system

Abstract

The system according to this embodiment aims to generate business flow diagrams in a natural language conversational format and to create and provide business process reengineering (BPR) proposals. [Solution] The system according to the embodiment comprises a speech recognition unit, an analysis unit, a generation unit, and a provision unit. The speech recognition unit transcribes speech data into text. The analysis unit analyzes the data transcribed by the speech recognition unit and generates a business flow. The generation unit generates a BPR proposal based on the data analyzed by the analysis unit. The provision unit provides the BPR proposal generated by the generation unit as slides or a video.

Description

Technical Field

[0004] ,

[0006] , , , , , ,

[0005] , , , , ,

[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 the conventional technology, there is a problem that in local governments and private companies where the internalization of business process reengineering (BPR) does not progress, the generation of business processes and the creation of BPR plans require time and effort and are difficult to perform efficiently.

[0005] The system according to the embodiment aims to generate a business process and create and provide a BPR plan in a conversation form using natural language.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a speech recognition unit, an analysis unit, a generation unit, and a provision unit. The speech recognition unit transcribes speech data into text. The analysis unit analyzes the data transcribed by the speech recognition unit and generates a business flow. The generation unit generates a BPR (Business Process Reengineering) proposal based on the data analyzed by the analysis unit. The provision unit provides the BPR proposal generated by the generation unit as slides or a video. [Effects of the Invention]

[0007] The system according to this embodiment can generate business flow diagrams in a natural language conversational format and create and provide business process reengineering (BPR) proposals. [Brief explanation of the drawing]

[0008] [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. [Modes for carrying out the invention]

[0009] 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.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. 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).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a receiving 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 receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The business process reengineering system according to an embodiment of the present invention provides a mechanism for implementing business process reengineering (BPR) in a natural language conversational format for local governments and private companies that are not making progress in internalizing BPR. This system allows business personnel to easily create materials and videos for implementing BPR simply by verbally explaining the workflow. For example, when a business person verbally explains the workflow, a flowchart is created using speech recognition technology. For example, if a business person explains, "First, we receive inquiries from customers, and then a staff member handles them," the speech recognition technology transcribes the content and generates a flowchart. Next, if there are any missing parts in the generated flowchart, additional information is provided to correct it into a more accurate flowchart. For example, by providing additional information such as, "If there are multiple inquiries, the staff member prioritizes and handles them," the flowchart is corrected. Furthermore, anticipated challenges and proposed solutions are presented. For example, if delays in responding to inquiries are a challenge, a solution such as, "Introduce an AI-powered automated response system," is presented. Finally, the business flow, challenges, and solutions are summarized in slides, and a video is created. For example, generated flowcharts, issues, and solutions are compiled into slides, speaker notes are created based on these slides, and then converted into audio data. This process generates a video from the slides and speaker notes. This system allows business personnel to easily create materials and videos for implementing BPR simply by explaining the workflow in natural language. This will promote the in-house implementation of BPR in local governments and private companies, improving operational efficiency. In short, the business reform system allows business personnel to easily create materials and videos for implementing BPR simply by explaining the workflow in natural language.

[0029] The business process reform system according to this embodiment comprises a speech recognition unit, an analysis unit, a generation unit, and a provision unit. The speech recognition unit transcribes audio data into text. The audio data includes, for example, the audio file format (WAV, MP3, etc.) and the content of the audio (conversation, lecture, etc.), but is not limited to such examples. The speech recognition unit transcribes the audio data using, for example, a speech recognition algorithm. The analysis unit analyzes the data transcribed by the speech recognition unit and generates a business flow. The analysis unit analyzes the transcribed data using, for example, an analysis algorithm and generates a business flow based on the type of business process and the level of detail of the flow. The generation unit generates a BPR proposal based on the data analyzed by the analysis unit. The BPR proposal includes, for example, suggestions for improving business processes and specific reform methods, but is not limited to such examples. The generation unit generates the BPR proposal using, for example, a generation algorithm. The provision unit provides the BPR proposal generated by the generation unit as slides or videos. The slides or videos include, for example, the slide format and the length and resolution of the video, but is not limited to such examples. The service provider, for example, uses slide creation software or video editing software to provide the BPR proposal as slides or videos. This allows the business process reform system to efficiently implement business process reform by transcribing audio data, generating business flow diagrams, and providing the BPR proposal.

[0030] The speech recognition unit transcribes audio data into text. Audio data includes, but is not limited to, audio file formats (WAV, MP3, etc.) and audio content (conversations, speeches, etc.). The speech recognition unit transcribes the audio data using, for example, a speech recognition algorithm. Specifically, the speech recognition unit utilizes a deep learning-based speech recognition model to transcribe audio data with high accuracy. The speech recognition model is pre-trained using a large amount of audio data and corresponding text data, and can handle various accents and speaker differences. Upon receiving audio data, the speech recognition unit first preprocesses the audio signal, performing noise reduction and volume normalization. Then, it divides the audio signal into frames and extracts features from each frame. These features are input to the speech recognition model, and the corresponding text is output. Furthermore, the speech recognition unit uses a language model in conjunction to improve transcription accuracy by considering contextual information. The language model predicts appropriate words and phrases based on context, improving the naturalness and accuracy of the transcription result. This allows the speech recognition unit to quickly and accurately transcribe audio data such as conversations and lectures, and provide it to the subsequent analysis unit.

[0031] The analysis unit analyzes the data transcribed by the speech recognition unit and generates a business flow. For example, the analysis unit uses an analysis algorithm to analyze the transcribed data and generates a business flow based on the type of business process and the level of detail of the flow. Specifically, the analysis unit uses natural language processing technology to analyze the transcribed data and extract keywords and phrases related to the business process. These keywords and phrases indicate each step and action of the business process, and the analysis unit constructs a business flow based on these. First, the analysis unit tokenizes the transcribed data and analyzes the part of speech and meaning of each token. Next, it performs dependency analysis to clarify the relationships between each token. This makes it possible to understand how each step of the business process is interconnected. Furthermore, the analysis unit constructs the business flow hierarchically based on the type of business process and the level of detail of the flow. For example, it can generate a flowchart showing the higher-level business process and sub-flowcharts showing the detailed steps of each process. As a result, the analysis unit can generate a business flow that clearly shows the overall picture and details of the business process and provide it to the subsequent generation unit.

[0032] The generation unit generates BPR proposals based on data analyzed by the analysis unit. These proposals may include, but are not limited to, suggestions for improving business processes or specific reform methods. The generation unit generates BPR proposals using, for example, a generation algorithm. Specifically, it automatically generates proposals for streamlining and improving business processes based on the business flow provided by the analysis unit. The generation unit first evaluates each step of the business flow to identify bottlenecks and inefficiencies. Next, it refers to past success stories and best practices to propose solutions to these problems. Using a machine learning model, the generation unit proposes optimal improvements based on patterns learned from past data. For example, it can propose introducing tools or technologies to automate manual tasks in a specific business process, or propose streamlining the business flow. Furthermore, the generation unit simulates the effects of the proposed improvements and evaluates the predicted outcomes. This allows the generation unit to generate concrete and feasible BPR proposals and provide them to the subsequent delivery unit.

[0033] The providing department will provide the BPR proposals generated by the generating department as slides or videos. These slides or videos will include, but are not limited to, the slide format, video length, and resolution. The providing department will use, for example, slide creation software or video editing software to provide the BPR proposals as slides or videos. Specifically, the providing department will organize the information in slide or video format and create presentation materials to visually represent the BPR proposals provided by the generating department in an easily understandable way. Using slide creation software, they will visually represent improvement proposals and specific reform methods for each business process using diagrams and graphs. They will also use video editing software to create video explanations of the BPR proposals, adding narration and animation to provide content that is easy for viewers to understand. Furthermore, the providing department can customize the format and design of the slides and videos to create materials that align with the company's brand guidelines. This allows the providing department to provide visual materials that effectively communicate the generated BPR proposals and support the implementation of business reforms.

[0034] The modification unit can add additional information and modify the flowchart. For example, the modification unit can modify the flowchart when a business user provides additional information. For example, if a business user provides additional information such as "If there are multiple inquiries, the person in charge will prioritize and respond to them," the modification unit will modify the flowchart. The modification unit can also analyze the additional information provided by the business user and reflect it in the flowchart. For example, the modification unit can analyze the additional information provided by the business user and add branching points and detailed steps to the flowchart. Furthermore, the modification unit can review and optimize the overall structure of the flowchart based on the additional information provided by the business user. For example, the modification unit can review the overall structure of the flowchart based on the additional information provided by the business user to improve the efficiency of the business process. As a result, the modification unit can generate a more accurate flowchart by adding missing information. Additional information includes, but is not limited to, data types and methods of information acquisition. Some or all of the above processing in the modification unit may be performed using, for example, AI, or not using AI. For example, the modification unit can input additional information provided by the business person into the generation AI, and have the generation AI perform the modification of the flowchart.

[0035] The presentation unit can present problems or solutions. For example, the presentation unit can present problems that are anticipated based on the business flow. For example, the presentation unit might present a problem such as, "Delays in responding to inquiries are a problem." The presentation unit can also present solutions to problems. For example, the presentation unit might present a solution such as, "Implement an automated response system using AI." Furthermore, the presentation unit can also present priorities for problems and solutions. For example, the presentation unit might present priorities such as, "Delays in responding to inquiries are the highest priority problem, and implementing an automated response system using AI is the optimal solution." In this way, by presenting problems and solutions, the presentation unit can provide concrete proposals for business improvement. Problems or solutions include, but are not limited to, business problems and methods for proposing solutions. Some or all of the above processing in the presentation unit may be performed using, for example, AI, or not using AI. For example, the presentation unit can input business flow data into a generating AI and have the generating AI perform the presentation of problems and solutions.

[0036] The audio data conversion unit can convert presentation notes into audio data. For example, the audio data conversion unit can convert speaker notes into audio data. For example, the audio data conversion unit can convert the content of speaker notes into audio data using speech synthesis technology. The audio data conversion unit can also generate audio data that reads aloud the content of speaker notes. For example, the audio data conversion unit can generate audio data that reads aloud the content of speaker notes and use it in a presentation. Furthermore, the audio data conversion unit can convert the content of speaker notes into audio data in multiple languages. For example, the audio data conversion unit can convert the content of speaker notes into audio data in multiple languages ​​such as English, Japanese, and French. This makes it easier to create presentation materials by converting speaker notes into audio data. Presentation notes include, but are not limited to, the format of the notes and the level of detail in their content. Some or all of the above-described processes in the audio data conversion unit may be performed using, for example, AI, or not. For example, the audio data conversion unit can input the content of speaker notes into a generating AI and have the generating AI perform the audio data conversion.

[0037] The video creation unit can create videos from slides and presentation notes. For example, it can create videos based on slides and speaker notes. For instance, it can create a video that displays the slide content and plays the audio data of the speaker notes. The video creation unit can also create videos by adding animation effects to the slides. For example, it can add animation effects to the slide content to create a visually easy-to-understand video. Furthermore, the video creation unit can edit the slide and speaker note content to create short presentation videos. For example, it can edit the slide and speaker note content to create a concise presentation video. This allows the video creation unit to provide visually easy-to-understand materials by creating videos from slides and speaker notes. Videos include, but are not limited to, video length, resolution, and level of detail. Some or all of the above processes in the video creation unit may be performed using, for example, AI, or not. For example, the video creation unit can input slide and speaker note data into a generating AI and have the generating AI create the video.

[0038] The speech recognition unit can be equipped with a filtering function that automatically removes background noise during speech recognition. For example, the speech recognition unit can analyze ambient noise in real time during speech recognition and perform noise cancellation. For example, the speech recognition unit can collect ambient noise with a microphone and remove the noise using a noise cancellation algorithm. The speech recognition unit can also filter out noise in a specific frequency band and extract only the speech. For example, the speech recognition unit can filter out noise in a specific frequency band and enhance the speech signal. Furthermore, the speech recognition unit can use multiple microphones to identify noise sources and remove noise. For example, the speech recognition unit can use multiple microphones to identify noise sources and perform noise cancellation. This improves the accuracy of speech recognition by removing background noise. Background noise includes, but is not limited to, ambient sounds and background noise. Some or all of the above processing in the speech recognition unit may be performed using, for example, AI, or not using AI. For example, the speech recognition unit can have a generative AI perform the noise cancellation process.

[0039] The speech recognition unit can improve recognition accuracy by taking into account the speaker's accent and dialect during speech recognition. For example, the speech recognition unit can improve recognition accuracy by learning the speaker's accent in advance during speech recognition. For example, the speech recognition unit can learn the characteristics of the speaker's accent and reflect them in the recognition algorithm. The speech recognition unit can also analyze the characteristics of dialects and convert them to standard Japanese for recognition. For example, the speech recognition unit can use an algorithm that analyzes the characteristics of dialects and converts them to standard Japanese. Furthermore, the speech recognition unit can improve recognition accuracy by learning the speaker's pronunciation patterns in real time. For example, the speech recognition unit can learn the speaker's pronunciation patterns in real time and reflect them in the recognition algorithm. As a result, the speech recognition unit improves recognition accuracy by taking into account the speaker's accent and dialect. Accents and dialects include, but are not limited to, regional accents and dialect characteristics. Some or all of the above processing in the speech recognition unit may be performed using, for example, AI, or without using AI. For example, the speech recognition unit can input the speaker's accent and dialect characteristics into the generating AI, allowing the generating AI to improve recognition accuracy.

