system

Abstract

The system according to this embodiment aims to automatically convert the recorded content of video conference training into instruction manuals. [Solution] The system according to the embodiment comprises an acquisition unit, an analysis unit, a text generation unit, an image capture unit, and a re-text unit. The acquisition unit acquires recorded data of a video conference training session. The analysis unit analyzes the recorded data acquired by the acquisition unit and picks out the procedure explanations. The text generation unit converts the procedure explanations picked out by the analysis unit into text. The image capture unit captures images that correspond to the text generated by the text generation unit. If the procedure manual generated by the image capture unit is insufficient, the re-text unit specifies the recording time of the insufficient parts and re-texts them.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance 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 prior art, there was a problem that it took time and labor to manually convert the recorded content of video conference training into a procedure manual.

[0005] The system according to the embodiment aims to automatically convert the recorded content of video conference training into a procedure manual.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an acquisition unit, an analysis unit, a text generation unit, an image capture unit, and a re-text unit. The acquisition unit acquires recorded data of a video conference training session. The analysis unit analyzes the recorded data acquired by the acquisition unit and picks out the procedure explanations. The text generation unit converts the procedure explanations picked out by the analysis unit into text. The image capture unit captures images that correspond to the text generated by the text generation unit. If the procedure manual generated by the image capture unit is insufficient, the re-text unit specifies the recording time of the insufficient portion and re-texts it. [Effects of the Invention]

[0007] The system according to this embodiment can automatically convert the recorded content of video conference training into a procedure manual. [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 labeled 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 such as 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 automated procedure manual generation system according to an embodiment of the present invention is a system that acquires recorded data of a video conference training session, uses a generating AI to analyze the data and pick out only the procedure explanations, generates text for the procedure portion, and captures images corresponding to the text. The automated procedure manual generation system acquires recorded data of a video conference training session, and the generating AI analyzes the recorded data to pick out only the procedure explanations. The generating AI generates text for the procedure portion and further captures images from the video conference that correspond to the text. This automatically completes an automated procedure manual with images. For example, the automated procedure manual generation system acquires recorded data of a video conference training session. At this time, the recorded data is input to the generating AI. Next, the generating AI analyzes the recorded data and picks out only the procedure explanations from the conversation content. The generating AI identifies the procedure explanation portion and excludes unnecessary conversation portions. The generating AI generates text for the procedure portion. For example, it generates text that describes the procedure in detail based on the training content. Furthermore, the generating AI captures images from the video conference that correspond to the text. For example, it automatically acquires captured images of screens related to the procedure and inserts them into the text. Through this mechanism, an automated procedure manual is generated from recorded data of a video conference training session. The procedure manuals are in a format that combines text and images, making it easy to understand the training content. Furthermore, if the generated procedure manual is insufficient, the system allows users to specify the recording time of the insufficient section, re-textualize that portion, and complete the revised procedure manual. This system can be used for new employee training and self-study, and it helps to create a system that ensures business operations continue even when there are personnel changes or organizational changes. In short, the automated procedure manual generation system automatically generates procedure manuals from video conference training recordings and efficiently creates manuals by re-textualizing any insufficient parts.

[0029] The automated procedure manual generation system according to the embodiment comprises an acquisition unit, an analysis unit, a text generation unit, an image capture unit, and a re-text unit. The acquisition unit acquires recorded data of video conference training. The acquisition unit can, for example, download recorded data of video conference training from cloud storage. The acquisition unit can also directly acquire recorded data using the video conference API. Furthermore, the acquisition unit can also read recorded data stored in local storage. For example, the acquisition unit downloads recorded data from cloud storage and passes it to the analysis unit. The analysis unit analyzes the recorded data and picks out only the procedure descriptions from the conversation content. The analysis unit, for example, uses a generation AI to convert the audio of the recorded data into text and identifies the procedure description portion. The analysis unit can also extract the procedure description portion using natural language processing technology. Furthermore, the analysis unit can also analyze the content of the recorded data in order to identify the procedure description portion. For example, the analysis unit uses a generation AI to convert the audio of the recorded data into text and identifies the procedure description portion. The text generation unit generates the text of the procedure portion. The text generation unit generates the text of the procedure portion using a generation AI. Furthermore, the text generation unit can analyze the content of the recorded data to generate the text for the procedure section. In addition, the text generation unit can utilize manually entered information to generate the text for the procedure section. For example, the text generation unit generates the text for the procedure section using a generation AI. The image capture unit captures images from the video conference that correspond to the text. For example, the image capture unit can take a screenshot to capture the video conference screen. In addition, the image capture unit can extract specific frames from the video conference recording data. Furthermore, the image capture unit can capture specific scenes from the video conference recording data. For example, the image capture unit takes a screenshot to capture the video conference screen. If the generated procedure document is insufficient, the re-text unit re-texts it by specifying the recording time of the insufficient part. For example, the re-text unit identifies the insufficient part of the procedure document and re-texts it.Furthermore, the re-text unit can receive feedback from users to identify any shortcomings in the procedure manual. In addition, the re-text unit can re-analyze the content of the recorded data to identify any shortcomings in the procedure manual. For example, the re-text unit can identify any shortcomings in the procedure manual and re-text them. As a result, the automated procedure manual generation system according to this embodiment can efficiently create procedure manuals by automatically generating them from recorded video conference training data and re-texting any shortcomings in the manual.

[0030] The acquisition unit acquires recorded data from video conference training sessions. For example, the acquisition unit can download recorded data from cloud storage. Specifically, it uses the API of a cloud storage service to acquire recorded data from a specified folder. The acquisition unit can also directly acquire recorded data using the video conferencing API. By using the video conferencing API, it is possible to programmatically acquire recorded data associated with a specific meeting ID. Furthermore, the acquisition unit can also read recorded data stored in local storage. For example, by specifying the path to recorded data manually saved by the user in local storage, the acquisition unit can read that data. The acquisition unit combines these methods to acquire the recorded data in the most efficient way and passes it to the analysis unit. This allows the acquisition unit to flexibly acquire recorded data in response to various environments and situations.

[0031] The analysis unit analyzes the recorded data and extracts only the procedural explanations from the conversation. For example, the analysis unit uses a generative AI to convert the audio of the recorded data into text and identify the procedural explanation portion. The generative AI can convert the audio of the recorded data into text with high accuracy using speech recognition technology. Furthermore, the analysis unit can also extract the procedural explanation portion using natural language processing technology. By using natural language processing technology, keywords and phrases related to the procedural explanation can be identified from the transcribed data, and the procedural explanation portion can be extracted. In order to identify the procedural explanation portion, the analysis unit analyzes the content of the recorded data in detail. For example, when converting the audio of the recorded data into text using a generative AI to identify the procedural explanation portion, the procedural explanation portion can be identified with higher accuracy by pre-training the AI ​​with specific keywords and phrases related to the procedural explanation. As a result, the analysis unit can quickly and accurately extract the procedural explanation portion from the recorded data.

[0032] The text generation unit generates the text for the procedure section. For example, the text generation unit uses a generation AI to generate the text for the procedure section. The generation AI can generate a procedure manual as natural-sounding text based on the text for the procedure explanation section. The text generation unit can also analyze the content of video data in order to generate the text for the procedure section. By analyzing the content of video data in detail, it can accurately grasp the information related to the procedure explanation and generate text in an appropriate format for a procedure manual. Furthermore, the text generation unit can also utilize manually entered information to generate the text for the procedure section. For example, by reflecting supplementary information and corrections manually entered by the user, it can generate a more accurate and detailed procedure manual. In this way, the text generation unit can generate the text for the procedure section from various information sources and create procedure manuals efficiently and accurately.

[0033] The image capture unit captures images from a video conference in accordance with the text. For example, the image capture unit can take screenshots to capture the video conference screen. Specifically, it can take screenshots based on specific timestamps during playback of recorded data to obtain images to insert into the procedure manual. The image capture unit can also extract specific frames from the video conference recording data. It analyzes the recording data frame by frame, identifies scenes relevant to the procedure explanation, and captures those frames. Furthermore, the image capture unit can capture specific scenes from the video conference recording data. For example, by capturing important operations or screen displays related to the procedure explanation and inserting them into the procedure manual, it is possible to create a procedure manual that is easy to understand visually. In this way, the image capture unit can capture appropriate images in accordance with the text and visually complement the procedure manual.

[0034] The retext unit, if the generated procedure manual is insufficient, will retext it by specifying the recording time of the insufficient portion. For example, the retext unit will identify the insufficient portion of the procedure manual and retext it. Specifically, it will analyze the content of the procedure manual, identify the insufficient portion, and obtain the timestamp of the recording data corresponding to that portion. The retext unit can also receive feedback from the user to identify the insufficient portion of the procedure manual. By having the user point out the insufficient portion of the procedure manual and provide the timestamp of the recording data corresponding to that portion, the retext unit will retext that portion. Furthermore, the retext unit can also reanalyze the content of the recording data to identify the insufficient portion of the procedure manual. By reanalyzing the content of the recording data and supplementing the information related to the insufficient portion, the accuracy of the procedure manual can be improved. In this way, the retext unit can efficiently supplement the insufficient portion of the generated procedure manual and create a more accurate and detailed procedure manual.

[0035] The acquisition unit can acquire recorded data from video conference training sessions. For example, the acquisition unit can download recorded data from cloud storage. The acquisition unit can also directly acquire recorded data using the video conferencing API. The acquisition unit can also read recorded data stored in local storage. For example, the acquisition unit downloads recorded data from cloud storage and passes it to the analysis unit. This allows the acquisition unit to collect the data necessary for creating procedure manuals by acquiring recorded data from video conference training sessions. Recorded data from video conference training sessions may include, but are not limited to, video format, audio format, slideshow format, etc. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or not using AI. For example, when the acquisition unit acquires recorded data using the video conferencing API, it may use AI to optimize the timing of the acquisition of the recorded data.

