically adjust the urgency and priority of tasks, important tasks are quickly assigned to the appropriate personnel.

[0350] Step 7:

[0351] The terminal works in conjunction with a task management system to assign generated tasks in real time and monitor the progress of each task.

[0352] Step 8:

[0353] The user reviews meeting minutes and sentiment information from their device and follows up on the progress of assigned tasks. They take prompt action and provide additional communication as needed.

[0354] (Example 2)

[0355] 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".

[0356] Even with automated conversion of audio data from meetings to text data, traditional systems process information without considering participants' emotions or tone of voice. This makes it difficult to prioritize follow-up tasks that reflect these nuances, resulting in challenges to operational efficiency and response speed.

[0357] 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.

[0358] In this invention, the server includes a speech recognition means for acquiring audio data and converting it into text data, a means for extracting important information from the text data using natural language processing technology and automatically generating meeting minutes, and a means for identifying emotional states using sentiment analysis technology and reflecting them in the meeting minutes. This makes it possible to prioritize follow-up tasks that incorporate the emotional nuances of meetings, enabling more efficient work and faster responses.

[0359] "Speech recognition technology" is a technology that analyzes audio data and converts it into text data, and is a means of understanding human spoken language in a digital format.

[0360] "Natural language processing technology" is a technology that allows computers to understand and analyze human language, and is a technology for extracting meaning from text data.

[0361] "Sentiment analysis technology" is a technique that identifies the emotional state and tone of a statement based on text or audio data, and is a means of classifying emotional nuances as numerical values ​​or categories.

[0362] Meeting minutes are documents that summarize the content of statements and discussions during a meeting and are used for later reference and record-keeping.

[0363] A "follow-up task" is an action item generated to support work processes, based on the meeting results and minutes, outlining the next steps to take and necessary procedures.

[0364] "Priority adjustment" is the process of determining the order in which follow-up tasks are performed based on specific criteria (e.g., importance, urgency).

[0365] The system of the present invention aims to improve voice input processing in meeting management by integrating speech recognition and natural language processing technologies to efficiently generate meeting minutes and further improve follow-up tasks through sentiment analysis.

[0366] First, the user acquires the meeting audio using a voice input device (e.g., a smartphone or a dedicated voice capture device). This device captures the meeting speeches in real time and converts them into a digital format.

[0367] Next, the device sends this audio data to a server via the internet. The server implements an external speech recognition service (e.g., a cloud-based speech recognition API) as speech recognition technology, and the audio data is converted into text data here. The speech service uses different speech models to identify the speaker and efficiently converts it into text.

[0368] The server then processes the text data, uses natural language processing technology (e.g., natural language understanding APIs) to extract key points from the meeting, and automatically generates meeting minutes. This documents a summary of the meeting, making it easy to refer to later.

[0369] Furthermore, the server's sentiment analysis engine analyzes text and audio data to identify the emotional state of participants. This sentiment information is not only reflected in the meeting minutes but is also used as a crucial factor in determining the priority of follow-up tasks. Based on this information, the server works in conjunction with the task management system to assign tasks to the appropriate personnel, thereby streamlining operations.

[0370] For example, if emotional discussions about a new strategy arise during a marketing meeting, the emotions identified through sentiment analysis will be prioritized by the server for subsequent follow-up meetings. This ensures that important nuances from the meeting are efficiently utilized.

[0371] An example of a prompt using a generative AI model is: "We have audio data of a new product announcement from a meeting. Based on this data, extract the emotions, summarize the key points as meeting minutes, and generate follow-up tasks based on that information."

[0372] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0373] Step 1:

[0374] The user captures audio using an audio input device at the start of the meeting. The input at this stage is the raw audio signal acquired through the meeting's microphone. This audio signal is transmitted to the terminal as digital audio data. The terminal performs noise reduction processing to improve the quality of the audio data.

[0375] Step 2:

[0376] The terminal sends noise-reduced audio data to the server. The input is audio data processed in digital format. The server passes this audio data to an external speech recognition service to convert it into text data. The output is the converted string data. This conversion uses acoustic and language models to enable highly accurate text conversion.

[0377] Step 3:

[0378] The server processes the received text data through a natural language processing engine. The input is a draft of meeting minutes in text format. The natural language processing engine extracts important keywords and topics from this data and generates a summary. The output is an automatically generated meeting minute containing essential information. During this process, the importance and frequency of keywords are analyzed, and the information is organized.

[0379] Step 4:

[0380] The server then sends text data to the sentiment analysis engine. The input is meeting minutes with key points organized. The sentiment analysis engine identifies the emotional tone of each statement from these minutes. The output is meeting minutes data with emotional states assigned to it. Here, sentiment scoring of statements is performed using dictionary-based or machine learning models.

[0381] Step 5:

[0382] The server generates follow-up tasks based on sentiment-analyzed meeting minutes. The input for this process is meeting minutes with sentiment fields added. The server sets the urgency and priority of tasks according to the sentiment state and assigns them to the most suitable person. The output is the assigned follow-up task, which is then integrated with the business management system. This operation involves task re-evaluation and system integration based on sentiment scores.

[0383] (Application Example 2)

[0384] 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."

[0385] In modern family communication, effectively understanding family conversations and providing appropriate advice that takes emotions into account is a challenging task. Conventional conversation support technologies often fail to adequately capture emotional nuances, resulting in insufficient support. To address these challenges, there is a need for a system that can effectively support decision-making and problem-solving within families.

[0386] 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.

[0387] In this invention, the server includes means for inputting acoustic data and converting said acoustic data into text data using acoustic recognition technology, means for extracting important information from the text data and automatically generating a record using text processing technology, and means for identifying the speaker's emotional state using emotion analysis technology and recording the result in the record. This enables real-time understanding of conversations within the home and provides effective communication support through helpful advice and task management that takes emotions into account.

[0388] "Audio data" refers to data that represents sound in digital format and is the subject of conversion into text data using speech recognition technology.

[0389] "Acoustic recognition technology" is a technology that analyzes input acoustic data and converts it into linguistic data.

[0390] "Text data" refers to text-based data generated using acoustic recognition technology, which is used for further analysis and processing.

[0391] "Text processing technology" refers to techniques for extracting semantic information from text data and identifying important points.

[0392] A "record" is a document that includes text data and emotional information generated from audio data, and accurately represents the content of a conversation.

[0393] "Emotion analysis technology" is a technology that determines the emotional state of a speaker based on acoustic data and text data.

[0394] The "speaker" is the entity that produced the sound that forms the basis of the audio data.

[0395] A "task management platform" is an external system used to manage and monitor the progress and completion status of generated tasks.

[0396] "Priority" is an indicator used to set an order for multiple tasks or items based on their importance and urgency.

[0397] Embodiments of this invention include a system comprising a communication support robot placed in the home. The user captures the audio of a conversation through an acoustic input device, and this acoustic data is transmitted in real time to a server by the terminal. The server converts the acoustic data into text data using acoustic recognition technology, and further extracts important information from the text data using text processing technology, automatically generating it as a record.

[0398] Furthermore, emotion analysis technology installed on the server analyzes the acoustic data to identify the speaker's emotional state. The obtained emotional information is incorporated into the record, and the priority of follow-up tasks is adjusted based on this. The generated tasks are sent to an external task management platform, where their progress is monitored.

[0399] As a concrete example, when a family is discussing holiday plans, a robot can analyze the speakers' excitement and anticipation and create a record summarizing the plans. As a result, the server can provide helpful advice to the user and set up follow-up tasks as needed. In this case, an example of a prompt to the generating AI model would be, "Detect emotional arousal from this conversation and generate tasks that require suggestions."

[0400] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0401] Step 1:

[0402] The user captures the audio of the conversation through an acoustic input device. This acoustic data is collected by the terminal and sent to a server. The input is real-time acoustic data, and the output is the transmission of acoustic data to the server. Specifically, a microphone is used to record the audio of the conversation as digital data.