[0040] The speech recognition unit can analyze the tone and speed of the speaker's voice during speech recognition and select an appropriate recognition model. For example, the speech recognition unit can analyze the tone of the speaker's voice during speech recognition and select a recognition model that matches the emotion. For example, the speech recognition unit can analyze the pitch and volume of the speaker's voice, estimate the emotion, and select an appropriate recognition model. The speech recognition unit can also analyze the speed at which the speaker is speaking and select a recognition model that matches the speed. For example, the speech recognition unit can analyze the speed of the speaker in real time and select a recognition model that matches the speed. Furthermore, the speech recognition unit can analyze the volume of the speaker's voice and select an appropriate recognition model. For example, the speech recognition unit can analyze the volume of the speaker's voice in real time and select a recognition model that matches the volume. As a result, the speech recognition unit improves recognition accuracy by selecting a recognition model that matches the tone and speed of the speaker's voice. The tone and speed of the voice include, but are not limited to, methods for measuring pitch and speed. Some or all of the above-described processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input data on the speaker's voice tone and speed into a generating AI and have the generating AI select a recognition model.

[0041] The speech recognition unit can be equipped with a function to individually recognize multiple speakers even when they are speaking simultaneously. For example, the speech recognition unit can separate the voices of multiple speakers and recognize them individually during speech recognition. For example, the speech recognition unit can collect the voices of multiple speakers with microphones, separate the voices using a speech separation algorithm, and recognize them individually. The speech recognition unit can also analyze the speech characteristics of each speaker and recognize them individually. For example, the speech recognition unit can analyze the speech characteristics of each speaker in real time and recognize them individually. Furthermore, the speech recognition unit can separate the content of each speaker's speech in real time and recognize it individually. For example, the speech recognition unit can separate the content of each speaker's speech in real time and recognize it individually. This improves the recognition accuracy of the speech recognition unit by allowing it to individually recognize multiple speakers even when they are speaking simultaneously. Multiple speakers include, but are not limited to, speaker separation algorithms and simultaneous recognition techniques. Some or all of the above processing in the speech recognition unit may be performed using, for example, AI, or not using AI. For example, the speech recognition unit can input speech data from multiple speakers into the generating AI and have the generating AI perform individual recognition processing.

[0042] The analysis unit can dynamically change the analysis algorithm during analysis according to the complexity of the business flow. For example, if the business flow is simple, the analysis unit applies a simple analysis algorithm. For example, the analysis unit applies a simple analysis algorithm to business flows with few steps and branching points. The analysis unit can also apply a detailed analysis algorithm if the business flow is complex. For example, the analysis unit applies a detailed analysis algorithm to business flows with many steps and branching points. Furthermore, the analysis unit can select an appropriate analysis algorithm according to the intermediate complexity of the business flow. For example, the analysis unit selects an algorithm that is intermediate between a simple analysis algorithm and a detailed analysis algorithm, depending on the complexity of the business flow. This improves the accuracy of the analysis by applying an analysis algorithm appropriate to the complexity of the business flow. The complexity of the business flow includes, but is not limited to, the number of steps and branching points in the flow. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input data on the complexity of the business flow into the generating AI and have the generating AI select an analysis algorithm.

[0043] The analysis unit can improve the accuracy of its analysis by referring to past business flow data during the analysis process. For example, the analysis unit analyzes the current business flow based on past business flow data. For example, the analysis unit can refer to past business flow data to identify similar patterns and improve the accuracy of the analysis. The analysis unit can also analyze past business flow data and select the optimal analysis method. For example, the analysis unit analyzes past business flow data and selects the optimal analysis method. Furthermore, the analysis unit can supplement the analysis results by referring to past business flow data. For example, the analysis unit supplements the current analysis results by referring to past business flow data. In this way, the analysis unit improves the accuracy of its analysis by referring to past business flow data. Past business flow data includes, but is not limited to, details such as data type and referencing method. Some or all of the above processes in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input past business flow data into a generating AI and have the generating AI perform the improvement of analysis accuracy.

[0044] The analysis unit can measure the time taken for each step of a business process during analysis and propose an efficient flow. For example, the analysis unit can measure the time taken for each step and identify the most time-consuming step. For example, the analysis unit can record the start and end times of each step of a business process and identify the most time-consuming step. The analysis unit can also analyze the time taken for each step and propose an efficient flow. For example, the analysis unit can analyze the time taken for each step and propose improvement plans to reduce the time taken. Furthermore, the analysis unit can compare the time taken for each step and propose the optimal flow. For example, the analysis unit compares the time taken for each step and proposes the most efficient flow. In this way, the analysis unit can propose an efficient business process by measuring the time taken for each step. The time taken for each step includes, but is not limited to, the time measurement method and evaluation criteria. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input the time data for each step into a generating AI and have the generating AI execute a proposal for an efficient flow.

[0045] The analysis unit can improve the accuracy of its analysis by referring to relevant documentation of the business process during the analysis. For example, the analysis unit can refer to relevant documentation of the business process to improve the accuracy of its analysis. For example, the analysis unit can select the optimal analysis method based on the relevant documentation of the business process. The analysis unit can also analyze relevant documentation of the business process to supplement the analysis results. For example, the analysis unit can analyze relevant documentation of the business process to supplement the current analysis results. Furthermore, the analysis unit can improve its analysis algorithm based on relevant documentation of the business process. For example, the analysis unit improves its analysis algorithm and accuracy based on relevant documentation of the business process. As a result, the analysis unit improves its analysis accuracy by referring to relevant documentation of the business process. Relevant documentation includes, but is not limited to, the type of documentation and details of how to refer to it. Some or all of the above processes in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input relevant documentation data of the business process into a generating AI and have the generating AI perform the improvement of analysis accuracy.

[0046] The generation unit can adjust the level of detail of the generated content based on the importance of the business process flow during generation. For example, the generation unit can generate detailed BPR proposals for important business processes. For example, the generation unit evaluates the importance of business processes and generates detailed BPR proposals for important business processes. The generation unit can also generate concise BPR proposals for less important business processes. For example, the generation unit evaluates the importance of business processes and generates concise BPR proposals for less important business processes. Furthermore, the generation unit can generate BPR proposals with an appropriate level of detail according to the importance of the business processes. For example, the generation unit evaluates the importance of business processes and generates BPR proposals with an appropriate level of detail. This enables efficient business improvement by generating BPR proposals with a level of detail appropriate to the importance of the business processes. The importance of business processes includes, but is not limited to, the criteria for evaluating importance and the details of the adjustment method. Some or all of the above-described processes in the generation unit may be performed using, for example, AI, or not using AI. For example, the generation unit can input importance data of the business flow into the generation AI and have the generation AI perform adjustments to the level of detail.

[0047] The generation unit can apply different generation algorithms depending on the category of the business flow during generation. For example, if the business flow is customer service, the generation unit can apply a generation algorithm specialized for customer service. For example, the generation unit can apply a generation algorithm specialized for customer service business flows. The generation unit can also apply a generation algorithm specialized for internal management if the business flow is internal management. For example, the generation unit can apply a generation algorithm specialized for internal management business flows. Furthermore, if the business flow is production management, the generation unit can apply a generation algorithm specialized for production management. For example, the generation unit can apply a generation algorithm specialized for production management business flows. In this way, the generation unit can generate the optimal BPR proposal by applying a generation algorithm according to the category of the business flow. The categories of business flows include, for example, the type of category and the details of the algorithm to be applied, but are not limited to such examples. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input business flow category data into a generation AI and have the generation AI execute the application of the generation algorithm.

[0048] The generation unit can determine the priority of the generated content based on the submission timing of the business process flow during generation. For example, the generation unit can prioritize generating BPR proposals for business process flows with approaching submission deadlines. For example, the generation unit can evaluate the submission deadlines of business process flows and prioritize generating BPR proposals for those with approaching deadlines. The generation unit can also postpone generating BPR proposals for business process flows with distant submission deadlines. For example, the generation unit can evaluate the submission deadlines of business process flows and postpone generating BPR proposals for those with distant deadlines. Furthermore, the generation unit can generate BPR proposals with appropriate priorities according to the submission timing. For example, the generation unit can evaluate the submission timing of business process flows and generate BPR proposals with appropriate priorities. This enables efficient business improvement by allowing the generation unit to determine priorities based on the submission timing of business process flows. The submission timing includes, but is not limited to, the evaluation criteria for submission timing and the details of the method for determining priorities. Some or all of the above processing in the generation unit may be performed using, for example, AI, or not using AI. For example, the generation unit can input data on the submission timing of business workflows into the generation AI, and have the generation AI determine the priorities.

[0049] The generation unit can adjust the order of generated content based on the relevance of business processes during generation. For example, the generation unit can prioritize the inclusion of highly relevant business processes in the BPR proposal. For example, the generation unit evaluates the relevance of business processes and prioritizes the inclusion of highly relevant business processes in the BPR proposal. The generation unit can also postpone the inclusion of less relevant business processes in the BPR proposal. For example, the generation unit evaluates the relevance of business processes and postpones the inclusion of less relevant business processes in the BPR proposal. Furthermore, the generation unit can generate the BPR proposal in an appropriate order according to the relevance of business processes. For example, the generation unit evaluates the relevance of business processes and generates the BPR proposal in an appropriate order. In this way, the generation unit can provide the optimal BPR proposal by adjusting the order of generated content based on the relevance of business processes. The relevance of business processes includes, but is not limited to, the criteria for evaluating relevance and the details of the adjustment method. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the relevance data of the business flow into the generation AI and have the generation AI perform the order adjustments.

[0050] The service provider can select the optimal delivery method by referring to the user's past usage history at the time of delivery. For example, the service provider can select the optimal delivery method based on the format of slides or videos the user has used in the past. For example, the service provider can analyze the user's past usage history, identify preferred formats, and select a delivery method. The service provider can also select the optimal delivery method from the user's past usage history. For example, the service provider can refer to the user's past usage history and select the optimal delivery method. Furthermore, the service provider can adjust the delivery method based on the user's past usage history. For example, the service provider can analyze the user's past usage history and adjust the delivery method. In this way, the service provider can select the optimal delivery method by referring to the user's past usage history. Past usage history includes, but is not limited to, the type of history and details of how it was referenced. Some or all of the above processing in the service provider may be performed using, for example, AI, or not using AI. For example, the service provider can input the user's past usage history data into a generating AI and have the generating AI perform the selection of the optimal delivery method.

[0051] The delivery unit can select the optimal delivery format at the time of delivery, taking into account the user's device information. For example, if the user is using a smartphone, the delivery unit can select a delivery format that matches the screen size. For example, the delivery unit can select a delivery format optimized for smartphones based on the user's device information. The delivery unit can also select a delivery format optimized for larger screens if the user is using a tablet. For example, the delivery unit can select a delivery format optimized for tablets based on the user's device information. Furthermore, if the user is using a desktop, the delivery unit can select a high-resolution delivery format. For example, the delivery unit can select a high-resolution delivery format optimized for desktops based on the user's device information. This improves visibility by allowing the delivery unit to select the optimal delivery format based on the user's device information. Device information includes, but is not limited to, the type of device and the method of acquiring the information. Some or all of the above processing in the delivery unit may be performed using, for example, AI, or not using AI. For example, the delivery unit can input the user's device information into a generating AI and have the generating AI select the optimal delivery format.

[0052] The service provider can select the optimal service delivery method at the time of delivery, taking into account the user's geographical location information. For example, if the user is in the office, the service provider can select the optimal service delivery method for the office environment. For example, the service provider can select a service delivery method optimized for the office environment based on the user's geographical location information. The service provider can also select the optimal service delivery method for the home environment if the user is at home. For example, the service provider can select a service delivery method optimized for the home environment based on the user's geographical location information. Furthermore, if the user is out and about, the service provider can select the optimal service delivery method for the mobile environment. For example, the service provider can select a service delivery method optimized for the mobile environment based on the user's geographical location information. This improves visibility by allowing the service provider to select the optimal service delivery method based on the user's geographical location information. Geographical location information includes, but is not limited to, the type of location information and the method of acquiring the information. Some or all of the above processing in the service provider may be performed using, for example, AI, or not using AI. For example, the service provider can input the user's geographical location information into a generating AI and have the generating AI select the optimal service delivery method.

[0053] The service provider can analyze the user's social media activity and provide relevant slides and videos at the time of delivery. For example, the service provider can analyze the user's social media activity and provide relevant slides and videos. For example, the service provider can provide relevant slides and videos based on the user's social media activity. The service provider can also provide relevant slides and videos based on topics the user has shown interest in. For example, the service provider can analyze the user's social media activity and provide relevant slides and videos based on topics the user has shown interest in. Furthermore, the service provider can analyze the content of the user's social media posts and provide relevant slides and videos. For example, the service provider can analyze the content of the user's social media posts and provide relevant slides and videos. In this way, the service provider can provide relevant slides and videos by analyzing the user's social media activity. Social media activity includes, but is not limited to, the type of activity and details of the analysis method. Some or all of the processing described above in the service provider may be performed using, for example, AI, or not using AI. For example, the service provider can input the user's social media activity data into a generating AI and have the generating AI perform the provision of relevant slides and videos.

[0054] The modification unit can select the optimal modification method by referring to the past modification history of the business flow when making modifications. For example, the modification unit can select the optimal modification method based on the past modification history. For example, the modification unit can refer to the past modification history, identify similar modification patterns, and select a modification method. The modification unit can also analyze the past modification history and select the optimal modification method. For example, the modification unit can analyze the past modification history and select the optimal modification method. Furthermore, the modification unit can improve the modification algorithm based on the past modification history. For example, the modification unit improves the modification algorithm based on the past modification history to improve accuracy. As a result, the modification unit can select the optimal modification method by referring to the past modification history of the business flow. The past modification history includes, but is not limited to, the type of history and details of the referencing method. Some or all of the above processes in the modification unit may be performed using AI, for example, or without AI. For example, the modification unit can input past modification history data into a generating AI and have the generating AI select the optimal modification method.