[0036] The analysis unit can analyze the recorded data and pick out only the procedural explanations from the conversation. For example, the analysis unit can use a generative AI to convert the audio of the recorded data into text and identify the procedural explanation portion. The analysis unit can also use natural language processing technology to extract the procedural explanation portion. The analysis unit can also analyze the content of the recorded data in order to identify the procedural explanation portion. For example, the analysis unit can use a generative AI to convert the audio of the recorded data into text and identify the procedural explanation portion. This allows for the efficient extraction of the content of the instruction manual by analyzing the recorded data and picking out only the procedural explanations. Procedural explanations include, but are not limited to, operating procedures, usage instructions, and precautions. Some or all of the above-described processes in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the audio of the recorded data into a generative AI and have the generative AI perform the extraction of the procedural explanation portion.

[0037] The text generation unit can generate text for the procedure section. The text generation unit can generate text for the procedure section using, for example, a generation AI. The text generation unit can also analyze the contents of recorded data in order to generate text for the procedure section. The text generation unit can also utilize manually entered information in order to generate text for the procedure section. For example, the text generation unit can generate text for the procedure section using a generation AI. This allows for a clear description of the contents of the procedure manual by generating text for the procedure section. The text for the procedure section may include, but is not limited to, operating procedures, usage instructions, and precautions. Some or all of the above-described processes in the text generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the text generation unit can input the contents of recorded data into a generation AI and have the generation AI perform the generation of text for the procedure section.

[0038] The image capture unit can capture images within a video conference aligned with the text. For example, the image capture unit can take screenshots to capture the video conference screen. The image capture unit can also extract specific frames from the video conference recording data. The image capture unit can also capture specific scenes from the video conference recording data. For example, the image capture unit takes screenshots to capture the video conference screen. This helps in the visual understanding of the procedure manual by capturing images aligned with the text. Images within a video conference aligned with the text include, but are not limited to, operation screens, usage examples, and points to note. Some or all of the above processing in the image capture unit may be performed, for example, using a generative AI, or without a generative AI. For example, the image capture unit can input video conference recording data into a generative AI and have the generative AI extract specific frames.

[0039] The retext unit can retext the generated procedure manual if it is insufficient, by specifying the recording time of the insufficient parts. The retext unit can, for example, identify the insufficient parts of the procedure manual and retext them. The retext unit can also receive feedback from the user to identify the insufficient parts of the procedure manual. The retext unit can also reanalyze the content of the recording data to identify the insufficient parts of the procedure manual. For example, the retext unit can identify the insufficient parts of the procedure manual and retext them. This allows the content of the procedure manual to be supplemented by retexting it when it is insufficient. Insufficiencies include, but are not limited to, missing information, errors, and ambiguities. Some or all of the above processing in the retext unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the retext unit can input the insufficient parts of the procedure manual into a generating AI and have the generating AI perform the retexting.

[0040] The acquisition unit analyzes the user's past recording data acquisition history and selects the optimal acquisition method. The acquisition unit can analyze the user's past recording data acquisition history and select the optimal acquisition method. For example, the acquisition unit can analyze the time periods in which the user frequently acquired data in the past and acquire recording data during those time periods. The acquisition unit can also analyze the content of data previously acquired by the user and prioritize the acquisition of similar content. The acquisition unit can also prioritize the acquisition of data related to specific events or topics from the user's past acquisition history. For example, the acquisition unit can analyze the time periods in which the user frequently acquired data in the past and acquire recording data during those time periods. This allows the acquisition unit to select the optimal acquisition method by analyzing the user's past recording data acquisition history. The optimal acquisition method includes, but is not limited to, data quality and acquisition efficiency. Some or all of the above processing in the acquisition unit may be performed using, for example, AI, or not using AI. For example, the acquisition unit can input the user's past recording data acquisition history into AI and have the AI ​​select the optimal acquisition method.

[0041] The acquisition unit filters the recorded video data based on the user's current projects and areas of interest when acquiring it. The acquisition unit can filter the recorded video data based on the user's current projects and areas of interest when acquiring it. For example, the acquisition unit prioritizes acquiring recorded video data related to the project the user is currently working on. The acquisition unit can also filter and acquire relevant recorded video data based on the user's areas of interest. The acquisition unit can also select and acquire necessary recorded video data according to the progress of the user's projects. For example, the acquisition unit prioritizes acquiring recorded video data related to the project the user is currently working on. This allows for the acquisition of highly relevant data by filtering based on the user's current projects and areas of interest. The user's current projects and areas of interest include, but are not limited to, project management tools and survey results. Some or all of the above processing in the acquisition unit may be performed using, for example, AI, or not using AI. For example, the acquisition unit can input the user's current projects and areas of interest into AI and have AI perform the filtering of recorded video data.

[0042] The acquisition unit prioritizes acquiring highly relevant data when acquiring recorded data, taking into account the user's geographical location information. The acquisition unit can prioritize acquiring highly relevant data when acquiring recorded data, taking into account the user's geographical location information. For example, if the user is in a specific region, the acquisition unit prioritizes acquiring recorded data related to that region. If the user is traveling, the acquisition unit can also prioritize acquiring recorded data related to the travel destination. If the user is participating in a specific event, the acquisition unit can also prioritize acquiring recorded data related to that event. For example, if the acquisition unit is in a specific region, it prioritizes acquiring recorded data related to that region. This allows for the priority acquisition of highly relevant data by considering the user's geographical location information. The user's geographical location information includes, but is not limited to, GPS data and IP addresses. Some or all of the above processing in the acquisition unit may be performed using, for example, AI, or without AI. For example, the acquisition unit can input the user's geographical location information into AI and have the AI ​​determine the priority for acquiring recorded data.

[0043] The acquisition unit analyzes the user's social media activity and obtains relevant data when acquiring recorded data. The acquisition unit can analyze the user's social media activity and obtain relevant data when acquiring recorded data. For example, the acquisition unit can prioritize acquiring recorded data related to content shared by the user on social media. The acquisition unit can also prioritize acquiring recorded data related to accounts followed by the user on social media. The acquisition unit can also prioritize acquiring recorded data related to topics the user has shown interest in on social media. For example, the acquisition unit prioritizes acquiring recorded data related to content shared by the user on social media. This allows relevant data to be obtained by analyzing the user's social media activity. The user's social media activity includes, but is not limited to, posts, number of followers, and number of likes. Some or all of the above processing in the acquisition unit may be performed using, for example, AI, or not using AI. For example, the acquisition unit can input the user's social media activity into AI and have the AI ​​determine the priority for acquiring recorded data.

[0044] The analysis unit improves the accuracy of the analysis by considering the audio quality of the recorded data during the analysis. The analysis unit can improve the accuracy of the analysis by considering the audio quality of the recorded data during the analysis. For example, if the audio of the recorded data is clear, the analysis unit will analyze the detailed procedural explanation. If the audio of the recorded data is unclear, the analysis unit can also perform noise reduction to improve the accuracy of the analysis. The analysis unit can also apply different analysis algorithms depending on the audio quality of the recorded data. For example, if the audio of the recorded data is clear, the analysis unit will analyze the detailed procedural explanation. This improves the accuracy of the analysis by considering the audio quality of the recorded data. Audio quality includes, but is not limited to, noise level and speech clarity. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the audio quality of the recorded data into a generative AI and have the generative AI perform the improvement of the analysis accuracy.

[0045] The analysis unit applies different analysis algorithms depending on the content of the recorded data during analysis. The analysis unit can apply different analysis algorithms depending on the content of the recorded data during analysis. For example, the analysis unit can apply an algorithm that analyzes technical terms to recorded data with technical content. The analysis unit can also apply an algorithm that analyzes educational terms to recorded data with educational content. The analysis unit can also apply an algorithm that analyzes business terms to recorded data with business-related content. For example, the analysis unit applies an algorithm that analyzes technical terms to recorded data with technical content. This improves the accuracy of the analysis by applying different analysis algorithms depending on the content of the recorded data. Different analysis algorithms include, but are not limited to, speech recognition algorithms and natural language processing algorithms. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the content of the recorded data into a generative AI and have the generative AI execute the application of different analysis algorithms.

[0046] The analysis unit determines the priority of analysis based on the submission date of the recorded data during analysis. The analysis unit can determine the priority of analysis based on the submission date of the recorded data during analysis. For example, the analysis unit prioritizes the analysis of recently submitted recorded data. The analysis unit can also prioritize the analysis of recorded data with approaching deadlines. If the user is in a hurry, the analysis unit can also prioritize the analysis regardless of the submission date. For example, the analysis unit prioritizes the analysis of recently submitted recorded data. This allows for the priority of analysis of important data by determining the priority of analysis based on the submission date of the recorded data. The submission date includes, but is not limited to, the submission date and time. Some or all of the above processing in the analysis unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the analysis unit can input the submission date of the recorded data into a generating AI and have the generating AI determine the priority of analysis.

[0047] The analysis unit improves the accuracy of the analysis by referring to relevant literature related to the recorded data during the analysis. The analysis unit can improve the accuracy of the analysis by referring to relevant literature related to the recorded data during the analysis. For example, the analysis unit improves the accuracy of the analysis by referring to literature related to the content of the recorded data. The analysis unit can also improve the accuracy of the analysis by referring to research papers related to the content of the recorded data. The analysis unit can also improve the accuracy of the analysis by referring to books related to the content of the recorded data. For example, the analysis unit improves the accuracy of the analysis by referring to literature related to the content of the recorded data. This improves the accuracy of the analysis by referring to relevant literature related to the recorded data. Relevant literature includes, but is not limited to, academic papers and technical documents. Some or all of the above processing in the analysis unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the analysis unit can input the content of the recorded data into a generating AI and have the generating AI perform the referencing of relevant literature.

[0048] The text generation unit adjusts the level of detail in the text based on the importance of the procedure during text generation. The text generation unit can adjust the level of detail in the text based on the importance of the procedure during text generation. For example, the text generation unit generates text with detailed explanations for important procedures. The text generation unit can also generate text with concise explanations for less important procedures. The text generation unit can also generate text with different levels of detail depending on the importance of the procedure. For example, the text generation unit generates text with detailed explanations for important procedures. This allows important procedures to be described in detail by adjusting the level of detail in the text based on the importance of the procedure. The importance of a procedure includes, but is not limited to, the frequency of the operation and the magnitude of its impact. Some or all of the above processing in the text generation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the text generation unit can input the importance of the procedure into the generation AI and have the generation AI perform the adjustment of the level of detail in the text.

