system

Abstract

We provide the system. [Solution] Data collection methods that acquire data from various digital platforms, A learning method that analyzes the aforementioned data to learn the past decision-making tendencies of a specific user, A proposal generation means that automatically generates a proposal document based on the learned trends, An interface means for presenting the generated proposal document to the user and obtaining their approval, A means of communication for recording the approval result and notifying the relevant parties, 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 method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern workplaces, middle managers have many tasks and tend to spend a lot of time on coordinating with superiors and subordinates, participating in meetings, approval tasks, etc. Therefore, they cannot allocate sufficient time to important decision-making matters and creative activities that should be focused on originally, and there is a demand for improving work efficiency and accelerating decision-making. Conventional systems cannot sufficiently solve these problems, and the burden on management positions is increasing.

Means for Solving the Problems

[0005] This invention provides an AI system that analyzes data acquired from various digital platforms and learns the thought patterns of specific users. Based on the learned data, this AI system automatically generates proposal documents, enabling users to quickly approve them. The documents generated by the AI ​​are created using natural language processing technology and presented to the user via a digital interface. This mechanism reduces delays in operations and alleviates the workload of managers.

[0006] "Data collection means" refers to components that have the function of acquiring information from various digital platforms.

[0007] A "learning tool" is a component that has the function of analyzing acquired data and learning from the past decision-making tendencies of a specific user.

[0008] A "proposal generation means" is a component that has the function of automatically creating a proposal document based on learned trends.

[0009] An "interface means" is a component that has the function of presenting the generated proposal document to the user and performing operations and displays to obtain approval.

[0010] "Communication means" refers to a component that has the function of recording the approval result and notifying relevant parties as necessary. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] This invention is a system that improves the work efficiency of middle managers by utilizing a generative AI agent. In implementation, the server first collects data from multiple digital platforms accessed by the user, such as email services, scheduling tools, online meeting systems, spreadsheet software, and presentation tools. This data collection is automated via APIs, and new information is acquired periodically.

[0033] Next, the server processes the collected information, removing unnecessary data and formatting it. Here, natural language processing techniques are used to analyze the content of emails and meetings, extracting important information relevant to the business. This allows the data to be efficiently stored in a structured format within the database.

[0034] Subsequently, the server uses machine learning algorithms to learn the specific user's past decision-making patterns and approval tendencies. This learning allows it to predict under what conditions the user is most likely to approve.

[0035] Based on predicted thought patterns, the server generates a suggestion document. This document is automatically created using natural language processing and includes specific content and recommendations. At this stage, the suggestion document is adjusted to align with the user's past work style and recent activities.

[0036] The terminal presents the generated proposal document to the user through a user interface. The user can review the proposal content on the screen and add comments or make modifications if necessary. If the proposal is approved, the terminal sends the result to the server, which records the result in a database.

[0037] Finally, based on the approved proposal, the server sends notifications to the necessary stakeholders and proceeds with the next business process. In this way, each step works in conjunction to reduce the user's burden and streamline operations. As a concrete example, weekly meeting agendas can be automatically generated based on the user's past approval patterns, allowing users to review and approve the content, thus enabling rapid decision-making. This significantly reduces the workload of managers and speeds up the decision-making process.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The server accesses various digital platforms via APIs and automatically collects data related to the user's work. This collected data includes emails, calendar events, and online meeting information.

[0041] Step 2:

[0042] The server analyzes the collected raw data. It uses natural language processing techniques to format the text data, remove noise, and extract important information. For example, it might extract meeting dates and agenda items from email text.

[0043] Step 3:

[0044] The server stores the analyzed data in a database. Simultaneously, it organizes the metadata associated with the data to enable efficient searching and access.

[0045] Step 4:

[0046] The server uses stored data to analyze the user's past decision-making and approval history using machine learning algorithms. This allows it to learn the user's unique thinking patterns and use that knowledge to predict future approval behaviors.

[0047] Step 5:

[0048] The server automatically generates suggestion documents based on learned thought patterns. The generation process ensures that specific suggestions and recommendations are incorporated into the documents based on previous data.

[0049] Step 6:

[0050] The terminal displays the generated proposal document in a user interface. The interface is designed to be intuitive for the user to operate, and it provides a means for reviewing and approving the proposal.

[0051] Step 7:

[0052] Users can review the presented proposal document and make revisions or comments as needed. They can formally approve the proposal by clicking the approve button.

[0053] Step 8:

[0054] The terminal sends the user's approval action to the server. The server records the approval result in detail and uses it as a trigger to execute the next processing step.

[0055] Step 9:

[0056] The server sends notifications to stakeholders based on approved proposals. These notifications provide information on the next steps to take and automatically advance the business process.

[0057] (Example 1)

[0058] 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."

[0059] With the rapid advancement of information technology, digital data from various information terminals is exploding. In business environments, particularly for middle managers, there is a need to quickly and accurately process the information necessary for effective decision-making. However, this data is diverse, and processing all of it alone requires a tremendous amount of time and effort. Furthermore, in today's world where speed of decision-making is paramount, information selection and proposal creation become bottlenecks, necessitating increased work efficiency. Solving this challenge is crucial for achieving both increased efficiency and reduced workload.

[0060] 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.

[0061] In this invention, the server includes an information gathering means for acquiring information from various information terminals, a learning means for analyzing the information and learning the past decision-making tendencies of a specific user, and a proposal generation means for generating proposal texts using natural language processing based on the learned tendencies. This enables integrated management and efficient processing of information, and facilitates the decision-making process through the rapid generation of proposal texts.

[0062] "Information gathering means" refers to methods for acquiring digital data such as electronic messages, schedule events, and online meeting information from various information terminals.

[0063] "Learning methods" refer to algorithms and methods used to analyze collected information and learn the past decision-making tendencies of a specific user.

[0064] A "proposal generation method" is a means of automatically generating a proposal text to present to the user using natural language processing based on learned information.

[0065] A "dialogue mechanism" is an interface for presenting the generated proposal to the user and obtaining their approval.

[0066] "Communication means" refers to a means that has the function of recording the approval results and notifying the relevant parties.

[0067] This invention is a system that utilizes a generating AI agent to improve the work efficiency of middle managers. Specific embodiments are described below.

[0068] The server automatically collects information from various information terminals. These terminals include email services, scheduling tools, and online meeting systems. For example, to obtain email information, data can be retrieved via APIs from Gmail and Outlook. Similarly, appropriate APIs are used to retrieve calendar events from Google Calendar and other scheduling services. Information collection is securely performed through an authentication process using OAuth 2.0.

[0069] Subsequently, the server uses machine learning tools such as TENSORFLOW® and scikit-learn to organize the collected information and learn the decision-making patterns of specific users. This learning process allows the server to analyze trends derived from past data and form a model to predict future decisions.

[0070] Furthermore, the server automatically generates suggestion texts using natural language processing technology. This technology utilizes software such as Google Cloud Natural Language API and Amazon Comprehend, which extract data and then formulate useful suggestions. The generated suggestion texts are then verified to be consistent with the user's past work style and recent activities.

[0071] The terminal presents this proposal through the user interface, allowing the user to review its contents. The user can then review the displayed proposal and add any necessary revisions or comments. For example, they can add an item to the generated meeting agenda.

[0072] Ultimately, based on the approved proposal, the server sends notifications to the relevant parties to ensure the smooth progress of the next business process. This reduces the burden on users and allows business processes to be carried out quickly and efficiently.

[0073] An example of a prompt might be, "Automatically generate an agenda for the next meeting and propose it, incorporating the content of past meetings." The system will receive this prompt, gather the appropriate information, and generate a proposal.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The server collects information from various information terminals. Input at this stage includes data from emails, calendar events, and online meetings. Specifically, it uses APIs from email services and scheduling tools to retrieve the latest information in JSON format. The output is the retrieved data stored in temporary storage.

[0077] Step 2:

[0078] The server analyzes the collected data. The input for this stage is the raw data collected in step 1. Here, a natural language processing engine is used to extract keywords from the text content of emails and meeting minutes and identify important information. The relevant data is structured, and only the information relevant to the business is cleansed and stored in the database.

[0079] Step 3:

[0080] The server learns the user's past decision-making tendencies through machine learning algorithms. The input for this stage comes from an analyzed database. Using tools such as TensorFlow, it analyzes past case studies and decision history to generate a predictive model. The output is a generated and updated model that reflects the user's decision-making patterns.

[0081] Step 4:

[0082] The server generates a proposal document based on the generated model. The input here is the decision-making model obtained through learning. Using natural language processing techniques, it creates a proposal document that aligns with the predicted user's desired work content. The proposal document is adjusted to match the user's past activity style. The final output is a completed proposal document presented to the user.

[0083] Step 5:

[0084] The terminal displays the proposal document generated by the server to the user. The input at this stage is the proposal document sent from the server. The user can review it on the screen and insert additional comments or make corrections as needed. The output is a reviewed or corrected version of the proposal.

[0085] Step 6:

[0086] Once the user approves the proposal, the terminal sends the result to the server. The input at this stage is the user's approval and comments. The server receives this and records the approved content in its database. The output is the recorded approval result and a notification sent to the relevant parties to proceed to the next step.

[0087] (Application Example 1)

[0088] 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."

[0089] In modern industrial product production management, it is essential to process diverse information quickly and accurately to maximize production efficiency. However, traditional methods heavily rely on human judgment, leading to wasted time and insufficient data utilization. Furthermore, they increase the burden on managers and decrease operational efficiency. Therefore, there is a need for systems that automatically collect and efficiently process various digital information to optimize production plans.

[0090] 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.

[0091] In this invention, the server includes an information gathering means, a learning means, and a proposal generation means. This allows the server to acquire necessary information from various digital information infrastructures and learn past decision-making trends, thereby automatically generating proposals to optimize production plans, enabling production managers to make optimal decisions quickly.

[0092] An "information gathering device" is a device that has the function of automatically acquiring information from various digital information infrastructures and efficiently storing it.

[0093] A "learning tool" is a device that analyzes acquired information and has the function of understanding and learning the past decision-making tendencies of a specific user.

[0094] A "proposal generation device" is a device that automatically generates proposal documents based on learned information and has the function of encouraging users to make optimal decisions.

[0095] A "display means" is a device that presents the generated proposal document to the user and provides an interface that allows the user to review and modify its contents as needed.

[0096] "Communication means" refers to communication equipment and technology that have the function of recording approval results and notifying the necessary parties.

[0097] A "plan generation device" is a device that generates proposals to optimize production plans for manufacturing industrial products, thereby supporting the decision-making of managers.

[0098] A "control device" is a device that uses generated suggestions to support the execution of industrial processes and performs operations to improve production efficiency.

[0099] A system for implementing this invention comprises information gathering means, learning means, proposal generation means, display means, communication means, plan generation means, and control means.

[0100] The server first automatically collects necessary data from various digital information infrastructures, such as electronic communications, event schedule management, and virtual meeting information, using information gathering tools. This utilizes data acquisition technologies via Amazon Web Services (AWS®) services and APIs. The collected data is then analyzed using learning tools, and analytical processing is performed to understand past decision-making trends. Natural language processing is performed using Python's NLTK and spaCy libraries to extract important parts of the data.

[0101] The proposal generation system generates optimal proposal documents for the user based on organized information and learned data. Using a generation AI model, specific and highly relevant proposals are provided to the user.

[0102] The terminal presents the generated proposal document to the user via a display mechanism, allowing the user to review, modify, or approve it on the screen. This interface provides a user-friendly application environment developed using React Native.

[0103] The approval results are transmitted to the server via communication means and recorded in the database. Subsequently, the planning generation means automatically generates a production plan, and the control means efficiently executes the industrial process. This allows administrators to quickly and efficiently apply the production plan.

[0104] As a concrete example, when optimizing the production schedule in a food factory, the program generates appropriate suggestions using prompts such as: "Analyze past production order history and quality control data, and propose the optimal production schedule for this week." This enables the efficient allocation of resources on the production floor.

[0105] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0106] Step 1:

[0107] The server automatically collects data from various digital information infrastructures through information gathering means. For example, it obtains necessary data from electronic communications, event schedule management, virtual meeting information, etc., via APIs. The input is data obtained via APIs, and the output is structured data stored on the server.

[0108] Step 2:

[0109] The server analyzes the collected data using a learning method. Natural language processing is performed using Python's NLTK and spaCy libraries to extract important keywords and information related to decision-making from the data. The input for this step is the data accumulated in step 1, and the output is the dataset of the analysis results.

[0110] Step 3:

[0111] The server uses a proposal generation mechanism to learn the user's past decision-making tendencies from the analyzed information and generates a proposal document based on the results. It utilizes a generation AI model to automatically create proposals tailored to the user. The input is the analysis results obtained in step 2, and the output is the generated proposal document.

[0112] Step 4:

[0113] The terminal displays the generated proposal document to the user via a display device. The user can review the proposal and modify or approve its contents. The input for this step is the proposal document generated in step 3, and the output is the document modified and approved by the user.