[0055] The modification unit can propose modifications by referring to relevant documentation for the business process during the modification process. For example, the modification unit can refer to relevant documentation for the business process and propose modifications. For example, the modification unit can propose the optimal modification method based on relevant documentation for the business process. The modification unit can also analyze relevant documentation for the business process and supplement the modifications. For example, the modification unit can analyze relevant documentation for the business process and supplement the current modifications. Furthermore, the modification unit can improve the modification algorithm based on relevant documentation for the business process. For example, the modification unit improves the modification algorithm and increases accuracy based on relevant documentation for the business process. As a result, the accuracy of the modifications is improved by the modification unit referring to relevant documentation for the business process. Relevant documentation includes, but is not limited to, the type of documentation and details of how to refer to it. Some or all of the above processes in the modification unit may be performed using AI, for example, or without AI. For example, the modification unit can input relevant documentation data for the business process into a generating AI and have the generating AI execute the modification proposal.

[0056] The presentation unit can adjust the level of detail of the presentation content based on the importance of the business process flow. For example, the presentation unit can present detailed issues and solutions for important business processes. For example, the presentation unit can evaluate the importance of business processes and present detailed issues and solutions for important business processes. The presentation unit can also present concise issues and solutions for less important business processes. For example, the presentation unit can evaluate the importance of business processes and present concise issues and solutions for less important business processes. Furthermore, the presentation unit can present issues and solutions with an appropriate level of detail according to the importance of the business process flow. For example, the presentation unit can evaluate the importance of business processes and present issues and solutions with an appropriate level of detail. This enables efficient business improvement by presenting issues and solutions with a level of detail appropriate to the importance of the business process flow. The importance of a business process flow includes, but is not limited to, the criteria for evaluating importance and the details of the adjustment method. Some or all of the above processing in the presentation unit may be performed using, for example, AI, or not using AI. For example, the presentation unit can input importance data for business workflows into the generating AI and have the generating AI adjust the level of detail.

[0057] The presentation unit can adjust the order of the presented content based on the relevance of the business processes during presentation. For example, the presentation unit can prioritize the inclusion of highly relevant business processes in issues and solutions. For example, the presentation unit can evaluate the relevance of business processes and prioritize the inclusion of highly relevant business processes in issues and solutions. The presentation unit can also postpone the inclusion of less relevant business processes in issues and solutions. For example, the presentation unit can evaluate the relevance of business processes and postpone the inclusion of less relevant business processes in issues and solutions. Furthermore, the presentation unit can present issues and solutions in an appropriate order according to the relevance of the business processes. For example, the presentation unit evaluates the relevance of business processes and presents issues and solutions in an appropriate order. In this way, the presentation unit can provide optimal issues and solutions by adjusting the order of the presented content based on the relevance of business processes. The relevance of business processes includes, but is not limited to, the criteria for evaluating relevance and the details of the adjustment method. Some or all of the above processing in the presentation unit may be performed using, for example, AI, or not using AI. For example, the presentation unit can input relationship data of the business flow into the generating AI and have the generating AI perform the order adjustments.

[0058] The audio data conversion unit can adjust the tone and speed of the audio according to the content of the speaker notes during the audio data conversion process. For example, if the content of the speaker notes is important, the audio data conversion unit will convert it to audio data in a calm tone. For example, the audio data conversion unit will analyze the content of the speaker notes and convert important content to audio data in a calm tone. The audio data conversion unit can also convert the content of the speaker notes to audio data in a bright tone if the content is not important. For example, the audio data conversion unit will analyze the content of the speaker notes and convert light content to audio data in a bright tone. Furthermore, if the content of the speaker notes is urgent, the audio data conversion unit can convert it to audio data quickly. For example, the audio data conversion unit will analyze the content of the speaker notes and convert urgent content to audio data quickly. In this way, the audio data conversion unit can generate more appropriate audio data by adjusting the tone and speed according to the content of the speaker notes. The tone and speed of the audio include, but are not limited to, the pitch and speed of the tone and the method of adjusting the speed. Some or all of the above-described processing in the audio data conversion unit may be performed using AI, for example, or without AI. For example, the audio data conversion unit can input speaker note content data into a generating AI and have the generating AI perform adjustments to the tone and speed of the speech.

[0059] The audio data conversion unit can improve the accuracy of audio data conversion by referring to relevant literature for speaker notes during the conversion process. For example, the audio data conversion unit can improve the accuracy of audio data conversion by referring to relevant literature for speaker notes. For example, the audio data conversion unit can select the optimal audio data conversion method based on the relevant literature for speaker notes. The audio data conversion unit can also improve the accuracy of audio data conversion by analyzing the relevant literature for speaker notes. For example, the audio data conversion unit can improve the accuracy of audio data conversion by analyzing the relevant literature for speaker notes. Furthermore, the audio data conversion unit can improve the audio data conversion algorithm based on the relevant literature for speaker notes. For example, the audio data conversion unit can improve the accuracy of audio data conversion by improving the audio data conversion algorithm based on the relevant literature for speaker notes. As a result, the audio data conversion unit improves the accuracy of audio data conversion by referring to relevant literature for speaker notes. The relevant literature includes, but is not limited to, the type of literature and details of how it is referenced. Some or all of the above processing in the audio data conversion unit may be performed using, for example, AI, or not using AI. For example, the audio data conversion unit can input related literature data for speaker notes into the generating AI, allowing the generating AI to improve the accuracy of the audio data conversion.

[0060] The video creation unit can adjust the video's structure according to the content of the slides and speaker notes during video creation. For example, if the content of the slides or speaker notes is important, the video creation unit will create a detailed video. For example, the video creation unit will analyze the content of the slides and speaker notes and create a detailed video for the important content. The video creation unit can also create a concise video if the content of the slides or speaker notes is light. For example, the video creation unit will analyze the content of the slides and speaker notes and create a concise video for the light content. Furthermore, the video creation unit can quickly create a video if the content of the slides or speaker notes is urgent. For example, the video creation unit will analyze the content of the slides and speaker notes and quickly create a video for the urgent content. In this way, the video creation unit can generate a more appropriate video by adjusting the video's structure according to the content of the slides and speaker notes. The video structure includes, but is not limited to, detailed structure and adjustment criteria. Some or all of the above processes in the video creation unit may be performed using, for example, AI, or not using AI. For example, the video creation unit can input content data from slides and speaker notes into a generation AI, and have the generation AI perform adjustments to the video's structure.

[0061] The video creation unit can improve the accuracy of video creation by referring to relevant literature in the slides and speaker notes during video creation. For example, the video creation unit can improve the accuracy of video creation by referring to relevant literature in the slides and speaker notes. For example, the video creation unit can select the optimal video creation method based on the relevant literature in the slides and speaker notes. The video creation unit can also improve the accuracy of video creation by analyzing the relevant literature in the slides and speaker notes. For example, the video creation unit can improve the accuracy of video creation by analyzing the relevant literature in the slides and speaker notes. Furthermore, the video creation unit can improve the accuracy of video creation based on the relevant literature in the slides and speaker notes. For example, the video creation unit can improve the accuracy of video creation by improving the video creation algorithm based on the relevant literature in the slides and speaker notes. As a result, the video creation unit improves the accuracy of video creation by referring to relevant literature in the slides and speaker notes. The relevant literature includes, but is not limited to, the type of literature and details of how to refer to it. Some or all of the above processing in the video creation unit may be performed using, for example, AI, or not using AI. For example, the video creation unit can input relevant bibliographic data for slides and speaker notes into a generation AI, allowing the AI ​​to improve the accuracy of video creation.

[0062] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0063] The analysis unit can dynamically change the analysis algorithm during analysis according to the complexity of the business flow. For example, if the business flow is simple, a simple analysis algorithm is applied. For example, the analysis unit applies a simple analysis algorithm to business flows with few steps and branching points. If the business flow is complex, a detailed analysis algorithm can also be applied. For example, the analysis unit applies a detailed analysis algorithm to business flows with many steps and branching points. Furthermore, an appropriate analysis algorithm can be selected according to the intermediate complexity of the business flow. For example, the analysis unit selects an algorithm that is intermediate between a simple analysis algorithm and a detailed analysis algorithm, depending on the complexity of the business flow. This improves the accuracy of the analysis by applying an analysis algorithm appropriate to the complexity of the business flow. The complexity of the business flow includes, but is not limited to, the number of steps and branching points in the flow. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input business flow complexity data into a generating AI and have the generating AI select the analysis algorithm.

[0064] The modification unit can select the optimal modification method by referring to the past modification history of the business flow when making modifications. For example, it can select the optimal modification method based on past modification history. For example, the modification unit can refer to past modification history, identify similar modification patterns, and select a modification method. It can also analyze past modification history and select the optimal modification method. For example, the modification unit can analyze past modification history and select the optimal modification method. Furthermore, it can improve the modification algorithm based on past modification history. For example, the modification unit can improve the modification algorithm based on past modification history to increase accuracy. As a result, the modification unit can select the optimal modification method by referring to the past modification history of the business flow. Past modification history includes, but is not limited to, the type of history and details of the referencing method. Some or all of the above processes in the modification unit may be performed using AI, for example, or without AI. For example, the modification unit can input past modification history data into a generating AI and have the generating AI select the optimal modification method.

[0065] The presentation unit can adjust the level of detail of the presented content based on the importance of the business process flow. For example, it can present detailed issues and solutions for important business processes. For example, the presentation unit can evaluate the importance of business processes and present detailed issues and solutions for important business processes. It can also present concise issues and solutions for less important business processes. For example, the presentation unit can evaluate the importance of business processes and present concise issues and solutions for less important business processes. Furthermore, it can present issues and solutions with an appropriate level of detail according to the importance of the business process flow. For example, the presentation unit can evaluate the importance of business processes and present issues and solutions with an appropriate level of detail. This enables efficient business improvement by presenting issues and solutions with a level of detail appropriate to the importance of the business process flow. The importance of a business process flow includes, but is not limited to, the criteria for evaluating importance and the details of the adjustment method. Some or all of the above processing in the presentation unit may be performed using, for example, AI, or not using AI. For example, the presentation unit can input importance data for business workflows into the generating AI and have the generating AI adjust the level of detail.

[0066] The audio data conversion unit can adjust the tone and speed of the audio according to the content of the speaker notes during the audio data conversion process. For example, if the content of the speaker notes is important, the audio data conversion can be performed in a calm tone. For example, the audio data conversion unit analyzes the content of the speaker notes and performs audio data conversion in a calm tone for important content. Also, if the content of the speaker notes is not important, the audio data conversion can be performed in a bright tone. For example, the audio data conversion unit analyzes the content of the speaker notes and performs audio data conversion in a bright tone for less important content. Furthermore, if the content of the speaker notes is urgent, the audio data conversion can be performed quickly. For example, the audio data conversion unit analyzes the content of the speaker notes and performs audio data conversion quickly for urgent content. In this way, the audio data conversion unit can generate more appropriate audio data by adjusting the tone and speed of the audio according to the content of the speaker notes. The tone and speed of the audio include, but are not limited to, methods for adjusting the pitch and speed of the tone. Some or all of the above processing in the audio data conversion unit may be performed using, for example, AI, or not using AI. For example, the audio data conversion unit can input the content data of the speaker notes into a generating AI, which can then perform adjustments to the tone and speed of the audio.

[0067] The video creation unit can improve the accuracy of video creation by referring to relevant literature in the slides and speaker notes during the video creation process. For example, it can improve the accuracy of video creation by referring to relevant literature in the slides and speaker notes. For example, the video creation unit can select the optimal video creation method based on the relevant literature in the slides and speaker notes. It can also improve the accuracy of video creation by analyzing the relevant literature in the slides and speaker notes. For example, the video creation unit can improve the accuracy of video creation by analyzing the relevant literature in the slides and speaker notes. Furthermore, it can improve the video creation algorithm based on the relevant literature in the slides and speaker notes. For example, the video creation unit can improve the accuracy of video creation by improving the video creation algorithm based on the relevant literature in the slides and speaker notes. As a result, the video creation unit improves the accuracy of video creation by referring to relevant literature in the slides and speaker notes. The relevant literature includes, but is not limited to, the type of literature and details of how to refer to it. Some or all of the above processing in the video creation unit may be performed using AI, for example, or not using AI. For example, the video creation unit can input relevant bibliographic data for slides and speaker notes into a generation AI, allowing the AI ​​to improve the accuracy of video creation.

[0068] The following briefly describes the processing flow for example form 1.

[0069] Step 1: The speech recognition unit transcribes the audio data into text. The audio data includes, but is not limited to, the audio file format (WAV, MP3, etc.) and the content of the audio (conversation, lecture, etc.). The speech recognition unit transcribes the audio data using, for example, a speech recognition algorithm. Step 2: The analysis unit analyzes the data transcribed by the speech recognition unit and generates a business flow. For example, the analysis unit uses an analysis algorithm to analyze the transcribed data and generates a business flow based on the type of business process and the level of detail of the flow. Step 3: The generation unit generates a BPR proposal based on the data analyzed by the analysis unit. The BPR proposal may include, but is not limited to, suggestions for improving business processes or specific reform methods. The generation unit generates the BPR proposal using, for example, a generation algorithm. Step 4: The provider provides the BPR proposal generated by the generator as slides or a video. The slides or video may include, but are not limited to, the slide format, video length, and resolution. The provider may, for example, use slide creation software or video editing software to provide the BPR proposal as slides or a video.