[0049] The text generation unit applies different text generation algorithms depending on the procedure category when generating text. The text generation unit can apply different text generation algorithms depending on the procedure category when generating text. For example, the text generation unit can apply a text generation algorithm that includes technical terms to technical procedures. The text generation unit can also apply a text generation algorithm that includes educational terms to educational procedures. The text generation unit can also apply a text generation algorithm that includes business terms to business-related procedures. For example, the text generation unit applies a text generation algorithm that includes technical terms to technical procedures. This allows for the generation of appropriate text by applying different text generation algorithms depending on the procedure category. Procedure categories include, but are not limited to, operating procedures, setup procedures, and troubleshooting. Some or all of the above-described processes in the text generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the text generation unit can input the procedure category into the generation AI and cause the generation AI to apply different text generation algorithms.

[0050] The text generation unit determines the priority of text based on the submission date of each procedure when generating text. The text generation unit can determine the priority of text based on the submission date of each procedure when generating text. For example, the text generation unit can prioritize generating text for procedures with approaching deadlines. The text generation unit can also prioritize generating text for recently submitted procedures. If the user is in a hurry, the text generation unit can also prioritize generating text regardless of the submission date. For example, the text generation unit prioritizes generating text for procedures with approaching deadlines. This allows for the priority generation of important procedures by determining the text priority based on the submission date of each procedure. The submission date includes, but is not limited to, the submission date and time. Some or all of the above processing in the text generation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the text generation unit can input the submission dates of procedures into the generation AI and have the generation AI determine the text priority.

[0051] The text generation unit adjusts the order of text based on the relevance of the procedures during text generation. The text generation unit can adjust the order of text based on the relevance of the procedures during text generation. For example, the text generation unit places important procedures first and generates text in order of relevance. The text generation unit can also adjust the order of text based on the relevance of the procedures. The text generation unit can also generate text in different orders depending on the relevance of the procedures. For example, the text generation unit places important procedures first and generates text in order of relevance. This allows the text to be provided in an appropriate order by adjusting the order of text based on the relevance of the procedures. The relevance of procedures includes, but is not limited to, the order of operations and related operations. Some or all of the above processing in the text generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the text generation unit can input the relevance of procedures into a generation AI and have the generation AI perform the adjustment of the text order.

[0052] The image capture unit adjusts the level of detail of the captured image based on the importance of the procedure during image capture. The image capture unit can adjust the level of detail of the captured image based on the importance of the procedure during image capture. For example, the image capture unit captures images containing detailed information for important procedures. The image capture unit can also capture images containing concise information for less important procedures. The image capture unit can also capture images with different levels of detail depending on the importance of the procedure. For example, the image capture unit captures images containing detailed information for important procedures. This allows important procedures to be described in detail by adjusting the level of detail of the captured image based on the importance of the procedure. The importance of a procedure includes, but is not limited to, the frequency of the operation and the magnitude of its impact. Some or all of the above processing in the image capture unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the image capture unit can input the importance of the procedure into the generative AI and have the generative AI perform the adjustment of the level of detail of the captured image.

[0053] The image capture unit applies different capture algorithms depending on the procedure category when capturing images. The image capture unit can apply different capture algorithms depending on the procedure category when capturing images. For example, for technical procedures, it applies an algorithm that captures images containing specialized information. The image capture unit can also apply an algorithm that captures images containing educational information for educational procedures. The image capture unit can also apply an algorithm that captures images containing business information for business-related procedures. For example, the image capture unit applies an algorithm that captures images containing specialized information for technical procedures. This allows for the provision of appropriate images by applying different capture algorithms depending on the procedure category. Procedure categories include, but are not limited to, operating procedures, setup procedures, and troubleshooting. Some or all of the above processing in the image capture unit may be performed, for example, using a generative AI, or without a generative AI. For example, the image capture unit can input the procedure category into a generative AI and cause the generative AI to apply different capture algorithms.

[0054] The image capture unit determines the priority of captured images based on the submission date of the procedure when capturing an image. The image capture unit can determine the priority of captured images based on the submission date of the procedure when capturing an image. For example, the image capture unit can prioritize the generation of captured images for procedures with approaching deadlines. The image capture unit can also prioritize the generation of captured images for recently submitted procedures. If the user is in a hurry, the image capture unit can also prioritize the generation of captured images regardless of the submission date. For example, the image capture unit can prioritize the generation of captured images for procedures with approaching deadlines. This allows for the priority generation of important procedures by determining the priority of captured images based on the submission date of the procedure. The submission date includes, but is not limited to, the submission date and time. Some or all of the above processing in the image capture unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the image capture unit can input the procedure submission date into the generation AI and have the generation AI perform the determination of the priority of captured images.

[0055] The image capture unit adjusts the order of captured images based on the relevance of the procedures during image capture. The image capture unit can adjust the order of captured images based on the relevance of the procedures during image capture. For example, the image capture unit places important procedures first and generates captured images in order of relevance. The image capture unit can also adjust the order of captured images based on the relevance of the procedures. The image capture unit can also generate captured images in different orders depending on the relevance of the procedures. For example, the image capture unit places important procedures first and generates captured images in order of relevance. This allows images to be provided in the appropriate order by adjusting the order of captured images based on the relevance of the procedures. The relevance of procedures includes, but is not limited to, the order of operations and related operations. Some or all of the above processing in the image capture unit may be performed using, for example, a generative AI, or without a generative AI. For example, the image capture unit can input the relevance of the procedures into a generative AI and have the generative AI perform the adjustment of the order of captured images.

[0056] The retext unit identifies insufficient parts of the procedure manual and selects the optimal retext method during the retext process. The retext unit can identify insufficient parts of the procedure manual and select the optimal retext method during the retext process. For example, the retext unit can automatically identify insufficient parts of the procedure manual and add detailed explanations. The retext unit can also add relevant information to insufficient parts of the procedure manual. The retext unit can also identify insufficient parts of the procedure manual and retext based on user feedback. For example, the retext unit can automatically identify insufficient parts of the procedure manual and add detailed explanations. This allows for the supplementation of the procedure manual's content by identifying insufficient parts and selecting the optimal retext method. Insufficient parts include, but are not limited to, missing information, errors, and ambiguities. Some or all of the above-described processes in the retext unit may be performed, for example, using a generative AI, or without using a generative AI. For example, the re-text unit can input the insufficient parts of the procedure manual into the generating AI and have the generating AI select the optimal re-text method.

[0057] The retext unit applies different retext algorithms depending on the content of the procedure manual during retexting. The retext unit can apply different retext algorithms depending on the content of the procedure manual during retexting. For example, the retext unit applies a retext algorithm that includes technical terms to technical procedure manuals. The retext unit can also apply a retext algorithm that includes educational terms to educational procedure manuals. The retext unit can also apply a retext algorithm that includes business terms to business-related procedure manuals. For example, the retext unit applies a retext algorithm that includes technical terms to technical procedure manuals. This allows for appropriate retexting by applying different retext algorithms depending on the content of the procedure manual. Examples of different retext algorithms include, but are not limited to, speech recognition algorithms and natural language processing algorithms. Some or all of the processing described above in the retext unit may be performed using, for example, generative AI, or without generative AI. For example, the retext conversion unit can input the contents of the procedure manual into the generating AI and have the generating AI execute different retext conversion algorithms.

[0058] The retext unit determines the priority of retexting based on the submission date of the procedure manuals during the retexting process. The retext unit can determine the priority of retexting based on the submission date of the procedure manuals during the retexting process. For example, the retext unit may prioritize retexting procedure manuals with approaching deadlines. The retext unit may also prioritize retexting recently submitted procedure manuals. If the user is in a hurry, the retext unit may also prioritize retexting regardless of the submission date. For example, the retext unit may prioritize retexting procedure manuals with approaching deadlines. This allows important procedure manuals to be prioritized for retexting by determining the priority of retexting based on the submission date of the procedure manuals. The submission date includes, but is not limited to, the submission date and time. Some or all of the above processing in the retext unit may be performed, for example, using a generative AI, or not using a generative AI. For example, the re-text conversion unit can input the submission deadline for the procedure manual into the generating AI and have the generating AI determine the priority of the re-text conversion.

[0059] The retext unit improves the accuracy of retext by referring to relevant literature for the procedure manual during the retexting process. The retext unit can improve the accuracy of retext by referring to relevant literature for the procedure manual during the retexting process. For example, the retext unit can improve the accuracy of retext by referring to literature related to the content of the procedure manual. The retext unit can also improve the accuracy of retext by referring to research papers related to the content of the procedure manual. The retext unit can also improve the accuracy of retext by referring to books related to the content of the procedure manual. For example, the retext unit improves the accuracy of retext by referring to literature related to the content of the procedure manual. This improves the accuracy of retext by referring to relevant literature for the procedure manual. Relevant literature includes, but is not limited to, academic papers and technical documents. Some or all of the above processing in the retext unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the retext unit can input the content of the procedure manual into a generating AI and have the generating AI perform the referencing of relevant literature.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The acquisition unit can analyze the user's past recording data acquisition history and select the optimal acquisition method. For example, it can analyze the time periods in which the user frequently acquired data in the past and acquire recording data during those times. It can also analyze the content of data the user has acquired in the past and prioritize the acquisition of similar content. It can also prioritize the acquisition of data related to specific events or topics from the user's past acquisition history. In this way, the optimal acquisition method can be selected by analyzing the user's past recording data acquisition history.

[0062] The acquisition unit can filter recorded data based on the user's current projects and areas of interest. For example, it can prioritize the acquisition of recorded data related to the user's current project. It can also filter and acquire relevant recorded data based on the user's areas of interest. It can also select and acquire necessary recorded data according to the progress of the user's project. This allows for the acquisition of highly relevant data by filtering based on the user's current projects and areas of interest.