[0114] Step 5:

[0115] The server records the user's approval results via communication channels and notifies the necessary parties. The input is the document approved by the user in step 4, and the output is the approval result recorded in the database and the evidence that the notification was sent.

[0116] Step 6:

[0117] The server uses a plan generation means to generate proposals to optimize the production plan and transmits instructions to relevant equipment via a control means to efficiently execute the industrial process. The input is the approval result obtained in step 5, and the output is the optimized production plan and execution instructions.

[0118] 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.

[0119] This invention aims to improve the work efficiency of middle managers by incorporating an emotion engine that recognizes user emotions into an AI-powered system. This system collects and analyzes work data and learns the user's past decision-making and emotional patterns. It then generates proposal documents tailored to the emotional state and supports the approval process.

[0120] Specifically, the server first collects data from each platform via APIs, including email, calendar events, and online meetings. This data is also used by the emotion engine to analyze the emotional state the user displayed during communication.

[0121] The analyzed data is structured by the server and stored in a database. Natural language processing technology and sentiment analysis algorithms recognize the user's emotions from the acquired text and audio information. Based on these recognition results, a learning algorithm analyzes and learns the user's decision-making and emotional patterns.

[0122] Next, using these learned outcomes, the server generates a suggestion document based on the user's emotions. This suggestion document includes content that reflects past work history and emotional patterns, and is presented in a way that is most acceptable to the user.

[0123] The terminal presents the generated proposal document to the user. The interface can be customized to take into account the user's emotions and work situation, and is designed to be intuitive to use.

[0124] Once the user reviews the proposal and approves it, the terminal sends the result to the server. The server records this approval result in a database and incorporates it into the next business flow. The server then notifies relevant parties of the approved proposal, ensuring the smooth progress of the business process.

[0125] For example, if the server analyzes a user's voice tone and language expression during an online meeting and detects that the user is experiencing stress, it can generate and present a more considerate suggested document, thereby reducing the user's workload. By taking emotions into account in this way, more personalized responses become possible, improving overall work efficiency.

[0126] The following describes the processing flow.

[0127] Step 1:

[0128] The server automatically collects information from various digital platforms via APIs, including email, calendar events, and online meetings. This data collection centralizes information relevant to the user's work.

[0129] Step 2:

[0130] The server formats the collected data and stores it in a database as structured data. During this formatting process, natural language processing techniques are used to extract important information.

[0131] Step 3:

[0132] The server uses an emotion engine to analyze the user's emotional state from the content of online meetings and emails. Based on voice tone and linguistic expressions, it identifies emotions such as stress, fatigue, and satisfaction.

[0133] Step 4:

[0134] The server uses machine learning algorithms to learn from past decision-making history and analyzed sentiment data to identify the user's decision-making patterns. This identification allows it to predict which proposals are more likely to be accepted.

[0135] Step 5:

[0136] The server automatically generates the most suitable suggestion document based on learned thought patterns and emotions. This document takes into account the user's current emotional state and includes language that is easily accepted.

[0137] Step 6:

[0138] The terminal presents the generated proposal document to the user. The interface simplifies user operation and provides a customized, emotionally sensitive look as needed.

[0139] Step 7:

[0140] Users review the proposed document displayed on their device and, if satisfied with its content, press the approve button to approve it. They can also provide suggestions for revisions as needed.

[0141] Step 8:

[0142] The terminal sends user input and approval results to the server, where they are recorded in a database. This record can then be used for future data analysis and operational improvements.

[0143] Step 9:

[0144] The server sends notifications to relevant stakeholders based on approved proposals. This notification function facilitates the next workflow and improves the overall efficiency of the process.

[0145] (Example 2)

[0146] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0147] In many organizations, middle managers often find it difficult to make decisions in their daily work due to information overload and emotional fluctuations. This leads to decreased work efficiency and increased stress, ultimately resulting in a decline in overall organizational productivity.

[0148] 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.

[0149] In this invention, the server includes data collection means for acquiring data from various information processing infrastructures, learning means for analyzing the data to learn the past decision-making tendencies and emotional states of a specific user, and proposal generation means for automatically generating proposal documents based on the learned tendencies and emotional states. This enables improved work efficiency and increased accuracy of decision-making by providing optimal proposal documents that take into account the emotional states of middle managers.

[0150] "Various information processing infrastructures" refer to technological foundations for collecting and processing various types of data, including digital communications, time-managed events, and remote conferencing information.

[0151] "Data acquisition means" refers to functions and technologies for acquiring relevant digital data from information processing infrastructure.

[0152] A "learning tool" is a function that analyzes collected data to learn about a specific user's past decision-making tendencies and emotional state.

[0153] "Suggestion generation means" refers to functions and technologies for automatically generating suggestion documents to be provided to users based on learned trends and emotional states.

[0154] "Exchange method" refers to an interface or protocol for presenting a generated proposal document to a user and obtaining their approval.

[0155] "Communication means" refers to technologies and functions for recording approval results and notifying relevant parties of necessary information.

[0156] "Natural language processing" is a technology that enables computers to understand and generate human language.

[0157] "Emotional analysis" is a technology that identifies a person's emotional state from written or spoken information.

[0158] The embodiments for carrying out the present invention will be described in detail. This system is designed to collect and analyze data from an information processing infrastructure in order to understand the past decision-making tendencies and emotional states of a specific user.

[0159] The server retrieves digital communications, time-managed events, and remote meeting information via APIs from each platform. For example, it uses the email API to collect email content and sending / receiving history, and the calendar API to retrieve schedule data. Furthermore, it uses the meeting solution API to collect audio and chat logs from remote meetings. The data obtained in this way is structured on the server and stored in a database.

[0160] The server uses natural language processing (NLP) techniques and sentiment analysis algorithms to analyze the user's emotional state from the collected data. For example, it recognizes emotions from keywords and writing style in emails, and analyzes tone and speed from audio data during meetings to determine the user's stress level. This creates a more detailed personal profile, clarifying the user's emotions and decision-making tendencies.

[0161] Using the learned results, the server employs a generative AI model to create suggestion documents based on the user's emotional state and work history. Specifically, based on prompts such as "Please suggest the next steps to reduce the user's stress," the AI ​​model provides optimal suggestions. These generated suggestion documents are then presented to the user via a terminal to support their decision-making in their work. The interface is designed for intuitive operation, allowing users to easily review and approve the suggestions.

[0162] Finally, once the user approves the proposed document, the terminal sends the result to the server. The server records the approval in its database and incorporates it into the next workflow. Notifications are also sent to relevant parties, helping to ensure the smooth progress of the workflow.

[0163] This invention enables middle managers to process information accurately and efficiently and make emotion-based decisions, resulting in improved operational efficiency throughout the organization.

[0164] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0165] Step 1:

[0166] The server retrieves data from various information processing infrastructures. Specifically, it uses email APIs, calendar APIs, and meeting APIs to collect email content, time management events, and remote meeting information. The input data mainly consists of text data, date information, and audio data, which are formatted for structured purposes and stored in a database.

[0167] Step 2:

[0168] The server analyzes stored data using natural language processing techniques and sentiment analysis algorithms. It takes email and meeting speech data as input and determines the user's emotional state through text analysis. For example, it calculates an emotional score by identifying positive keywords and negative phrases. The output is evaluation data regarding the user's emotional state.

[0169] Step 3:

[0170] The server runs an algorithm that learns emotional states and past decision-making tendencies. The emotional evaluations obtained in step 2 and past work history data are used as input data. The learning algorithm models the user's decision-making patterns through trend analysis and applies them to decision-making in new tasks. The output is behavioral pattern analysis data that reflects the user's characteristics.

[0171] Step 4:

[0172] The server generates suggestion documents using an AI model based on the learning results. The AI ​​is given instructions such as "Please suggest the next steps to reduce user stress," taking into account sentiment evaluation, behavioral pattern analysis data, and work history data as input. The AI ​​model then creates and outputs the most suitable suggestion document. The output document includes suggestions that take sentiment into consideration.

[0173] Step 5:

[0174] The terminal presents the generated proposal document to the user. It receives the generated proposal document from the server as input and displays it in a visually and easily understandable format on the user interface. The user can intuitively manipulate this document, review its contents, and approve it.

[0175] Step 6:

[0176] When a user approves a proposal document, the terminal sends the result to the server. The server receives the approval data as input and records it in its database. Finally, it notifies relevant parties and incorporates the changes into the next business process. The output includes the approved proposal and updated information on the decision history.

[0177] (Application Example 2)

[0178] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0179] In modern work environments, workers' emotions and workloads are often overlooked, which can lead to decreased work efficiency. This is especially true in workplaces where concentration and precision are paramount, such as factories, where support that considers workers' emotions is essential. Traditional systems struggled to provide individualized suggestions and support based on workers' emotions in real time, resulting in decreased work efficiency.

[0180] 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.

[0181] In this invention, the server includes information gathering means for acquiring information from various information platforms, learning means for analyzing the information to learn the past judgment tendencies and emotional state of a specific worker, and suggestion generation means for automatically generating suggestion documents to support the worker based on the learned tendencies and emotional state. This enables the provision of appropriate suggestions based on the worker's emotions, thereby improving work efficiency.

[0182] "Information gathering means" refers to methods and devices for obtaining necessary information from various information platforms, and is capable of collecting diverse information such as audio data and document data.

[0183] A "learning tool" is a method or device for analyzing collected information and learning a specific worker's past judgment tendencies and emotional state.

[0184] A "suggestion generation means" is a method or apparatus that automatically generates suggestion documents to support workers based on learned tendencies and emotional states.

[0185] "Display means" refers to methods or devices for presenting the generated proposal document to the worker and receiving approval or feedback.

[0186] "Means of communication" refers to methods or devices for recording approval or feedback results and notifying relevant parties.

[0187] "Emotional analysis means" refers to methods or devices for analyzing a worker's voice information and evaluating their emotions.

[0188] A system for carrying out this invention includes information gathering means, learning means, suggestion generation means, display means, communication means, and sentiment analysis means. A server can integrate these means in a factory or other work environment to improve the work efficiency of workers.

[0189] The server first acquires information from various information platforms. This information is collected via APIs, and includes audio data, document data, and work schedules. The information is structured and stored in a database on the server.

[0190] As a learning tool, the server uses collected information to learn the worker's past decision-making tendencies and emotional state. Natural language processing technology and sentiment analysis algorithms are used to analyze emotions from the worker's words, actions, and voice.

[0191] The suggestion generation system generates suggestion documents to support workers based on learned trends and emotional states. It utilizes a generation AI model to generate optimal suggestions and display them to the worker.

[0192] The terminal displays the proposed document sent from the server to the worker. This allows the worker to review the proposal and take action as needed. Approvals or feedback from the terminal are sent to the server and notified to relevant parties through communication channels, thereby improving the business process.

[0193] The system has a function that analyzes emotions using the worker's voice information, allowing for real-time analysis of stress and other emotional states. For example, if the server analyzes the worker's voice tone during work and detects that the worker is experiencing stress, it can adjust the work speed or suggest auxiliary tasks to reduce the worker's burden.

[0194] An example of a prompt sentence to be used as input to a generative AI model is: "Please tell me how to design an AI system that analyzes voice data, identifies stress levels, and provides appropriate support to workers."

[0195] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0196] Step 1:

[0197] The server retrieves information from various information platforms via APIs. Inputs include audio data, document data, and work schedules, and this information is stored in a structured format in a database within the server.

[0198] Step 2:

[0199] The server analyzes the information to learn the worker's past decision-making tendencies and emotional state. The input is the data collected in step 1, and the data is processed using natural language processing technology and emotion analysis algorithms to output the worker's emotional pattern.

[0200] Step 3:

[0201] The server automatically generates suggestion documents to support the worker via a suggestion generation mechanism, based on learned trends and emotional situations. The input is the analysis result from step 2, and the generating AI model outputs the optimal suggestion content using prompt sentences.

[0202] Step 4:

[0203] The terminal displays the proposal document sent from the server to the worker. The input is the generated proposal document, which is output to the screen for easy confirmation by the worker.

[0204] Step 5:

[0205] The user reviews the proposal document displayed on the terminal and approves or provides feedback as needed. Input consists of the proposal document and the worker's judgment, while output is approval or feedback information.

[0206] Step 6:

[0207] The server records the approval or feedback results sent from the terminal and notifies the relevant parties. The input is the output of step 5, and this is used to reflect the changes in the business process using communication methods.

[0208] Step 7:

[0209] The server analyzes the worker's emotions in real time using their voice information. The input is real-time voice data, and the emotion analysis algorithm outputs stress and other emotional states. In this case, it is possible to use a generative AI model to suggest specific support.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] [Second Embodiment]

[0214] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0215] 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.

[0216] 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).

[0217] 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.

[0218] 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.

[0219] 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).

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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".

[0226] This invention is a system that improves the work efficiency of middle managers by utilizing a generative AI agent. In implementation, the server first collects data from multiple digital platforms accessed by the user, such as email services, scheduling tools, online meeting systems, spreadsheet software, and presentation tools. This data collection is automated via APIs, and new information is acquired periodically.