[0070] (Example of form 2) The business process reengineering system according to an embodiment of the present invention provides a mechanism for implementing business process reengineering (BPR) in a natural language conversational format for local governments and private companies that are not making progress in internalizing BPR. This system allows business personnel to easily create materials and videos for implementing BPR simply by verbally explaining the workflow. For example, when a business person verbally explains the workflow, a flowchart is created using speech recognition technology. For example, if a business person explains, "First, we receive inquiries from customers, and then a staff member handles them," the speech recognition technology transcribes the content and generates a flowchart. Next, if there are any missing parts in the generated flowchart, additional information is provided to correct it into a more accurate flowchart. For example, by providing additional information such as, "If there are multiple inquiries, the staff member prioritizes and handles them," the flowchart is corrected. Furthermore, anticipated challenges and proposed solutions are presented. For example, if delays in responding to inquiries are a challenge, a solution such as, "Introduce an AI-powered automated response system," is presented. Finally, the business flow, challenges, and solutions are summarized in slides, and a video is created. For example, generated flowcharts, issues, and solutions are compiled into slides, speaker notes are created based on these slides, and then converted into audio data. This process generates a video from the slides and speaker notes. This system allows business personnel to easily create materials and videos for implementing BPR simply by explaining the workflow in natural language. This will promote the in-house implementation of BPR in local governments and private companies, improving operational efficiency. In short, the business reform system allows business personnel to easily create materials and videos for implementing BPR simply by explaining the workflow in natural language.

[0071] The business process reform system according to this embodiment comprises a speech recognition unit, an analysis unit, a generation unit, and a provision unit. The speech recognition unit transcribes audio data into text. The audio data includes, for example, the audio file format (WAV, MP3, etc.) and the content of the audio (conversation, lecture, etc.), but is not limited to such examples. The speech recognition unit transcribes the audio data using, for example, a speech recognition algorithm. The analysis unit analyzes the data transcribed by the speech recognition unit and generates a business flow. The analysis unit analyzes the transcribed data using, for example, an analysis algorithm and generates a business flow based on the type of business process and the level of detail of the flow. The generation unit generates a BPR proposal based on the data analyzed by the analysis unit. The BPR proposal includes, for example, suggestions for improving business processes and specific reform methods, but is not limited to such examples. The generation unit generates the BPR proposal using, for example, a generation algorithm. The provision unit provides the BPR proposal generated by the generation unit as slides or videos. The slides or videos include, for example, the slide format and the length and resolution of the video, but is not limited to such examples. The service provider, for example, uses slide creation software or video editing software to provide the BPR proposal as slides or videos. This allows the business process reform system to efficiently implement business process reform by transcribing audio data, generating business flow diagrams, and providing the BPR proposal.

[0072] The speech recognition unit transcribes audio data into text. Audio data includes, but is not limited to, audio file formats (WAV, MP3, etc.) and audio content (conversations, speeches, etc.). The speech recognition unit transcribes the audio data using, for example, a speech recognition algorithm. Specifically, the speech recognition unit utilizes a deep learning-based speech recognition model to transcribe audio data with high accuracy. The speech recognition model is pre-trained using a large amount of audio data and corresponding text data, and can handle various accents and speaker differences. Upon receiving audio data, the speech recognition unit first preprocesses the audio signal, performing noise reduction and volume normalization. Then, it divides the audio signal into frames and extracts features from each frame. These features are input to the speech recognition model, and the corresponding text is output. Furthermore, the speech recognition unit uses a language model in conjunction to improve transcription accuracy by considering contextual information. The language model predicts appropriate words and phrases based on context, improving the naturalness and accuracy of the transcription result. This allows the speech recognition unit to quickly and accurately transcribe audio data such as conversations and lectures, and provide it to the subsequent analysis unit.

[0073] The analysis unit analyzes the data transcribed by the speech recognition unit and generates a business flow. For example, the analysis unit uses an analysis algorithm to analyze the transcribed data and generates a business flow based on the type of business process and the level of detail of the flow. Specifically, the analysis unit uses natural language processing technology to analyze the transcribed data and extract keywords and phrases related to the business process. These keywords and phrases indicate each step and action of the business process, and the analysis unit constructs a business flow based on these. First, the analysis unit tokenizes the transcribed data and analyzes the part of speech and meaning of each token. Next, it performs dependency analysis to clarify the relationships between each token. This makes it possible to understand how each step of the business process is interconnected. Furthermore, the analysis unit constructs the business flow hierarchically based on the type of business process and the level of detail of the flow. For example, it can generate a flowchart showing the higher-level business process and sub-flowcharts showing the detailed steps of each process. As a result, the analysis unit can generate a business flow that clearly shows the overall picture and details of the business process and provide it to the subsequent generation unit.

[0074] The generation unit generates BPR proposals based on data analyzed by the analysis unit. These proposals may include, but are not limited to, suggestions for improving business processes or specific reform methods. The generation unit generates BPR proposals using, for example, a generation algorithm. Specifically, it automatically generates proposals for streamlining and improving business processes based on the business flow provided by the analysis unit. The generation unit first evaluates each step of the business flow to identify bottlenecks and inefficiencies. Next, it refers to past success stories and best practices to propose solutions to these problems. Using a machine learning model, the generation unit proposes optimal improvements based on patterns learned from past data. For example, it can propose introducing tools or technologies to automate manual tasks in a specific business process, or propose streamlining the business flow. Furthermore, the generation unit simulates the effects of the proposed improvements and evaluates the predicted outcomes. This allows the generation unit to generate concrete and feasible BPR proposals and provide them to the subsequent delivery unit.

[0075] The providing department will provide the BPR proposals generated by the generating department as slides or videos. These slides or videos will include, but are not limited to, the slide format, video length, and resolution. The providing department will use, for example, slide creation software or video editing software to provide the BPR proposals as slides or videos. Specifically, the providing department will organize the information in slide or video format and create presentation materials to visually represent the BPR proposals provided by the generating department in an easily understandable way. Using slide creation software, they will visually represent improvement proposals and specific reform methods for each business process using diagrams and graphs. They will also use video editing software to create video explanations of the BPR proposals, adding narration and animation to provide content that is easy for viewers to understand. Furthermore, the providing department can customize the format and design of the slides and videos to create materials that align with the company's brand guidelines. This allows the providing department to provide visual materials that effectively communicate the generated BPR proposals and support the implementation of business reforms.

[0076] The modification unit can add additional information and modify the flowchart. For example, the modification unit can modify the flowchart when a business user provides additional information. For example, if a business user provides additional information such as "If there are multiple inquiries, the person in charge will prioritize and respond to them," the modification unit will modify the flowchart. The modification unit can also analyze the additional information provided by the business user and reflect it in the flowchart. For example, the modification unit can analyze the additional information provided by the business user and add branching points and detailed steps to the flowchart. Furthermore, the modification unit can review and optimize the overall structure of the flowchart based on the additional information provided by the business user. For example, the modification unit can review the overall structure of the flowchart based on the additional information provided by the business user to improve the efficiency of the business process. As a result, the modification unit can generate a more accurate flowchart by adding missing information. Additional information includes, but is not limited to, data types and methods of information acquisition. Some or all of the above processing in the modification unit may be performed using, for example, AI, or not using AI. For example, the modification unit can input additional information provided by the business person into the generation AI, and have the generation AI perform the modification of the flowchart.

[0077] The presentation unit can present problems or solutions. For example, the presentation unit can present problems that are anticipated based on the business flow. For example, the presentation unit might present a problem such as, "Delays in responding to inquiries are a problem." The presentation unit can also present solutions to problems. For example, the presentation unit might present a solution such as, "Implement an automated response system using AI." Furthermore, the presentation unit can also present priorities for problems and solutions. For example, the presentation unit might present priorities such as, "Delays in responding to inquiries are the highest priority problem, and implementing an automated response system using AI is the optimal solution." In this way, by presenting problems and solutions, the presentation unit can provide concrete proposals for business improvement. Problems or solutions include, but are not limited to, business problems and methods for proposing solutions. Some or all of the above processing in the presentation unit may be performed using, for example, AI, or not using AI. For example, the presentation unit can input business flow data into a generating AI and have the generating AI perform the presentation of problems and solutions.

[0078] The audio data conversion unit can convert presentation notes into audio data. For example, the audio data conversion unit can convert speaker notes into audio data. For example, the audio data conversion unit can convert the content of speaker notes into audio data using speech synthesis technology. The audio data conversion unit can also generate audio data that reads aloud the content of speaker notes. For example, the audio data conversion unit can generate audio data that reads aloud the content of speaker notes and use it in a presentation. Furthermore, the audio data conversion unit can convert the content of speaker notes into audio data in multiple languages. For example, the audio data conversion unit can convert the content of speaker notes into audio data in multiple languages ​​such as English, Japanese, and French. This makes it easier to create presentation materials by converting speaker notes into audio data. Presentation notes include, but are not limited to, the format of the notes and the level of detail in their content. Some or all of the above-described processes in the audio data conversion unit may be performed using, for example, AI, or not. For example, the audio data conversion unit can input the content of speaker notes into a generating AI and have the generating AI perform the audio data conversion.

[0079] The video creation unit can create videos from slides and presentation notes. For example, it can create videos based on slides and speaker notes. For instance, it can create a video that displays the slide content and plays the audio data of the speaker notes. The video creation unit can also create videos by adding animation effects to the slides. For example, it can add animation effects to the slide content to create a visually easy-to-understand video. Furthermore, the video creation unit can edit the slide and speaker note content to create short presentation videos. For example, it can edit the slide and speaker note content to create a concise presentation video. This allows the video creation unit to provide visually easy-to-understand materials by creating videos from slides and speaker notes. Videos include, but are not limited to, video length, resolution, and level of detail. Some or all of the above processes in the video creation unit may be performed using, for example, AI, or not. For example, the video creation unit can input slide and speaker note data into a generating AI and have the generating AI create the video.

[0080] The speech recognition unit can estimate the user's emotions and adjust the accuracy of speech recognition in real time based on the estimated emotions. For example, if the user is nervous, the speech recognition unit can increase the sensitivity of speech recognition to recognize speech more accurately. For example, the speech recognition unit can analyze the user's heart rate and facial expressions to detect tension. Also, if the user is relaxed, the speech recognition unit can return the sensitivity of speech recognition to normal to recognize natural conversation. For example, the speech recognition unit can analyze the tone and speed of the user's voice to detect relaxation. Furthermore, if the user is in a hurry, the speech recognition unit can increase the speed of speech recognition to process speech quickly. For example, the speech recognition unit can analyze the user's speaking speed to detect urgency. In this way, the speech recognition unit improves recognition accuracy by adjusting the accuracy of speech recognition according to the user's emotions. User emotions include, for example, the emotion estimation algorithm and the type of data used, but are not limited to such examples. Speech recognition accuracy includes, for example, the recognition rate and the misrecognition rate, but are not limited to such examples. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input user emotion data into the generative AI and have the generative AI perform adjustments to the accuracy of speech recognition.

[0081] The speech recognition unit can be equipped with a filtering function that automatically removes background noise during speech recognition. For example, the speech recognition unit can analyze ambient noise in real time during speech recognition and perform noise cancellation. For example, the speech recognition unit can collect ambient noise with a microphone and remove the noise using a noise cancellation algorithm. The speech recognition unit can also filter out noise in a specific frequency band and extract only the speech. For example, the speech recognition unit can filter out noise in a specific frequency band and enhance the speech signal. Furthermore, the speech recognition unit can use multiple microphones to identify noise sources and remove noise. For example, the speech recognition unit can use multiple microphones to identify noise sources and perform noise cancellation. This improves the accuracy of speech recognition by removing background noise. Background noise includes, but is not limited to, ambient sounds and background noise. Some or all of the above processing in the speech recognition unit may be performed using, for example, AI, or not using AI. For example, the speech recognition unit can have a generative AI perform the noise cancellation process.

[0082] The speech recognition unit can improve recognition accuracy by taking into account the speaker's accent and dialect during speech recognition. For example, the speech recognition unit can improve recognition accuracy by learning the speaker's accent in advance during speech recognition. For example, the speech recognition unit can learn the characteristics of the speaker's accent and reflect them in the recognition algorithm. The speech recognition unit can also analyze the characteristics of dialects and convert them to standard Japanese for recognition. For example, the speech recognition unit can use an algorithm that analyzes the characteristics of dialects and converts them to standard Japanese. Furthermore, the speech recognition unit can improve recognition accuracy by learning the speaker's pronunciation patterns in real time. For example, the speech recognition unit can learn the speaker's pronunciation patterns in real time and reflect them in the recognition algorithm. As a result, the speech recognition unit improves recognition accuracy by taking into account the speaker's accent and dialect. Accents and dialects include, but are not limited to, regional accents and dialect characteristics. Some or all of the above processing in the speech recognition unit may be performed using, for example, AI, or without using AI. For example, the speech recognition unit can input the speaker's accent and dialect characteristics into the generating AI, allowing the generating AI to improve recognition accuracy.

[0083] The speech recognition unit can estimate the user's emotions and prioritize processing the speech recognition results based on the estimated emotions. For example, if the user is nervous, the speech recognition unit will prioritize recognizing and processing important keywords. For example, the speech recognition unit will analyze the user's heart rate and facial expressions to detect tension and prioritize recognizing important keywords. Also, if the user is relaxed, the speech recognition unit can perform speech recognition while emphasizing the overall context. For example, the speech recognition unit will analyze the user's tone and speed of speech to detect relaxation and perform speech recognition while emphasizing the overall context. Furthermore, if the user is in a hurry, the speech recognition unit can prioritize recognizing short phrases and process them quickly. For example, the speech recognition unit will analyze the user's speaking speed to detect urgency and prioritize recognizing short phrases. In this way, the speech recognition unit can quickly obtain important information by prioritizing the processing of speech recognition results according to the user's emotions. Speech recognition results include, but are not limited to, prioritizing the recognition results and details of how to process them. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input user emotion data into the generative AI and have the generative AI perform priority processing of the speech recognition results.