[0403] Step 2:

[0404] The server uses acoustic recognition technology to convert the received acoustic data into text data. This process employs an acoustic recognition algorithm. The input is acoustic data, and the output is the converted text data. Specifically, the process involves converting speech to text using a speech recognition API.

[0405] Step 3:

[0406] The server analyzes the converted text data using text processing techniques and extracts important information. The input is the previously obtained text data, and the output is a record summarizing the important information. Specifically, this involves extracting important keywords and phrases using a natural language processing library.

[0407] Step 4:

[0408] The server uses emotion analysis technology to analyze the speaker's emotional state from acoustic data. The input is acoustic data, and the output is identified emotion information. In this process, the emotion analysis engine determines the emotion based on the tone and content of the speech.

[0409] Step 5:

[0410] The server integrates the collected emotional information and important points, incorporates them into the record, and adjusts the priority of follow-up tasks. The input is emotional information and important points, and the output is prioritized tasks. Specifically, task management is performed based on an algorithm set according to the urgency of the tasks.

[0411] Step 6:

[0412] Finally, the generated tasks are sent to an external task management platform for progress monitoring. The input is prioritized task information, and the output is the task monitoring status. Specifically, progress is tracked via a task management API.

[0413] 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.

[0414] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0415] 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.

[0416] [Third Embodiment]

[0417] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0418] 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.

[0419] 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).

[0420] 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.

[0421] 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.

[0422] 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).

[0423] 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.

[0424] 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.

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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".

[0429] The system of this invention aims to improve the efficiency of meetings by utilizing speech recognition technology and natural language processing technology, and is implemented as follows.

[0430] When the meeting begins, (the user) captures audio using an audio input device installed in the meeting room. This audio data is connected to (the terminal) in real time and sent to (the server) in streaming format. (The server) sends the received audio data to an external speech recognition service, which converts the audio into text data.

[0431] Next, the server analyzes the text data using natural language processing technology to extract important topics and decisions. Based on this information, the server automatically generates meeting minutes, which are then provided to the user after the meeting. This process ensures that what was said during the meeting is accurately recorded and can be used as a document for later reference.

[0432] Furthermore, the server analyzes the generated meeting minutes and extracts necessary follow-up tasks. These tasks are automatically assigned to the appropriate personnel based on pre-configured rules, eliminating the need for users to manually assign tasks and improving work efficiency. The terminal integrates with the task management system to monitor the progress of each task. This allows for real-time monitoring of project and operational progress, enabling immediate detection of delays and problems.

[0433] As a concrete example, suppose a meeting discusses the launch plan for the next product. The (server) transcribes the meeting audio into text, recording important points regarding the product launch as meeting minutes. Subsequently, necessary follow-up tasks, such as preparing marketing activities and conducting internal training on the new product, are automatically generated and assigned to the responsible parties. The (user) can check these tasks and track their progress through a dedicated (terminal) or device. In this way, work proceeds smoothly and productivity is improved.

[0434] The following describes the processing flow.

[0435] Step 1:

[0436] The user starts a meeting and captures the meeting audio through an audio input device. The audio data is transmitted to the terminal in real time.

[0437] Step 2:

[0438] The (terminal) transfers the received audio data to the (server) in streaming format. The (server) sends this audio data to an external speech recognition service and begins the process of converting it into text data.

[0439] Step 3:

[0440] The server inputs the converted text data into a natural language processing (NLP) engine, which analyzes the content of the statements within the text data. This extracts important topics, decisions, action items, etc.

[0441] Step 4:

[0442] The server automatically generates meeting minutes using the extracted information. The minutes are summarized and compiled into a document containing the key points.

[0443] Step 5:

[0444] After the meeting ends, the server extracts follow-up tasks from the generated meeting minutes and automatically creates a task list. This list includes specific action items required by the assigned person.

[0445] Step 6:

[0446] The server refers to pre-configured rules and assigns each task to the appropriate person. This assignment information is reflected in the project management system in real time.

[0447] Step 7:

[0448] The terminal seamlessly integrates with external task management systems to monitor the progress of each person in charge. This allows for real-time checking of task completion status and incomplete tasks.

[0449] Step 8:

[0450] The user uses their device to review the generated meeting minutes and follow up on the progress of their assigned tasks. This information is used to improve work efficiency and inform future decision-making processes.

[0451] (Example 1)

[0452] 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."

[0453] In business and project meetings, accurately and efficiently recording discussions, effectively extracting key points, and smoothly managing follow-up tasks are major challenges in improving operational efficiency and productivity. Traditional methods primarily involved manual recording and task allocation, which were time-consuming, labor-intensive, and prone to human error. Furthermore, real-time monitoring of progress was difficult, leading to problems such as project delays and the inability to detect problems early.

[0454] 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.

[0455] In this invention, the server includes means for acquiring audio information and converting the audio information into text information using speech recognition technology; means for extracting important information from the text information using natural language processing technology and automatically generating a record document; and means for generating tracking tasks based on the generated record document and assigning the tasks to personnel based on pre-set rules. As a result, the content of each meeting is accurately recorded in real time, important agenda items and decisions are automatically extracted, and follow-up tasks based on them are quickly assigned to personnel, significantly improving work efficiency.

[0456] "Voice information" refers to digital data related to human voices acquired through voice input devices.

[0457] "Speech recognition technology" is a technical means for converting acquired speech information into linguistic information.

[0458] "Textual information" refers to digital data in text format that is obtained by converting audio information using speech recognition technology.

[0459] "Natural language processing technology" refers to the technical means by which computers understand, analyze, and process the meaning of human natural language.

[0460] "Important information" refers to information that should be given particular importance in a meeting, such as agenda items and decisions, which is extracted using natural language processing technology.

[0461] A "record document" is a text document that is automatically generated based on important information.

[0462] "Follow-up tasks" are tasks and action items that need to be done after a meeting, generated from the recorded documents.

[0463] "Pre-established rules" are predetermined standards or rules used for assigning and managing tracking tasks.

[0464] An "external work management system" is a computer system or software used to manage tracking tasks and monitoring their progress.

[0465] A "network" is a communication system used to transmit information.

[0466] "Access" refers to the act of referencing or manipulating record documents or tracking operations.

[0467] This invention is essentially a system that acquires speech as digital data and analyzes it using natural language processing technology. A specific embodiment of this system is shown below.

[0468] Capture and transmission of audio data

[0469] Users capture speech in real time during meetings using an audio input device installed in the conference room. The audio input device includes a microphone and an audio signal processor. This device also has the function of converting the received audio signals into digital audio information.

[0470] Speech-to-text conversion

[0471] The terminal transmits the acquired audio information to the server in streaming format. The server uses external speech recognition technology to convert the audio information into text. This process often utilizes commercially available speech recognition services.

[0472] Extraction of important information and generation of meeting minutes

[0473] The server analyzes textual information using natural language processing software and extracts important information. Based on the extracted information, it automatically generates a record document. The generated record document is stored via cloud storage and can be accessed by users over the network.

[0474] Generation and management of follow-up tasks

[0475] The server generates tracking tasks from the generated record documents, which are then integrated with external work management software and assigned to the responsible personnel. The terminals function to allow users to monitor these tracking tasks in real time.

[0476] For example, in a meeting about a new product launch, the server transcribes the audio into text and generates a document containing important information such as product specifications and launch plans. Subsequently, follow-up tasks such as creating a marketing plan are automatically generated and assigned to the appropriate person.

[0477] An example of a prompt message might be: "Transcribe the audio of the next meeting in real time, extract the important points, and create meeting minutes. Also, generate necessary follow-up tasks, automatically assign them to the respective personnel, and monitor their progress." In this way, the present invention aims to improve business efficiency by automating the entire process from acquiring audio information to transcribing it into text, extracting information, and managing the work.