[0227] Next, the server processes the collected information, removing unnecessary data and formatting it. Here, natural language processing techniques are used to analyze the content of emails and meetings, extracting important information relevant to the business. This allows the data to be efficiently stored in a structured format within the database.

[0228] Subsequently, the server uses machine learning algorithms to learn the specific user's past decision-making patterns and approval tendencies. This learning allows it to predict under what conditions the user is most likely to approve.

[0229] Based on predicted thought patterns, the server generates a suggestion document. This document is automatically created using natural language processing and includes specific content and recommendations. At this stage, the suggestion document is adjusted to align with the user's past work style and recent activities.

[0230] The terminal presents the generated proposal document to the user through a user interface. The user can review the proposal content on the screen and add comments or make modifications if necessary. If the proposal is approved, the terminal sends the result to the server, which records the result in a database.

[0231] Finally, based on the approved proposal, the server sends notifications to the necessary stakeholders and proceeds with the next business process. In this way, each step works in conjunction to reduce the user's burden and streamline operations. As a concrete example, weekly meeting agendas can be automatically generated based on the user's past approval patterns, allowing users to review and approve the content, thus enabling rapid decision-making. This significantly reduces the workload of managers and speeds up the decision-making process.

[0232] The following describes the processing flow.

[0233] Step 1:

[0234] The server accesses various digital platforms via APIs and automatically collects data related to the user's work. This collected data includes emails, calendar events, and online meeting information.

[0235] Step 2:

[0236] The server analyzes the collected raw data. It uses natural language processing techniques to format the text data, remove noise, and extract important information. For example, it might extract meeting dates and agenda items from email text.

[0237] Step 3:

[0238] The server stores the analyzed data in a database. Simultaneously, it organizes the metadata associated with the data to enable efficient searching and access.

[0239] Step 4:

[0240] The server uses stored data to analyze the user's past decision-making and approval history using machine learning algorithms. This allows it to learn the user's unique thinking patterns and use that knowledge to predict future approval behaviors.

[0241] Step 5:

[0242] The server automatically generates suggestion documents based on learned thought patterns. The generation process ensures that specific suggestions and recommendations are incorporated into the documents based on previous data.

[0243] Step 6:

[0244] The terminal displays the generated proposal document in a user interface. The interface is designed to be intuitive for the user to operate, and it provides a means for reviewing and approving the proposal.

[0245] Step 7:

[0246] Users can review the presented proposal document and make revisions or comments as needed. They can formally approve the proposal by clicking the approve button.

[0247] Step 8:

[0248] The terminal sends the user's approval action to the server. The server records the approval result in detail and uses it as a trigger to execute the next processing step.

[0249] Step 9:

[0250] The server sends notifications to stakeholders based on approved proposals. These notifications provide information on the next steps to take and automatically advance the business process.

[0251] (Example 1)

[0252] 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."

[0253] With the rapid advancement of information technology, digital data from various information terminals is exploding. In business environments, particularly for middle managers, there is a need to quickly and accurately process the information necessary for effective decision-making. However, this data is diverse, and processing all of it alone requires a tremendous amount of time and effort. Furthermore, in today's world where speed of decision-making is paramount, information selection and proposal creation become bottlenecks, necessitating increased work efficiency. Solving this challenge is crucial for achieving both increased efficiency and reduced workload.

[0254] 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.

[0255] In this invention, the server includes an information gathering means for acquiring information from various information terminals, a learning means for analyzing the information and learning the past decision-making tendencies of a specific user, and a proposal generation means for generating proposal texts using natural language processing based on the learned tendencies. This enables integrated management and efficient processing of information, and facilitates the decision-making process through the rapid generation of proposal texts.

[0256] "Information gathering means" refers to methods for acquiring digital data such as electronic messages, schedule events, and online meeting information from various information terminals.

[0257] "Learning methods" refer to algorithms and methods used to analyze collected information and learn the past decision-making tendencies of a specific user.

[0258] A "proposal generation method" is a means of automatically generating a proposal text to present to the user using natural language processing based on learned information.

[0259] A "dialogue mechanism" is an interface for presenting the generated proposal to the user and obtaining their approval.

[0260] "Communication means" refers to a means that has the function of recording the approval results and notifying the relevant parties.

[0261] This invention is a system that utilizes a generating AI agent to improve the work efficiency of middle managers. Specific embodiments are described below.

[0262] The server automatically collects information from various information terminals. These terminals include email services, scheduling tools, and online meeting systems. For example, to obtain email information, data can be retrieved via APIs from Gmail and Outlook. Similarly, appropriate APIs are used to retrieve calendar events from Google Calendar and other scheduling services. Information collection is securely performed through an authentication process using OAuth 2.0.

[0263] Subsequently, the server uses machine learning tools such as TensorFlow and scikit-learn to organize the collected information and learn the decision-making patterns of specific users. This learning process allows it to analyze trends derived from past data and form a model to predict future decisions.

[0264] Furthermore, the server automatically generates suggestion texts using natural language processing technology. This technology utilizes software such as Google Cloud Natural Language API and Amazon Comprehend, which extract data and then formulate useful suggestions. The generated suggestion texts are then verified to be consistent with the user's past work style and recent activities.

[0265] The terminal presents this proposal through the user interface, allowing the user to review its contents. The user can then review the displayed proposal and add any necessary revisions or comments. For example, they can add an item to the generated meeting agenda.

[0266] Ultimately, based on the approved proposal, the server sends notifications to the relevant parties to ensure the smooth progress of the next business process. This reduces the burden on users and allows business processes to be carried out quickly and efficiently.

[0267] An example of a prompt might be, "Automatically generate an agenda for the next meeting and propose it, incorporating the content of past meetings." The system will receive this prompt, gather the appropriate information, and generate a proposal.

[0268] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0269] Step 1:

[0270] The server collects information from various information terminals. Input at this stage includes data from emails, calendar events, and online meetings. Specifically, it uses APIs from email services and scheduling tools to retrieve the latest information in JSON format. The output is the retrieved data stored in temporary storage.

[0271] Step 2:

[0272] The server analyzes the collected data. The input for this stage is the raw data collected in step 1. Here, a natural language processing engine is used to extract keywords from the text content of emails and meeting minutes and identify important information. The relevant data is structured, and only the information relevant to the business is cleansed and stored in the database.

[0273] Step 3:

[0274] The server learns the user's past decision-making tendencies through machine learning algorithms. The input for this stage comes from an analyzed database. Using tools such as TensorFlow, it analyzes past case studies and decision history to generate a predictive model. The output is a generated and updated model that reflects the user's decision-making patterns.

[0275] Step 4:

[0276] The server generates a proposal document based on the generated model. The input here is the decision-making model obtained through learning. Using natural language processing techniques, it creates a proposal document that aligns with the predicted user's desired work content. The proposal document is adjusted to match the user's past activity style. The final output is a completed proposal document presented to the user.

[0277] Step 5:

[0278] The terminal displays the proposal document generated by the server to the user. The input at this stage is the proposal document sent from the server. The user can review it on the screen and insert additional comments or make corrections as needed. The output is a reviewed or corrected version of the proposal.

[0279] Step 6:

[0280] Once the user approves the proposal, the terminal sends the result to the server. The input at this stage is the user's approval and comments. The server receives this and records the approved content in its database. The output is the recorded approval result and a notification sent to the relevant parties to proceed to the next step.

[0281] (Application Example 1)

[0282] 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."

[0283] In modern industrial product production management, it is essential to process diverse information quickly and accurately to maximize production efficiency. However, traditional methods heavily rely on human judgment, leading to wasted time and insufficient data utilization. Furthermore, they increase the burden on managers and decrease operational efficiency. Therefore, there is a need for systems that automatically collect and efficiently process various digital information to optimize production plans.

[0284] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following means.

[0285] In this invention, the server includes an information collection means, a learning means, and a proposal generation means. Thereby, it is possible to obtain necessary information from various digital information bases, learn the past decision-making tendencies, automatically generate proposals for optimizing the production plan, and enable the production manager to make a quick and optimal decision.

[0286] The "information collection means" is a device having a function of automatically acquiring information from various digital information bases and efficiently accumulating it.

[0287] The "learning means" is a device having a function of analyzing the acquired information and grasping / learning the past decision-making tendencies of a specific user.

[0288] The "proposal generation means" is a device having a function of automatically generating a proposal document based on the learned information and prompting the user to make an optimal decision.

[0289] The "display means" is a device that provides an interface for presenting the generated proposal document to the user and enabling the user to confirm / modify its content as needed.

[0290] The "communication means" is a communication facility and technology having a function of recording the approval result and notifying the necessary related parties.

[0291] The "plan generation means" is a device that generates a proposal for optimizing the production plan for producing industrial products and supports the decision-making of the administrator.

[0292] The "control means" is a device that uses the generated proposal to support the execution of the industrial process and performs operations to achieve production efficiency improvement.

[0293] A system for implementing this invention comprises information gathering means, learning means, proposal generation means, display means, communication means, plan generation means, and control means.

[0294] The server first automatically collects necessary data from various digital information infrastructures, such as electronic communications, event schedule management, and virtual meeting information, using information gathering tools. This utilizes data acquisition technologies via Amazon Web Services (AWS) services and APIs. The collected data is then analyzed using learning tools, and analytical processing is performed to understand past decision-making trends. Natural language processing is performed using Python's NLTK and spaCy libraries to extract important parts of the data.

[0295] The proposal generation system generates optimal proposal documents for the user based on organized information and learned data. Using a generation AI model, specific and highly relevant proposals are provided to the user.

[0296] The terminal presents the generated proposal document to the user via a display mechanism, allowing the user to review, modify, or approve it on the screen. This interface provides a user-friendly application environment developed using React Native.

[0297] The approval results are transmitted to the server via communication means and recorded in the database. Subsequently, the planning generation means automatically generates a production plan, and the control means efficiently executes the industrial process. This allows administrators to quickly and efficiently apply the production plan.

[0298] As a concrete example, when optimizing the production schedule in a food factory, the program generates appropriate suggestions using prompts such as: "Analyze past production order history and quality control data, and propose the optimal production schedule for this week." This enables the efficient allocation of resources on the production floor.

[0299] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0300] Step 1:

[0301] The server automatically collects data from various digital information bases through the information collection means. Here, for example, necessary data is obtained via an API from electronic communication, event schedule management, virtual meeting information, etc. The input is the data obtained via the API, and the output is the structured data accumulated on the server.

[0302] Step 2:

[0303] The server analyzes the collected data by means of learning. Natural language processing is performed using Python's NLTK and spaCy libraries to extract important keywords and information related to decision-making within the data. The input for this step is the data accumulated in Step 1, and the output is the dataset of the analysis results.

[0304] Step 3:

[0305] The server uses the proposal generation means to learn the user's past decision-making tendencies from the analyzed information and generates a proposal document based on the results. By leveraging the generation AI model, proposals suitable for the user are automatically created. The input is the analysis result obtained in Step 2, and the output is the generated proposal document.

[0306] Step 4:

[0307] The terminal presents the generated proposal document to the user via the display means. The user can check the proposal document and modify or approve its content. The input for this step is the proposal document generated in Step 3, and the output is the document modified / approved by the user.

[0308] Step 5:

[0309] The server records the user's approval results via communication channels and notifies the necessary parties. The input is the document approved by the user in step 4, and the output is the approval result recorded in the database and the evidence that the notification was sent.

[0310] Step 6:

[0311] The server uses a plan generation means to generate proposals to optimize the production plan and transmits instructions to relevant equipment via a control means to efficiently execute the industrial process. The input is the approval result obtained in step 5, and the output is the optimized production plan and execution instructions.

[0312] 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.

[0313] This invention aims to improve the work efficiency of middle managers by incorporating an emotion engine that recognizes user emotions into an AI-powered system. This system collects and analyzes work data and learns the user's past decision-making and emotional patterns. It then generates proposal documents tailored to the emotional state and supports the approval process.

[0314] Specifically, the server first collects data from each platform via APIs, including email, calendar events, and online meetings. This data is also used by the emotion engine to analyze the emotional state the user displayed during communication.

[0315] The analyzed data is structured by the server and stored in a database. Natural language processing technology and sentiment analysis algorithms recognize the user's emotions from the acquired text and audio information. Based on these recognition results, a learning algorithm analyzes and learns the user's decision-making and emotional patterns.

[0316] Next, using these learned outcomes, the server generates a suggestion document based on the user's emotions. This suggestion document includes content that reflects past work history and emotional patterns, and is presented in a way that is most acceptable to the user.

[0317] The terminal presents the generated proposal document to the user. The interface can be customized to take into account the user's emotions and work situation, and is designed to be intuitive to use.

[0318] Once the user reviews the proposal and approves it, the terminal sends the result to the server. The server records this approval result in a database and incorporates it into the next business flow. The server then notifies relevant parties of the approved proposal, ensuring the smooth progress of the business process.

