system

Abstract

The system according to this embodiment aims to efficiently collect and analyze opinions during meetings and discussions. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a conversion unit, and a learning unit. The collection unit collects opinions. The analysis unit performs sentiment analysis on the opinions collected by the collection unit. The conversion unit converts the opinions analyzed by the analysis unit into text. The learning unit learns the text converted by the conversion unit.

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 the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, opinion collection and analysis in meetings and discussions are not efficiently performed, and there is room for improvement.

[0005] The system according to the embodiment aims to efficiently collect and analyze opinions in meetings and discussions.

Means for Solving the Problems

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a conversion unit, and a learning unit. The collection unit collects opinions. The analysis unit performs sentiment analysis on the opinions collected by the collection unit. The conversion unit converts the opinions analyzed by the analysis unit into text. The learning unit learns the text converted by the conversion unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently collect and analyze opinions during meetings and discussions. [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 signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[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 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are 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 Idea Dashboard with AI Agent according to an embodiment of the present invention is an innovative AI agent solution for dramatically improving the efficiency and productivity of meetings and discussions. This AI agent solution collects opinions in real time and automatically segments them. Next, it performs sentiment analysis on the collected opinions to grasp positive / negative feedback and changes in emotion in real time. Furthermore, it converts meeting audio into text in real time and records it automatically. This allows for later review of the meeting content. The AI ​​agent also learns from the meeting data and makes optimal suggestions and improvements for future meetings. This can overcome the "dislike of meetings" culture in Japanese companies and improve meeting productivity. For example, the AI ​​agent collects opinions in real time during a meeting. Participants can post their opinions anonymously, providing an environment where they can speak freely. For example, if a participant posts, "I have an opinion on the progress of this project," the AI ​​agent collects that opinion and automatically segments it. Next, it performs sentiment analysis on the collected opinions. The AI ​​agent analyzes the participants' statements and grasps positive / negative feedback and changes in emotion in real time. For example, if a participant says, "This project is progressing smoothly," the AI ​​agent will analyze this as positive feedback. Furthermore, it will convert the meeting audio into text in real time and record it automatically. This allows for later review of the meeting content. For example, if a question is asked during the meeting, "What is the next step?", the question and answer will be recorded as text. The AI ​​agent also learns from the meeting data and makes optimal suggestions and improvements for future meetings. For example, if there was a suggestion in the previous meeting that "we would like a more detailed report on the project's progress," the next meeting will include a suggestion that reflects this suggestion. This system can overcome the "aversion to meetings" culture in Japanese companies and improve meeting productivity. For example, it can extract excellent, previously unpublished opinions and ideas in real time after the meeting, such as "We should have done this" or "I would have done it this way."Furthermore, by automatically summarizing meeting content, generating tasks, and performing follow-up, it's possible to clarify post-meeting action plans. This dramatically improves meeting efficiency and productivity, leading to improved overall business efficiency within the company. In short, Idea Dashboard with AI Agent can dramatically improve the efficiency and productivity of meetings and discussions.

[0029] The Idea Dashboard with AI Agent according to this embodiment comprises a collection unit, an analysis unit, a conversion unit, and a learning unit. The collection unit collects opinions. For example, the collection unit collects opinions spoken by participants during a meeting in real time. The collection unit can also collect opinions posted by participants through an online platform. Furthermore, the collection unit provides a function for posting opinions anonymously, creating an environment where participants can freely express their opinions. For example, the collection unit provides an interface for participants to post opinions anonymously, protecting personal information. The collection unit also has a function to automatically segment the collected opinions. For example, the collection unit creates segments based on the content of the opinions and groups related opinions. The analysis unit performs sentiment analysis on the opinions collected by the collection unit. For example, the analysis unit uses natural language processing technology to analyze the sentiment of the opinions and grasps positive / negative feedback and changes in sentiment in real time. Furthermore, the analysis unit can provide appropriate feedback based on the results of the sentiment analysis. For example, the analysis unit displays encouraging messages for positive opinions and offers solutions for negative opinions. The conversion unit converts the opinions analyzed by the analysis unit into text. The conversion unit, for example, uses speech recognition technology to convert meeting audio into text in real time and automatically records it. The conversion unit also summarizes the converted opinions to make the meeting content easy to understand. For example, the conversion unit extracts the key points of the meeting and displays them as a summary. The learning unit learns from the text converted by the conversion unit. The learning unit, for example, uses machine learning algorithms to learn from meeting data and makes optimal suggestions and improvements for future meetings. The learning unit can also generate post-meeting action plans and perform follow-up. For example, the learning unit generates tasks based on the meeting content and assigns them to responsible persons. As a result, the Idea Dashboard with AI Agent according to this embodiment can efficiently collect opinions, analyze sentiment, convert text, and learn.