[0084] The speech recognition unit can analyze the tone and speed of the speaker's voice during speech recognition and select an appropriate recognition model. For example, the speech recognition unit can analyze the tone of the speaker's voice during speech recognition and select a recognition model that matches the emotion. For example, the speech recognition unit can analyze the pitch and volume of the speaker's voice, estimate the emotion, and select an appropriate recognition model. The speech recognition unit can also analyze the speed at which the speaker is speaking and select a recognition model that matches the speed. For example, the speech recognition unit can analyze the speed of the speaker in real time and select a recognition model that matches the speed. Furthermore, the speech recognition unit can analyze the volume of the speaker's voice and select an appropriate recognition model. For example, the speech recognition unit can analyze the volume of the speaker's voice in real time and select a recognition model that matches the volume. As a result, the speech recognition unit improves recognition accuracy by selecting a recognition model that matches the tone and speed of the speaker's voice. The tone and speed of the voice include, but are not limited to, methods for measuring pitch and speed. Some or all of the above-described processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input data on the speaker's voice tone and speed into a generating AI and have the generating AI select a recognition model.

[0085] The speech recognition unit can be equipped with a function to individually recognize multiple speakers even when they are speaking simultaneously. For example, the speech recognition unit can separate the voices of multiple speakers and recognize them individually during speech recognition. For example, the speech recognition unit can collect the voices of multiple speakers with microphones, separate the voices using a speech separation algorithm, and recognize them individually. The speech recognition unit can also analyze the speech characteristics of each speaker and recognize them individually. For example, the speech recognition unit can analyze the speech characteristics of each speaker in real time and recognize them individually. Furthermore, the speech recognition unit can separate the content of each speaker's speech in real time and recognize it individually. For example, the speech recognition unit can separate the content of each speaker's speech in real time and recognize it individually. This improves the recognition accuracy of the speech recognition unit by allowing it to individually recognize multiple speakers even when they are speaking simultaneously. Multiple speakers include, but are not limited to, speaker separation algorithms and simultaneous recognition techniques. Some or all of the above processing in the speech recognition unit may be performed using, for example, AI, or not using AI. For example, the speech recognition unit can input speech data from multiple speakers into the generating AI and have the generating AI perform individual recognition processing.

[0086] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the user is tense, the analysis unit can provide a simple and easy-to-read display method. For example, the analysis unit can analyze the user's heart rate and facial expressions to detect tension and provide a simple display method. The analysis unit can also provide a display method that includes detailed information if the user is relaxed. For example, the analysis unit can analyze the user's voice tone and speed to detect relaxation and provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the analysis unit can provide a concise display method. For example, the analysis unit can analyze the user's speech speed to detect urgency and provide a concise display method. In this way, the analysis unit improves readability by adjusting the display method of the analysis results according to the user's emotions. The display method of the analysis results includes, but is not limited to, display format and adjustment criteria. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the processing described above in the analysis unit may be performed using AI, or not using AI. For example, the analysis unit may input user emotion data into the generation AI and have the generation AI adjust the display method.

[0087] The analysis unit can dynamically change the analysis algorithm during analysis according to the complexity of the business flow. For example, if the business flow is simple, the analysis unit applies a simple analysis algorithm. For example, the analysis unit applies a simple analysis algorithm to business flows with few steps and branching points. The analysis unit can also apply a detailed analysis algorithm if the business flow is complex. For example, the analysis unit applies a detailed analysis algorithm to business flows with many steps and branching points. Furthermore, the analysis unit can select an appropriate analysis algorithm according to the intermediate complexity of the business flow. For example, the analysis unit selects an algorithm that is intermediate between a simple analysis algorithm and a detailed analysis algorithm, depending on the complexity of the business flow. This improves the accuracy of the analysis by applying an analysis algorithm appropriate to the complexity of the business flow. The complexity of the business flow includes, but is not limited to, the number of steps and branching points in the flow. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input data on the complexity of the business flow into the generating AI and have the generating AI select an analysis algorithm.

[0088] The analysis unit can improve the accuracy of its analysis by referring to past business flow data during the analysis process. For example, the analysis unit analyzes the current business flow based on past business flow data. For example, the analysis unit can refer to past business flow data to identify similar patterns and improve the accuracy of the analysis. The analysis unit can also analyze past business flow data and select the optimal analysis method. For example, the analysis unit analyzes past business flow data and selects the optimal analysis method. Furthermore, the analysis unit can supplement the analysis results by referring to past business flow data. For example, the analysis unit supplements the current analysis results by referring to past business flow data. In this way, the analysis unit improves the accuracy of its analysis by referring to past business flow data. Past business flow data includes, but is not limited to, details such as data type and referencing method. Some or all of the above processes in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input past business flow data into a generating AI and have the generating AI perform the improvement of analysis accuracy.

[0089] The analysis unit can estimate the user's emotions and prioritize the analysis results based on the estimated emotions. For example, if the user is tense, the analysis unit will prioritize displaying important analysis results. For instance, it might analyze the user's heart rate and facial expressions to detect tension and prioritize displaying important results. Furthermore, if the user is relaxed, the analysis unit can display the overall analysis results in a balanced manner. For example, it might analyze the user's voice tone and speed to detect relaxation and prioritize displaying the overall analysis results. Additionally, if the user is in a hurry, the analysis unit can prioritize displaying analysis results that can be quickly understood. For example, it might analyze the user's speech rate to detect urgency and prioritize displaying analysis results that can be quickly understood. This allows the analysis unit to quickly provide important information by prioritizing analysis results according to the user's emotions. Prioritization of analysis results includes, but is not limited to, criteria for evaluating importance and methods for prioritization. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generating AI may be a text generating AI (e.g., LLM) or a multimodal generating AI, but is not limited to such examples. Some or all of the processing described above in the analysis unit may be performed using AI, or not using AI. For example, the analysis unit can input user emotion data into the generating AI and have the generating AI perform priority determination of the analysis results.

[0090] The analysis unit can measure the time taken for each step of a business process during analysis and propose an efficient flow. For example, the analysis unit can measure the time taken for each step and identify the most time-consuming step. For example, the analysis unit can record the start and end times of each step of a business process and identify the most time-consuming step. The analysis unit can also analyze the time taken for each step and propose an efficient flow. For example, the analysis unit can analyze the time taken for each step and propose improvement plans to reduce the time taken. Furthermore, the analysis unit can compare the time taken for each step and propose the optimal flow. For example, the analysis unit compares the time taken for each step and proposes the most efficient flow. In this way, the analysis unit can propose an efficient business process by measuring the time taken for each step. The time taken for each step includes, but is not limited to, the time measurement method and evaluation criteria. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input the time data for each step into a generating AI and have the generating AI execute a proposal for an efficient flow.

[0091] The analysis unit can improve the accuracy of its analysis by referring to relevant documentation of the business process during the analysis. For example, the analysis unit can refer to relevant documentation of the business process to improve the accuracy of its analysis. For example, the analysis unit can select the optimal analysis method based on the relevant documentation of the business process. The analysis unit can also analyze relevant documentation of the business process to supplement the analysis results. For example, the analysis unit can analyze relevant documentation of the business process to supplement the current analysis results. Furthermore, the analysis unit can improve its analysis algorithm based on relevant documentation of the business process. For example, the analysis unit improves its analysis algorithm and accuracy based on relevant documentation of the business process. As a result, the analysis unit improves its analysis accuracy by referring to relevant documentation of the business process. Relevant documentation includes, but is not limited to, the type of documentation and details of how to refer to it. Some or all of the above processes in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input relevant documentation data of the business process into a generating AI and have the generating AI perform the improvement of analysis accuracy.

[0092] The generation unit can estimate the user's emotions and adjust the content of the generated BPR (Business Process Reengineering) proposal based on the estimated emotions. For example, if the user is nervous, the generation unit can generate a simple and easy-to-understand BPR proposal. For example, the generation unit can analyze the user's heart rate and facial expressions to detect the state of tension and generate a simple BPR proposal. The generation unit can also generate a BPR proposal with detailed information if the user is relaxed. For example, the generation unit can analyze the user's voice tone and speed to detect the relaxed state and generate a BPR proposal with detailed information. Furthermore, if the user is in a hurry, the generation unit can generate a BPR proposal that gets straight to the point. For example, the generation unit can analyze the user's speech speed to detect the hurried state and generate a BPR proposal that gets straight to the point. In this way, the generation unit can make more appropriate suggestions by adjusting the content of the BPR proposal according to the user's emotions. The content of the BPR proposal may include, but is not limited to, adjustment criteria and detailed content. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using AI, or not using AI. For example, the generation unit can input user sentiment data into the generation AI and have the generation AI perform content adjustments to the BPR proposal.

[0093] The generation unit can adjust the level of detail of the generated content based on the importance of the business process flow during generation. For example, the generation unit can generate detailed BPR proposals for important business processes. For example, the generation unit evaluates the importance of business processes and generates detailed BPR proposals for important business processes. The generation unit can also generate concise BPR proposals for less important business processes. For example, the generation unit evaluates the importance of business processes and generates concise BPR proposals for less important business processes. Furthermore, the generation unit can generate BPR proposals with an appropriate level of detail according to the importance of the business processes. For example, the generation unit evaluates the importance of business processes and generates BPR proposals with an appropriate level of detail. This enables efficient business improvement by generating BPR proposals with a level of detail appropriate to the importance of the business processes. The importance of business processes includes, but is not limited to, the criteria for evaluating importance and the details of the adjustment method. Some or all of the above-described processes in the generation unit may be performed using, for example, AI, or not using AI. For example, the generation unit can input importance data of the business flow into the generation AI and have the generation AI perform adjustments to the level of detail.

[0094] The generation unit can apply different generation algorithms depending on the category of the business flow during generation. For example, if the business flow is customer service, the generation unit can apply a generation algorithm specialized for customer service. For example, the generation unit can apply a generation algorithm specialized for customer service business flows. The generation unit can also apply a generation algorithm specialized for internal management if the business flow is internal management. For example, the generation unit can apply a generation algorithm specialized for internal management business flows. Furthermore, if the business flow is production management, the generation unit can apply a generation algorithm specialized for production management. For example, the generation unit can apply a generation algorithm specialized for production management business flows. In this way, the generation unit can generate the optimal BPR proposal by applying a generation algorithm according to the category of the business flow. The categories of business flows include, for example, the type of category and the details of the algorithm to be applied, but are not limited to such examples. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input business flow category data into a generation AI and have the generation AI execute the application of the generation algorithm.

[0095] The generation unit can estimate the user's emotions and determine the priority of BPR (Business Process Reengineering) proposals based on the estimated emotions. For example, if the user is tense, the generation unit will prioritize displaying important BPR proposals. For instance, it might analyze the user's heart rate and facial expressions to detect tension and prioritize displaying important BPR proposals. Furthermore, if the user is relaxed, the generation unit can display a balanced selection of BPR proposals. For example, it might analyze the user's voice tone and speed to detect relaxation and prioritize displaying a balanced selection of BPR proposals. Additionally, if the user is in a hurry, the generation unit can prioritize displaying BPR proposals that can be quickly understood. For example, it might analyze the user's speech rate to detect urgency and prioritize displaying BPR proposals that can be quickly understood. This allows the generation unit to quickly provide important information by prioritizing BPR proposals according to the user's emotions. The prioritization of BPR proposals includes, but is not limited to, the evaluation criteria and determination methods for prioritizing. Emotion estimation is achieved using an emotion estimation function, for example, by using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can input user emotion data into the generative AI and have the generative AI perform priority determination of BPR proposals.

[0096] The generation unit can determine the priority of the generated content based on the submission timing of the business process flow during generation. For example, the generation unit can prioritize generating BPR proposals for business process flows with approaching submission deadlines. For example, the generation unit can evaluate the submission deadlines of business process flows and prioritize generating BPR proposals for those with approaching deadlines. The generation unit can also postpone generating BPR proposals for business process flows with distant submission deadlines. For example, the generation unit can evaluate the submission deadlines of business process flows and postpone generating BPR proposals for those with distant deadlines. Furthermore, the generation unit can generate BPR proposals with appropriate priorities according to the submission timing. For example, the generation unit can evaluate the submission timing of business process flows and generate BPR proposals with appropriate priorities. This enables efficient business improvement by allowing the generation unit to determine priorities based on the submission timing of business process flows. The submission timing includes, but is not limited to, the evaluation criteria for submission timing and the details of the method for determining priorities. Some or all of the above processing in the generation unit may be performed using, for example, AI, or not using AI. For example, the generation unit can input data on the submission timing of business workflows into the generation AI, and have the generation AI determine the priorities.

[0097] The generation unit can adjust the order of generated content based on the relevance of business processes during generation. For example, the generation unit can prioritize the inclusion of highly relevant business processes in the BPR proposal. For example, the generation unit evaluates the relevance of business processes and prioritizes the inclusion of highly relevant business processes in the BPR proposal. The generation unit can also postpone the inclusion of less relevant business processes in the BPR proposal. For example, the generation unit evaluates the relevance of business processes and postpones the inclusion of less relevant business processes in the BPR proposal. Furthermore, the generation unit can generate the BPR proposal in an appropriate order according to the relevance of business processes. For example, the generation unit evaluates the relevance of business processes and generates the BPR proposal in an appropriate order. In this way, the generation unit can provide the optimal BPR proposal by adjusting the order of generated content based on the relevance of business processes. The relevance of business processes includes, but is not limited to, the criteria for evaluating relevance and the details of the adjustment method. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the relevance data of the business flow into the generation AI and have the generation AI perform the order adjustments.

[0098] The service provider can estimate the user's emotions and adjust the content of the slides and videos provided based on the estimated emotions. For example, if the user is nervous, the service provider can provide simple and easy-to-understand slides and videos. For example, the service provider can analyze the user's heart rate and facial expressions to detect tension and provide simple slides and videos. The service provider can also provide slides and videos with detailed information if the user is relaxed. For example, the service provider can analyze the user's tone and speed of speech to detect relaxation and provide slides and videos with detailed information. Furthermore, if the user is in a hurry, the service provider can provide slides and videos that get straight to the point. For example, the service provider can analyze the user's speaking speed to detect urgency and provide slides and videos that get straight to the point. In this way, the service provider improves readability by adjusting the content of slides and videos according to the user's emotions. The content of slides and videos may include, but is not limited to, adjustment criteria and content details. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal-generating AI. Some or all of the processing described above in the service provider may be performed using AI, or not using AI. For example, the service provider may input user emotion data into the generative AI and have the generative AI perform content adjustments for slides and videos.