[0319] For example, if the server analyzes a user's voice tone and language expression during an online meeting and detects that the user is experiencing stress, it can generate and present a more considerate suggested document, thereby reducing the user's workload. By taking emotions into account in this way, more personalized responses become possible, improving overall work efficiency.

[0320] The following describes the processing flow.

[0321] Step 1:

[0322] The server automatically collects information from various digital platforms via APIs, including email, calendar events, and online meetings. This data collection centralizes information relevant to the user's work.

[0323] Step 2:

[0324] The server formats the collected data and stores it in a database as structured data. During this formatting process, natural language processing techniques are used to extract important information.

[0325] Step 3:

[0326] The server uses an emotion engine to analyze the user's emotional state from the content of online meetings and emails. Based on voice tone and linguistic expressions, it identifies emotions such as stress, fatigue, and satisfaction.

[0327] Step 4:

[0328] The server uses machine learning algorithms to learn from past decision-making history and analyzed sentiment data to identify the user's decision-making patterns. This identification allows it to predict which proposals are more likely to be accepted.

[0329] Step 5:

[0330] The server automatically generates the most suitable suggestion document based on learned thought patterns and emotions. This document takes into account the user's current emotional state and includes language that is easily accepted.

[0331] Step 6:

[0332] The terminal presents the generated proposal document to the user. The interface simplifies user operation and provides a customized, emotionally sensitive look as needed.

[0333] Step 7:

[0334] Users review the proposed document displayed on their device and, if satisfied with its content, press the approve button to approve it. They can also provide suggestions for revisions as needed.

[0335] Step 8:

[0336] The terminal sends user input and approval results to the server, where they are recorded in a database. This record can then be used for future data analysis and operational improvements.

[0337] Step 9:

[0338] The server sends notifications to relevant stakeholders based on approved proposals. This notification function facilitates the next workflow and improves the overall efficiency of the process.

[0339] (Example 2)

[0340] 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".

[0341] In many organizations, middle managers often find it difficult to make decisions in their daily work due to information overload and emotional fluctuations. This leads to decreased work efficiency and increased stress, ultimately resulting in a decline in overall organizational productivity.

[0342] 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.

[0343] In this invention, the server includes data collection means for acquiring data from various information processing infrastructures, learning means for analyzing the data to learn the past decision-making tendencies and emotional states of a specific user, and proposal generation means for automatically generating proposal documents based on the learned tendencies and emotional states. This enables improved work efficiency and increased accuracy of decision-making by providing optimal proposal documents that take into account the emotional states of middle managers.

[0344] "Various information processing infrastructures" refer to technological foundations for collecting and processing various types of data, including digital communications, time-managed events, and remote conferencing information.

[0345] "Data acquisition means" refers to functions and technologies for acquiring relevant digital data from information processing infrastructure.

[0346] A "learning tool" is a function that analyzes collected data to learn about a specific user's past decision-making tendencies and emotional state.

[0347] "Suggestion generation means" refers to functions and technologies for automatically generating suggestion documents to be provided to users based on learned trends and emotional states.

[0348] "Exchange method" refers to an interface or protocol for presenting a generated proposal document to a user and obtaining their approval.

[0349] "Communication means" refers to technologies and functions for recording approval results and notifying relevant parties of necessary information.

[0350] "Natural language processing" is a technology that enables computers to understand and generate human language.

[0351] "Emotional analysis" is a technology that identifies a person's emotional state from written or spoken information.

[0352] The embodiments for carrying out the present invention will be described in detail. This system is designed to collect and analyze data from an information processing infrastructure in order to understand the past decision-making tendencies and emotional states of a specific user.

[0353] The server retrieves digital communications, time-managed events, and remote meeting information via APIs from each platform. For example, it uses the email API to collect email content and sending / receiving history, and the calendar API to retrieve schedule data. Furthermore, it uses the meeting solution API to collect audio and chat logs from remote meetings. The data obtained in this way is structured on the server and stored in a database.

[0354] The server uses natural language processing (NLP) techniques and sentiment analysis algorithms to analyze the user's emotional state from the collected data. For example, it recognizes emotions from keywords and writing style in emails, and analyzes tone and speed from audio data during meetings to determine the user's stress level. This creates a more detailed personal profile, clarifying the user's emotions and decision-making tendencies.

[0355] Using the learned results, the server employs a generative AI model to create suggestion documents based on the user's emotional state and work history. Specifically, based on prompts such as "Please suggest the next steps to reduce the user's stress," the AI ​​model provides optimal suggestions. These generated suggestion documents are then presented to the user via a terminal to support their decision-making in their work. The interface is designed for intuitive operation, allowing users to easily review and approve the suggestions.

[0356] Finally, once the user approves the proposed document, the terminal sends the result to the server. The server records the approval in its database and incorporates it into the next workflow. Notifications are also sent to relevant parties, helping to ensure the smooth progress of the workflow.

[0357] This invention enables middle managers to process information accurately and efficiently and make emotion-based decisions, resulting in improved operational efficiency throughout the organization.

[0358] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0359] Step 1:

[0360] The server retrieves data from various information processing infrastructures. Specifically, it uses email APIs, calendar APIs, and meeting APIs to collect email content, time management events, and remote meeting information. The input data mainly consists of text data, date information, and audio data, which are formatted for structured purposes and stored in a database.

[0361] Step 2:

[0362] The server analyzes stored data using natural language processing techniques and sentiment analysis algorithms. It takes email and meeting speech data as input and determines the user's emotional state through text analysis. For example, it calculates an emotional score by identifying positive keywords and negative phrases. The output is evaluation data regarding the user's emotional state.

[0363] Step 3:

[0364] The server runs an algorithm that learns emotional states and past decision-making tendencies. The emotional evaluations obtained in step 2 and past work history data are used as input data. The learning algorithm models the user's decision-making patterns through trend analysis and applies them to decision-making in new tasks. The output is behavioral pattern analysis data that reflects the user's characteristics.

[0365] Step 4:

[0366] The server generates suggestion documents using an AI model based on the learning results. The AI ​​is given instructions such as "Please suggest the next steps to reduce user stress," taking into account sentiment evaluation, behavioral pattern analysis data, and work history data as input. The AI ​​model then creates and outputs the most suitable suggestion document. The output document includes suggestions that take sentiment into consideration.

[0367] Step 5:

[0368] The terminal presents the generated proposal document to the user. It receives the generated proposal document from the server as input and displays it in a visually and easily understandable format on the user interface. The user can intuitively manipulate this document, review its contents, and approve it.

[0369] Step 6:

[0370] When a user approves a proposal document, the terminal sends the result to the server. The server receives the approval data as input and records it in its database. Finally, it notifies relevant parties and incorporates the changes into the next business process. The output includes the approved proposal and updated information on the decision history.

[0371] (Application Example 2)

[0372] 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."

[0373] In modern work environments, workers' emotions and workloads are often overlooked, which can lead to decreased work efficiency. This is especially true in workplaces where concentration and precision are paramount, such as factories, where support that considers workers' emotions is essential. Traditional systems struggled to provide individualized suggestions and support based on workers' emotions in real time, resulting in decreased work efficiency.

[0374] 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.

[0375] In this invention, the server includes information gathering means for acquiring information from various information platforms, learning means for analyzing the information to learn the past judgment tendencies and emotional state of a specific worker, and suggestion generation means for automatically generating suggestion documents to support the worker based on the learned tendencies and emotional state. This enables the provision of appropriate suggestions based on the worker's emotions, thereby improving work efficiency.

[0376] "Information gathering means" refers to methods and devices for obtaining necessary information from various information platforms, and is capable of collecting diverse information such as audio data and document data.

[0377] A "learning tool" is a method or device for analyzing collected information and learning a specific worker's past judgment tendencies and emotional state.

[0378] A "suggestion generation means" is a method or apparatus that automatically generates suggestion documents to support workers based on learned tendencies and emotional states.

[0379] "Display means" refers to methods or devices for presenting the generated proposal document to the worker and receiving approval or feedback.

[0380] "Means of communication" refers to methods or devices for recording approval or feedback results and notifying relevant parties.

[0381] "Emotional analysis means" refers to methods or devices for analyzing a worker's voice information and evaluating their emotions.

[0382] A system for carrying out this invention includes information gathering means, learning means, suggestion generation means, display means, communication means, and sentiment analysis means. A server can integrate these means in a factory or other work environment to improve the work efficiency of workers.

[0383] The server first acquires information from various information platforms. This information is collected via APIs, and includes audio data, document data, and work schedules. The information is structured and stored in a database on the server.

[0384] As a learning tool, the server uses collected information to learn the worker's past decision-making tendencies and emotional state. Natural language processing technology and sentiment analysis algorithms are used to analyze emotions from the worker's words, actions, and voice.

[0385] The suggestion generation system generates suggestion documents to support workers based on learned trends and emotional states. It utilizes a generation AI model to generate optimal suggestions and display them to the worker.

[0386] The terminal displays the proposed document sent from the server to the worker. This allows the worker to review the proposal and take action as needed. Approvals or feedback from the terminal are sent to the server and notified to relevant parties through communication channels, thereby improving the business process.

[0387] The system has a function that analyzes emotions using the worker's voice information, allowing for real-time analysis of stress and other emotional states. For example, if the server analyzes the worker's voice tone during work and detects that the worker is experiencing stress, it can adjust the work speed or suggest auxiliary tasks to reduce the worker's burden.

[0388] An example of a prompt sentence to be used as input to a generative AI model is: "Please tell me how to design an AI system that analyzes voice data, identifies stress levels, and provides appropriate support to workers."

[0389] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0390] Step 1:

[0391] The server retrieves information from various information platforms via APIs. Inputs include audio data, document data, and work schedules, and this information is stored in a structured format in a database within the server.

[0392] Step 2:

[0393] The server analyzes the information to learn the worker's past decision-making tendencies and emotional state. The input is the data collected in step 1, and the data is processed using natural language processing technology and emotion analysis algorithms to output the worker's emotional pattern.

[0394] Step 3:

[0395] The server automatically generates suggestion documents to support the worker via a suggestion generation mechanism, based on learned trends and emotional situations. The input is the analysis result from step 2, and the generating AI model outputs the optimal suggestion content using prompt sentences.

[0396] Step 4:

[0397] The terminal displays the proposal document sent from the server to the worker. The input is the generated proposal document, which is output to the screen for easy confirmation by the worker.

[0398] Step 5:

[0399] The user reviews the proposal document displayed on the terminal and approves or provides feedback as needed. Input consists of the proposal document and the worker's judgment, while output is approval or feedback information.

[0400] Step 6:

[0401] The server records the approval or feedback results sent from the terminal and notifies the relevant parties. The input is the output of step 5, and this is used to reflect the changes in the business process using communication methods.

[0402] Step 7:

[0403] The server analyzes the worker's emotions in real time using their voice information. The input is real-time voice data, and the emotion analysis algorithm outputs stress and other emotional states. In this case, it is possible to use a generative AI model to suggest specific support.

[0404] 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.

[0405] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0406] 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.

[0407] [Third Embodiment]

[0408] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0409] 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.

[0410] 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).

[0411] 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.

[0412] 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.

[0413] 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).

[0414] 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.

[0415] 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.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] 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".

[0420] This invention is a system that improves the work efficiency of middle managers by utilizing a generative AI agent. In implementation, the server first collects data from multiple digital platforms accessed by the user, such as email services, scheduling tools, online meeting systems, spreadsheet software, and presentation tools. This data collection is automated via APIs, and new information is acquired periodically.

[0421] Next, the server processes the collected information, removing unnecessary data and formatting it. Here, natural language processing techniques are used to analyze the content of emails and meetings, extracting important information relevant to the business. This allows the data to be efficiently stored in a structured format within the database.

[0422] Subsequently, the server uses machine learning algorithms to learn the specific user's past decision-making patterns and approval tendencies. This learning allows it to predict under what conditions the user is most likely to approve.

[0423] Based on predicted thought patterns, the server generates a suggestion document. This document is automatically created using natural language processing and includes specific content and recommendations. At this stage, the suggestion document is adjusted to align with the user's past work style and recent activities.

[0424] The terminal presents the generated proposal document to the user through a user interface. The user can review the proposal content on the screen and add comments or make modifications if necessary. If the proposal is approved, the terminal sends the result to the server, which records the result in a database.

[0425] Finally, based on the approved proposal, the server sends notifications to the necessary stakeholders and proceeds with the next business process. In this way, each step works in conjunction to reduce the user's burden and streamline operations. As a concrete example, weekly meeting agendas can be automatically generated based on the user's past approval patterns, allowing users to review and approve the content, thus enabling rapid decision-making. This significantly reduces the workload of managers and speeds up the decision-making process.

[0426] The following describes the processing flow.

[0427] Step 1:

[0428] The server accesses various digital platforms via APIs and automatically collects data related to the user's work. This collected data includes emails, calendar events, and online meeting information.