[0030] The collection unit collects opinions. For example, it collects opinions spoken by participants during meetings in real time. Specifically, it uses microphones and speech recognition devices installed in the meeting room to capture participants' speech with high accuracy and collects it as audio data. The collection unit can also collect opinions posted by participants through an online platform. The online platform is equipped with chat and comment functions, and participants can post their opinions in text format. Furthermore, the collection unit provides a function to post opinions anonymously, creating an environment where participants can freely express their opinions. For example, the collection unit provides an interface for participants to post opinions anonymously, protecting personal information. The anonymous posting function is an important element for enabling participants to freely express their opinions and is essential for ensuring diversity of opinions. The collection unit also has a function to automatically segment the collected opinions. For example, the collection unit creates segments based on the content of the opinions and groups related opinions. Segmentation is an important process for facilitating the organization and analysis of opinions and helps to efficiently grasp the content of opinions. This allows the collection unit to efficiently collect and organize diverse opinions. Furthermore, the data collection unit can securely store the collected data and, as needed, integrate with other systems and departments. For example, collected opinion data can be stored on a cloud server, making it accessible to the analysis and transformation units. The data collection unit can also adjust the frequency and accuracy of data collection, enabling flexible responses to specific situations and conditions. This allows the data collection unit to efficiently and effectively collect opinions and improve the overall system performance.

[0031] The analysis unit performs sentiment analysis on the opinions collected by the collection unit. For example, the analysis unit uses natural language processing techniques to analyze the sentiment of opinions, enabling it to grasp positive / negative feedback and changes in sentiment in real time. Specifically, it uses sentiment analysis algorithms to analyze the collected text data and classify the sentiment of each opinion. This allows it to identify positive, negative, and neutral opinions. Furthermore, the analysis unit can provide appropriate feedback based on the sentiment analysis results. For example, it can display encouraging messages for positive opinions and offer solutions for negative opinions. In addition, the analysis unit can track changes in the sentiment of opinions, enabling it to grasp the progress of the meeting and participant reactions in real time. This allows it to evaluate the atmosphere of the meeting and participant satisfaction, and adjust the meeting's progress as needed. The analysis unit can also utilize historical data and statistical information to analyze long-term sentiment trends. For example, based on past meeting data, it can predict fluctuations in participants' sentiments regarding specific themes or agenda items and plan countermeasures for the next meeting. Furthermore, the analysis unit can use anomaly detection algorithms to detect unusual patterns and abnormal data, enabling it to issue warnings early. This allows the analysis unit to handle not only real-time sentiment analysis but also long-term sentiment management and anomaly detection, thereby improving the overall reliability and safety of the system.

[0032] The conversion unit converts the opinions analyzed by the analysis unit into text. For example, the conversion unit uses speech recognition technology to convert meeting audio into text in real time and automatically record it. Specifically, it uses a high-precision speech recognition engine to transcribe speech during the meeting in real time and generate organized text data for each speaker. The conversion unit also summarizes the converted opinions, making the meeting content easily understandable. For example, it uses natural language processing technology to extract key points from the meeting and display them as a summary. This allows participants to quickly grasp the main points of the meeting and understand important information without missing anything. Furthermore, the conversion unit saves the text data in a searchable format for easy later reference. For example, it organizes meeting minutes using keyword search and tagging functions, allowing for quick retrieval of necessary information. This enables the conversion unit to efficiently manage meeting records and promote information sharing and utilization. The conversion unit can also support multiple languages, functioning effectively in international meetings and multilingual environments. For example, the speech recognition engine can recognize speech in different languages ​​and convert it into corresponding text. This allows the conversion unit to have high flexibility and adaptability even in a global business environment.