[0063] The analysis unit can improve the accuracy of the analysis by considering the audio quality of the recorded data during the analysis. For example, if the audio of the recorded data is clear, it can analyze detailed procedural explanations. If the audio of the recorded data is unclear, noise reduction can be performed to improve the accuracy of the analysis. Different analysis algorithms can also be applied depending on the audio quality of the recorded data. In this way, the accuracy of the analysis can be improved by considering the audio quality of the recorded data.

[0064] The text generation unit can adjust the level of detail in the text based on the importance of each step during text generation. For example, it can generate text with detailed explanations for important steps, and text with concise explanations for less important steps. It can also generate text with different levels of detail depending on the importance of each step. This allows important steps to be described in detail by adjusting the level of detail based on the importance of each step.

[0065] The image capture unit can adjust the level of detail in captured images based on the importance of each step. For example, important steps can be captured with images containing detailed information. Less important steps can be captured with images containing concise information. Images with different levels of detail can also be captured depending on the importance of each step. This allows for detailed descriptions of important steps by adjusting the level of detail in captured images based on their importance.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The acquisition unit acquires the recorded data of the video conference training. For example, the acquisition unit can download the recorded data of the video conference training from cloud storage. It can also directly acquire the recorded data using the video conferencing API. Furthermore, it can read the recorded data stored in local storage. Step 2: The analysis unit analyzes the recorded data acquired by the acquisition unit and picks out only the procedural explanations from the conversation. For example, the analysis unit uses a generation AI to convert the audio of the recorded data into text and identify the procedural explanation portion. Alternatively, natural language processing technology can be used to extract the procedural explanation portion. Step 3: The text generation unit converts the procedure descriptions picked up by the analysis unit into text. The text generation unit generates the procedure text using, for example, a generation AI. It can also utilize manually entered information. Step 4: The image capture unit captures images from the video conference in accordance with the text generated by the text generation unit. The image capture unit can, for example, take screenshots to capture the video conference screen. It can also extract specific frames or scenes from the video conference recording data. Step 5: If the generated procedure manual is insufficient, the re-text unit will re-text it by specifying the recording time of the insufficient parts. For example, the re-text unit will identify the insufficient parts of the procedure manual and re-text them. It can also receive feedback from the user.

[0068] (Example of form 2) The automated procedure manual generation system according to an embodiment of the present invention is a system that acquires recorded data of a video conference training session, uses a generating AI to analyze the data and pick out only the procedure explanations, generates text for the procedure portion, and captures images corresponding to the text. The automated procedure manual generation system acquires recorded data of a video conference training session, and the generating AI analyzes the recorded data to pick out only the procedure explanations. The generating AI generates text for the procedure portion and further captures images from the video conference that correspond to the text. This automatically completes an automated procedure manual with images. For example, the automated procedure manual generation system acquires recorded data of a video conference training session. At this time, the recorded data is input to the generating AI. Next, the generating AI analyzes the recorded data and picks out only the procedure explanations from the conversation content. The generating AI identifies the procedure explanation portion and excludes unnecessary conversation portions. The generating AI generates text for the procedure portion. For example, it generates text that describes the procedure in detail based on the training content. Furthermore, the generating AI captures images from the video conference that correspond to the text. For example, it automatically acquires captured images of screens related to the procedure and inserts them into the text. Through this mechanism, an automated procedure manual is generated from recorded data of a video conference training session. The procedure manuals are in a format that combines text and images, making it easy to understand the training content. Furthermore, if the generated procedure manual is insufficient, the system allows users to specify the recording time of the insufficient section, re-textualize that portion, and complete the revised procedure manual. This system can be used for new employee training and self-study, and it helps to create a system that ensures business operations continue even when there are personnel changes or organizational changes. In short, the automated procedure manual generation system automatically generates procedure manuals from video conference training recordings and efficiently creates manuals by re-textualizing any insufficient parts.

[0069] The automated procedure manual generation system according to the embodiment comprises an acquisition unit, an analysis unit, a text generation unit, an image capture unit, and a re-text unit. The acquisition unit acquires recorded data of video conference training. The acquisition unit can, for example, download recorded data of video conference training from cloud storage. The acquisition unit can also directly acquire recorded data using the video conference API. Furthermore, the acquisition unit can also read recorded data stored in local storage. For example, the acquisition unit downloads recorded data from cloud storage and passes it to the analysis unit. The analysis unit analyzes the recorded data and picks out only the procedure descriptions from the conversation content. The analysis unit, for example, uses a generation AI to convert the audio of the recorded data into text and identifies the procedure description portion. The analysis unit can also extract the procedure description portion using natural language processing technology. Furthermore, the analysis unit can also analyze the content of the recorded data in order to identify the procedure description portion. For example, the analysis unit uses a generation AI to convert the audio of the recorded data into text and identifies the procedure description portion. The text generation unit generates the text of the procedure portion. The text generation unit generates the text of the procedure portion using a generation AI. Furthermore, the text generation unit can analyze the content of the recorded data to generate the text for the procedure section. In addition, the text generation unit can utilize manually entered information to generate the text for the procedure section. For example, the text generation unit generates the text for the procedure section using a generation AI. The image capture unit captures images from the video conference that correspond to the text. For example, the image capture unit can take a screenshot to capture the video conference screen. In addition, the image capture unit can extract specific frames from the video conference recording data. Furthermore, the image capture unit can capture specific scenes from the video conference recording data. For example, the image capture unit takes a screenshot to capture the video conference screen. If the generated procedure document is insufficient, the re-text unit re-texts it by specifying the recording time of the insufficient part. For example, the re-text unit identifies the insufficient part of the procedure document and re-texts it.Furthermore, the re-text unit can receive feedback from users to identify any shortcomings in the procedure manual. In addition, the re-text unit can re-analyze the content of the recorded data to identify any shortcomings in the procedure manual. For example, the re-text unit can identify any shortcomings in the procedure manual and re-text them. As a result, the automated procedure manual generation system according to this embodiment can efficiently create procedure manuals by automatically generating them from recorded video conference training data and re-texting any shortcomings in the manual.

[0070] The acquisition unit acquires recorded data from video conference training sessions. For example, the acquisition unit can download recorded data from cloud storage. Specifically, it uses the API of a cloud storage service to acquire recorded data from a specified folder. The acquisition unit can also directly acquire recorded data using the video conferencing API. By using the video conferencing API, it is possible to programmatically acquire recorded data associated with a specific meeting ID. Furthermore, the acquisition unit can also read recorded data stored in local storage. For example, by specifying the path to recorded data manually saved by the user in local storage, the acquisition unit can read that data. The acquisition unit combines these methods to acquire the recorded data in the most efficient way and passes it to the analysis unit. This allows the acquisition unit to flexibly acquire recorded data in response to various environments and situations.

[0071] The analysis unit analyzes the recorded data and extracts only the procedural explanations from the conversation. For example, the analysis unit uses a generative AI to convert the audio of the recorded data into text and identify the procedural explanation portion. The generative AI can convert the audio of the recorded data into text with high accuracy using speech recognition technology. Furthermore, the analysis unit can also extract the procedural explanation portion using natural language processing technology. By using natural language processing technology, keywords and phrases related to the procedural explanation can be identified from the transcribed data, and the procedural explanation portion can be extracted. In order to identify the procedural explanation portion, the analysis unit analyzes the content of the recorded data in detail. For example, when converting the audio of the recorded data into text using a generative AI to identify the procedural explanation portion, the procedural explanation portion can be identified with higher accuracy by pre-training the AI ​​with specific keywords and phrases related to the procedural explanation. As a result, the analysis unit can quickly and accurately extract the procedural explanation portion from the recorded data.

[0072] The text generation unit generates the text for the procedure section. For example, the text generation unit uses a generation AI to generate the text for the procedure section. The generation AI can generate a procedure manual as natural-sounding text based on the text for the procedure explanation section. The text generation unit can also analyze the content of video data in order to generate the text for the procedure section. By analyzing the content of video data in detail, it can accurately grasp the information related to the procedure explanation and generate text in an appropriate format for a procedure manual. Furthermore, the text generation unit can also utilize manually entered information to generate the text for the procedure section. For example, by reflecting supplementary information and corrections manually entered by the user, it can generate a more accurate and detailed procedure manual. In this way, the text generation unit can generate the text for the procedure section from various information sources and create procedure manuals efficiently and accurately.

[0073] The image capture unit captures images from a video conference in accordance with the text. For example, the image capture unit can take screenshots to capture the video conference screen. Specifically, it can take screenshots based on specific timestamps during playback of recorded data to obtain images to insert into the procedure manual. The image capture unit can also extract specific frames from the video conference recording data. It analyzes the recording data frame by frame, identifies scenes relevant to the procedure explanation, and captures those frames. Furthermore, the image capture unit can capture specific scenes from the video conference recording data. For example, by capturing important operations or screen displays related to the procedure explanation and inserting them into the procedure manual, it is possible to create a procedure manual that is easy to understand visually. In this way, the image capture unit can capture appropriate images in accordance with the text and visually complement the procedure manual.

[0074] The retext unit, if the generated procedure manual is insufficient, will retext it by specifying the recording time of the insufficient portion. For example, the retext unit will identify the insufficient portion of the procedure manual and retext it. Specifically, it will analyze the content of the procedure manual, identify the insufficient portion, and obtain the timestamp of the recording data corresponding to that portion. The retext unit can also receive feedback from the user to identify the insufficient portion of the procedure manual. By having the user point out the insufficient portion of the procedure manual and provide the timestamp of the recording data corresponding to that portion, the retext unit will retext that portion. Furthermore, the retext unit can also reanalyze the content of the recording data to identify the insufficient portion of the procedure manual. By reanalyzing the content of the recording data and supplementing the information related to the insufficient portion, the accuracy of the procedure manual can be improved. In this way, the retext unit can efficiently supplement the insufficient portion of the generated procedure manual and create a more accurate and detailed procedure manual.