[0429] Step 2:

[0430] The server analyzes the collected raw data. It uses natural language processing techniques to format the text data, remove noise, and extract important information. For example, it might extract meeting dates and agenda items from email text.

[0431] Step 3:

[0432] The server stores the analyzed data in a database. Simultaneously, it organizes the metadata associated with the data to enable efficient searching and access.

[0433] Step 4:

[0434] The server uses stored data to analyze the user's past decision-making and approval history using machine learning algorithms. This allows it to learn the user's unique thinking patterns and use that knowledge to predict future approval behaviors.

[0435] Step 5:

[0436] The server automatically generates suggestion documents based on learned thought patterns. The generation process ensures that specific suggestions and recommendations are incorporated into the documents based on previous data.

[0437] Step 6:

[0438] The terminal displays the generated proposal document in a user interface. The interface is designed to be intuitive for the user to operate, and it provides a means for reviewing and approving the proposal.

[0439] Step 7:

[0440] Users can review the presented proposal document and make revisions or comments as needed. They can formally approve the proposal by clicking the approve button.

[0441] Step 8:

[0442] The terminal sends the user's approval action to the server. The server records the approval result in detail and uses it as a trigger to execute the next processing step.

[0443] Step 9:

[0444] The server sends notifications to stakeholders based on approved proposals. These notifications provide information on the next steps to take and automatically advance the business process.

[0445] (Example 1)

[0446] 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."

[0447] With the rapid advancement of information technology, digital data from various information terminals is exploding. In business environments, particularly for middle managers, there is a need to quickly and accurately process the information necessary for effective decision-making. However, this data is diverse, and processing all of it alone requires a tremendous amount of time and effort. Furthermore, in today's world where speed of decision-making is paramount, information selection and proposal creation become bottlenecks, necessitating increased work efficiency. Solving this challenge is crucial for achieving both increased efficiency and reduced workload.

[0448] 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.

[0449] In this invention, the server includes an information gathering means for acquiring information from various information terminals, a learning means for analyzing the information and learning the past decision-making tendencies of a specific user, and a proposal generation means for generating proposal texts using natural language processing based on the learned tendencies. This enables integrated management and efficient processing of information, and facilitates the decision-making process through the rapid generation of proposal texts.

[0450] "Information gathering means" refers to methods for acquiring digital data such as electronic messages, schedule events, and online meeting information from various information terminals.

[0451] "Learning methods" refer to algorithms and methods used to analyze collected information and learn the past decision-making tendencies of a specific user.

[0452] A "proposal generation method" is a means of automatically generating a proposal text to present to the user using natural language processing based on learned information.

[0453] A "dialogue mechanism" is an interface for presenting the generated proposal to the user and obtaining their approval.

[0454] "Communication means" refers to a means that has the function of recording the approval results and notifying the relevant parties.

[0455] This invention is a system that utilizes a generating AI agent to improve the work efficiency of middle managers. Specific embodiments are described below.

[0456] The server automatically collects information from various information terminals. These terminals include email services, scheduling tools, and online meeting systems. For example, to obtain email information, data can be retrieved via APIs from Gmail and Outlook. Similarly, appropriate APIs are used to retrieve calendar events from Google Calendar and other scheduling services. Information collection is securely performed through an authentication process using OAuth 2.0.

[0457] Subsequently, the server uses machine learning tools such as TensorFlow and scikit-learn to organize the collected information and learn the decision-making patterns of specific users. This learning process allows it to analyze trends derived from past data and form a model to predict future decisions.

[0458] Furthermore, the server automatically generates suggestion texts using natural language processing technology. This technology utilizes software such as Google Cloud Natural Language API and Amazon Comprehend, which extract data and then formulate useful suggestions. The generated suggestion texts are then verified to be consistent with the user's past work style and recent activities.

[0459] The terminal presents this proposal through the user interface, allowing the user to review its contents. The user can then review the displayed proposal and add any necessary revisions or comments. For example, they can add an item to the generated meeting agenda.

[0460] Ultimately, based on the approved proposal, the server sends notifications to the relevant parties to ensure the smooth progress of the next business process. This reduces the burden on users and allows business processes to be carried out quickly and efficiently.

[0461] An example of a prompt might be, "Automatically generate an agenda for the next meeting and propose it, incorporating the content of past meetings." The system will receive this prompt, gather the appropriate information, and generate a proposal.

[0462] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0463] Step 1:

[0464] The server collects information from various information terminals. Input at this stage includes data from emails, calendar events, and online meetings. Specifically, it uses APIs from email services and scheduling tools to retrieve the latest information in JSON format. The output is the retrieved data stored in temporary storage.

[0465] Step 2:

[0466] The server analyzes the collected data. The input for this stage is the raw data collected in step 1. Here, a natural language processing engine is used to extract keywords from the text content of emails and meeting minutes and identify important information. The relevant data is structured, and only the information relevant to the business is cleansed and stored in the database.

[0467] Step 3:

[0468] The server learns the user's past decision-making tendencies through machine learning algorithms. The input for this stage comes from an analyzed database. Using tools such as TensorFlow, it analyzes past case studies and decision history to generate a predictive model. The output is a generated and updated model that reflects the user's decision-making patterns.

[0469] Step 4:

[0470] The server generates a proposal document based on the generated model. The input here is the decision-making model obtained through learning. Using natural language processing techniques, it creates a proposal document that aligns with the predicted user's desired work content. The proposal document is adjusted to match the user's past activity style. The final output is a completed proposal document presented to the user.

[0471] Step 5:

[0472] The terminal displays the proposal document generated by the server to the user. The input at this stage is the proposal document sent from the server. The user can review it on the screen and insert additional comments or make corrections as needed. The output is a reviewed or corrected version of the proposal.

[0473] Step 6:

[0474] Once the user approves the proposal, the terminal sends the result to the server. The input at this stage is the user's approval and comments. The server receives this and records the approved content in its database. The output is the recorded approval result and a notification sent to the relevant parties to proceed to the next step.

[0475] (Application Example 1)

[0476] 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."

[0477] In modern industrial product production management, it is essential to process diverse information quickly and accurately to maximize production efficiency. However, traditional methods heavily rely on human judgment, leading to wasted time and insufficient data utilization. Furthermore, they increase the burden on managers and decrease operational efficiency. Therefore, there is a need for systems that automatically collect and efficiently process various digital information to optimize production plans.

[0478] 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.

[0479] In this invention, the server includes an information gathering means, a learning means, and a proposal generation means. This allows the server to acquire necessary information from various digital information infrastructures and learn past decision-making trends, thereby automatically generating proposals to optimize production plans, enabling production managers to make optimal decisions quickly.

[0480] An "information gathering device" is a device that has the function of automatically acquiring information from various digital information infrastructures and efficiently storing it.

[0481] A "learning tool" is a device that analyzes acquired information and has the function of understanding and learning the past decision-making tendencies of a specific user.

[0482] A "proposal generation device" is a device that automatically generates proposal documents based on learned information and has the function of encouraging users to make optimal decisions.

[0483] A "display means" is a device that presents the generated proposal document to the user and provides an interface that allows the user to review and modify its contents as needed.

[0484] "Communication means" refers to communication equipment and technology that have the function of recording approval results and notifying the necessary parties.

[0485] A "plan generation device" is a device that generates proposals to optimize production plans for manufacturing industrial products, thereby supporting the decision-making of managers.

[0486] A "control device" is a device that uses generated suggestions to support the execution of industrial processes and performs operations to improve production efficiency.

[0487] A system for implementing this invention comprises information gathering means, learning means, proposal generation means, display means, communication means, plan generation means, and control means.

[0488] The server first automatically collects necessary data from various digital information infrastructures, such as electronic communications, event schedule management, and virtual meeting information, using information gathering tools. This utilizes data acquisition technologies via Amazon Web Services (AWS) services and APIs. The collected data is then analyzed using learning tools, and analytical processing is performed to understand past decision-making trends. Natural language processing is performed using Python's NLTK and spaCy libraries to extract important parts of the data.

[0489] The proposal generation system generates optimal proposal documents for the user based on organized information and learned data. Using a generation AI model, specific and highly relevant proposals are provided to the user.

[0490] The terminal presents the generated proposal document to the user via a display mechanism, allowing the user to review, modify, or approve it on the screen. This interface provides a user-friendly application environment developed using React Native.

[0491] The approval results are transmitted to the server via communication means and recorded in the database. Subsequently, the planning generation means automatically generates a production plan, and the control means efficiently executes the industrial process. This allows administrators to quickly and efficiently apply the production plan.

[0492] As a concrete example, when optimizing the production schedule in a food factory, the program generates appropriate suggestions using prompts such as: "Analyze past production order history and quality control data, and propose the optimal production schedule for this week." This enables the efficient allocation of resources on the production floor.

[0493] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0494] Step 1:

[0495] The server automatically collects data from various digital information infrastructures through information gathering means. For example, it obtains necessary data from electronic communications, event schedule management, virtual meeting information, etc., via APIs. The input is data obtained via APIs, and the output is structured data stored on the server.

[0496] Step 2:

[0497] The server analyzes the collected data using a learning method. Natural language processing is performed using Python's NLTK and spaCy libraries to extract important keywords and information related to decision-making from the data. The input for this step is the data accumulated in step 1, and the output is the dataset of the analysis results.

[0498] Step 3:

[0499] The server uses a proposal generation mechanism to learn the user's past decision-making tendencies from the analyzed information and generates a proposal document based on the results. It utilizes a generation AI model to automatically create proposals tailored to the user. The input is the analysis results obtained in step 2, and the output is the generated proposal document.

[0500] Step 4:

[0501] The terminal displays the generated proposal document to the user via a display device. The user can review the proposal and modify or approve its contents. The input for this step is the proposal document generated in step 3, and the output is the document modified and approved by the user.

[0502] Step 5:

[0503] The server records the user's approval results via communication channels and notifies the necessary parties. The input is the document approved by the user in step 4, and the output is the approval result recorded in the database and the evidence that the notification was sent.

[0504] Step 6:

[0505] The server uses a plan generation means to generate proposals to optimize the production plan and transmits instructions to relevant equipment via a control means to efficiently execute the industrial process. The input is the approval result obtained in step 5, and the output is the optimized production plan and execution instructions.

[0506] 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.

[0507] This invention aims to improve the work efficiency of middle managers by incorporating an emotion engine that recognizes user emotions into an AI-powered system. This system collects and analyzes work data and learns the user's past decision-making and emotional patterns. It then generates proposal documents tailored to the emotional state and supports the approval process.

[0508] Specifically, the server first collects data from each platform via APIs, including email, calendar events, and online meetings. This data is also used by the emotion engine to analyze the emotional state the user displayed during communication.

[0509] The analyzed data is structured by the server and stored in a database. Natural language processing technology and sentiment analysis algorithms recognize the user's emotions from the acquired text and audio information. Based on these recognition results, a learning algorithm analyzes and learns the user's decision-making and emotional patterns.

[0510] Next, using these learned outcomes, the server generates a suggestion document based on the user's emotions. This suggestion document includes content that reflects past work history and emotional patterns, and is presented in a way that is most acceptable to the user.

[0511] The terminal presents the generated proposal document to the user. The interface can be customized to take into account the user's emotions and work situation, and is designed to be intuitive to use.

[0512] Once the user reviews the proposal and approves it, the terminal sends the result to the server. The server records this approval result in a database and incorporates it into the next business flow. The server then notifies relevant parties of the approved proposal, ensuring the smooth progress of the business process.

[0513] For example, if the server analyzes a user's voice tone and language expression during an online meeting and detects that the user is experiencing stress, it can generate and present a more considerate suggested document, thereby reducing the user's workload. By taking emotions into account in this way, more personalized responses become possible, improving overall work efficiency.

[0514] The following describes the processing flow.

[0515] Step 1:

[0516] The server automatically collects information from various digital platforms via APIs, including email, calendar events, and online meetings. This data collection centralizes information relevant to the user's work.

[0517] Step 2:

[0518] The server formats the collected data and stores it in a database as structured data. During this formatting process, natural language processing techniques are used to extract important information.

[0519] Step 3:

[0520] The server uses an emotion engine to analyze the user's emotional state from the content of online meetings and emails. Based on voice tone and linguistic expressions, it identifies emotions such as stress, fatigue, and satisfaction.

[0521] Step 4:

[0522] The server uses machine learning algorithms to learn from past decision-making history and analyzed sentiment data to identify the user's decision-making patterns. This identification allows it to predict which proposals are more likely to be accepted.

[0523] Step 5:

[0524] The server automatically generates the most suitable suggestion document based on learned thought patterns and emotions. This document takes into account the user's current emotional state and includes language that is easily accepted.

[0525] Step 6:

[0526] The terminal presents the generated proposal document to the user. The interface simplifies user operation and provides a customized, emotionally sensitive look as needed.

[0527] Step 7:

[0528] Users review the proposed document displayed on their device and, if satisfied with its content, press the approve button to approve it. They can also provide suggestions for revisions as needed.