[0099] The service provider can select the optimal delivery method by referring to the user's past usage history at the time of delivery. For example, the service provider can select the optimal delivery method based on the format of slides or videos the user has used in the past. For example, the service provider can analyze the user's past usage history, identify preferred formats, and select a delivery method. The service provider can also select the optimal delivery method from the user's past usage history. For example, the service provider can refer to the user's past usage history and select the optimal delivery method. Furthermore, the service provider can adjust the delivery method based on the user's past usage history. For example, the service provider can analyze the user's past usage history and adjust the delivery method. In this way, the service provider can select the optimal delivery method by referring to the user's past usage history. Past usage history includes, but is not limited to, the type of history and details of how it was referenced. Some or all of the above processing in the service provider may be performed using, for example, AI, or not using AI. For example, the service provider can input the user's past usage history data into a generating AI and have the generating AI perform the selection of the optimal delivery method.

[0100] The delivery unit can select the optimal delivery format at the time of delivery, taking into account the user's device information. For example, if the user is using a smartphone, the delivery unit can select a delivery format that matches the screen size. For example, the delivery unit can select a delivery format optimized for smartphones based on the user's device information. The delivery unit can also select a delivery format optimized for larger screens if the user is using a tablet. For example, the delivery unit can select a delivery format optimized for tablets based on the user's device information. Furthermore, if the user is using a desktop, the delivery unit can select a high-resolution delivery format. For example, the delivery unit can select a high-resolution delivery format optimized for desktops based on the user's device information. This improves visibility by allowing the delivery unit to select the optimal delivery format based on the user's device information. Device information includes, but is not limited to, the type of device and the method of acquiring the information. Some or all of the above processing in the delivery unit may be performed using, for example, AI, or not using AI. For example, the delivery unit can input the user's device information into a generating AI and have the generating AI select the optimal delivery format.

[0101] The delivery system can estimate the user's emotions and prioritize the slides and videos it delivers based on those emotions. For example, if the user is nervous, the system will prioritize important slides and videos. For instance, it could analyze the user's heart rate and facial expressions to detect tension and prioritize important slides and videos. Furthermore, if the user is relaxed, the system can deliver a balanced mix of slides and videos. For example, it could analyze the user's tone and speed of speech to detect relaxation and prioritize slides and videos. Additionally, if the user is in a hurry, the system can prioritize slides and videos that can be quickly understood. For example, it could analyze the user's speaking speed to detect urgency and prioritize slides and videos that can be quickly understood. This allows the system to deliver important information quickly by prioritizing slides and videos according to the user's emotions. Prioritization of slides and videos includes, but is not limited to, detailed criteria and methods for determining priority. Emotion estimation is achieved using an emotion estimation function, for example, by using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI or not using AI. For example, the service provider can input user emotion data into a generative AI and have the generative AI perform priority determination of slides and videos.

[0102] The service provider can select the optimal service delivery method at the time of delivery, taking into account the user's geographical location information. For example, if the user is in the office, the service provider can select the optimal service delivery method for the office environment. For example, the service provider can select a service delivery method optimized for the office environment based on the user's geographical location information. The service provider can also select the optimal service delivery method for the home environment if the user is at home. For example, the service provider can select a service delivery method optimized for the home environment based on the user's geographical location information. Furthermore, if the user is out and about, the service provider can select the optimal service delivery method for the mobile environment. For example, the service provider can select a service delivery method optimized for the mobile environment based on the user's geographical location information. This improves visibility by allowing the service provider to select the optimal service delivery method based on the user's geographical location information. Geographical location information includes, but is not limited to, the type of location information and the method of acquiring the information. Some or all of the above processing in the service provider may be performed using, for example, AI, or not using AI. For example, the service provider can input the user's geographical location information into a generating AI and have the generating AI select the optimal service delivery method.

[0103] The service provider can analyze the user's social media activity and provide relevant slides and videos at the time of delivery. For example, the service provider can analyze the user's social media activity and provide relevant slides and videos. For example, the service provider can provide relevant slides and videos based on the user's social media activity. The service provider can also provide relevant slides and videos based on topics the user has shown interest in. For example, the service provider can analyze the user's social media activity and provide relevant slides and videos based on topics the user has shown interest in. Furthermore, the service provider can analyze the content of the user's social media posts and provide relevant slides and videos. For example, the service provider can analyze the content of the user's social media posts and provide relevant slides and videos. In this way, the service provider can provide relevant slides and videos by analyzing the user's social media activity. Social media activity includes, but is not limited to, the type of activity and details of the analysis method. Some or all of the processing described above in the service provider may be performed using, for example, AI, or not using AI. For example, the service provider can input the user's social media activity data into a generating AI and have the generating AI perform the provision of relevant slides and videos.

[0104] The editing unit can estimate the user's emotions and prioritize the corrections based on those emotions. For example, if the user is nervous, the editing unit will prioritize displaying important corrections. For instance, it might analyze the user's heart rate and facial expressions to detect tension and prioritize displaying important corrections. Furthermore, if the user is relaxed, the editing unit can display all corrections in a balanced manner. For example, it might analyze the user's voice tone and speed to detect relaxation and prioritize displaying all corrections. Additionally, if the user is in a hurry, the editing unit can prioritize displaying corrections that can be quickly understood. For example, it might analyze the user's speech speed to detect urgency and prioritize displaying corrections that can be quickly understood. This allows the editing unit to quickly provide important information by prioritizing corrections according to the user's emotions. The prioritization of corrections includes, but is not limited to, detailed criteria for evaluating priority and determining the method. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generating AI may be a text generating AI (e.g., LLM) or a multimodal generating AI, but is not limited to such examples. Some or all of the processing described above in the editing unit may be performed using AI, or not using AI. For example, the editing unit may input user sentiment data into the generating AI and have the generating AI determine the priority of the corrections.

[0105] The modification unit can select the optimal modification method by referring to the past modification history of the business flow when making modifications. For example, the modification unit can select the optimal modification method based on the past modification history. For example, the modification unit can refer to the past modification history, identify similar modification patterns, and select a modification method. The modification unit can also analyze the past modification history and select the optimal modification method. For example, the modification unit can analyze the past modification history and select the optimal modification method. Furthermore, the modification unit can improve the modification algorithm based on the past modification history. For example, the modification unit improves the modification algorithm based on the past modification history to improve accuracy. As a result, the modification unit can select the optimal modification method by referring to the past modification history of the business flow. The past modification history includes, but is not limited to, the type of history and details of the referencing method. Some or all of the above processes in the modification unit may be performed using AI, for example, or without AI. For example, the modification unit can input past modification history data into a generating AI and have the generating AI select the optimal modification method.

[0106] The editing unit can estimate the user's emotions and adjust the display method of the edits based on the estimated emotions. For example, if the user is nervous, the editing unit can provide a simple and highly visible display method. For example, it can analyze the user's heart rate and facial expressions to detect the state of tension and provide a simple display method. The editing unit can also provide a display method that includes detailed information if the user is relaxed. For example, it can analyze the user's voice tone and speed to detect the relaxed state and provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the editing unit can provide a concise display method. For example, it can analyze the user's speech speed to detect the hurried state and provide a concise display method. In this way, the editing unit improves visibility by adjusting the display method of the edits according to the user's emotions. The display method of the edits includes, but is not limited to, display format and adjustment criteria. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generating AI may be a text generating AI (e.g., LLM) or a multimodal generating AI, but is not limited to such examples. Some or all of the above-described processes in the editing unit may be performed using AI, or not using AI. For example, the editing unit may input user sentiment data into the generating AI and have the generating AI adjust how the edited content is displayed.

[0107] The modification unit can propose modifications by referring to relevant documentation for the business process during the modification process. For example, the modification unit can refer to relevant documentation for the business process and propose modifications. For example, the modification unit can propose the optimal modification method based on relevant documentation for the business process. The modification unit can also analyze relevant documentation for the business process and supplement the modifications. For example, the modification unit can analyze relevant documentation for the business process and supplement the current modifications. Furthermore, the modification unit can improve the modification algorithm based on relevant documentation for the business process. For example, the modification unit improves the modification algorithm and increases accuracy based on relevant documentation for the business process. As a result, the accuracy of the modifications is improved by the modification unit referring to relevant documentation for the business process. Relevant documentation includes, but is not limited to, the type of documentation and details of how to refer to it. Some or all of the above processes in the modification unit may be performed using AI, for example, or without AI. For example, the modification unit can input relevant documentation data for the business process into a generating AI and have the generating AI execute the modification proposal.

[0108] The presentation unit can estimate the user's emotions and adjust the content of the tasks and solutions it presents based on the estimated emotions. For example, if the user is nervous, the presentation unit will present simple and easy-to-understand tasks and solutions. For example, it may analyze the user's heart rate and facial expressions to detect tension and present simple tasks and solutions. Furthermore, if the user is relaxed, the presentation unit can also present tasks and solutions with more detailed information. For example, it may analyze the user's voice tone and speed to detect relaxation and present tasks and solutions with more detailed information. Additionally, if the user is in a hurry, the presentation unit can present tasks and solutions that get straight to the point. For example, it may analyze the user's speech rate to detect urgency and present tasks and solutions that get straight to the point. This allows the presentation unit to make more appropriate suggestions by adjusting the content of tasks and solutions according to the user's emotions. The content of tasks and solutions may include, but is not limited to, adjustment criteria and detailed content. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generative AI may be a text-generating AI (e.g., LLM) or a multimodal generative AI, but is not limited to such examples. Some or all of the processing described above in the presentation unit may be performed using AI, or not using AI. For example, the presentation unit may input user emotion data into the generative AI and have the generative AI adjust the content of the problem and solution.

[0109] The presentation unit can adjust the level of detail of the presentation content based on the importance of the business process flow. For example, the presentation unit can present detailed issues and solutions for important business processes. For example, the presentation unit can evaluate the importance of business processes and present detailed issues and solutions for important business processes. The presentation unit can also present concise issues and solutions for less important business processes. For example, the presentation unit can evaluate the importance of business processes and present concise issues and solutions for less important business processes. Furthermore, the presentation unit can present issues and solutions with an appropriate level of detail according to the importance of the business process flow. For example, the presentation unit can evaluate the importance of business processes and present issues and solutions with an appropriate level of detail. This enables efficient business improvement by presenting issues and solutions with a level of detail appropriate to the importance of the business process flow. The importance of a business process flow includes, but is not limited to, the criteria for evaluating importance and the details of the adjustment method. Some or all of the above processing in the presentation unit may be performed using, for example, AI, or not using AI. For example, the presentation unit can input importance data for business workflows into the generating AI and have the generating AI adjust the level of detail.

[0110] The presentation unit can estimate the user's emotions and determine the priority of the tasks and solutions presented based on those emotions. For example, if the user is tense, the presentation unit will prioritize presenting important tasks and solutions. For instance, it might analyze the user's heart rate and facial expressions to detect tension and prioritize presenting important tasks and solutions. Furthermore, if the user is relaxed, the presentation unit can present a balanced mix of tasks and solutions. For example, it might analyze the user's tone and speed of speech to detect relaxation and present a balanced mix of tasks and solutions. Additionally, if the user is in a hurry, the presentation unit can prioritize tasks and solutions that can be quickly understood. For example, it might analyze the user's speaking speed to detect urgency and prioritize tasks and solutions that can be quickly understood. This allows the presentation unit to quickly provide important information by prioritizing tasks and solutions according to the user's emotions. Prioritization of tasks and solutions includes, but is not limited to, detailed criteria for evaluating priority and determining the method of priority. Emotion estimation is achieved using an emotion estimation function, for example, by using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the presentation unit may be performed using AI or not using AI. For example, the presentation unit can input user emotion data into a generative AI and have the generative AI perform the task of prioritizing problems and solutions.

[0111] The presentation unit can adjust the order of the presented content based on the relevance of the business processes during presentation. For example, the presentation unit can prioritize the inclusion of highly relevant business processes in issues and solutions. For example, the presentation unit can evaluate the relevance of business processes and prioritize the inclusion of highly relevant business processes in issues and solutions. The presentation unit can also postpone the inclusion of less relevant business processes in issues and solutions. For example, the presentation unit can evaluate the relevance of business processes and postpone the inclusion of less relevant business processes in issues and solutions. Furthermore, the presentation unit can present issues and solutions in an appropriate order according to the relevance of the business processes. For example, the presentation unit evaluates the relevance of business processes and presents issues and solutions in an appropriate order. In this way, the presentation unit can provide optimal issues and solutions by adjusting the order of the presented content based on the relevance of business processes. The relevance of business processes includes, but is not limited to, the criteria for evaluating relevance and the details of the adjustment method. Some or all of the above processing in the presentation unit may be performed using, for example, AI, or not using AI. For example, the presentation unit can input relationship data of the business flow into the generating AI and have the generating AI perform the order adjustments.

[0112] The voice data conversion unit can estimate the user's emotions and adjust the voice data conversion method based on the estimated emotions. For example, if the user is nervous, the voice data conversion unit will perform voice data conversion in a calm tone. For example, the voice data conversion unit can analyze the user's heart rate and facial expressions to detect tension and perform voice data conversion in a calm tone. The voice data conversion unit can also perform voice data conversion in a bright tone if the user is relaxed. For example, the voice data conversion unit can analyze the user's voice tone and speed to detect relaxation and perform voice data conversion in a bright tone. Furthermore, if the user is in a hurry, the voice data conversion unit can perform voice data conversion quickly. For example, the voice data conversion unit can analyze the user's speech speed to detect urgency and perform voice data conversion quickly. In this way, the voice data conversion unit can generate more appropriate voice data by adjusting the voice data conversion method according to the user's emotions. The voice data conversion method includes, but is not limited to, the data conversion technique and adjustment criteria. Emotion estimation is achieved using an emotion estimation function, for example, by using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speech data conversion unit may be performed using AI, for example, or without AI. For example, the speech data conversion unit can input user emotion data into the generative AI and have the generative AI perform adjustments to the speech data conversion method.