[0075] The acquisition unit can acquire recorded data from video conference training sessions. For example, the acquisition unit can download recorded data from cloud storage. The acquisition unit can also directly acquire recorded data using the video conferencing API. The acquisition unit can also read recorded data stored in local storage. For example, the acquisition unit downloads recorded data from cloud storage and passes it to the analysis unit. This allows the acquisition unit to collect the data necessary for creating procedure manuals by acquiring recorded data from video conference training sessions. Recorded data from video conference training sessions may include, but are not limited to, video format, audio format, slideshow format, etc. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or not using AI. For example, when the acquisition unit acquires recorded data using the video conferencing API, it may use AI to optimize the timing of the acquisition of the recorded data.

[0076] The analysis unit can analyze the recorded data and pick out only the procedural explanations from the conversation. For example, the analysis unit can use a generative AI to convert the audio of the recorded data into text and identify the procedural explanation portion. The analysis unit can also use natural language processing technology to extract the procedural explanation portion. The analysis unit can also analyze the content of the recorded data in order to identify the procedural explanation portion. For example, the analysis unit can use a generative AI to convert the audio of the recorded data into text and identify the procedural explanation portion. This allows for the efficient extraction of the content of the instruction manual by analyzing the recorded data and picking out only the procedural explanations. Procedural explanations include, but are not limited to, operating procedures, usage instructions, and precautions. Some or all of the above-described processes in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the audio of the recorded data into a generative AI and have the generative AI perform the extraction of the procedural explanation portion.

[0077] The text generation unit can generate text for the procedure section. The text generation unit can generate text for the procedure section using, for example, a generation AI. The text generation unit can also analyze the contents of recorded data in order to generate text for the procedure section. The text generation unit can also utilize manually entered information in order to generate text for the procedure section. For example, the text generation unit can generate text for the procedure section using a generation AI. This allows for a clear description of the contents of the procedure manual by generating text for the procedure section. The text for the procedure section may include, but is not limited to, operating procedures, usage instructions, and precautions. Some or all of the above-described processes in the text generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the text generation unit can input the contents of recorded data into a generation AI and have the generation AI perform the generation of text for the procedure section.

[0078] The image capture unit can capture images within a video conference aligned with the text. For example, the image capture unit can take screenshots to capture the video conference screen. The image capture unit can also extract specific frames from the video conference recording data. The image capture unit can also capture specific scenes from the video conference recording data. For example, the image capture unit takes screenshots to capture the video conference screen. This helps in the visual understanding of the procedure manual by capturing images aligned with the text. Images within a video conference aligned with the text include, but are not limited to, operation screens, usage examples, and points to note. Some or all of the above processing in the image capture unit may be performed, for example, using a generative AI, or without a generative AI. For example, the image capture unit can input video conference recording data into a generative AI and have the generative AI extract specific frames.

[0079] The retext unit can retext the generated procedure manual if it is insufficient, by specifying the recording time of the insufficient parts. The retext unit can, for example, identify the insufficient parts of the procedure manual and retext them. The retext unit can also receive feedback from the user to identify the insufficient parts of the procedure manual. The retext unit can also reanalyze the content of the recording data to identify the insufficient parts of the procedure manual. For example, the retext unit can identify the insufficient parts of the procedure manual and retext them. This allows the content of the procedure manual to be supplemented by retexting it when it is insufficient. Insufficiencies include, but are not limited to, missing information, errors, and ambiguities. Some or all of the above processing in the retext unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the retext unit can input the insufficient parts of the procedure manual into a generating AI and have the generating AI perform the retexting.

[0080] The acquisition unit estimates the user's emotions and adjusts the timing of recording data acquisition based on the estimated emotions. The acquisition unit can estimate the user's emotions and adjust the timing of recording data acquisition based on the estimated emotions. For example, if the user is concentrating, the acquisition unit can acquire recording data frequently to collect detailed data. If the user is tired, the acquisition unit can reduce the frequency of recording data acquisition and acquire only the important parts. If the user is excited, the acquisition unit can adjust the timing of recording data acquisition to acquire data at the peak of the emotion. For example, the acquisition unit can capture the user's facial expressions with a camera and estimate emotions using an emotion estimation algorithm. The acquisition unit can also record the user's voice and estimate emotions using voice analysis technology. The acquisition unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. This allows data to be acquired at the appropriate time by adjusting the timing of recording data acquisition based on the user's emotions. 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 acquisition unit may be performed using AI, or not using AI. For example, the acquisition unit can input user emotion data into the AI ​​and have the AI ​​adjust the timing of recording data acquisition.

[0081] The acquisition unit analyzes the user's past recording data acquisition history and selects the optimal acquisition method. The acquisition unit can analyze the user's past recording data acquisition history and select the optimal acquisition method. For example, the acquisition unit can analyze the time periods in which the user frequently acquired data in the past and acquire recording data during those time periods. The acquisition unit can also analyze the content of data previously acquired by the user and prioritize the acquisition of similar content. The acquisition unit can also prioritize the acquisition of data related to specific events or topics from the user's past acquisition history. For example, the acquisition unit can analyze the time periods in which the user frequently acquired data in the past and acquire recording data during those time periods. This allows the acquisition unit to select the optimal acquisition method by analyzing the user's past recording data acquisition history. The optimal acquisition method includes, but is not limited to, data quality and acquisition efficiency. Some or all of the above processing in the acquisition unit may be performed using, for example, AI, or not using AI. For example, the acquisition unit can input the user's past recording data acquisition history into AI and have the AI ​​select the optimal acquisition method.

[0082] The acquisition unit filters the recorded video data based on the user's current projects and areas of interest when acquiring it. The acquisition unit can filter the recorded video data based on the user's current projects and areas of interest when acquiring it. For example, the acquisition unit prioritizes acquiring recorded video data related to the project the user is currently working on. The acquisition unit can also filter and acquire relevant recorded video data based on the user's areas of interest. The acquisition unit can also select and acquire necessary recorded video data according to the progress of the user's projects. For example, the acquisition unit prioritizes acquiring recorded video data related to the project the user is currently working on. This allows for the acquisition of highly relevant data by filtering based on the user's current projects and areas of interest. The user's current projects and areas of interest include, but are not limited to, project management tools and survey results. Some or all of the above processing in the acquisition unit may be performed using, for example, AI, or not using AI. For example, the acquisition unit can input the user's current projects and areas of interest into AI and have AI perform the filtering of recorded video data.

[0083] The acquisition unit estimates the user's emotions and determines the priority of the recorded data to acquire based on the estimated user emotions. The acquisition unit can estimate the user's emotions and determine the priority of the recorded data to acquire based on the estimated user emotions. For example, if the user is feeling stressed, the acquisition unit will prioritize acquiring recorded data with relaxing content. The acquisition unit can also prioritize acquiring recorded data with interesting content if the user is excited. The acquisition unit can also prioritize acquiring recorded data with learning-related content if the user is focused. For example, if the acquisition unit is feeling stressed, it will prioritize acquiring recorded data with relaxing content. This allows for the priority acquisition of important data by determining the priority of recorded data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. 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 acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input user emotion data into the AI ​​and have the AI ​​determine the priority of the recorded data.

[0084] The acquisition unit prioritizes acquiring highly relevant data when acquiring recorded data, taking into account the user's geographical location information. The acquisition unit can prioritize acquiring highly relevant data when acquiring recorded data, taking into account the user's geographical location information. For example, if the user is in a specific region, the acquisition unit prioritizes acquiring recorded data related to that region. If the user is traveling, the acquisition unit can also prioritize acquiring recorded data related to the travel destination. If the user is participating in a specific event, the acquisition unit can also prioritize acquiring recorded data related to that event. For example, if the acquisition unit is in a specific region, it prioritizes acquiring recorded data related to that region. This allows for the priority acquisition of highly relevant data by considering the user's geographical location information. The user's geographical location information includes, but is not limited to, GPS data and IP addresses. Some or all of the above processing in the acquisition unit may be performed using, for example, AI, or without AI. For example, the acquisition unit can input the user's geographical location information into AI and have the AI ​​determine the priority for acquiring recorded data.

[0085] The acquisition unit analyzes the user's social media activity and obtains relevant data when acquiring recorded data. The acquisition unit can analyze the user's social media activity and obtain relevant data when acquiring recorded data. For example, the acquisition unit can prioritize acquiring recorded data related to content shared by the user on social media. The acquisition unit can also prioritize acquiring recorded data related to accounts followed by the user on social media. The acquisition unit can also prioritize acquiring recorded data related to topics the user has shown interest in on social media. For example, the acquisition unit prioritizes acquiring recorded data related to content shared by the user on social media. This allows relevant data to be obtained by analyzing the user's social media activity. The user's social media activity includes, but is not limited to, posts, number of followers, and number of likes. Some or all of the above processing in the acquisition unit may be performed using, for example, AI, or not using AI. For example, the acquisition unit can input the user's social media activity into AI and have the AI ​​determine the priority for acquiring recorded data.

[0086] The analysis unit estimates the user's emotions and adjusts the criteria for selecting procedure instructions based on the estimated emotions. The analysis unit can estimate the user's emotions and adjust the criteria for selecting procedure instructions based on the estimated emotions. For example, if the user is relaxed, the analysis unit will select detailed procedure instructions. If the user is in a hurry, the analysis unit can also select concise procedure instructions. If the user is excited, the analysis unit can also select visually stimulating procedure instructions. For example, the analysis unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The analysis unit can also record the user's voice and estimate their emotions using voice analysis technology. The analysis unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows for the extraction of appropriate procedure instructions by adjusting the criteria for selecting procedure instructions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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 the generation AI, or not using the generation AI. For example, the analysis unit may input user sentiment data into the generation AI and have the generation AI adjust the criteria for selecting procedural explanations.