[0478] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0479] Step 1:

[0480] The user captures the audio during the meeting in real time using an audio input device installed in the meeting room. The input is an analog audio signal, which is captured by a microphone. This device outputs the audio signal as digital audio information and improves its quality through a noise reduction filter. The digital audio data is then transmitted to the terminal.

[0481] Step 2:

[0482] The terminal receives digital audio data from the user and sends it to the server in streaming format. The input is digital audio data, and the output is data packets to be sent to the server. It utilizes a data transfer protocol and is optimized to maintain low latency during transmission.

[0483] Step 3:

[0484] The server converts received audio data into text information using speech recognition technology. The input is streamed digital audio data, and the output is text data. The server calls a commercially available speech recognition service and uses a language model to convert the audio to text. This process performs highly accurate speech identification and speaker tagging.

[0485] Step 4:

[0486] The server analyzes the converted text information using natural language processing techniques and extracts important information. The input is text data, and the output is a list of important information. The natural language processing engine identifies specific terms and phrases and automatically prioritizes agenda items and decisions for meetings.

[0487] Step 5:

[0488] The server automatically generates record documents based on the extracted key information. The input is a list of key information, and the output is a record document. The record document is generated using a standardized template and stored in the cloud for later access by the user.

[0489] Step 6:

[0490] The server analyzes the recorded documents and generates tracking tasks. The input is the recorded documents, and the output is a list of tracking tasks. The server uses pre-configured rules to assign the work tasks to the appropriate personnel.

[0491] Step 7:

[0492] The terminal integrates with an external work management system to manage tracking tasks, allowing users to monitor work progress. Inputs are the tracking tasks and their progress, and output is a progress dashboard that users can view. Real-time updates enable quick detection of work delays and problems.

[0493] (Application Example 1)

[0494] 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."

[0495] In family communication, the inefficiency of managing family schedules and dividing tasks is a challenge, leading to confusion and forgetfulness. Furthermore, there is a lack of tools to automatically extract necessary information from everyday conversations and organize and manage it as schedules and tasks.

[0496] 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.

[0497] In this invention, the server includes means for acquiring voice information and converting said voice information into text information using voice recognition technology, means for extracting important information from said text information using natural language processing technology and automatically generating a recorded document, and means for acquiring voice conversations within the home and organizing and managing personal schedules and tasks. This makes it possible to efficiently organize necessary information from communication within the home and automate schedule management and task allocation.

[0498] "Auditory information" refers to acoustic signals that are recorded or transmitted by physical or electrical means from human speech.

[0499] "Speech recognition technology" is a technology that analyzes acquired speech information and formally converts its content into text information.

[0500] "Textual information" refers to the string of characters that constitutes information converted by speech recognition technology, and is information expressed as natural language.

[0501] "Natural language processing technology" is a technology that understands human language and extracts important information by performing syntactic and semantic analysis.

[0502] A "record document" is a document automatically generated based on extracted important information, and it organizes and records the content of the conversation.

[0503] A "tracking task" is an item that indicates subsequent activities generated from the record document, and is assigned to the person in charge according to pre-established rules.

[0504] A "progress management system" is a system for monitoring the progress of assigned tasks and updating information in a timely manner.

[0505] "Voice conversations within the home" refers to conversations that take place between family members at home, and the content of these conversations is related to schedule management and task sharing.

[0506] "Schedule management" is the act of organizing and recording the future activities and events of each individual member.

[0507] "Task sharing" refers to the act of appropriately assigning various household activities to individual members and managing them to ensure they are carried out efficiently.

[0508] The system for implementing this invention acquires voice information and supports family communication by utilizing voice recognition technology and natural language processing technology. Its specific form is described below.

[0509] First, hardware equipped with a microphone installed in the home collects voice information. This hardware can, for example, be a microphone built into a mobile device or home appliance. The collected voice information is transmitted to a server in real time.

[0510] The server uses the "Google Speech Recognition API" as its speech recognition library to convert speech information into text. The converted text is then analyzed by the natural language processing engine "spaCy" and extracted as important information and tracking tasks. This organizes the content of the conversation into a recorded document.

[0511] The extracted tracking tasks are integrated with a progress management system to automate scheduling and task allocation for each family member. Assignments are made to assigned personnel based on pre-defined family rules, and the server monitors task progress in conjunction with the progress management system (e.g., Google Calendar or Todoist) and updates information in a timely manner.

[0512] For example, if someone says in a morning conversation, "Let's weed the garden this weekend," the server analyzes this, adds the plan to the family's shared calendar, and sets a reminder the day before, such as "Prepare the necessary tools."

[0513] It is possible to utilize generative AI models and prompt statements; for example, using prompt statements such as "Generate text to extract tasks from family communications" can make system automation more efficient.

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

[0515] Step 1:

[0516] The user engages in voice conversations within their home, and this voice information is captured through a microphone. The input is the user's voice, and the output is an analog voice signal collected by the microphone. The microphone converts this analog signal into digital audio data.

[0517] Step 2:

[0518] The converted digital audio data is transmitted to the server in real time. The server receives this digital audio data as input and generates data packets as output, sending them to the next processing step. Digital data streaming takes place.

[0519] Step 3:

[0520] The server uses the Google Speech Recognition API to convert digital audio data into text. The input is streamed audio data, and the output is text-formatted character information. This step involves analysis using speech recognition technology.

[0521] Step 4:

[0522] The server uses spaCy to perform natural language processing on the converted text information and extract important points and tasks. It receives text information as input and generates an output of extracted important points and a list of scheduled tasks. Contextual analysis and keyword extraction are performed in this step.

[0523] Step 5:

[0524] The server automatically assigns schedule management and task sharing to family members based on the extracted tracking tasks. It receives a task list and established family rules as input and generates a task list assigned to the appropriate member as output. This step involves rule-based task assignment.

[0525] Step 6:

[0526] The server works in conjunction with the progress management system to monitor task progress and update information. Inputs are tasks assigned to members and their progress, while output is an updated progress report. This step involves status checks and database updates.

[0527] 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.

[0528] The system of the present invention combines standard meeting management functions with an emotion engine that recognizes user emotions, thereby enabling more detailed understanding and follow-up of meetings.

[0529] When the meeting begins, the user captures the meeting audio through a voice input device. This audio data is transmitted in real time to the server by the terminal. The server uses speech recognition technology to convert the audio data into text data, and then uses natural language processing technology to extract important information from the text data and automatically generate meeting minutes.

[0530] Furthermore, in this invention, an emotion engine installed in the server analyzes the voice data and identifies the user's emotional state. This allows for an understanding of the tone and emotions of speakers during a meeting, and by recording this information in the meeting minutes, it improves the understanding of the meeting's context.

[0531] The emotional information obtained by the emotion engine is also reflected in the generation of follow-up tasks. The server automatically adjusts task priorities according to the emotional state. For example, when a high-priority issue is discussed, it is assigned to the person in charge as a high-urgency task. This approach allows for improved work efficiency and accurate task management by utilizing emotional information.

[0532] For example, if a marketing strategy is discussed during a meeting and some speakers express feelings of caution or concern, that sentiment data is reflected in the meeting minutes. The server can then use the sentiment engine's results to generate a follow-up task to schedule an urgent meeting and assign it preferentially to the marketing team. This allows important emotional nuances from meetings to be utilized in work and enables a swift response.

[0533] The following describes the processing flow.

[0534] Step 1:

[0535] When the user starts a meeting, the audio of the meeting is captured using the voice input device. The audio data is captured on the device in real time.

[0536] Step 2:

[0537] The (terminal) sends the acquired audio data to the (server) in streaming format. The (server) uses speech recognition technology to convert the audio data into text data.