[0529] Step 8:

[0530] The terminal sends user input and approval results to the server, where they are recorded in a database. This record can then be used for future data analysis and operational improvements.

[0531] Step 9:

[0532] The server sends notifications to relevant stakeholders based on approved proposals. This notification function facilitates the next workflow and improves the overall efficiency of the process.

[0533] (Example 2)

[0534] 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."

[0535] In many organizations, middle managers often find it difficult to make decisions in their daily work due to information overload and emotional fluctuations. This leads to decreased work efficiency and increased stress, ultimately resulting in a decline in overall organizational productivity.

[0536] 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.

[0537] In this invention, the server includes data collection means for acquiring data from various information processing infrastructures, learning means for analyzing the data to learn the past decision-making tendencies and emotional states of a specific user, and proposal generation means for automatically generating proposal documents based on the learned tendencies and emotional states. This enables improved work efficiency and increased accuracy of decision-making by providing optimal proposal documents that take into account the emotional states of middle managers.

[0538] "Various information processing infrastructures" refer to technological foundations for collecting and processing various types of data, including digital communications, time-managed events, and remote conferencing information.

[0539] "Data acquisition means" refers to functions and technologies for acquiring relevant digital data from information processing infrastructure.

[0540] A "learning tool" is a function that analyzes collected data to learn about a specific user's past decision-making tendencies and emotional state.

[0541] "Suggestion generation means" refers to functions and technologies for automatically generating suggestion documents to be provided to users based on learned trends and emotional states.

[0542] "Exchange method" refers to an interface or protocol for presenting a generated proposal document to a user and obtaining their approval.

[0543] "Communication means" refers to technologies and functions for recording approval results and notifying relevant parties of necessary information.

[0544] "Natural language processing" is a technology that enables computers to understand and generate human language.

[0545] "Emotional analysis" is a technology that identifies a person's emotional state from written or spoken information.

[0546] The embodiments for carrying out the present invention will be described in detail. This system is designed to collect and analyze data from an information processing infrastructure in order to understand the past decision-making tendencies and emotional states of a specific user.

[0547] The server retrieves digital communications, time-managed events, and remote meeting information via APIs from each platform. For example, it uses the email API to collect email content and sending / receiving history, and the calendar API to retrieve schedule data. Furthermore, it uses the meeting solution API to collect audio and chat logs from remote meetings. The data obtained in this way is structured on the server and stored in a database.

[0548] The server uses natural language processing (NLP) techniques and sentiment analysis algorithms to analyze the user's emotional state from the collected data. For example, it recognizes emotions from keywords and writing style in emails, and analyzes tone and speed from audio data during meetings to determine the user's stress level. This creates a more detailed personal profile, clarifying the user's emotions and decision-making tendencies.

[0549] Using the learned results, the server employs a generative AI model to create suggestion documents based on the user's emotional state and work history. Specifically, based on prompts such as "Please suggest the next steps to reduce the user's stress," the AI ​​model provides optimal suggestions. These generated suggestion documents are then presented to the user via a terminal to support their decision-making in their work. The interface is designed for intuitive operation, allowing users to easily review and approve the suggestions.

[0550] Finally, once the user approves the proposed document, the terminal sends the result to the server. The server records the approval in its database and incorporates it into the next workflow. Notifications are also sent to relevant parties, helping to ensure the smooth progress of the workflow.

[0551] This invention enables middle managers to process information accurately and efficiently and make emotion-based decisions, resulting in improved operational efficiency throughout the organization.

[0552] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0553] Step 1:

[0554] The server retrieves data from various information processing infrastructures. Specifically, it uses email APIs, calendar APIs, and meeting APIs to collect email content, time management events, and remote meeting information. The input data mainly consists of text data, date information, and audio data, which are formatted for structured purposes and stored in a database.

[0555] Step 2:

[0556] The server analyzes stored data using natural language processing techniques and sentiment analysis algorithms. It takes email and meeting speech data as input and determines the user's emotional state through text analysis. For example, it calculates an emotional score by identifying positive keywords and negative phrases. The output is evaluation data regarding the user's emotional state.

[0557] Step 3:

[0558] The server runs an algorithm that learns emotional states and past decision-making tendencies. The emotional evaluations obtained in step 2 and past work history data are used as input data. The learning algorithm models the user's decision-making patterns through trend analysis and applies them to decision-making in new tasks. The output is behavioral pattern analysis data that reflects the user's characteristics.

[0559] Step 4:

[0560] The server generates suggestion documents using an AI model based on the learning results. The AI ​​is given instructions such as "Please suggest the next steps to reduce user stress," taking into account sentiment evaluation, behavioral pattern analysis data, and work history data as input. The AI ​​model then creates and outputs the most suitable suggestion document. The output document includes suggestions that take sentiment into consideration.

[0561] Step 5:

[0562] The terminal presents the generated proposal document to the user. It receives the generated proposal document from the server as input and displays it in a visually and easily understandable format on the user interface. The user can intuitively manipulate this document, review its contents, and approve it.

[0563] Step 6:

[0564] When a user approves a proposal document, the terminal sends the result to the server. The server receives the approval data as input and records it in its database. Finally, it notifies relevant parties and incorporates the changes into the next business process. The output includes the approved proposal and updated information on the decision history.

[0565] (Application Example 2)

[0566] 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."

[0567] In modern work environments, workers' emotions and workloads are often overlooked, which can lead to decreased work efficiency. This is especially true in workplaces where concentration and precision are paramount, such as factories, where support that considers workers' emotions is essential. Traditional systems struggled to provide individualized suggestions and support based on workers' emotions in real time, resulting in decreased work efficiency.

[0568] 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.

[0569] In this invention, the server includes information gathering means for acquiring information from various information platforms, learning means for analyzing the information to learn the past judgment tendencies and emotional state of a specific worker, and suggestion generation means for automatically generating suggestion documents to support the worker based on the learned tendencies and emotional state. This enables the provision of appropriate suggestions based on the worker's emotions, thereby improving work efficiency.

[0570] "Information gathering means" refers to methods and devices for obtaining necessary information from various information platforms, and is capable of collecting diverse information such as audio data and document data.

[0571] A "learning tool" is a method or device for analyzing collected information and learning a specific worker's past judgment tendencies and emotional state.

[0572] A "suggestion generation means" is a method or apparatus that automatically generates suggestion documents to support workers based on learned tendencies and emotional states.

[0573] "Display means" refers to methods or devices for presenting the generated proposal document to the worker and receiving approval or feedback.

[0574] "Means of communication" refers to methods or devices for recording approval or feedback results and notifying relevant parties.

[0575] "Emotional analysis means" refers to methods or devices for analyzing a worker's voice information and evaluating their emotions.

[0576] A system for carrying out this invention includes information gathering means, learning means, suggestion generation means, display means, communication means, and sentiment analysis means. A server can integrate these means in a factory or other work environment to improve the work efficiency of workers.

[0577] The server first acquires information from various information platforms. This information is collected via APIs, and includes audio data, document data, and work schedules. The information is structured and stored in a database on the server.

[0578] As a learning tool, the server uses collected information to learn the worker's past decision-making tendencies and emotional state. Natural language processing technology and sentiment analysis algorithms are used to analyze emotions from the worker's words, actions, and voice.

[0579] The suggestion generation system generates suggestion documents to support workers based on learned trends and emotional states. It utilizes a generation AI model to generate optimal suggestions and display them to the worker.

[0580] The terminal displays the proposed document sent from the server to the worker. This allows the worker to review the proposal and take action as needed. Approvals or feedback from the terminal are sent to the server and notified to relevant parties through communication channels, thereby improving the business process.

[0581] The system has a function that analyzes emotions using the worker's voice information, allowing for real-time analysis of stress and other emotional states. For example, if the server analyzes the worker's voice tone during work and detects that the worker is experiencing stress, it can adjust the work speed or suggest auxiliary tasks to reduce the worker's burden.

[0582] An example of a prompt sentence to be used as input to a generative AI model is: "Please tell me how to design an AI system that analyzes voice data, identifies stress levels, and provides appropriate support to workers."

[0583] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0584] Step 1:

[0585] The server retrieves information from various information platforms via APIs. Inputs include audio data, document data, and work schedules, and this information is stored in a structured format in a database within the server.

[0586] Step 2:

[0587] The server analyzes the information to learn the worker's past decision-making tendencies and emotional state. The input is the data collected in step 1, and the data is processed using natural language processing technology and emotion analysis algorithms to output the worker's emotional pattern.

[0588] Step 3:

[0589] The server automatically generates suggestion documents to support the worker via a suggestion generation mechanism, based on learned trends and emotional situations. The input is the analysis result from step 2, and the generating AI model outputs the optimal suggestion content using prompt sentences.

[0590] Step 4:

[0591] The terminal displays the proposal document sent from the server to the worker. The input is the generated proposal document, which is output to the screen for easy confirmation by the worker.

[0592] Step 5:

[0593] The user reviews the proposal document displayed on the terminal and approves or provides feedback as needed. Input consists of the proposal document and the worker's judgment, while output is approval or feedback information.

[0594] Step 6:

[0595] The server records the approval or feedback results sent from the terminal and notifies the relevant parties. The input is the output of step 5, and this is used to reflect the changes in the business process using communication methods.

[0596] Step 7:

[0597] The server analyzes the worker's emotions in real time using their voice information. The input is real-time voice data, and the emotion analysis algorithm outputs stress and other emotional states. In this case, it is possible to use a generative AI model to suggest specific support.

[0598] 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.

[0599] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0600] 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.

[0601] [Fourth Embodiment]

[0602] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0603] 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.

[0604] 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).

[0605] 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.

[0606] 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.

[0607] 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).

[0608] 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.

[0609] 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.

[0610] 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.

[0611] 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.

[0612] 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.

[0613] 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.

[0614] 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".

[0615] This invention is a system that improves the work efficiency of middle managers by utilizing a generative AI agent. In implementation, the server first collects data from multiple digital platforms accessed by the user, such as email services, scheduling tools, online meeting systems, spreadsheet software, and presentation tools. This data collection is automated via APIs, and new information is acquired periodically.

[0616] Next, the server processes the collected information, removing unnecessary data and formatting it. Here, natural language processing techniques are used to analyze the content of emails and meetings, extracting important information relevant to the business. This allows the data to be efficiently stored in a structured format within the database.

[0617] Subsequently, the server uses machine learning algorithms to learn the specific user's past decision-making patterns and approval tendencies. This learning allows it to predict under what conditions the user is most likely to approve.

[0618] Based on predicted thought patterns, the server generates a suggestion document. This document is automatically created using natural language processing and includes specific content and recommendations. At this stage, the suggestion document is adjusted to align with the user's past work style and recent activities.

[0619] The terminal presents the generated proposal document to the user through a user interface. The user can review the proposal content on the screen and add comments or make modifications if necessary. If the proposal is approved, the terminal sends the result to the server, which records the result in a database.

[0620] Finally, based on the approved proposal, the server sends notifications to the necessary stakeholders and proceeds with the next business process. In this way, each step works in conjunction to reduce the user's burden and streamline operations. As a concrete example, weekly meeting agendas can be automatically generated based on the user's past approval patterns, allowing users to review and approve the content, thus enabling rapid decision-making. This significantly reduces the workload of managers and speeds up the decision-making process.

[0621] The following describes the processing flow.

[0622] Step 1:

[0623] The server accesses various digital platforms via APIs and automatically collects data related to the user's work. This collected data includes emails, calendar events, and online meeting information.

[0624] Step 2:

[0625] The server analyzes the collected raw data. It uses natural language processing techniques to format the text data, remove noise, and extract important information. For example, it might extract meeting dates and agenda items from email text.

[0626] Step 3:

[0627] The server stores the analyzed data in a database. Simultaneously, it organizes the metadata associated with the data to enable efficient searching and access.

[0628] Step 4:

[0629] The server uses stored data to analyze the user's past decision-making and approval history using machine learning algorithms. This allows it to learn the user's unique thinking patterns and use that knowledge to predict future approval behaviors.

[0630] Step 5:

[0631] The server automatically generates suggestion documents based on learned thought patterns. The generation process ensures that specific suggestions and recommendations are incorporated into the documents based on previous data.

[0632] Step 6:

[0633] The terminal displays the generated proposal document in a user interface. The interface is designed to be intuitive for the user to operate, and it provides a means for reviewing and approving the proposal.

[0634] Step 7:

[0635] Users can review the presented proposal document and make revisions or comments as needed. They can formally approve the proposal by clicking the approve button.

[0636] Step 8:

[0637] The terminal sends the user's approval action to the server. The server records the approval result in detail and uses it as a trigger to execute the next processing step.

[0638] Step 9:

[0639] The server sends notifications to stakeholders based on approved proposals. These notifications provide information on the next steps to take and automatically advance the business process.

[0640] (Example 1)

[0641] 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".