[0113] The audio data conversion unit can adjust the tone and speed of the audio according to the content of the speaker notes during the audio data conversion process. For example, if the content of the speaker notes is important, the audio data conversion unit will convert it to audio data in a calm tone. For example, the audio data conversion unit will analyze the content of the speaker notes and convert important content to audio data in a calm tone. The audio data conversion unit can also convert the content of the speaker notes to audio data in a bright tone if the content is not important. For example, the audio data conversion unit will analyze the content of the speaker notes and convert light content to audio data in a bright tone. Furthermore, if the content of the speaker notes is urgent, the audio data conversion unit can convert it to audio data quickly. For example, the audio data conversion unit will analyze the content of the speaker notes and convert urgent content to audio data quickly. In this way, the audio data conversion unit can generate more appropriate audio data by adjusting the tone and speed according to the content of the speaker notes. The tone and speed of the audio include, but are not limited to, the pitch and speed of the tone and the method of adjusting the speed. Some or all of the above-described processing in the audio data conversion unit may be performed using AI, for example, or without AI. For example, the audio data conversion unit can input speaker note content data into a generating AI and have the generating AI perform adjustments to the tone and speed of the speech.

[0114] The voice data conversion unit can estimate the user's emotions and determine the priority of voice data conversion based on the estimated emotions. For example, if the user is nervous, the voice data conversion unit will prioritize the conversion of important voice data. For example, the voice data conversion unit may analyze the user's heart rate and facial expressions to detect the state of tension and prioritize the conversion of important voice data. The voice data conversion unit can also balance the conversion of all voice data if the user is relaxed. For example, the voice data conversion unit may analyze the tone and speed of the user's voice to detect the state of relaxation and balance the conversion of all voice data. Furthermore, if the user is in a hurry, the voice data conversion unit can perform voice data conversion quickly. For example, the voice data conversion unit may analyze the user's speaking speed to detect the state of urgency and perform voice data conversion quickly. In this way, the voice data conversion unit can quickly provide important information by determining the priority of voice data conversion according to the user's emotions. The priority of voice data conversion includes, but is not limited to, the evaluation criteria and details of the determination method for priority. Emotion estimation is achieved using an emotion estimation function, for example, by using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speech data conversion unit may be performed using AI, for example, or without AI. For example, the speech data conversion unit can input user emotion data into the generative AI and have the generative AI perform priority determination for speech data conversion.

[0115] The audio data conversion unit can improve the accuracy of audio data conversion by referring to relevant literature for speaker notes during the conversion process. For example, the audio data conversion unit can improve the accuracy of audio data conversion by referring to relevant literature for speaker notes. For example, the audio data conversion unit can select the optimal audio data conversion method based on the relevant literature for speaker notes. The audio data conversion unit can also improve the accuracy of audio data conversion by analyzing the relevant literature for speaker notes. For example, the audio data conversion unit can improve the accuracy of audio data conversion by analyzing the relevant literature for speaker notes. Furthermore, the audio data conversion unit can improve the audio data conversion algorithm based on the relevant literature for speaker notes. For example, the audio data conversion unit can improve the accuracy of audio data conversion by improving the audio data conversion algorithm based on the relevant literature for speaker notes. As a result, the audio data conversion unit improves the accuracy of audio data conversion by referring to relevant literature for speaker notes. The relevant literature includes, but is not limited to, the type of literature and details of how it is referenced. Some or all of the above processing in the audio data conversion unit may be performed using, for example, AI, or not using AI. For example, the audio data conversion unit can input related literature data for speaker notes into the generating AI, allowing the generating AI to improve the accuracy of the audio data conversion.

[0116] The video creation unit can estimate the user's emotions and adjust the video content based on those emotions. For example, if the user is nervous, the video creation unit can create a simple and easy-to-understand video. For instance, it can analyze the user's heart rate and facial expressions to detect tension and create a simple video. Furthermore, if the user is relaxed, the video creation unit can create a video with detailed information. For example, it can analyze the user's voice tone and speed to detect relaxation and create a video with detailed information. Additionally, if the user is in a hurry, the video creation unit can create a concise video. For example, it can analyze the user's speaking speed to detect urgency and create a concise video. This allows the video creation unit to improve readability by adjusting the video content according to the user's emotions. The video content may include, but is not limited to, adjustment criteria and detailed content. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generative AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processes in the video creation unit may be performed using AI, or not using AI. For example, the video creation unit can input user emotion data into the generative AI and have the generative AI perform content adjustments for the video creation.

[0117] The video creation unit can adjust the video's structure according to the content of the slides and speaker notes during video creation. For example, if the content of the slides or speaker notes is important, the video creation unit will create a detailed video. For example, the video creation unit will analyze the content of the slides and speaker notes and create a detailed video for the important content. The video creation unit can also create a concise video if the content of the slides or speaker notes is light. For example, the video creation unit will analyze the content of the slides and speaker notes and create a concise video for the light content. Furthermore, the video creation unit can quickly create a video if the content of the slides or speaker notes is urgent. For example, the video creation unit will analyze the content of the slides and speaker notes and quickly create a video for the urgent content. In this way, the video creation unit can generate a more appropriate video by adjusting the video's structure according to the content of the slides and speaker notes. The video structure includes, but is not limited to, detailed structure and adjustment criteria. Some or all of the above processes in the video creation unit may be performed using, for example, AI, or not using AI. For example, the video creation unit can input content data from slides and speaker notes into a generation AI, and have the generation AI perform adjustments to the video's structure.

[0118] The video creation unit can estimate the user's emotions and determine the priority of video creation based on those emotions. For example, if the user is nervous, the video creation unit will prioritize creating important videos. For example, it can analyze the user's heart rate and facial expressions to detect their state of tension and prioritize creating important videos. Furthermore, if the user is relaxed, the video creation unit can create a balanced overall video. For example, it can analyze the user's voice tone and speed to detect their relaxed state and create a balanced overall video. Additionally, if the user is in a hurry, the video creation unit can create videos quickly. For example, it can analyze the user's speaking speed to detect their urgency and quickly create videos. This allows the video creation unit to quickly provide important information by prioritizing video creation according to the user's emotions. Prioritization of video creation includes, but is not limited to, detailed criteria for evaluating and determining priorities. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generative AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processes in the video creation unit may be performed using AI, or not using AI. For example, the video creation unit can input user emotion data into the generative AI and have the generative AI perform the task of determining the priority of video creation.

[0119] The video creation unit can improve the accuracy of video creation by referring to relevant literature in the slides and speaker notes during video creation. For example, the video creation unit can improve the accuracy of video creation by referring to relevant literature in the slides and speaker notes. For example, the video creation unit can select the optimal video creation method based on the relevant literature in the slides and speaker notes. The video creation unit can also improve the accuracy of video creation by analyzing the relevant literature in the slides and speaker notes. For example, the video creation unit can improve the accuracy of video creation by analyzing the relevant literature in the slides and speaker notes. Furthermore, the video creation unit can improve the accuracy of video creation based on the relevant literature in the slides and speaker notes. For example, the video creation unit can improve the accuracy of video creation by improving the video creation algorithm based on the relevant literature in the slides and speaker notes. As a result, the video creation unit improves the accuracy of video creation by referring to relevant literature in the slides and speaker notes. The relevant literature includes, but is not limited to, the type of literature and details of how to refer to it. Some or all of the above processing in the video creation unit may be performed using, for example, AI, or not using AI. For example, the video creation unit can input relevant bibliographic data for slides and speaker notes into a generation AI, allowing the AI ​​to improve the accuracy of video creation.

[0120] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0121] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the user is nervous, it can provide a simple and easy-to-read display method. For example, the analysis unit can analyze the user's heart rate and facial expressions to detect the state of tension and provide a simple display method. Also, if the user is relaxed, it can provide a display method that includes detailed information. For example, the analysis unit can analyze the user's voice tone and speed to detect the relaxed state and provide a display method that includes detailed information. Furthermore, if the user is in a hurry, it can provide a display method that gets straight to the point. For example, the analysis unit can analyze the user's speech speed to detect the hurried state and provide a display method that gets straight to the point. In this way, the analysis unit improves readability by adjusting the display method of the analysis results according to the user's emotions. The display method of the analysis results includes, but is not limited to, display format and adjustment criteria. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the processing described above in the analysis unit may be performed using AI, or not using AI. For example, the analysis unit may input user emotion data into the generation AI and have the generation AI adjust the display method.

[0122] The editing unit can estimate the user's emotions and prioritize the corrections based on those emotions. For example, if the user is nervous, it can prioritize displaying important corrections. For instance, the editing unit can analyze the user's heart rate and facial expressions to detect tension and prioritize displaying important corrections. If the user is relaxed, it can also display a balanced mix of corrections. For example, it can analyze the user's voice tone and speed to detect relaxation and display a balanced mix of corrections. Furthermore, if the user is in a hurry, it can prioritize displaying corrections that can be quickly understood. For example, it can analyze the user's speech speed to detect urgency and prioritize displaying corrections that can be quickly understood. This allows the editing unit to quickly provide important information by prioritizing corrections according to the user's emotions. The prioritization of corrections includes, but is not limited to, the evaluation criteria and determination methods for prioritizing. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generating AI may be a text generating AI (e.g., LLM) or a multimodal generating AI, but is not limited to such examples. Some or all of the processing described above in the editing unit may be performed using AI, or not using AI. For example, the editing unit may input user sentiment data into the generating AI and have the generating AI determine the priority of the corrections.

[0123] The presentation unit can estimate the user's emotions and adjust the content of the tasks and solutions presented based on the estimated emotions. For example, if the user is nervous, it can present simple and easy-to-understand tasks and solutions. For instance, the presentation unit can analyze the user's heart rate and facial expressions to detect tension and present simple tasks and solutions. If the user is relaxed, it can also present tasks and solutions with more detailed information. For example, it can analyze the user's voice tone and speed to detect relaxation and present tasks and solutions with more detailed information. Furthermore, if the user is in a hurry, it can present tasks and solutions that get straight to the point. For example, it can analyze the user's speaking speed to detect urgency and present tasks and solutions that get straight to the point. In this way, the presentation unit can make more appropriate suggestions by adjusting the content of tasks and solutions according to the user's emotions. The content of tasks and solutions includes, but is not limited to, adjustment criteria and details of content. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generative AI may be a text-generating AI (e.g., LLM) or a multimodal generative AI, but is not limited to such examples. Some or all of the processing described above in the presentation unit may be performed using AI, or not using AI. For example, the presentation unit may input user emotion data into the generative AI and have the generative AI adjust the content of the problem and solution.

[0124] The generation unit can estimate the user's emotions and adjust the content of the generated BPR (Business Process Reengineering) proposal based on the estimated emotions. For example, if the user is nervous, it can generate a simple and easy-to-understand BPR proposal. For instance, the generation unit can analyze the user's heart rate and facial expressions to detect their state of tension and generate a simple BPR proposal. Furthermore, if the user is relaxed, it can generate a BPR proposal containing detailed information. For example, the generation unit can analyze the user's voice tone and speed to detect their relaxed state and generate a BPR proposal containing detailed information. Additionally, if the user is in a hurry, it can generate a BPR proposal that gets straight to the point. For example, the generation unit can analyze the user's speaking speed to detect their hurried state and generate a BPR proposal that gets straight to the point. This allows the generation unit to provide more appropriate suggestions by adjusting the content of the BPR proposal according to the user's emotions. The content of the BPR proposal may include, but is not limited to, adjustment criteria and detailed content. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using AI, or not using AI. For example, the generation unit can input user sentiment data into the generation AI and have the generation AI perform content adjustments to the BPR proposal.

[0125] The service provider can estimate the user's emotions and adjust the content of the slides and videos provided based on the estimated emotions. For example, if the user is nervous, it can provide simple and easy-to-understand slides and videos. For instance, the service provider can analyze the user's heart rate and facial expressions to detect tension and provide simple slides and videos. If the user is relaxed, it can also provide slides and videos containing detailed information. For example, the service provider can analyze the user's voice tone and speed to detect relaxation and provide slides and videos containing detailed information. Furthermore, if the user is in a hurry, it can provide slides and videos that get straight to the point. For example, the service provider can analyze the user's speaking speed to detect urgency and provide slides and videos that get straight to the point. In this way, the service provider improves readability by adjusting the content of slides and videos according to the user's emotions. The content of slides and videos may include, but is not limited to, adjustment criteria and content details. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal-generating AI. Some or all of the processing described above in the service provider may be performed using AI, or not using AI. For example, the service provider may input user emotion data into the generative AI and have the generative AI perform content adjustments for slides and videos.

[0126] The analysis unit can dynamically change the analysis algorithm during analysis according to the complexity of the business flow. For example, if the business flow is simple, a simple analysis algorithm is applied. For example, the analysis unit applies a simple analysis algorithm to business flows with few steps and branching points. If the business flow is complex, a detailed analysis algorithm can also be applied. For example, the analysis unit applies a detailed analysis algorithm to business flows with many steps and branching points. Furthermore, an appropriate analysis algorithm can be selected according to the intermediate complexity of the business flow. For example, the analysis unit selects an algorithm that is intermediate between a simple analysis algorithm and a detailed analysis algorithm, depending on the complexity of the business flow. This improves the accuracy of the analysis by applying an analysis algorithm appropriate to the complexity of the business flow. The complexity of the business flow includes, but is not limited to, the number of steps and branching points in the flow. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input business flow complexity data into a generating AI and have the generating AI select the analysis algorithm.