[0538] Step 3:

[0539] The server feeds the converted text data into a natural language processing engine to extract important topics and decisions. This analysis then generates a meeting summary.

[0540] Step 4:

[0541] The server, using its built-in emotion engine, analyzes the user's emotional state from the audio data and identifies the speaker's tone and emotions.

[0542] Step 5:

[0543] The server automatically generates meeting minutes based on the extracted information, taking into account the sentiment data identified by the sentiment engine. The sentiment information is recorded as part of the meeting minutes.

[0544] Step 6:

[0545] Based on meeting minutes, the server generates follow-up tasks. By using sentiment information to automatically adjust the urgency and priority of tasks, important tasks are quickly assigned to the appropriate personnel.

[0546] Step 7:

[0547] The terminal works in conjunction with a task management system to assign generated tasks in real time and monitor the progress of each task.

[0548] Step 8:

[0549] The user reviews meeting minutes and sentiment information from their device and follows up on the progress of assigned tasks. They take prompt action and provide additional communication as needed.

[0550] (Example 2)

[0551] 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."

[0552] Even with automated conversion of audio data from meetings to text data, traditional systems process information without considering participants' emotions or tone of voice. This makes it difficult to prioritize follow-up tasks that reflect these nuances, resulting in challenges to operational efficiency and response speed.

[0553] 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.

[0554] In this invention, the server includes a speech recognition means for acquiring audio data and converting it into text data, a means for extracting important information from the text data using natural language processing technology and automatically generating meeting minutes, and a means for identifying emotional states using sentiment analysis technology and reflecting them in the meeting minutes. This makes it possible to prioritize follow-up tasks that incorporate the emotional nuances of meetings, enabling more efficient work and faster responses.

[0555] "Speech recognition technology" is a technology that analyzes audio data and converts it into text data, and is a means of understanding human spoken language in a digital format.

[0556] "Natural language processing technology" is a technology that allows computers to understand and analyze human language, and is a technology for extracting meaning from text data.

[0557] "Sentiment analysis technology" is a technique that identifies the emotional state and tone of a statement based on text or audio data, and is a means of classifying emotional nuances as numerical values ​​or categories.

[0558] Meeting minutes are documents that summarize the content of statements and discussions during a meeting and are used for later reference and record-keeping.

[0559] A "follow-up task" is an action item generated to support work processes, based on the meeting results and minutes, outlining the next steps to take and necessary procedures.

[0560] "Priority adjustment" is the process of determining the order in which follow-up tasks are performed based on specific criteria (e.g., importance, urgency).

[0561] The system of the present invention aims to improve voice input processing in meeting management by integrating speech recognition and natural language processing technologies to efficiently generate meeting minutes and further improve follow-up tasks through sentiment analysis.

[0562] First, the user acquires the meeting audio using a voice input device (e.g., a smartphone or a dedicated voice capture device). This device captures the meeting speeches in real time and converts them into a digital format.

[0563] Next, the device sends this audio data to a server via the internet. The server implements an external speech recognition service (e.g., a cloud-based speech recognition API) as speech recognition technology, and the audio data is converted into text data here. The speech service uses different speech models to identify the speaker and efficiently converts it into text.

[0564] The server then processes the text data, uses natural language processing technology (e.g., natural language understanding APIs) to extract key points from the meeting, and automatically generates meeting minutes. This documents a summary of the meeting, making it easy to refer to later.

[0565] Furthermore, the server's sentiment analysis engine analyzes text and audio data to identify the emotional state of participants. This sentiment information is not only reflected in the meeting minutes but is also used as a crucial factor in determining the priority of follow-up tasks. Based on this information, the server works in conjunction with the task management system to assign tasks to the appropriate personnel, thereby streamlining operations.

[0566] For example, if emotional discussions about a new strategy arise during a marketing meeting, the emotions identified through sentiment analysis will be prioritized by the server for subsequent follow-up meetings. This ensures that important nuances from the meeting are efficiently utilized.

[0567] An example of a prompt using a generative AI model is: "We have audio data of a new product announcement from a meeting. Based on this data, extract the emotions, summarize the key points as meeting minutes, and generate follow-up tasks based on that information."

[0568] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0569] Step 1:

[0570] The user captures audio using an audio input device at the start of the meeting. The input at this stage is the raw audio signal acquired through the meeting's microphone. This audio signal is transmitted to the terminal as digital audio data. The terminal performs noise reduction processing to improve the quality of the audio data.

[0571] Step 2:

[0572] The terminal sends noise-reduced audio data to the server. The input is audio data processed in digital format. The server passes this audio data to an external speech recognition service to convert it into text data. The output is the converted string data. This conversion uses acoustic and language models to enable highly accurate text conversion.

[0573] Step 3:

[0574] The server processes the received text data through a natural language processing engine. The input is a draft of meeting minutes in text format. The natural language processing engine extracts important keywords and topics from this data and generates a summary. The output is an automatically generated meeting minute containing essential information. During this process, the importance and frequency of keywords are analyzed, and the information is organized.

[0575] Step 4:

[0576] The server then sends text data to the sentiment analysis engine. The input is meeting minutes with key points organized. The sentiment analysis engine identifies the emotional tone of each statement from these minutes. The output is meeting minutes data with emotional states assigned to it. Here, sentiment scoring of statements is performed using dictionary-based or machine learning models.

[0577] Step 5:

[0578] The server generates follow-up tasks based on sentiment-analyzed meeting minutes. The input for this process is meeting minutes with sentiment fields added. The server sets the urgency and priority of tasks according to the sentiment state and assigns them to the most suitable person. The output is the assigned follow-up task, which is then integrated with the business management system. This operation involves task re-evaluation and system integration based on sentiment scores.

[0579] (Application Example 2)

[0580] 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."

[0581] In modern family communication, effectively understanding family conversations and providing appropriate advice that takes emotions into account is a challenging task. Conventional conversation support technologies often fail to adequately capture emotional nuances, resulting in insufficient support. To address these challenges, there is a need for a system that can effectively support decision-making and problem-solving within families.

[0582] 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.

[0583] In this invention, the server includes means for inputting acoustic data and converting said acoustic data into text data using acoustic recognition technology, means for extracting important information from the text data and automatically generating a record using text processing technology, and means for identifying the speaker's emotional state using emotion analysis technology and recording the result in the record. This enables real-time understanding of conversations within the home and provides effective communication support through helpful advice and task management that takes emotions into account.

[0584] "Audio data" refers to data that represents sound in digital format and is the subject of conversion into text data using speech recognition technology.

[0585] "Acoustic recognition technology" is a technology that analyzes input acoustic data and converts it into linguistic data.

[0586] "Text data" refers to text-based data generated using acoustic recognition technology, which is used for further analysis and processing.

[0587] "Text processing technology" refers to techniques for extracting semantic information from text data and identifying important points.

[0588] A "record" is a document that includes text data and emotional information generated from audio data, and accurately represents the content of a conversation.

[0589] "Emotion analysis technology" is a technology that determines the emotional state of a speaker based on acoustic data and text data.

[0590] The "speaker" is the entity that produced the sound that forms the basis of the audio data.

[0591] A "task management platform" is an external system used to manage and monitor the progress and completion status of generated tasks.

[0592] "Priority" is an indicator used to set an order for multiple tasks or items based on their importance and urgency.

[0593] Embodiments of this invention include a system comprising a communication support robot placed in the home. The user captures the audio of a conversation through an acoustic input device, and this acoustic data is transmitted in real time to a server by the terminal. The server converts the acoustic data into text data using acoustic recognition technology, and further extracts important information from the text data using text processing technology, automatically generating it as a record.