[0033] The learning unit learns from the text converted by the conversion unit. For example, the learning unit uses machine learning algorithms to learn from meeting data and make optimal suggestions and improvements for future meetings. Specifically, it analyzes participant speaking patterns and opinion trends based on past meeting data, providing information useful for meeting progress and agenda setting. The learning unit can also generate post-meeting action plans and conduct follow-up. For example, it can generate tasks based on the meeting content and assign them to responsible parties. This ensures that decisions made in the meeting are implemented and that follow-up is effective. Furthermore, the learning unit collects participant feedback and provides data for continuously improving the quality of meetings. For example, it analyzes feedback provided by participants after meetings to derive areas for improvement and new suggestions for future meetings. The learning unit can also monitor the progress of meetings and participant reactions in real time and adjust the meeting progress as needed. This allows the learning unit to maximize meeting efficiency and effectiveness and improve participant satisfaction. Additionally, the learning unit can conduct long-term data analysis and contribute to improving the meeting culture and communication throughout the organization. For example, by analyzing past meeting data, the learning department can analyze communication patterns and opinion trends across the entire organization, providing information useful for strategic decision-making. This allows the learning department to contribute to improving the overall performance of the organization.

[0034] The collection unit allows participants to post opinions anonymously. For example, the collection unit provides an interface for participants to post opinions anonymously, protecting personal information. Furthermore, to ensure anonymity, the collection unit can automatically remove personally identifiable information from posted opinions. For example, the collection unit analyzes the content of opinions and detects and removes personal information such as names and addresses. The collection unit can also take measures to maintain anonymity when sharing anonymously posted opinions with other participants. For example, when sharing opinions, the collection unit replaces the poster's ID with a randomly generated number. This provides an environment where participants can freely post their opinions.

[0035] The analysis unit can grasp positive / negative feedback and emotional changes in real time. For example, the analysis unit uses natural language processing technology to analyze participants' statements and detect changes in emotion. Furthermore, the analysis unit can provide appropriate feedback based on the results of the emotion analysis. For example, the analysis unit displays encouraging messages for positive opinions and offers solutions for negative opinions. In addition, the analysis unit can analyze nonverbal information such as tone of voice and facial expressions in order to grasp emotional changes in real time. For example, the analysis unit detects changes in emotion by raising or lowering the tone of voice and estimates emotions from the participant's facial expressions using facial recognition technology. This allows for the provision of appropriate feedback by grasping emotional changes in real time.

[0036] The conversion unit can convert meeting audio into text in real time and record it automatically. For example, it uses speech recognition technology to convert meeting speeches into text in real time. The conversion unit also automatically records the converted text for later review. For example, it can extract key points from the meeting and display them as a summary. Furthermore, the conversion unit saves the converted text in a searchable format, allowing for quick retrieval of necessary information. For example, the conversion unit can automatically generate meeting minutes for later review by participants. This allows for review of the meeting content afterward.

[0037] The learning unit can learn from meeting data and make optimal suggestions and improvements for future meetings. For example, the learning unit can use machine learning algorithms to learn from past meeting data and extract suggestions and areas for improvement for the next meeting. The learning unit can also generate post-meeting action plans and follow up. For example, the learning unit can generate tasks based on the meeting content and assign them to responsible parties. Furthermore, the learning unit can monitor the progress of meetings and suggest improvements in real time. For example, the learning unit can analyze the frequency and content of contributions during meetings and make suggestions to balance the discussion. This can improve the productivity of meetings.

[0038] The collection unit can automatically segment the collected opinions. For example, it can create segments based on the content of the opinions and group related opinions together. The collection unit can also visually display the segmented opinions so that participants can grasp the overall picture of the opinions. For example, the collection unit can color-code the opinions by category to make them visually easy to understand. Furthermore, the collection unit can support the progress of the discussion based on the segmented opinions. For example, the collection unit can prioritize opinions related to a specific segment and make suggestions to deepen the discussion. This allows for the efficient organization of opinions.

[0039] The summarization unit can automatically summarize the content of a meeting. For example, it can extract the key points of a meeting and display them as a summary. The summarization unit can also share the summarized content with participants, allowing them to grasp the meeting's content concisely. For example, the summarization unit can automatically generate a summary after the meeting and send it to participants via email. Furthermore, the summarization unit can create an agenda for the next meeting based on the summarized content. For example, it can summarize the important topics discussed in the previous meeting and add them to the agenda as items to be revisited in the next meeting. This allows for a concise understanding of the meeting's content.