[0642] With the rapid advancement of information technology, digital data from various information terminals is exploding. In business environments, particularly for middle managers, there is a need to quickly and accurately process the information necessary for effective decision-making. However, this data is diverse, and processing all of it alone requires a tremendous amount of time and effort. Furthermore, in today's world where speed of decision-making is paramount, information selection and proposal creation become bottlenecks, necessitating increased work efficiency. Solving this challenge is crucial for achieving both increased efficiency and reduced workload.

[0643] 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.

[0644] In this invention, the server includes an information gathering means for acquiring information from various information terminals, a learning means for analyzing the information and learning the past decision-making tendencies of a specific user, and a proposal generation means for generating proposal texts using natural language processing based on the learned tendencies. This enables integrated management and efficient processing of information, and facilitates the decision-making process through the rapid generation of proposal texts.

[0645] "Information gathering means" refers to methods for acquiring digital data such as electronic messages, schedule events, and online meeting information from various information terminals.

[0646] "Learning methods" refer to algorithms and methods used to analyze collected information and learn the past decision-making tendencies of a specific user.

[0647] A "proposal generation method" is a means of automatically generating a proposal text to present to the user using natural language processing based on learned information.

[0648] A "dialogue mechanism" is an interface for presenting the generated proposal to the user and obtaining their approval.

[0649] "Communication means" refers to a means that has the function of recording the approval results and notifying the relevant parties.

[0650] This invention is a system that utilizes a generating AI agent to improve the work efficiency of middle managers. Specific embodiments are described below.

[0651] The server automatically collects information from various information terminals. These terminals include email services, scheduling tools, and online meeting systems. For example, to obtain email information, data can be retrieved via APIs from Gmail and Outlook. Similarly, appropriate APIs are used to retrieve calendar events from Google Calendar and other scheduling services. Information collection is securely performed through an authentication process using OAuth 2.0.

[0652] Subsequently, the server uses machine learning tools such as TensorFlow and scikit-learn to organize the collected information and learn the decision-making patterns of specific users. This learning process allows it to analyze trends derived from past data and form a model to predict future decisions.

[0653] Furthermore, the server automatically generates suggestion texts using natural language processing technology. This technology utilizes software such as Google Cloud Natural Language API and Amazon Comprehend, which extract data and then formulate useful suggestions. The generated suggestion texts are then verified to be consistent with the user's past work style and recent activities.

[0654] The terminal presents this proposal through the user interface, allowing the user to review its contents. The user can then review the displayed proposal and add any necessary revisions or comments. For example, they can add an item to the generated meeting agenda.

[0655] Ultimately, based on the approved proposal, the server sends notifications to the relevant parties to ensure the smooth progress of the next business process. This reduces the burden on users and allows business processes to be carried out quickly and efficiently.

[0656] An example of a prompt might be, "Automatically generate an agenda for the next meeting and propose it, incorporating the content of past meetings." The system will receive this prompt, gather the appropriate information, and generate a proposal.

[0657] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0658] Step 1:

[0659] The server collects information from various information terminals. Input at this stage includes data from emails, calendar events, and online meetings. Specifically, it uses APIs from email services and scheduling tools to retrieve the latest information in JSON format. The output is the retrieved data stored in temporary storage.

[0660] Step 2:

[0661] The server analyzes the collected data. The input for this stage is the raw data collected in step 1. Here, a natural language processing engine is used to extract keywords from the text content of emails and meeting minutes and identify important information. The relevant data is structured, and only the information relevant to the business is cleansed and stored in the database.

[0662] Step 3:

[0663] The server learns the user's past decision-making tendencies through machine learning algorithms. The input for this stage comes from an analyzed database. Using tools such as TensorFlow, it analyzes past case studies and decision history to generate a predictive model. The output is a generated and updated model that reflects the user's decision-making patterns.

[0664] Step 4:

[0665] The server generates a proposal document based on the generated model. The input here is the decision-making model obtained through learning. Using natural language processing techniques, it creates a proposal document that aligns with the predicted user's desired work content. The proposal document is adjusted to match the user's past activity style. The final output is a completed proposal document presented to the user.

[0666] Step 5:

[0667] The terminal displays the proposal document generated by the server to the user. The input at this stage is the proposal document sent from the server. The user can review it on the screen and insert additional comments or make corrections as needed. The output is a reviewed or corrected version of the proposal.

[0668] Step 6:

[0669] Once the user approves the proposal, the terminal sends the result to the server. The input at this stage is the user's approval and comments. The server receives this and records the approved content in its database. The output is the recorded approval result and a notification sent to the relevant parties to proceed to the next step.

[0670] (Application Example 1)

[0671] 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".

[0672] In modern industrial product production management, it is essential to process diverse information quickly and accurately to maximize production efficiency. However, traditional methods heavily rely on human judgment, leading to wasted time and insufficient data utilization. Furthermore, they increase the burden on managers and decrease operational efficiency. Therefore, there is a need for systems that automatically collect and efficiently process various digital information to optimize production plans.

[0673] 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.

[0674] In this invention, the server includes an information gathering means, a learning means, and a proposal generation means. This allows the server to acquire necessary information from various digital information infrastructures and learn past decision-making trends, thereby automatically generating proposals to optimize production plans, enabling production managers to make optimal decisions quickly.

[0675] An "information gathering device" is a device that has the function of automatically acquiring information from various digital information infrastructures and efficiently storing it.

[0676] A "learning tool" is a device that analyzes acquired information and has the function of understanding and learning the past decision-making tendencies of a specific user.

[0677] A "proposal generation device" is a device that automatically generates proposal documents based on learned information and has the function of encouraging users to make optimal decisions.

[0678] A "display means" is a device that presents the generated proposal document to the user and provides an interface that allows the user to review and modify its contents as needed.

[0679] "Communication means" refers to communication equipment and technology that have the function of recording approval results and notifying the necessary parties.

[0680] A "plan generation device" is a device that generates proposals to optimize production plans for manufacturing industrial products, thereby supporting the decision-making of managers.

[0681] A "control device" is a device that uses generated suggestions to support the execution of industrial processes and performs operations to improve production efficiency.

[0682] A system for implementing this invention comprises information gathering means, learning means, proposal generation means, display means, communication means, plan generation means, and control means.

[0683] The server first automatically collects necessary data from various digital information infrastructures, such as electronic communications, event schedule management, and virtual meeting information, using information gathering tools. This utilizes data acquisition technologies via Amazon Web Services (AWS) services and APIs. The collected data is then analyzed using learning tools, and analytical processing is performed to understand past decision-making trends. Natural language processing is performed using Python's NLTK and spaCy libraries to extract important parts of the data.

[0684] The proposal generation system generates optimal proposal documents for the user based on organized information and learned data. Using a generation AI model, specific and highly relevant proposals are provided to the user.

[0685] The terminal presents the generated proposal document to the user via a display mechanism, allowing the user to review, modify, or approve it on the screen. This interface provides a user-friendly application environment developed using React Native.

[0686] The approval results are transmitted to the server via communication means and recorded in the database. Subsequently, the planning generation means automatically generates a production plan, and the control means efficiently executes the industrial process. This allows administrators to quickly and efficiently apply the production plan.

[0687] As a concrete example, when optimizing the production schedule in a food factory, the program generates appropriate suggestions using prompts such as: "Analyze past production order history and quality control data, and propose the optimal production schedule for this week." This enables the efficient allocation of resources on the production floor.

[0688] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0689] Step 1:

[0690] The server automatically collects data from various digital information infrastructures through information gathering means. For example, it obtains necessary data from electronic communications, event schedule management, virtual meeting information, etc., via APIs. The input is data obtained via APIs, and the output is structured data stored on the server.

[0691] Step 2:

[0692] The server analyzes the collected data using a learning method. Natural language processing is performed using Python's NLTK and spaCy libraries to extract important keywords and information related to decision-making from the data. The input for this step is the data accumulated in step 1, and the output is the dataset of the analysis results.

[0693] Step 3:

[0694] The server uses a proposal generation mechanism to learn the user's past decision-making tendencies from the analyzed information and generates a proposal document based on the results. It utilizes a generation AI model to automatically create proposals tailored to the user. The input is the analysis results obtained in step 2, and the output is the generated proposal document.

[0695] Step 4:

[0696] The terminal displays the generated proposal document to the user via a display device. The user can review the proposal and modify or approve its contents. The input for this step is the proposal document generated in step 3, and the output is the document modified and approved by the user.

[0697] Step 5:

[0698] The server records the user's approval results via communication channels and notifies the necessary parties. The input is the document approved by the user in step 4, and the output is the approval result recorded in the database and the evidence that the notification was sent.

[0699] Step 6:

[0700] The server uses a plan generation means to generate proposals to optimize the production plan and transmits instructions to relevant equipment via a control means to efficiently execute the industrial process. The input is the approval result obtained in step 5, and the output is the optimized production plan and execution instructions.

[0701] 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.

[0702] This invention aims to improve the work efficiency of middle managers by incorporating an emotion engine that recognizes user emotions into an AI-powered system. This system collects and analyzes work data and learns the user's past decision-making and emotional patterns. It then generates proposal documents tailored to the emotional state and supports the approval process.

[0703] Specifically, the server first collects data from each platform via APIs, including email, calendar events, and online meetings. This data is also used by the emotion engine to analyze the emotional state the user displayed during communication.

[0704] The analyzed data is structured by the server and stored in a database. Natural language processing technology and sentiment analysis algorithms recognize the user's emotions from the acquired text and audio information. Based on these recognition results, a learning algorithm analyzes and learns the user's decision-making and emotional patterns.

[0705] Next, using these learned outcomes, the server generates a suggestion document based on the user's emotions. This suggestion document includes content that reflects past work history and emotional patterns, and is presented in a way that is most acceptable to the user.

[0706] The terminal presents the generated proposal document to the user. The interface can be customized to take into account the user's emotions and work situation, and is designed to be intuitive to use.

[0707] Once the user reviews the proposal and approves it, the terminal sends the result to the server. The server records this approval result in a database and incorporates it into the next business flow. The server then notifies relevant parties of the approved proposal, ensuring the smooth progress of the business process.

[0708] For example, if the server analyzes a user's voice tone and language expression during an online meeting and detects that the user is experiencing stress, it can generate and present a more considerate suggested document, thereby reducing the user's workload. By taking emotions into account in this way, more personalized responses become possible, improving overall work efficiency.

[0709] The following describes the processing flow.

[0710] Step 1:

[0711] The server automatically collects information from various digital platforms via APIs, including email, calendar events, and online meetings. This data collection centralizes information relevant to the user's work.

[0712] Step 2:

[0713] The server formats the collected data and stores it in a database as structured data. During this formatting process, natural language processing techniques are used to extract important information.

[0714] Step 3:

[0715] The server uses an emotion engine to analyze the user's emotional state from the content of online meetings and emails. Based on voice tone and linguistic expressions, it identifies emotions such as stress, fatigue, and satisfaction.

[0716] Step 4:

[0717] The server uses machine learning algorithms to learn from past decision-making history and analyzed sentiment data to identify the user's decision-making patterns. This identification allows it to predict which proposals are more likely to be accepted.

[0718] Step 5:

[0719] The server automatically generates the most suitable suggestion document based on learned thought patterns and emotions. This document takes into account the user's current emotional state and includes language that is easily accepted.

[0720] Step 6:

[0721] The terminal presents the generated proposal document to the user. The interface simplifies user operation and provides a customized, emotionally sensitive look as needed.

[0722] Step 7:

[0723] Users review the proposed document displayed on their device and, if satisfied with its content, press the approve button to approve it. They can also provide suggestions for revisions as needed.

[0724] Step 8:

[0725] The terminal sends user input and approval results to the server, where they are recorded in a database. This record can then be used for future data analysis and operational improvements.

[0726] Step 9:

[0727] The server sends notifications to relevant stakeholders based on approved proposals. This notification function facilitates the next workflow and improves the overall efficiency of the process.

[0728] (Example 2)

[0729] 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".

[0730] In many organizations, middle managers often find it difficult to make decisions in their daily work due to information overload and emotional fluctuations. This leads to decreased work efficiency and increased stress, ultimately resulting in a decline in overall organizational productivity.

[0731] 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.

[0732] In this invention, the server includes data collection means for acquiring data from various information processing infrastructures, learning means for analyzing the data to learn the past decision-making tendencies and emotional states of a specific user, and proposal generation means for automatically generating proposal documents based on the learned tendencies and emotional states. This enables improved work efficiency and increased accuracy of decision-making by providing optimal proposal documents that take into account the emotional states of middle managers.

[0733] "Various information processing infrastructures" refer to technological foundations for collecting and processing various types of data, including digital communications, time-managed events, and remote conferencing information.

[0734] "Data acquisition means" refers to functions and technologies for acquiring relevant digital data from information processing infrastructure.

[0735] A "learning tool" is a function that analyzes collected data to learn about a specific user's past decision-making tendencies and emotional state.

[0736] "Suggestion generation means" refers to functions and technologies for automatically generating suggestion documents to be provided to users based on learned trends and emotional states.