[0087] The analysis unit improves the accuracy of the analysis by considering the audio quality of the recorded data during the analysis. The analysis unit can improve the accuracy of the analysis by considering the audio quality of the recorded data during the analysis. For example, if the audio of the recorded data is clear, the analysis unit will analyze the detailed procedural explanation. If the audio of the recorded data is unclear, the analysis unit can also perform noise reduction to improve the accuracy of the analysis. The analysis unit can also apply different analysis algorithms depending on the audio quality of the recorded data. For example, if the audio of the recorded data is clear, the analysis unit will analyze the detailed procedural explanation. This improves the accuracy of the analysis by considering the audio quality of the recorded data. Audio quality includes, but is not limited to, noise level and speech clarity. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the audio quality of the recorded data into a generative AI and have the generative AI perform the improvement of the analysis accuracy.

[0088] The analysis unit applies different analysis algorithms depending on the content of the recorded data during analysis. The analysis unit can apply different analysis algorithms depending on the content of the recorded data during analysis. For example, the analysis unit can apply an algorithm that analyzes technical terms to recorded data with technical content. The analysis unit can also apply an algorithm that analyzes educational terms to recorded data with educational content. The analysis unit can also apply an algorithm that analyzes business terms to recorded data with business-related content. For example, the analysis unit applies an algorithm that analyzes technical terms to recorded data with technical content. This improves the accuracy of the analysis by applying different analysis algorithms depending on the content of the recorded data. Different analysis algorithms include, but are not limited to, speech recognition algorithms and natural language processing algorithms. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the content of the recorded data into a generative AI and have the generative AI execute the application of different analysis algorithms.

[0089] The analysis unit estimates the user's emotions and adjusts the display method of the analysis results based on the estimated emotions. 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 provides a simple and highly visible display method. If the user is relaxed, the analysis unit can also provide a display method that includes detailed information. If the user is in a hurry, the analysis unit can also provide a concise display method. For example, the analysis unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The analysis unit can also record the user's voice and estimate their emotions using voice analysis technology. The analysis unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the system to provide an appropriate display method by adjusting the display method of the analysis results based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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 the generation AI, or not using the generation AI. For example, the analysis unit can input user emotion data into the generation AI and have the generation AI adjust how the analysis results are displayed.

[0090] The analysis unit determines the priority of analysis based on the submission date of the recorded data during analysis. The analysis unit can determine the priority of analysis based on the submission date of the recorded data during analysis. For example, the analysis unit prioritizes the analysis of recently submitted recorded data. The analysis unit can also prioritize the analysis of recorded data with approaching deadlines. If the user is in a hurry, the analysis unit can also prioritize the analysis regardless of the submission date. For example, the analysis unit prioritizes the analysis of recently submitted recorded data. This allows for the priority of analysis of important data by determining the priority of analysis based on the submission date of the recorded data. The submission date includes, but is not limited to, the submission date and time. Some or all of the above processing in the analysis unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the analysis unit can input the submission date of the recorded data into a generating AI and have the generating AI determine the priority of analysis.

[0091] The analysis unit improves the accuracy of the analysis by referring to relevant literature related to the recorded data during the analysis. The analysis unit can improve the accuracy of the analysis by referring to relevant literature related to the recorded data during the analysis. For example, the analysis unit improves the accuracy of the analysis by referring to literature related to the content of the recorded data. The analysis unit can also improve the accuracy of the analysis by referring to research papers related to the content of the recorded data. The analysis unit can also improve the accuracy of the analysis by referring to books related to the content of the recorded data. For example, the analysis unit improves the accuracy of the analysis by referring to literature related to the content of the recorded data. This improves the accuracy of the analysis by referring to relevant literature related to the recorded data. Relevant literature includes, but is not limited to, academic papers and technical documents. Some or all of the above processing in the analysis unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the analysis unit can input the content of the recorded data into a generating AI and have the generating AI perform the referencing of relevant literature.

[0092] The text generation unit estimates the user's emotions and adjusts the text's expression based on those emotions. For example, if the user is relaxed, the text generation unit will use a friendly style of expression. If the user is in a hurry, the text generation unit may use a concise and to-the-point style of expression. If the user is excited, the text generation unit may use a visually stimulating style of expression. For example, the text generation unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. It can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, the text generation unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the text to be presented in an appropriate style by adjusting its expression based on the user's emotions. Emotion estimation is achieved, for example, using 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 text generation unit may be performed using a generative AI, or not using a generative AI. For example, the text generation unit may input user sentiment data into the generative AI and have the generative AI adjust the way the text is expressed.

[0093] The text generation unit adjusts the level of detail in the text based on the importance of the procedure during text generation. The text generation unit can adjust the level of detail in the text based on the importance of the procedure during text generation. For example, the text generation unit generates text with detailed explanations for important procedures. The text generation unit can also generate text with concise explanations for less important procedures. The text generation unit can also generate text with different levels of detail depending on the importance of the procedure. For example, the text generation unit generates text with detailed explanations for important procedures. This allows important procedures to be described in detail by adjusting the level of detail in the text based on the importance of the procedure. The importance of a procedure includes, but is not limited to, the frequency of the operation and the magnitude of its impact. Some or all of the above processing in the text generation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the text generation unit can input the importance of the procedure into the generation AI and have the generation AI perform the adjustment of the level of detail in the text.

[0094] The text generation unit applies different text generation algorithms depending on the procedure category when generating text. The text generation unit can apply different text generation algorithms depending on the procedure category when generating text. For example, the text generation unit can apply a text generation algorithm that includes technical terms to technical procedures. The text generation unit can also apply a text generation algorithm that includes educational terms to educational procedures. The text generation unit can also apply a text generation algorithm that includes business terms to business-related procedures. For example, the text generation unit applies a text generation algorithm that includes technical terms to technical procedures. This allows for the generation of appropriate text by applying different text generation algorithms depending on the procedure category. Procedure categories include, but are not limited to, operating procedures, setup procedures, and troubleshooting. Some or all of the above-described processes in the text generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the text generation unit can input the procedure category into the generation AI and cause the generation AI to apply different text generation algorithms.

[0095] The text generation unit estimates the user's emotions and adjusts the length of the text based on the estimated emotions. For example, if the user is in a hurry, the text generation unit can generate short, concise text. If the user is relaxed, the text generation unit can also generate longer text with detailed explanations. If the user is excited, the text generation unit can also generate text with visually stimulating effects. For example, the text generation unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. It can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, the text generation unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the system to provide text of appropriate length by adjusting the length based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, 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 text generation unit may be performed using a generative AI, or not using a generative AI. For example, the text generation unit may input user sentiment data into the generative AI and have the generative AI adjust the length of the text.

[0096] The text generation unit determines the priority of text based on the submission date of each procedure when generating text. The text generation unit can determine the priority of text based on the submission date of each procedure when generating text. For example, the text generation unit can prioritize generating text for procedures with approaching deadlines. The text generation unit can also prioritize generating text for recently submitted procedures. If the user is in a hurry, the text generation unit can also prioritize generating text regardless of the submission date. For example, the text generation unit prioritizes generating text for procedures with approaching deadlines. This allows for the priority generation of important procedures by determining the text priority based on the submission date of each procedure. The submission date includes, but is not limited to, the submission date and time. Some or all of the above processing in the text generation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the text generation unit can input the submission dates of procedures into the generation AI and have the generation AI determine the text priority.

[0097] The text generation unit adjusts the order of text based on the relevance of the procedures during text generation. The text generation unit can adjust the order of text based on the relevance of the procedures during text generation. For example, the text generation unit places important procedures first and generates text in order of relevance. The text generation unit can also adjust the order of text based on the relevance of the procedures. The text generation unit can also generate text in different orders depending on the relevance of the procedures. For example, the text generation unit places important procedures first and generates text in order of relevance. This allows the text to be provided in an appropriate order by adjusting the order of text based on the relevance of the procedures. The relevance of procedures includes, but is not limited to, the order of operations and related operations. Some or all of the above processing in the text generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the text generation unit can input the relevance of procedures into a generation AI and have the generation AI perform the adjustment of the text order.

[0098] The image capture unit estimates the user's emotions and adjusts the criteria for selecting captured images based on the estimated emotions. For example, if the user is relaxed, the image capture unit may select a visually calming image. If the user is excited, the image capture unit may select a visually stimulating image. If the user is focused, the image capture unit may select an image containing detailed information. For example, the image capture unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. It can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, the image capture unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows for the provision of appropriate images by adjusting the criteria for selecting captured images based on the user's emotions. Emotion estimation is achieved, for example, using an emotion engine or generative 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 processing described above in the image capture unit may be performed using the generation AI, or not. For example, the image capture unit can input user emotion data into the generation AI and have the generation AI adjust the selection criteria for captured images.

[0099] The image capture unit adjusts the level of detail of the captured image based on the importance of the procedure during image capture. The image capture unit can adjust the level of detail of the captured image based on the importance of the procedure during image capture. For example, the image capture unit captures images containing detailed information for important procedures. The image capture unit can also capture images containing concise information for less important procedures. The image capture unit can also capture images with different levels of detail depending on the importance of the procedure. For example, the image capture unit captures images containing detailed information for important procedures. This allows important procedures to be described in detail by adjusting the level of detail of the captured image based on the importance of the procedure. The importance of a procedure includes, but is not limited to, the frequency of the operation and the magnitude of its impact. Some or all of the above processing in the image capture unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the image capture unit can input the importance of the procedure into the generative AI and have the generative AI perform the adjustment of the level of detail of the captured image.

[0100] The image capture unit applies different capture algorithms depending on the procedure category when capturing images. The image capture unit can apply different capture algorithms depending on the procedure category when capturing images. For example, for technical procedures, it applies an algorithm that captures images containing specialized information. The image capture unit can also apply an algorithm that captures images containing educational information for educational procedures. The image capture unit can also apply an algorithm that captures images containing business information for business-related procedures. For example, the image capture unit applies an algorithm that captures images containing specialized information for technical procedures. This allows for the provision of appropriate images by applying different capture algorithms depending on the procedure category. Procedure categories include, but are not limited to, operating procedures, setup procedures, and troubleshooting. Some or all of the above processing in the image capture unit may be performed, for example, using a generative AI, or without a generative AI. For example, the image capture unit can input the procedure category into a generative AI and cause the generative AI to apply different capture algorithms.