[0040] The learning department can generate and follow up on tasks. For example, it can generate tasks based on meeting content and assign them to individuals. It can also monitor task progress and follow up. For instance, it can periodically check task progress and send reminders if delays occur. Furthermore, it can record task completion status and report it at the next meeting. For example, it can automatically generate a list of completed tasks and use it as a report for the next meeting. This clarifies the action plan after the meeting.

[0041] The data collection unit can analyze participants' past statements and select the most suitable collection method. For example, it can prioritize collecting information on topics that participants have frequently discussed in the past. It can also analyze participants' statements and select the most appropriate question format. Furthermore, based on participants' past statements, the data collection unit can suggest relevant topics and collect opinions. For instance, it can automatically suggest relevant topics and collect opinions based on participants' past statements. This allows for efficient opinion collection by selecting the most suitable collection method based on past statements.

[0042] The data collection unit can filter opinions based on participants' current projects and areas of interest. For example, it can prioritize collecting opinions related to projects participants are currently involved in. It can also suggest relevant topics and collect opinions based on participants' areas of interest. Furthermore, it can collect opinions at appropriate times, taking into account the progress of participants' projects. For example, it can monitor participants' project progress in real time and collect opinions at the right time. This allows for the collection of highly relevant opinions based on participants' interests.

[0043] The data collection unit can prioritize collecting highly relevant opinions by considering the geographical location of participants during the opinion gathering process. For example, if participants are in different regions, the data collection unit will prioritize collecting opinions related to those regions. Furthermore, based on the participants' geographical location, the data collection unit can collect opinions on region-specific issues and challenges. In addition, if participants are in a specific region, the data collection unit can prioritize collecting opinions relevant to the situation in that region. For example, the data collection unit can monitor participants' geographical location in real time and collect opinions on region-specific issues and challenges. This allows for the collection of opinions on region-specific issues and challenges by considering geographical location.

[0044] The data collection unit can analyze participants' social media activity and collect relevant opinions when gathering feedback. For example, it can analyze the content of participants' social media posts and collect relevant opinions. Furthermore, based on participants' social media activity history, the data collection unit can suggest topics of high interest and collect opinions. In addition, the data collection unit can gather relevant opinions by referencing the opinions of participants' social media followers and friends. For example, the data collection unit can monitor participants' social media posts in real time and collect relevant opinions. This allows for the collection of opinions based on participants' interests by analyzing their social media activity.

[0045] The analysis unit can adjust the level of detail of the analysis based on the importance of the opinions during the analysis. For example, the analysis unit can perform a detailed analysis and provide specific data for opinions of high importance. Conversely, the analysis unit can perform a simplified analysis and provide only an overview for opinions of low importance. Furthermore, the analysis unit can evaluate the importance of opinions in real time and dynamically adjust the level of detail of the analysis. For example, the analysis unit can monitor the importance of opinions in real time and adjust the level of detail of the analysis according to the importance. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the opinions.

[0046] The analysis unit can apply different analysis algorithms depending on the category of the opinion during analysis. For example, for technical opinions, the analysis unit can apply a technical analysis algorithm to provide detailed technical data. Similarly, for management opinions, the analysis unit can apply a management analysis algorithm to provide management data. Furthermore, the analysis unit can classify opinion categories in real time and dynamically apply the appropriate analysis algorithm. For example, the analysis unit can classify opinion categories in real time, select an appropriate analysis algorithm, and apply it. This allows for the application of highly accurate analysis results by applying the appropriate analysis algorithm according to the opinion category.

[0047] The analysis unit can determine the priority of analysis based on when the opinions were submitted. For example, the analysis unit can prioritize the analysis of the most recent opinions and provide real-time feedback. It can also postpone the analysis of older opinions. Furthermore, the analysis unit can grasp the timing of opinion submissions in real time and dynamically adjust the analysis priority. For example, the analysis unit can monitor the timing of opinion submissions in real time and adjust the analysis priority according to the submission timing. This allows for the rapid analysis of the most recent opinions by determining the analysis priority based on the timing of opinion submission.