[0127] The modification unit can select the optimal modification method by referring to the past modification history of the business flow when making modifications. For example, it can select the optimal modification method based on past modification history. For example, the modification unit can refer to past modification history, identify similar modification patterns, and select a modification method. It can also analyze past modification history and select the optimal modification method. For example, the modification unit can analyze past modification history and select the optimal modification method. Furthermore, it can improve the modification algorithm based on past modification history. For example, the modification unit can improve the modification algorithm based on past modification history to increase accuracy. As a result, the modification unit can select the optimal modification method by referring to the past modification history of the business flow. Past modification history includes, but is not limited to, the type of history and details of the referencing method. Some or all of the above processes in the modification unit may be performed using AI, for example, or without AI. For example, the modification unit can input past modification history data into a generating AI and have the generating AI select the optimal modification method.

[0128] The presentation unit can adjust the level of detail of the presented content based on the importance of the business process flow. For example, it can present detailed issues and solutions for important business processes. For example, the presentation unit can evaluate the importance of business processes and present detailed issues and solutions for important business processes. It can also present concise issues and solutions for less important business processes. For example, the presentation unit can evaluate the importance of business processes and present concise issues and solutions for less important business processes. Furthermore, it can present issues and solutions with an appropriate level of detail according to the importance of the business process flow. For example, the presentation unit can evaluate the importance of business processes and present issues and solutions with an appropriate level of detail. This enables efficient business improvement by presenting issues and solutions with a level of detail appropriate to the importance of the business process flow. The importance of a business process flow includes, but is not limited to, the criteria for evaluating importance and the details of the adjustment method. Some or all of the above processing in the presentation unit may be performed using, for example, AI, or not using AI. For example, the presentation unit can input importance data for business workflows into the generating AI and have the generating AI adjust the level of detail.

[0129] The audio data conversion unit can adjust the tone and speed of the audio according to the content of the speaker notes during the audio data conversion process. For example, if the content of the speaker notes is important, the audio data conversion can be performed in a calm tone. For example, the audio data conversion unit analyzes the content of the speaker notes and performs audio data conversion in a calm tone for important content. Also, if the content of the speaker notes is not important, the audio data conversion can be performed in a bright tone. For example, the audio data conversion unit analyzes the content of the speaker notes and performs audio data conversion in a bright tone for less important content. Furthermore, if the content of the speaker notes is urgent, the audio data conversion can be performed quickly. For example, the audio data conversion unit analyzes the content of the speaker notes and performs audio data conversion quickly for urgent content. In this way, the audio data conversion unit can generate more appropriate audio data by adjusting the tone and speed of the audio according to the content of the speaker notes. The tone and speed of the audio include, but are not limited to, methods for adjusting the pitch and speed of the tone. Some or all of the above processing in the audio data conversion unit may be performed using, for example, AI, or not using AI. For example, the audio data conversion unit can input the content data of the speaker notes into a generating AI, which can then perform adjustments to the tone and speed of the audio.

[0130] The video creation unit can improve the accuracy of video creation by referring to relevant literature in the slides and speaker notes during the video creation process. For example, it can improve the accuracy of video creation by referring to relevant literature in the slides and speaker notes. For example, the video creation unit can select the optimal video creation method based on the relevant literature in the slides and speaker notes. It can also improve the accuracy of video creation by analyzing the relevant literature in the slides and speaker notes. For example, the video creation unit can improve the accuracy of video creation by analyzing the relevant literature in the slides and speaker notes. Furthermore, it can improve the video creation algorithm based on the relevant literature in the slides and speaker notes. For example, the video creation unit can improve the accuracy of video creation by improving the video creation algorithm based on the relevant literature in the slides and speaker notes. As a result, the video creation unit improves the accuracy of video creation by referring to relevant literature in the slides and speaker notes. The relevant literature includes, but is not limited to, the type of literature and details of how to refer to it. Some or all of the above processing in the video creation unit may be performed using AI, for example, or not using AI. For example, the video creation unit can input relevant bibliographic data for slides and speaker notes into a generation AI, allowing the AI ​​to improve the accuracy of video creation.

[0131] The following briefly describes the processing flow for example form 2.

[0132] Step 1: The speech recognition unit transcribes the audio data into text. The audio data includes, but is not limited to, the audio file format (WAV, MP3, etc.) and the content of the audio (conversation, lecture, etc.). The speech recognition unit transcribes the audio data using, for example, a speech recognition algorithm. Step 2: The analysis unit analyzes the data transcribed by the speech recognition unit and generates a business flow. For example, the analysis unit uses an analysis algorithm to analyze the transcribed data and generates a business flow based on the type of business process and the level of detail of the flow. Step 3: The generation unit generates a BPR proposal based on the data analyzed by the analysis unit. The BPR proposal may include, but is not limited to, suggestions for improving business processes or specific reform methods. The generation unit generates the BPR proposal using, for example, a generation algorithm. Step 4: The provider provides the BPR proposal generated by the generator as slides or a video. The slides or video may include, but are not limited to, the slide format, video length, and resolution. The provider may, for example, use slide creation software or video editing software to provide the BPR proposal as slides or a video.

[0133] 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.

[0134] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0135] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0136] For example, the speech recognition unit is implemented by the processor 46 of the smart device 14 and transcribes the speech data into text. The analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the transcribed data to generate a business flow. The generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a BPR (Business Process Reengineering) proposal based on the analyzed data. The provision unit is implemented by the control unit 46A of the smart device 14 and provides the generated BPR proposal as slides or a video. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0137] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0138] 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.

[0139] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0140] 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.

[0141] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0142] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0143] 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.

[0144] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0145] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0146] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0147] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0148] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0149] 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.

[0150] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0151] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0152] For example, the speech recognition unit is implemented by the processor 46 of the smart glasses 214, which transcribes the speech data into text. The analysis unit is implemented by the specific processing unit 290 of the data processing device 12, which analyzes the transcribed data and generates a business flow. The generation unit is implemented by the specific processing unit 290 of the data processing device 12, which generates a BPR (Business Process Reengineering) proposal based on the analyzed data. The provision unit is implemented by the control unit 46A of the smart glasses 214, which provides the generated BPR proposal as slides or a video. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0153] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0154] 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.

[0155] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0156] 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.

[0157] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0158] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0159] 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.

[0160] 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.

[0161] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0162] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0163] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0164] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0165] 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.

[0166] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0167] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0168] For example, the speech recognition unit is implemented by the processor 46 of the headset terminal 314 and transcribes the speech data into text. The analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the transcribed data to generate a business flow. The generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a BPR (Business Process Reengineering) proposal based on the analyzed data. The provision unit is implemented by the control unit 46A of the headset terminal 314 and provides the generated BPR proposal as slides or a video. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0169] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0170] 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.

[0171] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0172] 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.

[0173] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0174] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0175] 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.

[0176] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0177] 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.

[0178] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0179] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0180] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0181] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0182] 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.

[0183] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0184] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0185] For example, the speech recognition unit is implemented by the processor 46 of the robot 414 and transcribes the speech data into text. The analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the transcribed data to generate a business flow. The generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a BPR (Business Process Reengineering) proposal based on the analyzed data. The provision unit is implemented by the control unit 46A of the robot 414 and provides the generated BPR proposal as slides or a video. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0186] 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.

[0187] Figure 9 shows the 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.

[0188] 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.

[0189] 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.

[0190] 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, and motorcycles, 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 based, for example, 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.

[0191] 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."

[0192] 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.

[0193] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0202] 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 other things 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.

[0203] 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.

[0204] (Note 1) A speech recognition unit that transcribes audio data into text, An analysis unit analyzes the data transcribed by the aforementioned speech recognition unit and generates a business flow, A generation unit that generates a BPR proposal based on the data analyzed by the aforementioned analysis unit, The system comprises a providing unit that provides the BPR proposal generated by the generation unit as a slide or video. A system characterized by the following features. (Note 2) It includes a modification section for adding additional information and correcting the flowchart. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes a section that presents problems or solutions. The system described in Appendix 1, characterized by the features described herein. (Note 4) It includes an audio data conversion unit that converts presentation notes into audio data. The system described in Appendix 1, characterized by the features described herein. (Note 5) It includes a video creation section that creates videos from slides and presentation notes. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned speech recognition unit, It estimates the user's emotions and adjusts the accuracy of speech recognition in real time based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned speech recognition unit, Add a filtering function that automatically removes background noise during speech recognition. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned speech recognition unit, When performing speech recognition, the accuracy of the recognition is improved by taking into account the speaker's accent and dialect. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned speech recognition unit, It estimates the user's emotions and prioritizes processing the speech recognition results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned speech recognition unit, During speech recognition, the tone and speed of the speaker's voice are analyzed to select an appropriate recognition model. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned speech recognition unit, Add a feature to speech recognition that allows for individual recognition even when multiple speakers are speaking simultaneously. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, During analysis, the analysis algorithm is dynamically changed according to the complexity of the business workflow. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During analysis, we improve the accuracy of the analysis by referring to past business flow data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, It estimates the user's emotions and prioritizes the analysis results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, During analysis, the time taken for each step of the business workflow is measured, and an efficient workflow is proposed. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During analysis, we improve the accuracy of the analysis by referring to relevant literature on business workflows. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is We estimate the user's emotions and adjust the content of the BPR proposal generated based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is During generation, the level of detail in the generated content is adjusted based on the importance of the business process. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is During generation, different generation algorithms are applied depending on the category of the business flow. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is Estimate user emotions and prioritize BPR proposals generated based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is During generation, the priority of the generated content is determined based on the submission timing of the business flow. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is During generation, the order of generated content is adjusted based on the relationships within the business workflow. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned supply unit is, It estimates the user's emotions and adjusts the content of the slides and videos provided based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, When providing the service, the optimal delivery method is selected by referring to the user's past usage history. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, When providing the service, the optimal delivery format will be selected considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, It estimates the user's emotions and prioritizes the slides and videos to be presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned supply unit is, When providing the service, the optimal delivery method will be selected, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned supply unit is, When providing the service, we analyze the user's social media activity and provide relevant slides and videos. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned modification section is, The system estimates user sentiment and prioritizes the necessary modifications based on that estimated sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 31) The aforementioned modification section is, When making corrections, refer to the past correction history of the business process flow to select the most appropriate correction method. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned modification section is, It estimates the user's emotions and adjusts how the corrections are displayed based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned modification section is, When making revisions, we will propose revisions by referring to relevant documentation on the business process flow. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned display unit is, It estimates the user's emotions and adjusts the content of the tasks and solutions presented based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 35) The aforementioned display unit is, When presenting the information, adjust the level of detail based on the importance of the business process. The system described in Appendix 3, characterized by the features described herein. (Note 36) The aforementioned display unit is, It estimates the user's emotions and determines the priority of the issues and solutions presented based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned display unit is, When presenting the information, adjust the order of the presented content based on the relevance of the business workflow. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned audio data conversion unit, The system estimates the user's emotions and adjusts the method of converting the data into audio based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 39) The aforementioned audio data conversion unit, When converting to audio data, the tone and speed of the audio are adjusted according to the content of the speaker notes. The system described in Appendix 4, characterized by the features described herein. (Note 40) The aforementioned audio data conversion unit, The system estimates the user's emotions and determines the priority of audio data creation based on the estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 41) The aforementioned audio data conversion unit, When converting to audio data, we improve the accuracy of the audio data by referring to relevant literature in the speaker notes. The system described in Appendix 4, characterized by the features described herein. (Note 42) The aforementioned video creation unit, The system estimates the user's emotions and adjusts the video content based on those emotions. The system described in Appendix 5, characterized by the features described herein. (Note 43) The aforementioned video creation unit, When creating a video, adjust the video's structure according to the content of the slides and speaker notes. The system described in Appendix 5, characterized by the features described herein. (Note 44) The aforementioned video creation unit, It estimates user emotions and prioritizes video creation based on those estimated emotions. The system described in Appendix 5, characterized by the features described herein. (Note 45) The aforementioned video creation unit, When creating videos, refer to relevant literature such as slides and speaker notes to improve the accuracy of the video. The system described in Appendix 5, characterized by the features described herein. [Explanation of Symbols]

[0205] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A speech recognition unit that transcribes audio data into text, An analysis unit analyzes the data transcribed by the aforementioned speech recognition unit and generates a business flow, A generation unit that generates a BPR proposal based on the data analyzed by the aforementioned analysis unit, The system comprises a providing unit that provides the BPR proposal generated by the generation unit as a slide or video. A system characterized by the following features.

2. It includes a modification section for adding additional information and correcting the flowchart. The system according to feature 1.

3. It includes a section that presents problems or solutions. The system according to feature 1.

4. It includes an audio data conversion unit that converts presentation notes into audio data. The system according to feature 1.

5. It includes a video creation section that creates videos from slides and presentation notes. The system according to feature 1.

6. The aforementioned speech recognition unit, It estimates the user's emotions and adjusts the accuracy of speech recognition in real time based on the estimated emotions. The system according to feature 1.

7. The aforementioned speech recognition unit, Add a filtering function that automatically removes background noise during speech recognition. The system according to feature 1.

8. The aforementioned speech recognition unit, When performing speech recognition, the accuracy of the recognition is improved by taking into account the speaker's accent and dialect. The system according to feature 1.

9. The aforementioned speech recognition unit, It estimates the user's emotions and prioritizes processing the speech recognition results based on the estimated user emotions. The system according to feature 1.

10. The aforementioned speech recognition unit, During speech recognition, the tone and speed of the speaker's voice are analyzed to select an appropriate recognition model. The system according to feature 1.

Images