[0101] The image capture unit estimates the user's emotions and adjusts the display method of the captured image based on the estimated emotions. The image capture unit can estimate the user's emotions and adjust the display method of the captured image based on the estimated emotions. For example, if the user is tense, the image capture unit provides a simple and highly visible display method. If the user is relaxed, the image capture unit can also provide a display method that includes detailed information. If the user is in a hurry, the image capture unit can also provide a concise display method. For example, the image capture unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The image capture unit can also record the user's voice and estimate their emotions using voice analysis technology. The image capture unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the system to provide an appropriate display method by adjusting the display method of the captured image based on the user's emotions. Emotion estimation is achieved, for example, using an emotion engine or generative 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 processing described above in the image capture unit may be performed using a generation AI, or not. For example, the image capture unit can input user emotion data into the generation AI and have the generation AI adjust how the captured image is displayed.

[0102] The image capture unit determines the priority of captured images based on the submission date of the procedure when capturing an image. The image capture unit can determine the priority of captured images based on the submission date of the procedure when capturing an image. For example, the image capture unit can prioritize the generation of captured images for procedures with approaching deadlines. The image capture unit can also prioritize the generation of captured images for recently submitted procedures. If the user is in a hurry, the image capture unit can also prioritize the generation of captured images regardless of the submission date. For example, the image capture unit can prioritize the generation of captured images for procedures with approaching deadlines. This allows for the priority generation of important procedures by determining the priority of captured images based on the submission date of the procedure. The submission date includes, but is not limited to, the submission date and time. Some or all of the above processing in the image capture unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the image capture unit can input the procedure submission date into the generation AI and have the generation AI perform the determination of the priority of captured images.

[0103] The image capture unit adjusts the order of captured images based on the relevance of the procedures during image capture. The image capture unit can adjust the order of captured images based on the relevance of the procedures during image capture. For example, the image capture unit places important procedures first and generates captured images in order of relevance. The image capture unit can also adjust the order of captured images based on the relevance of the procedures. The image capture unit can also generate captured images in different orders depending on the relevance of the procedures. For example, the image capture unit places important procedures first and generates captured images in order of relevance. This allows images to be provided in the appropriate order by adjusting the order of captured images based on the relevance of the procedures. The relevance of procedures includes, but is not limited to, the order of operations and related operations. Some or all of the above processing in the image capture unit may be performed using, for example, a generative AI, or without a generative AI. For example, the image capture unit can input the relevance of the procedures into a generative AI and have the generative AI perform the adjustment of the order of captured images.

[0104] The retext unit estimates the user's emotions and adjusts the retexting method based on the estimated emotions. The retext unit can estimate the user's emotions and adjust the retexting method based on the estimated emotions. For example, if the user is relaxed, the retext unit will use a friendly style of expression. If the user is in a hurry, the retext unit can also use a concise and to-the-point style of expression. If the user is excited, the retext unit can also use a visually stimulating style of expression. For example, the retext unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The retext unit can also record the user's voice and estimate their emotions using speech analysis technology. The retext unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the retext unit to provide an appropriate style of expression by adjusting the retexting method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the retext unit may be performed using the generating AI, or not using the generating AI. For example, the retext unit can input user sentiment data into the generating AI and have the generating AI adjust the retext method.

[0105] The retext unit identifies insufficient parts of the procedure manual and selects the optimal retext method during the retext process. The retext unit can identify insufficient parts of the procedure manual and select the optimal retext method during the retext process. For example, the retext unit can automatically identify insufficient parts of the procedure manual and add detailed explanations. The retext unit can also add relevant information to insufficient parts of the procedure manual. The retext unit can also identify insufficient parts of the procedure manual and retext based on user feedback. For example, the retext unit can automatically identify insufficient parts of the procedure manual and add detailed explanations. This allows for the supplementation of the procedure manual's content by identifying insufficient parts and selecting the optimal retext method. Insufficient parts include, but are not limited to, missing information, errors, and ambiguities. Some or all of the above-described processes in the retext unit may be performed, for example, using a generative AI, or without using a generative AI. For example, the re-text unit can input the insufficient parts of the procedure manual into the generating AI and have the generating AI select the optimal re-text method.

[0106] The retext unit applies different retext algorithms depending on the content of the procedure manual during retexting. The retext unit can apply different retext algorithms depending on the content of the procedure manual during retexting. For example, the retext unit applies a retext algorithm that includes technical terms to technical procedure manuals. The retext unit can also apply a retext algorithm that includes educational terms to educational procedure manuals. The retext unit can also apply a retext algorithm that includes business terms to business-related procedure manuals. For example, the retext unit applies a retext algorithm that includes technical terms to technical procedure manuals. This allows for appropriate retexting by applying different retext algorithms depending on the content of the procedure manual. Examples of different retext algorithms include, but are not limited to, speech recognition algorithms and natural language processing algorithms. Some or all of the processing described above in the retext unit may be performed using, for example, generative AI, or without generative AI. For example, the retext conversion unit can input the contents of the procedure manual into the generating AI and have the generating AI execute different retext conversion algorithms.

[0107] The retext unit estimates the user's emotions and determines the priority of retexting based on the estimated emotions. The retext unit can estimate the user's emotions and determine the priority of retexting based on the estimated emotions. For example, if the user is in a hurry, the retext unit will prioritize retexting important sections. If the user is relaxed, the retext unit can also prioritize retexting sections containing detailed explanations. If the user is excited, the retext unit can also prioritize retexting visually stimulating sections. For example, the retext unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The retext unit can also record the user's voice and estimate their emotions using voice analysis technology. The retext unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the retext unit to prioritize retexting important sections by determining the priority of retexting based on the user's emotions. 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, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the retext unit may be performed using the generative AI, or not using the generative AI. For example, the retext unit can input user emotion data into the generative AI and have the generative AI determine the priority of retexting.

[0108] The retext unit determines the priority of retexting based on the submission date of the procedure manuals during the retexting process. The retext unit can determine the priority of retexting based on the submission date of the procedure manuals during the retexting process. For example, the retext unit may prioritize retexting procedure manuals with approaching deadlines. The retext unit may also prioritize retexting recently submitted procedure manuals. If the user is in a hurry, the retext unit may also prioritize retexting regardless of the submission date. For example, the retext unit may prioritize retexting procedure manuals with approaching deadlines. This allows important procedure manuals to be prioritized for retexting by determining the priority of retexting based on the submission date of the procedure manuals. The submission date includes, but is not limited to, the submission date and time. Some or all of the above processing in the retext unit may be performed, for example, using a generative AI, or not using a generative AI. For example, the re-text conversion unit can input the submission deadline for the procedure manual into the generating AI and have the generating AI determine the priority of the re-text conversion.

[0109] The retext unit improves the accuracy of retext by referring to relevant literature for the procedure manual during the retexting process. The retext unit can improve the accuracy of retext by referring to relevant literature for the procedure manual during the retexting process. For example, the retext unit can improve the accuracy of retext by referring to literature related to the content of the procedure manual. The retext unit can also improve the accuracy of retext by referring to research papers related to the content of the procedure manual. The retext unit can also improve the accuracy of retext by referring to books related to the content of the procedure manual. For example, the retext unit improves the accuracy of retext by referring to literature related to the content of the procedure manual. This improves the accuracy of retext by referring to relevant literature for the procedure manual. Relevant literature includes, but is not limited to, academic papers and technical documents. Some or all of the above processing in the retext unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the retext unit can input the content of the procedure manual into a generating AI and have the generating AI perform the referencing of relevant literature.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] The acquisition unit can estimate the user's emotions and adjust the timing of recording data acquisition based on the estimated emotions. For example, if the user is focused, recording data can be acquired frequently to collect detailed data. If the user is tired, the frequency of recording data acquisition can be reduced, and only important parts can be acquired. If the user is excited, the timing of recording data acquisition can be adjusted to capture data at the peak of their emotions. In this way, by adjusting the timing of recording data acquisition based on the user's emotions, data can be acquired at the appropriate time.

[0112] The analysis unit can estimate the user's emotions and adjust the criteria for selecting instructions based on those emotions. For example, if the user is relaxed, detailed instructions can be selected. If the user is in a hurry, concise instructions can be selected. If the user is excited, visually stimulating instructions can be selected. By adjusting the criteria for selecting instructions based on the user's emotions, appropriate instructions can be extracted.

[0113] The text generation unit can estimate the user's emotions and adjust the text's expression based on those emotions. For example, if the user is relaxed, a friendly expression can be used. If the user is in a hurry, a concise and to-the-point expression can be used. If the user is excited, a visually stimulating expression can be used. In this way, by adjusting the text's expression based on the user's emotions, an appropriate expression can be provided.

[0114] The image capture unit can estimate the user's emotions and adjust the criteria for selecting captured images based on those emotions. For example, if the user is relaxed, it can select a visually calming image. If the user is excited, it can select a visually stimulating image. If the user is focused, it can select an image containing detailed information. In this way, by adjusting the criteria for selecting captured images based on the user's emotions, the system can provide appropriate images.

[0115] The retext generation unit can estimate the user's emotions and adjust the retext generation method based on the estimated emotions. For example, if the user is relaxed, a friendly expression can be used. If the user is in a hurry, a concise and to-the-point expression can be used. If the user is excited, a visually stimulating expression can be used. In this way, by adjusting the retext generation method based on the user's emotions, an appropriate expression can be provided.

[0116] The acquisition unit can analyze the user's past recording data acquisition history and select the optimal acquisition method. For example, it can analyze the time periods in which the user frequently acquired data in the past and acquire recording data during those times. It can also analyze the content of data the user has acquired in the past and prioritize the acquisition of similar content. It can also prioritize the acquisition of data related to specific events or topics from the user's past acquisition history. In this way, the optimal acquisition method can be selected by analyzing the user's past recording data acquisition history.