[0594] Furthermore, emotion analysis technology installed on the server analyzes the acoustic data to identify the speaker's emotional state. The obtained emotional information is incorporated into the record, and the priority of follow-up tasks is adjusted based on this. The generated tasks are sent to an external task management platform, where their progress is monitored.

[0595] As a concrete example, when a family is discussing holiday plans, a robot can analyze the speakers' excitement and anticipation and create a record summarizing the plans. As a result, the server can provide helpful advice to the user and set up follow-up tasks as needed. In this case, an example of a prompt to the generating AI model would be, "Detect emotional arousal from this conversation and generate tasks that require suggestions."

[0596] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0597] Step 1:

[0598] The user captures the audio of the conversation through an acoustic input device. This acoustic data is collected by the terminal and sent to a server. The input is real-time acoustic data, and the output is the transmission of acoustic data to the server. Specifically, a microphone is used to record the audio of the conversation as digital data.

[0599] Step 2:

[0600] The server uses acoustic recognition technology to convert the received acoustic data into text data. This process employs an acoustic recognition algorithm. The input is acoustic data, and the output is the converted text data. Specifically, the process involves converting speech to text using a speech recognition API.

[0601] Step 3:

[0602] The server analyzes the converted text data using text processing techniques and extracts important information. The input is the previously obtained text data, and the output is a record summarizing the important information. Specifically, this involves extracting important keywords and phrases using a natural language processing library.

[0603] Step 4:

[0604] The server uses emotion analysis technology to analyze the speaker's emotional state from acoustic data. The input is acoustic data, and the output is identified emotion information. In this process, the emotion analysis engine determines the emotion based on the tone and content of the speech.

[0605] Step 5:

[0606] The server integrates the collected emotional information and important points, incorporates them into the record, and adjusts the priority of follow-up tasks. The input is emotional information and important points, and the output is prioritized tasks. Specifically, task management is performed based on an algorithm set according to the urgency of the tasks.

[0607] Step 6:

[0608] Finally, the generated tasks are sent to an external task management platform for progress monitoring. The input is prioritized task information, and the output is the task monitoring status. Specifically, progress is tracked via a task management API.

[0609] 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.

[0610] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0611] 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.

[0612] [Fourth Embodiment]

[0613] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0614] 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.

[0615] 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).

[0616] 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.

[0617] 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.

[0618] 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).

[0619] 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.

[0620] 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.

[0621] 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.

[0622] 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.

[0623] 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.

[0624] 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.

[0625] 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".

[0626] The system of this invention aims to improve the efficiency of meetings by utilizing speech recognition technology and natural language processing technology, and is implemented as follows.

[0627] When the meeting begins, (the user) captures audio using an audio input device installed in the meeting room. This audio data is connected to (the terminal) in real time and sent to (the server) in streaming format. (The server) sends the received audio data to an external speech recognition service, which converts the audio into text data.

[0628] Next, the server analyzes the text data using natural language processing technology to extract important topics and decisions. Based on this information, the server automatically generates meeting minutes, which are then provided to the user after the meeting. This process ensures that what was said during the meeting is accurately recorded and can be used as a document for later reference.

[0629] Furthermore, the server analyzes the generated meeting minutes and extracts necessary follow-up tasks. These tasks are automatically assigned to the appropriate personnel based on pre-configured rules, eliminating the need for users to manually assign tasks and improving work efficiency. The terminal integrates with the task management system to monitor the progress of each task. This allows for real-time monitoring of project and operational progress, enabling immediate detection of delays and problems.

[0630] As a concrete example, suppose a meeting discusses the launch plan for the next product. The (server) transcribes the meeting audio into text, recording important points regarding the product launch as meeting minutes. Subsequently, necessary follow-up tasks, such as preparing marketing activities and conducting internal training on the new product, are automatically generated and assigned to the responsible parties. The (user) can check these tasks and track their progress through a dedicated (terminal) or device. In this way, work proceeds smoothly and productivity is improved.

[0631] The following describes the processing flow.

[0632] Step 1:

[0633] The user starts a meeting and captures the meeting audio through an audio input device. The audio data is transmitted to the terminal in real time.

[0634] Step 2:

[0635] The (terminal) transfers the received audio data to the (server) in streaming format. The (server) sends this audio data to an external speech recognition service and begins the process of converting it into text data.

[0636] Step 3:

[0637] The server inputs the converted text data into a natural language processing (NLP) engine, which analyzes the content of the statements within the text data. This extracts important topics, decisions, action items, etc.

[0638] Step 4:

[0639] The server automatically generates meeting minutes using the extracted information. The minutes are summarized and compiled into a document containing the key points.

[0640] Step 5:

[0641] After the meeting ends, the server extracts follow-up tasks from the generated meeting minutes and automatically creates a task list. This list includes specific action items required by the assigned person.

[0642] Step 6:

[0643] The server refers to pre-configured rules and assigns each task to the appropriate person. This assignment information is reflected in the project management system in real time.

[0644] Step 7:

[0645] The terminal seamlessly integrates with external task management systems to monitor the progress of each person in charge. This allows for real-time checking of task completion status and incomplete tasks.

[0646] Step 8:

[0647] The user uses their device to review the generated meeting minutes and follow up on the progress of their assigned tasks. This information is used to improve work efficiency and inform future decision-making processes.

[0648] (Example 1)

[0649] 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".

[0650] In business and project meetings, accurately and efficiently recording discussions, effectively extracting key points, and smoothly managing follow-up tasks are major challenges in improving operational efficiency and productivity. Traditional methods primarily involved manual recording and task allocation, which were time-consuming, labor-intensive, and prone to human error. Furthermore, real-time monitoring of progress was difficult, leading to problems such as project delays and the inability to detect problems early.

[0651] 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.

[0652] In this invention, the server includes means for acquiring audio information and converting the audio information into text information using speech recognition technology; means for extracting important information from the text information using natural language processing technology and automatically generating a record document; and means for generating tracking tasks based on the generated record document and assigning the tasks to personnel based on pre-set rules. As a result, the content of each meeting is accurately recorded in real time, important agenda items and decisions are automatically extracted, and follow-up tasks based on them are quickly assigned to personnel, significantly improving work efficiency.

[0653] "Voice information" refers to digital data related to human voices acquired through voice input devices.

[0654] "Speech recognition technology" is a technical means for converting acquired speech information into linguistic information.

[0655] "Textual information" refers to digital data in text format that is obtained by converting audio information using speech recognition technology.

[0656] "Natural language processing technology" refers to the technical means by which computers understand, analyze, and process the meaning of human natural language.

[0657] "Important information" refers to information that should be given particular importance in a meeting, such as agenda items and decisions, which is extracted using natural language processing technology.

[0658] A "record document" is a text document that is automatically generated based on important information.

[0659] "Follow-up tasks" are tasks and action items that need to be done after a meeting, generated from the recorded documents.

[0660] "Pre-established rules" are predetermined standards or rules used for assigning and managing tracking tasks.

[0661] An "external work management system" is a computer system or software used to manage tracking tasks and monitoring their progress.

[0662] A "network" is a communication system used to transmit information.

[0663] "Access" refers to the act of referencing or manipulating record documents or tracking operations.

[0664] This invention is essentially a system that acquires speech as digital data and analyzes it using natural language processing technology. A specific embodiment of this system is shown below.

[0665] Capture and transmission of audio data

[0666] Users capture speech in real time during meetings using an audio input device installed in the conference room. The audio input device includes a microphone and an audio signal processor. This device also has the function of converting the received audio signals into digital audio information.

[0667] Speech-to-text conversion

[0668] The terminal transmits the acquired audio information to the server in streaming format. The server uses external speech recognition technology to convert the audio information into text. This process often utilizes commercially available speech recognition services.

[0669] Extraction of important information and generation of meeting minutes

[0670] The server analyzes textual information using natural language processing software and extracts important information. Based on the extracted information, it automatically generates a record document. The generated record document is stored via cloud storage and can be accessed by users over the network.