[0737] "Exchange method" refers to an interface or protocol for presenting a generated proposal document to a user and obtaining their approval.

[0738] "Communication means" refers to technologies and functions for recording approval results and notifying relevant parties of necessary information.

[0739] "Natural language processing" is a technology that enables computers to understand and generate human language.

[0740] "Emotional analysis" is a technology that identifies a person's emotional state from written or spoken information.

[0741] The embodiments for carrying out the present invention will be described in detail. This system is designed to collect and analyze data from an information processing infrastructure in order to understand the past decision-making tendencies and emotional states of a specific user.

[0742] The server retrieves digital communications, time-managed events, and remote meeting information via APIs from each platform. For example, it uses the email API to collect email content and sending / receiving history, and the calendar API to retrieve schedule data. Furthermore, it uses the meeting solution API to collect audio and chat logs from remote meetings. The data obtained in this way is structured on the server and stored in a database.

[0743] The server uses natural language processing (NLP) techniques and sentiment analysis algorithms to analyze the user's emotional state from the collected data. For example, it recognizes emotions from keywords and writing style in emails, and analyzes tone and speed from audio data during meetings to determine the user's stress level. This creates a more detailed personal profile, clarifying the user's emotions and decision-making tendencies.

[0744] Using the learned results, the server employs a generative AI model to create suggestion documents based on the user's emotional state and work history. Specifically, based on prompts such as "Please suggest the next steps to reduce the user's stress," the AI ​​model provides optimal suggestions. These generated suggestion documents are then presented to the user via a terminal to support their decision-making in their work. The interface is designed for intuitive operation, allowing users to easily review and approve the suggestions.

[0745] Finally, once the user approves the proposed document, the terminal sends the result to the server. The server records the approval in its database and incorporates it into the next workflow. Notifications are also sent to relevant parties, helping to ensure the smooth progress of the workflow.

[0746] This invention enables middle managers to process information accurately and efficiently and make emotion-based decisions, resulting in improved operational efficiency throughout the organization.

[0747] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0748] Step 1:

[0749] The server retrieves data from various information processing infrastructures. Specifically, it uses email APIs, calendar APIs, and meeting APIs to collect email content, time management events, and remote meeting information. The input data mainly consists of text data, date information, and audio data, which are formatted for structured purposes and stored in a database.

[0750] Step 2:

[0751] The server analyzes stored data using natural language processing techniques and sentiment analysis algorithms. It takes email and meeting speech data as input and determines the user's emotional state through text analysis. For example, it calculates an emotional score by identifying positive keywords and negative phrases. The output is evaluation data regarding the user's emotional state.

[0752] Step 3:

[0753] The server runs an algorithm that learns emotional states and past decision-making tendencies. The emotional evaluations obtained in step 2 and past work history data are used as input data. The learning algorithm models the user's decision-making patterns through trend analysis and applies them to decision-making in new tasks. The output is behavioral pattern analysis data that reflects the user's characteristics.

[0754] Step 4:

[0755] The server generates suggestion documents using an AI model based on the learning results. The AI ​​is given instructions such as "Please suggest the next steps to reduce user stress," taking into account sentiment evaluation, behavioral pattern analysis data, and work history data as input. The AI ​​model then creates and outputs the most suitable suggestion document. The output document includes suggestions that take sentiment into consideration.

[0756] Step 5:

[0757] The terminal presents the generated proposal document to the user. It receives the generated proposal document from the server as input and displays it in a visually and easily understandable format on the user interface. The user can intuitively manipulate this document, review its contents, and approve it.

[0758] Step 6:

[0759] When a user approves a proposal document, the terminal sends the result to the server. The server receives the approval data as input and records it in its database. Finally, it notifies relevant parties and incorporates the changes into the next business process. The output includes the approved proposal and updated information on the decision history.

[0760] (Application Example 2)

[0761] 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".

[0762] In modern work environments, workers' emotions and workloads are often overlooked, which can lead to decreased work efficiency. This is especially true in workplaces where concentration and precision are paramount, such as factories, where support that considers workers' emotions is essential. Traditional systems struggled to provide individualized suggestions and support based on workers' emotions in real time, resulting in decreased work efficiency.

[0763] 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.

[0764] In this invention, the server includes information gathering means for acquiring information from various information platforms, learning means for analyzing the information to learn the past judgment tendencies and emotional state of a specific worker, and suggestion generation means for automatically generating suggestion documents to support the worker based on the learned tendencies and emotional state. This enables the provision of appropriate suggestions based on the worker's emotions, thereby improving work efficiency.

[0765] "Information gathering means" refers to methods and devices for obtaining necessary information from various information platforms, and is capable of collecting diverse information such as audio data and document data.

[0766] A "learning tool" is a method or device for analyzing collected information and learning a specific worker's past judgment tendencies and emotional state.

[0767] A "suggestion generation means" is a method or apparatus that automatically generates suggestion documents to support workers based on learned tendencies and emotional states.

[0768] "Display means" refers to methods or devices for presenting the generated proposal document to the worker and receiving approval or feedback.

[0769] "Means of communication" refers to methods or devices for recording approval or feedback results and notifying relevant parties.

[0770] "Emotional analysis means" refers to methods or devices for analyzing a worker's voice information and evaluating their emotions.

[0771] A system for carrying out this invention includes information gathering means, learning means, suggestion generation means, display means, communication means, and sentiment analysis means. A server can integrate these means in a factory or other work environment to improve the work efficiency of workers.

[0772] The server first acquires information from various information platforms. This information is collected via APIs, and includes audio data, document data, and work schedules. The information is structured and stored in a database on the server.

[0773] As a learning tool, the server uses collected information to learn the worker's past decision-making tendencies and emotional state. Natural language processing technology and sentiment analysis algorithms are used to analyze emotions from the worker's words, actions, and voice.

[0774] The suggestion generation system generates suggestion documents to support workers based on learned trends and emotional states. It utilizes a generation AI model to generate optimal suggestions and display them to the worker.

[0775] The terminal displays the proposed document sent from the server to the worker. This allows the worker to review the proposal and take action as needed. Approvals or feedback from the terminal are sent to the server and notified to relevant parties through communication channels, thereby improving the business process.

[0776] The system has a function that analyzes emotions using the worker's voice information, allowing for real-time analysis of stress and other emotional states. For example, if the server analyzes the worker's voice tone during work and detects that the worker is experiencing stress, it can adjust the work speed or suggest auxiliary tasks to reduce the worker's burden.

[0777] An example of a prompt sentence to be used as input to a generative AI model is: "Please tell me how to design an AI system that analyzes voice data, identifies stress levels, and provides appropriate support to workers."

[0778] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0779] Step 1:

[0780] The server retrieves information from various information platforms via APIs. Inputs include audio data, document data, and work schedules, and this information is stored in a structured format in a database within the server.

[0781] Step 2:

[0782] The server analyzes the information to learn the worker's past decision-making tendencies and emotional state. The input is the data collected in step 1, and the data is processed using natural language processing technology and emotion analysis algorithms to output the worker's emotional pattern.

[0783] Step 3:

[0784] The server automatically generates suggestion documents to support the worker via a suggestion generation mechanism, based on learned trends and emotional situations. The input is the analysis result from step 2, and the generating AI model outputs the optimal suggestion content using prompt sentences.

[0785] Step 4:

[0786] The terminal displays the proposal document sent from the server to the worker. The input is the generated proposal document, which is output to the screen for easy confirmation by the worker.

[0787] Step 5:

[0788] The user reviews the proposal document displayed on the terminal and approves or provides feedback as needed. Input consists of the proposal document and the worker's judgment, while output is approval or feedback information.

[0789] Step 6:

[0790] The server records the approval or feedback results sent from the terminal and notifies the relevant parties. The input is the output of step 5, and this is used to reflect the changes in the business process using communication methods.

[0791] Step 7:

[0792] The server analyzes the worker's emotions in real time using their voice information. The input is real-time voice data, and the emotion analysis algorithm outputs stress and other emotional states. In this case, it is possible to use a generative AI model to suggest specific support.

[0793] 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.

[0794] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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."

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] The following is further disclosed regarding the embodiments described above.

[0815] (Claim 1)

[0816] Data collection methods that acquire data from various digital platforms,

[0817] A learning method that analyzes the aforementioned data to learn the past decision-making tendencies of a specific user,

[0818] A proposal generation means that automatically generates a proposal document based on the learned trends,

[0819] An interface means for presenting the generated proposal document to the user and obtaining their approval,

[0820] A means of communication for recording the approval result and notifying the relevant parties,

[0821] A system that includes this.

[0822] (Claim 2)

[0823] The system according to claim 1, wherein the data collection means is configured to process various types of digital data, including emails, calendar events, and online meeting information.

[0824] (Claim 3)

[0825] The system according to claim 1, wherein the proposal generation means is configured to generate a proposal document using natural language processing.

[0826] "Example 1"

[0827] (Claim 1)

[0828] Information gathering means for acquiring information from various information terminals,

[0829] A learning method that analyzes the aforementioned information to learn the past decision-making tendencies of a specific user,

[0830] A proposal generation means that generates a proposal sentence using natural language processing based on the learned trends,

[0831] A means of dialogue for presenting the generated proposal to the user and obtaining their approval,

[0832] A means of communication for recording the approval results and notifying the relevant parties,

[0833] A system that includes this.

[0834] (Claim 2)

[0835] The system according to claim 1, wherein the information gathering means is configured to process various types of information data, including electronic messages, schedule events, and online meeting information.

[0836] (Claim 3)

[0837] The system according to claim 1, wherein the proposal generation means is configured to generate proposal text that reflects the decision-making behavior of past users.

[0838] "Application Example 1"

[0839] (Claim 1)

[0840] Information gathering means for acquiring information from various digital information infrastructures,

[0841] A learning method that analyzes the aforementioned information to learn the past decision-making tendencies of a specific user,

[0842] A proposal generation means that automatically generates a proposal document based on the learned trends,

[0843] A means for presenting the generated proposal document to the user and obtaining their approval,

[0844] A means of communication for recording the approval result and notifying the relevant parties,

[0845] A plan generation means that generates proposals to optimize production plans for producing industrial products,

[0846] The above proposal is presented to the user and includes control means for supporting the execution of industrial processes,

[0847] A system that includes this.

[0848] (Claim 2)

[0849] The system according to claim 1, wherein the information gathering means is configured to process various types of digital information, including electronic communications, event schedule management, and virtual meeting information.

[0850] (Claim 3)

[0851] The system according to claim 1, wherein the proposal generation means is configured to generate a proposal document using natural language processing and to optimize the production process of an industrial product in cooperation with the plan generation means.

[0852] "Example 2 of combining an emotion engine"

[0853] (Claim 1)

[0854] A data collection method for acquiring data from various information processing infrastructures,

[0855] A learning method that analyzes the aforementioned data to learn the past decision-making tendencies and emotional state of a specific user,

[0856] A proposal generation means that automatically generates a proposal document based on the learned tendencies and emotional states,

[0857] A means of exchange for presenting the generated proposal document to the user and obtaining their approval,

[0858] A means of communication for recording the approval result and notifying the relevant parties,

[0859] A system that includes this.

[0860] (Claim 2)

[0861] The system according to claim 1, wherein the data collection means is configured to process various types of digital data, including digital communications, time management events, and remote conferencing information.

[0862] (Claim 3)

[0863] The system according to claim 1, wherein the proposal generation means is configured to generate a proposal document using natural language processing and sentiment analysis.

[0864] "Application example 2 when combining with an emotional engine"

[0865] (Claim 1)

[0866] Information gathering means for acquiring information from various information platforms,

[0867] A learning means that analyzes the aforementioned information to learn the past judgment tendencies and emotional state of a specific worker,

[0868] A suggestion generation means that automatically generates a suggestion document to support the worker based on the learned trends and emotional state,

[0869] A display means for presenting the generated proposal document to the worker and receiving approval or feedback,

[0870] A means of recording the approval or feedback results and notifying the relevant parties,

[0871] An emotion analysis method that analyzes the voice information of workers to evaluate their emotions,

[0872] A system that includes this.

[0873] (Claim 2)

[0874] The system according to claim 1, wherein the information gathering means is configured to process various types of information, including voice data, document data, and work schedules.

[0875] (Claim 3)

[0876] The system according to claim 1, wherein the proposal generation means is configured to generate a proposal document using natural language processing and sentiment analysis techniques. [Explanation of symbols]

[0877] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Data collection methods that acquire data from various digital platforms, A learning method that analyzes the aforementioned data to learn the past decision-making tendencies of a specific user, A proposal generation means that automatically generates a proposal document based on the learned trends, An interface means for presenting the generated proposal document to the user and obtaining their approval, A means of communication for recording the approval result and notifying the relevant parties, A system that includes this.

2. The system according to claim 1, wherein the data collection means is configured to process various types of digital data, including emails, calendar events, and online meeting information.

3. The system according to claim 1, wherein the proposal generation means is configured to generate a proposal document using natural language processing.

Images