[0117] The acquisition unit can filter recorded data based on the user's current projects and areas of interest. For example, it can prioritize the acquisition of recorded data related to the user's current project. It can also filter and acquire relevant recorded data based on the user's areas of interest. It can also select and acquire necessary recorded data according to the progress of the user's project. This allows for the acquisition of highly relevant data by filtering based on the user's current projects and areas of interest.

[0118] The analysis unit can improve the accuracy of the analysis by considering the audio quality of the recorded data during the analysis. For example, if the audio of the recorded data is clear, it can analyze detailed procedural explanations. If the audio of the recorded data is unclear, noise reduction can be performed to improve the accuracy of the analysis. Different analysis algorithms can also be applied depending on the audio quality of the recorded data. In this way, the accuracy of the analysis can be improved by considering the audio quality of the recorded data.

[0119] The text generation unit can adjust the level of detail in the text based on the importance of each step during text generation. For example, it can generate text with detailed explanations for important steps, and text with concise explanations for less important steps. It can also generate text with different levels of detail depending on the importance of each step. This allows important steps to be described in detail by adjusting the level of detail based on the importance of each step.

[0120] The image capture unit can adjust the level of detail in captured images based on the importance of each step. For example, important steps can be captured with images containing detailed information. Less important steps can be captured with images containing concise information. Images with different levels of detail can also be captured depending on the importance of each step. This allows for detailed descriptions of important steps by adjusting the level of detail in captured images based on their importance.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The acquisition unit acquires the recorded data of the video conference training. For example, the acquisition unit can download the recorded data of the video conference training from cloud storage. It can also directly acquire the recorded data using the video conferencing API. Furthermore, it can read the recorded data stored in local storage. Step 2: The analysis unit analyzes the recorded data acquired by the acquisition unit and picks out only the procedural explanations from the conversation. For example, the analysis unit uses a generation AI to convert the audio of the recorded data into text and identify the procedural explanation portion. Alternatively, natural language processing technology can be used to extract the procedural explanation portion. Step 3: The text generation unit converts the procedure descriptions picked up by the analysis unit into text. The text generation unit generates the procedure text using, for example, a generation AI. It can also utilize manually entered information. Step 4: The image capture unit captures images from the video conference in accordance with the text generated by the text generation unit. The image capture unit can, for example, take screenshots to capture the video conference screen. It can also extract specific frames or scenes from the video conference recording data. Step 5: If the generated procedure manual is insufficient, the re-text unit will re-text it by specifying the recording time of the insufficient parts. For example, the re-text unit will identify the insufficient parts of the procedure manual and re-text them. It can also receive feedback from the user.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] Each of the multiple elements described above, including the acquisition unit, analysis unit, text generation unit, image capture unit, and re-text unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the acquisition unit can acquire recorded video conference training data via the communication I / F 44 of the smart device 14. The analysis unit analyzes the recorded data using the specific processing unit 290 of the data processing device 12 and picks out the procedure explanations. The text generation unit generates text for the procedure sections using the specific processing unit 290 of the data processing device 12. The image capture unit captures images from the video conference using the control unit 46A of the smart device 14. The re-text unit re-texts any insufficient parts of the procedure manual using the specific processing unit 290 of the data processing device 12. 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.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0132] 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).

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] Each of the multiple elements described above, including the acquisition unit, analysis unit, text generation unit, image capture unit, and re-text unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the acquisition unit can acquire recorded video conference training data via the communication I / F 44 of the smart glasses 214. The analysis unit analyzes the recorded data using the specific processing unit 290 of the data processing unit 12 and picks out the procedure explanations. The text generation unit generates text for the procedure sections using the specific processing unit 290 of the data processing unit 12. The image capture unit captures images from the video conference using the control unit 46A of the smart glasses 214. The re-text unit re-texts any insufficient parts of the procedure manual using the specific processing unit 290 of the data processing unit 12. 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.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.).

[0155] 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.

[0156] 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.

[0157] 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.

[0158] Each of the multiple elements described above, including the acquisition unit, analysis unit, text generation unit, image capture unit, and re-text unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the acquisition unit can acquire recorded video conference training data via the communication I / F 44 of the headset terminal 314. The analysis unit analyzes the recorded data using the specific processing unit 290 of the data processing unit 12 and picks out the procedure explanations. The text generation unit generates text for the procedure sections using the specific processing unit 290 of the data processing unit 12. The image capture unit captures images from the video conference using the control unit 46A of the headset terminal 314. The re-text unit re-texts any insufficient parts of the procedure manual using the specific processing unit 290 of the data processing unit 12. 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.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0164] 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).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.).

[0172] 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.

[0173] 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.

[0174] 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.

[0175] Each of the multiple elements described above, including the acquisition unit, analysis unit, text generation unit, image capture unit, and re-text unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the acquisition unit can acquire recorded video conference training data via the communication I / F 44 of the robot 414. The analysis unit analyzes the recorded data using the specific processing unit 290 of the data processing unit 12 and picks out the procedure explanations. The text generation unit generates text for the procedure portions using the specific processing unit 290 of the data processing unit 12. The image capture unit captures images from the video conference using the control unit 46A of the robot 414. The re-text unit re-texts any insufficient parts of the procedure manual using the specific processing unit 290 of the data processing unit 12. 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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."

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] (Note 1) An acquisition unit that acquires recorded data of video conference training, An analysis unit analyzes the recorded data acquired by the acquisition unit and picks out procedural explanations, A text generation unit that converts the procedure description picked up by the analysis unit into text, An image capture unit captures an image corresponding to the text generated by the text generation unit, The system includes a retexting unit that, if the procedure manual generated by the image capture unit is insufficient, specifies the recording time of the insufficient parts and retexts them. A system characterized by the following features. (Note 2) The acquisition unit is, Obtain recorded data from video conference training sessions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, The recorded data is analyzed, and only the procedural explanations are extracted from the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 4) The text generation unit, Generate the text for the procedure section. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned image capture unit, Capture images within a video conference that are aligned with the text. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned retext conversion unit, If the generated procedure manual is insufficient, specify the recording time for the insufficient parts and re-text it. The system described in Appendix 1, characterized by the features described herein. (Note 7) The acquisition unit is, The system estimates the user's emotions and adjusts the timing of recording data acquisition based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The acquisition unit is, The system analyzes the user's past recording data acquisition history and selects the optimal acquisition method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The acquisition unit is, When acquiring recorded data, filtering is performed based on the user's current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The acquisition unit is, The system estimates the user's emotions and determines the priority of the recorded data to acquire based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The acquisition unit is, When acquiring recorded data, the system prioritizes the acquisition of highly relevant data, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The acquisition unit is, When acquiring recorded data, the system analyzes the user's social media activity and retrieves relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, The system estimates the user's emotions and adjusts the criteria for selecting instructions based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During analysis, the audio quality of the recorded data is taken into consideration to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the content of the recorded data. The system described in Appendix 1, characterized by the features described herein. (Note 16) 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 17) The aforementioned analysis unit, During analysis, the priority of the analysis is determined based on when the video data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During analysis, we refer to relevant literature on the video data to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 19) The text generation unit, It estimates the user's emotions and adjusts the way text is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The text generation unit, When generating text, adjust the level of detail in the text based on the importance of each step. The system described in Appendix 1, characterized by the features described herein. (Note 21) The text generation unit, When generating text, different text generation algorithms are applied depending on the category of the procedure. The system described in Appendix 1, characterized by the features described herein. (Note 22) The text generation unit, It estimates the user's emotions and adjusts the length of the text based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The text generation unit, When generating text, prioritize the text based on when the procedure was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 24) The text generation unit, When generating text, adjust the order of the text based on the relevance of the steps. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned image capture unit, The system estimates the user's emotions and adjusts the selection criteria for captured images based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned image capture unit, When capturing images, adjust the level of detail of the captured images based on the importance of the procedure. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned image capture unit, When capturing images, different capture algorithms are applied depending on the category of the procedure. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned image capture unit, It estimates the user's emotions and adjusts how captured images are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned image capture unit, When capturing images, prioritize the captured images based on the submission date of the procedure. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned image capture unit, When capturing images, adjust the order of captured images based on the relevance of the procedure. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned retext conversion unit, It estimates the user's emotions and adjusts the retexting method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned retext conversion unit, During the re-text conversion process, identify any shortcomings in the procedure manual and select the most suitable re-text conversion method. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned retext conversion unit, When re-texting, different re-texting algorithms are applied depending on the content of the procedure manual. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned retext conversion unit, The system estimates the user's emotions and determines the priority of retexting based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned retext conversion unit, When re-texting, prioritize the re-texting based on the submission date of the procedure manual. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned retext conversion unit, When re-texting, we improve the accuracy of the re-texting by referring to related documents in the procedure manual. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0195] 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. An acquisition unit that acquires recorded data of video conference training, An analysis unit analyzes the recorded data acquired by the acquisition unit and picks out procedural explanations, A text generation unit that converts the procedure description picked up by the analysis unit into text, An image capture unit captures an image corresponding to the text generated by the text generation unit, The system includes a retexting unit that, if the procedure manual generated by the image capture unit is insufficient, retexts the insufficient parts by specifying the recording time. A system characterized by the following features.

2. The acquisition unit is, Obtain recorded data from video conference training sessions. The system according to feature 1.

3. The aforementioned analysis unit, The recorded data is analyzed, and only the procedural explanations are extracted from the conversation. The system according to feature 1.

4. The text generation unit, Generate the text for the procedure section. The system according to feature 1.

5. The aforementioned image capture unit, Capture images within a video conference that are aligned with the text. The system according to feature 1.

6. The aforementioned retext conversion unit, If the generated procedure manual is insufficient, specify the recording time for the insufficient parts and re-text it. The system according to feature 1.

7. The acquisition unit is, The system estimates the user's emotions and adjusts the timing of recording data acquisition based on the estimated emotions. The system according to feature 1.

8. The acquisition unit is, The system analyzes the user's past recording data acquisition history and selects the optimal acquisition method. The system according to feature 1.

Images