[0671] Generation and management of follow-up tasks

[0672] The server generates tracking tasks from the generated record documents, which are then integrated with external work management software and assigned to the responsible personnel. The terminals function to allow users to monitor these tracking tasks in real time.

[0673] For example, in a meeting about a new product launch, the server transcribes the audio into text and generates a document containing important information such as product specifications and launch plans. Subsequently, follow-up tasks such as creating a marketing plan are automatically generated and assigned to the appropriate person.

[0674] An example of a prompt message might be: "Transcribe the audio of the next meeting in real time, extract the important points, and create meeting minutes. Also, generate necessary follow-up tasks, automatically assign them to the respective personnel, and monitor their progress." In this way, the present invention aims to improve business efficiency by automating the entire process from acquiring audio information to transcribing it into text, extracting information, and managing the work.

[0675] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0676] Step 1:

[0677] The user captures the audio during the meeting in real time using an audio input device installed in the meeting room. The input is an analog audio signal, which is captured by a microphone. This device outputs the audio signal as digital audio information and improves its quality through a noise reduction filter. The digital audio data is then transmitted to the terminal.

[0678] Step 2:

[0679] The terminal receives digital audio data from the user and sends it to the server in streaming format. The input is digital audio data, and the output is data packets to be sent to the server. It utilizes a data transfer protocol and is optimized to maintain low latency during transmission.

[0680] Step 3:

[0681] The server converts received audio data into text information using speech recognition technology. The input is streamed digital audio data, and the output is text data. The server calls a commercially available speech recognition service and uses a language model to convert the audio to text. This process performs highly accurate speech identification and speaker tagging.

[0682] Step 4:

[0683] The server analyzes the converted text information using natural language processing techniques and extracts important information. The input is text data, and the output is a list of important information. The natural language processing engine identifies specific terms and phrases and automatically prioritizes agenda items and decisions for meetings.

[0684] Step 5:

[0685] The server automatically generates record documents based on the extracted key information. The input is a list of key information, and the output is a record document. The record document is generated using a standardized template and stored in the cloud for later access by the user.

[0686] Step 6:

[0687] The server analyzes the recorded documents and generates tracking tasks. The input is the recorded documents, and the output is a list of tracking tasks. The server uses pre-configured rules to assign the work tasks to the appropriate personnel.

[0688] Step 7:

[0689] The terminal integrates with an external work management system to manage tracking tasks, allowing users to monitor work progress. Inputs are the tracking tasks and their progress, and output is a progress dashboard that users can view. Real-time updates enable quick detection of work delays and problems.

[0690] (Application Example 1)

[0691] 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".

[0692] In family communication, the inefficiency of managing family schedules and dividing tasks is a challenge, leading to confusion and forgetfulness. Furthermore, there is a lack of tools to automatically extract necessary information from everyday conversations and organize and manage it as schedules and tasks.

[0693] 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.

[0694] In this invention, the server includes means for acquiring voice information and converting said voice information into text information using voice recognition technology, means for extracting important information from said text information using natural language processing technology and automatically generating a recorded document, and means for acquiring voice conversations within the home and organizing and managing personal schedules and tasks. This makes it possible to efficiently organize necessary information from communication within the home and automate schedule management and task allocation.

[0695] "Auditory information" refers to acoustic signals that are recorded or transmitted by physical or electrical means from human speech.

[0696] "Speech recognition technology" is a technology that analyzes acquired speech information and formally converts its content into text information.

[0697] "Textual information" refers to the string of characters that constitutes information converted by speech recognition technology, and is information expressed as natural language.

[0698] "Natural language processing technology" is a technology that understands human language and extracts important information by performing syntactic and semantic analysis.

[0699] A "record document" is a document automatically generated based on extracted important information, and it organizes and records the content of the conversation.

[0700] A "tracking task" is an item that indicates subsequent activities generated from the record document, and is assigned to the person in charge according to pre-established rules.

[0701] A "progress management system" is a system for monitoring the progress of assigned tasks and updating information in a timely manner.

[0702] "Voice conversations within the home" refers to conversations that take place between family members at home, and the content of these conversations is related to schedule management and task sharing.

[0703] "Schedule management" is the act of organizing and recording the future activities and events of each individual member.

[0704] "Task sharing" refers to the act of appropriately assigning various household activities to individual members and managing them to ensure they are carried out efficiently.

[0705] The system for implementing this invention acquires voice information and supports family communication by utilizing voice recognition technology and natural language processing technology. Its specific form is described below.

[0706] First, hardware equipped with a microphone installed in the home collects voice information. This hardware can, for example, be a microphone built into a mobile device or home appliance. The collected voice information is transmitted to a server in real time.

[0707] The server uses the "Google Speech Recognition API" as its speech recognition library to convert speech information into text. The converted text is then analyzed by the natural language processing engine "spaCy" and extracted as important information and tracking tasks. This organizes the content of the conversation into a recorded document.

[0708] The extracted tracking tasks are integrated with a progress management system to automate scheduling and task allocation for each family member. Assignments are made to assigned personnel based on pre-defined family rules, and the server monitors task progress in conjunction with the progress management system (e.g., Google Calendar or Todoist) and updates information in a timely manner.

[0709] For example, if someone says in a morning conversation, "Let's weed the garden this weekend," the server analyzes this, adds the plan to the family's shared calendar, and sets a reminder the day before, such as "Prepare the necessary tools."

[0710] It is possible to utilize generative AI models and prompt statements; for example, using prompt statements such as "Generate text to extract tasks from family communications" can make system automation more efficient.

[0711] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0712] Step 1:

[0713] The user engages in voice conversations within their home, and this voice information is captured through a microphone. The input is the user's voice, and the output is an analog voice signal collected by the microphone. The microphone converts this analog signal into digital audio data.

[0714] Step 2:

[0715] The converted digital audio data is transmitted to the server in real time. The server receives this digital audio data as input and generates data packets as output, sending them to the next processing step. Digital data streaming takes place.

[0716] Step 3:

[0717] The server uses the Google Speech Recognition API to convert digital audio data into text. The input is streamed audio data, and the output is text-formatted character information. This step involves analysis using speech recognition technology.

[0718] Step 4:

[0719] The server uses spaCy to perform natural language processing on the converted text information and extract important points and tasks. It receives text information as input and generates an output of extracted important points and a list of scheduled tasks. Contextual analysis and keyword extraction are performed in this step.

[0720] Step 5:

[0721] The server automatically assigns schedule management and task sharing to family members based on the extracted tracking tasks. It receives a task list and established family rules as input and generates a task list assigned to the appropriate member as output. This step involves rule-based task assignment.

[0722] Step 6:

[0723] The server works in conjunction with the progress management system to monitor task progress and update information. Inputs are tasks assigned to members and their progress, while output is an updated progress report. This step involves status checks and database updates.

[0724] 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.

[0725] The system of the present invention combines standard meeting management functions with an emotion engine that recognizes user emotions, thereby enabling more detailed understanding and follow-up of meetings.

[0726] When the meeting begins, the user captures the meeting audio through a voice input device. This audio data is transmitted in real time to the server by the terminal. The server uses speech recognition technology to convert the audio data into text data, and then uses natural language processing technology to extract important information from the text data and automatically generate meeting minutes.

[0727] Furthermore, in this invention, an emotion engine installed in the server analyzes the voice data and identifies the user's emotional state. This allows for an understanding of the tone and emotions of speakers during a meeting, and by recording this information in the meeting minutes, it improves the understanding of the meeting's context.

[0728] The emotional information obtained by the emotion engine is also reflected in the generation of follow-up tasks. The server automatically adjusts task priorities according to the emotional state. For example, when a high-priority issue is discussed, it is assigned to the person in charge as a high-urgency task. This approach allows for improved work efficiency and accurate task management by utilizing emotional information.

[0729] For example, if a marketing strategy is discussed during a meeting and some speakers express feelings of caution or concern, that sentiment data is reflected in the meeting minutes. The server can then use the sentiment engine's results to generate a follow-up task to schedule an urgent meeting and assign it preferentially to the marketing team. This allows important emotional nuances from meetings to be utilized in work and enables a swift response.

[0730] The following describes the processing flow.

[0731] Step 1:

[0732] When the user starts a meeting, the audio of the meeting is captured using the voice input device. The audio data is captured on the device in real time.

[0733] Step 2:

[0734] The (terminal) sends the acquired audio data to the (server) in streaming format. The (server) uses speech recognition technology to convert the audio data into text data.

[0735] Step 3:

[0736] The server feeds the converted text data into a natural language processing engine to extract important topics and decisions. This analysis then generates a meeting summary.

[0737] Step 4:

[0738] The server, using its built-in emotion engine, analyzes the user's emotional state from the audio data and identifies the speaker's tone and emotions.

[0739] Step 5:

[0740] The server automatically generates meeting minutes based on the extracted information, taking into account the sentiment data identified by the sentiment engine. The sentiment information is recorded as part of the meeting minutes.

[0741] Step 6:

[0742] Based on meeting minutes, the server generates follow-up tasks. By using sentiment information to automatically adjust the urgency and priority of tasks, important tasks are quickly assigned to the appropriate personnel.

[0743] Step 7:

[0744] The terminal works in conjunction with a task management system to assign generated tasks in real time and monitor the progress of each task.

[0745] Step 8:

[0746] The user reviews meeting minutes and sentiment information from their device and follows up on the progress of assigned tasks. They take prompt action and provide additional communication as needed.

[0747] (Example 2)

[0748] 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".

[0749] Even with automated conversion of audio data from meetings to text data, traditional systems process information without considering participants' emotions or tone of voice. This makes it difficult to prioritize follow-up tasks that reflect these nuances, resulting in challenges to operational efficiency and response speed.

[0750] 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.

[0751] In this invention, the server includes a speech recognition means for acquiring audio data and converting it into text data, a means for extracting important information from the text data using natural language processing technology and automatically generating meeting minutes, and a means for identifying emotional states using sentiment analysis technology and reflecting them in the meeting minutes. This makes it possible to prioritize follow-up tasks that incorporate the emotional nuances of meetings, enabling more efficient work and faster responses.

[0752] "Speech recognition technology" is a technology that analyzes audio data and converts it into text data, and is a means of understanding human spoken language in a digital format.

[0753] "Natural language processing technology" is a technology that allows computers to understand and analyze human language, and is a technology for extracting meaning from text data.

[0754] "Sentiment analysis technology" is a technique that identifies the emotional state and tone of a statement based on text or audio data, and is a means of classifying emotional nuances as numerical values ​​or categories.

[0755] Meeting minutes are documents that summarize the content of statements and discussions during a meeting and are used for later reference and record-keeping.

[0756] A "follow-up task" is an action item generated to support work processes, based on the meeting results and minutes, outlining the next steps to take and necessary procedures.

[0757] "Priority adjustment" is the process of determining the order in which follow-up tasks are performed based on specific criteria (e.g., importance, urgency).

[0758] The system of the present invention aims to improve voice input processing in meeting management by integrating speech recognition and natural language processing technologies to efficiently generate meeting minutes and further improve follow-up tasks through sentiment analysis.

[0759] First, the user acquires the meeting audio using a voice input device (e.g., a smartphone or a dedicated voice capture device). This device captures the meeting speeches in real time and converts them into a digital format.

[0760] Next, the device sends this audio data to a server via the internet. The server implements an external speech recognition service (e.g., a cloud-based speech recognition API) as speech recognition technology, and the audio data is converted into text data here. The speech service uses different speech models to identify the speaker and efficiently converts it into text.

[0761] The server then processes the text data, uses natural language processing technology (e.g., natural language understanding APIs) to extract key points from the meeting, and automatically generates meeting minutes. This documents a summary of the meeting, making it easy to refer to later.

[0762] Furthermore, the server's sentiment analysis engine analyzes text and audio data to identify the emotional state of participants. This sentiment information is not only reflected in the meeting minutes but is also used as a crucial factor in determining the priority of follow-up tasks. Based on this information, the server works in conjunction with the task management system to assign tasks to the appropriate personnel, thereby streamlining operations.

[0763] For example, if emotional discussions about a new strategy arise during a marketing meeting, the emotions identified through sentiment analysis will be prioritized by the server for subsequent follow-up meetings. This ensures that important nuances from the meeting are efficiently utilized.

[0764] An example of a prompt using a generative AI model is: "We have audio data of a new product announcement from a meeting. Based on this data, extract the emotions, summarize the key points as meeting minutes, and generate follow-up tasks based on that information."

[0765] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0766] Step 1:

[0767] The user captures audio using an audio input device at the start of the meeting. The input at this stage is the raw audio signal acquired through the meeting's microphone. This audio signal is transmitted to the terminal as digital audio data. The terminal performs noise reduction processing to improve the quality of the audio data.

[0768] Step 2:

[0769] The terminal sends noise-reduced audio data to the server. The input is audio data processed in digital format. The server passes this audio data to an external speech recognition service to convert it into text data. The output is the converted string data. This conversion uses acoustic and language models to enable highly accurate text conversion.

[0770] Step 3:

[0771] The server processes the received text data through a natural language processing engine. The input is a draft of meeting minutes in text format. The natural language processing engine extracts important keywords and topics from this data and generates a summary. The output is an automatically generated meeting minute containing essential information. During this process, the importance and frequency of keywords are analyzed, and the information is organized.

[0772] Step 4:

[0773] The server then sends text data to the sentiment analysis engine. The input is meeting minutes with key points organized. The sentiment analysis engine identifies the emotional tone of each statement from these minutes. The output is meeting minutes data with emotional states assigned to it. Here, sentiment scoring of statements is performed using dictionary-based or machine learning models.

[0774] Step 5:

[0775] The server generates follow-up tasks based on sentiment-analyzed meeting minutes. The input for this process is meeting minutes with sentiment fields added. The server sets the urgency and priority of tasks according to the sentiment state and assigns them to the most suitable person. The output is the assigned follow-up task, which is then integrated with the business management system. This operation involves task re-evaluation and system integration based on sentiment scores.

[0776] (Application Example 2)

[0777] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0778] In modern family communication, effectively understanding family conversations and providing appropriate advice that takes emotions into account is a challenging task. Conventional conversation support technologies often fail to adequately capture emotional nuances, resulting in insufficient support. To address these challenges, there is a need for a system that can effectively support decision-making and problem-solving within families.

[0779] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0780] In this invention, the server includes means for inputting acoustic data and converting said acoustic data into text data using acoustic recognition technology, means for extracting important information from the text data and automatically generating a record using text processing technology, and means for identifying the speaker's emotional state using emotion analysis technology and recording the result in the record. This enables real-time understanding of conversations within the home and provides effective communication support through helpful advice and task management that takes emotions into account.

[0781] "Audio data" refers to data that represents sound in digital format and is the subject of conversion into text data using speech recognition technology.

[0782] "Acoustic recognition technology" is a technology that analyzes input acoustic data and converts it into linguistic data.

[0783] "Text data" refers to text-based data generated using acoustic recognition technology, which is used for further analysis and processing.

[0784] "Text processing technology" refers to techniques for extracting semantic information from text data and identifying important points.

[0785] A "record" is a document that includes text data and emotional information generated from audio data, and accurately represents the content of a conversation.

[0786] "Emotion analysis technology" is a technology that determines the emotional state of a speaker based on acoustic data and text data.

[0787] The "speaker" is the entity that produced the sound that forms the basis of the audio data.

[0788] A "task management platform" is an external system used to manage and monitor the progress and completion status of generated tasks.

[0789] "Priority" is an indicator used to set an order for multiple tasks or items based on their importance and urgency.

[0790] Embodiments of this invention include a system comprising a communication support robot placed in the home. The user captures the audio of a conversation through an acoustic input device, and this acoustic data is transmitted in real time to a server by the terminal. The server converts the acoustic data into text data using acoustic recognition technology, and further extracts important information from the text data using text processing technology, automatically generating it as a record.

[0791] Furthermore, emotion analysis technology installed on the server analyzes the acoustic data to identify the speaker's emotional state. The obtained emotional information is incorporated into the record, and the priority of follow-up tasks is adjusted based on this. The generated tasks are sent to an external task management platform, where their progress is monitored.

[0792] As a concrete example, when a family is discussing holiday plans, a robot can analyze the speakers' excitement and anticipation and create a record summarizing the plans. As a result, the server can provide helpful advice to the user and set up follow-up tasks as needed. In this case, an example of a prompt to the generating AI model would be, "Detect emotional arousal from this conversation and generate tasks that require suggestions."

[0793] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0794] Step 1:

[0795] The user captures the audio of the conversation through an acoustic input device. This acoustic data is collected by the terminal and sent to a server. The input is real-time acoustic data, and the output is the transmission of acoustic data to the server. Specifically, a microphone is used to record the audio of the conversation as digital data.

[0796] Step 2:

[0797] The server uses acoustic recognition technology to convert the received acoustic data into text data. This process employs an acoustic recognition algorithm. The input is acoustic data, and the output is the converted text data. Specifically, the process involves converting speech to text using a speech recognition API.

[0798] Step 3:

[0799] The server analyzes the converted text data using text processing techniques and extracts important information. The input is the previously obtained text data, and the output is a record summarizing the important information. Specifically, this involves extracting important keywords and phrases using a natural language processing library.

[0800] Step 4:

[0801] The server uses emotion analysis technology to analyze the speaker's emotional state from acoustic data. The input is acoustic data, and the output is identified emotion information. In this process, the emotion analysis engine determines the emotion based on the tone and content of the speech.

[0802] Step 5:

[0803] The server integrates the collected emotional information and important points, incorporates them into the record, and adjusts the priority of follow-up tasks. The input is emotional information and important points, and the output is prioritized tasks. Specifically, task management is performed based on an algorithm set according to the urgency of the tasks.

[0804] Step 6:

[0805] Finally, the generated tasks are sent to an external task management platform for progress monitoring. The input is prioritized task information, and the output is the task monitoring status. Specifically, progress is tracked via a task management API.

[0806] 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.

[0807] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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."

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0827] The following is further disclosed regarding the embodiments described above.

[0828] (Claim 1)

[0829] A means for acquiring audio data and converting said audio data into text data using speech recognition technology,

[0830] A means for extracting important information from text data using natural language processing technology and automatically generating meeting minutes,

[0831] A means for generating follow-up tasks based on the generated meeting minutes and assigning those tasks to personnel based on pre-defined rules,

[0832] A means of monitoring task progress in conjunction with an external task management system,

[0833] A system that includes this.

[0834] (Claim 2)

[0835] The system according to claim 1, further comprising means for using an external speech recognition service to convert the audio data into text data in real time.

[0836] (Claim 3)

[0837] The system according to claim 1, comprising means for automatically assigning extracted follow-up tasks to personnel in accordance with project management rules.

[0838]

[0839] "Example 1"

[0840] (Claim 1)

[0841] A means for acquiring audio information and converting said audio information into text information using speech recognition technology,

[0842] A means for extracting important information from the textual information using natural language processing technology and automatically generating a recorded document,

[0843] A means for generating tracking tasks based on the generated record documents and assigning those tasks to personnel based on pre-established rules,

[0844] A means of monitoring the progress of work in conjunction with an external work management system,

[0845] A means for capturing speech during a meeting in real time through the aforementioned voice input device and transmitting the voice information with low latency using a data transmission function,

[0846] A means of re-analyzing transcribed information and setting priorities based on specific terms and expressions,

[0847] A means of storing generated record documents in cloud storage and providing access via a network,

[0848] A system that includes this.

[0849] (Claim 2)

[0850] The system according to claim 1, further comprising means for using an external speech recognition service to convert the aforementioned speech information into text information in real time.

[0851] (Claim 3)

[0852] The system according to claim 1, comprising means for automatically assigning extracted tracking tasks to personnel in accordance with business management rules.

[0853] "Application Example 1"

[0854] (Claim 1)

[0855] A means for acquiring audio information and converting said audio information into text information using speech recognition technology,

[0856] A means for extracting important information from the textual information using natural language processing technology and automatically generating a record document,

[0857] A means for generating tracking tasks based on the generated record documents and assigning those tasks to personnel based on pre-defined rules,

[0858] A means of monitoring task progress in conjunction with an external progress management system,

[0859] A means of capturing voice conversations within the home to organize and manage personal schedules and tasks,

[0860] A system that includes this.

[0861] (Claim 2)

[0862] The system according to claim 1, further comprising means for using an external speech recognition service to convert the aforementioned speech information into text information in real time.

[0863] (Claim 3)

[0864] The system according to claim 1, comprising means for automatically assigning extracted tracking tasks to personnel based on activity management rules.

[0865] "Example 2 of combining an emotion engine"

[0866] (Claim 1)

[0867] A means for acquiring audio data and converting said audio data into text data using speech recognition technology,

[0868] A means for extracting important information from text data using natural language processing technology and automatically generating meeting minutes,

[0869] A means for identifying emotional states using sentiment analysis technology based on the generated meeting minutes, and for reflecting the identified emotional information in the meeting minutes,

[0870] A means for adjusting and generating the priority of follow-up tasks based on emotional information, and assigning those tasks to the person in charge,

[0871] A means of monitoring task progress in conjunction with an external business management system,

[0872] A system that includes this.

[0873] (Claim 2)

[0874] The system according to claim 1, which uses an external speech recognition service to convert the audio data into text data in real time.

[0875] (Claim 3)

[0876] The system according to claim 1, which automatically assigns follow-up tasks to personnel using project management rules based on identified emotional information.

[0877] "Application example 2 when combining with an emotional engine"

[0878] (Claim 1)

[0879] A means for inputting acoustic data and converting said acoustic data into text data using acoustic recognition technology,

[0880] A means for extracting important information from the text data using text processing technology and automatically generating a record,

[0881] A means for generating tracking tasks based on the generated records and assigning those tasks to personnel based on pre-set rules,

[0882] A means of monitoring task progress in conjunction with an external task management platform,

[0883] A means for identifying the speaker's emotional state using emotion analysis technology and recording the results,

[0884] A means of adjusting task priorities based on emotional information,

[0885] A system that includes this.

[0886] (Claim 2)

[0887] The system according to claim 1, further comprising means for using an external acoustic recognition service to convert the acoustic data into text data in real time.

[0888] (Claim 3)

[0889] The system according to claim 1, comprising means for automatically assigning extracted tracking tasks to personnel based on project management rules. [Explanation of symbols]

[0890] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for acquiring audio data and converting said audio data into text data using speech recognition technology, A means for extracting important information from text data using natural language processing technology and automatically generating meeting minutes, A means for generating follow-up tasks based on the generated meeting minutes and assigning those tasks to personnel based on pre-defined rules, A means of monitoring task progress in conjunction with an external task management system, A system that includes this.

2. The system according to claim 1, further comprising means for using an external speech recognition service to convert the audio data into text data in real time.

3. The system according to claim 1, further comprising means for automatically assigning extracted follow-up tasks to personnel in accordance with project management rules.

Images