[0048] The analysis unit can adjust the order of analysis based on the relevance of the opinions during the analysis process. For example, the analysis unit can prioritize the analysis of highly relevant opinions and provide rapid feedback. Furthermore, the analysis unit can postpone the analysis of less relevant opinions. In addition, the analysis unit can evaluate the relevance of opinions in real time and dynamically adjust the order of analysis. For example, the analysis unit can monitor the relevance of opinions in real time and adjust the order of analysis according to the relevance. This allows for prioritizing the analysis of highly relevant opinions by adjusting the order of analysis based on their relevance.

[0049] The conversion unit can adjust the level of detail in the conversion based on the importance of the audio during the conversion process. For example, for high-importance audio, the conversion unit performs detailed text conversion to provide specific content. Conversely, for low-importance audio, the conversion unit can perform simplified text conversion to provide only an overview. Furthermore, the conversion unit can evaluate the importance of the audio in real time and dynamically adjust the level of detail in the conversion. For example, the conversion unit monitors the importance of the audio in real time and adjusts the level of detail in the conversion according to its importance. This allows for efficient conversion by adjusting the level of detail in the conversion based on the importance of the audio.

[0050] The conversion unit can apply different conversion algorithms depending on the audio category during conversion. For example, for technical audio, the conversion unit can apply a technical conversion algorithm and provide detailed technical data. Similarly, for business-related audio, the conversion unit can apply a business conversion algorithm and provide business data. Furthermore, the conversion unit can classify audio categories in real time and dynamically apply the appropriate conversion algorithm. For example, the conversion unit can classify audio categories in real time, select an appropriate conversion algorithm, and apply it. This allows for highly accurate conversion results by applying the appropriate conversion algorithm according to the audio category.

[0051] The conversion unit can determine conversion priorities based on the submission date of the audio during the conversion process. For example, the conversion unit can prioritize the conversion of the most recent audio and provide real-time feedback. It can also postpone the conversion of older audio. Furthermore, the conversion unit can grasp the submission date of the audio in real time and dynamically adjust the conversion priority. For example, the conversion unit monitors the submission date of the audio in real time and adjusts the conversion priority according to the submission date. This allows for the rapid conversion of the most recent audio by determining the conversion priority based on the submission date of the audio.

[0052] The conversion unit can adjust the order of conversion based on the relevance of the audio during the conversion process. For example, the conversion unit can prioritize the conversion of highly relevant audio and provide rapid feedback. Furthermore, the conversion unit can postpone the conversion of less relevant audio. In addition, the conversion unit can evaluate the relevance of the audio in real time and dynamically adjust the order of conversion. For example, the conversion unit can monitor the relevance of the audio in real time and adjust the order of conversion according to the relevance. This allows for the prioritization of highly relevant audio by adjusting the order of conversion based on the relevance of the audio.

[0053] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data and perform efficient learning. Furthermore, the learning unit can analyze past learning data and adjust the parameters of the learning algorithm. In addition, the learning unit can dynamically optimize the learning algorithm by referring to past learning data in real time. For example, the learning unit can monitor past learning data in real time and adjust the learning algorithm based on optimization criteria. This allows for efficient optimization of the learning algorithm by referring to past learning data.

[0054] The learning unit can apply different learning methods to each meeting category during the learning process. For example, for technical meetings, the learning unit can apply a technical learning method to learn detailed technical data. Similarly, for management meetings, the learning unit can apply a management learning method to learn management data. Furthermore, the learning unit can classify meeting categories in real time and dynamically apply the appropriate learning method. For example, the learning unit can classify meeting categories in real time, select and apply the appropriate learning method. This allows for the application of the appropriate learning method according to the meeting category, thereby providing highly accurate learning results.

[0055] The learning unit can weight the training data based on the submission date of the meeting during training. For example, the learning unit can prioritize learning the most recent meeting data and give it a higher weight. Conversely, it can give older meeting data a lower weight. Furthermore, the learning unit can grasp the meeting submission date in real time and dynamically adjust the weighting of the training data. For example, the learning unit can monitor the meeting submission date in real time and adjust the weighting of the training data according to the submission date. This allows the learning unit to prioritize learning the most recent data by weighting the training data based on the meeting submission date.

[0056] The learning unit can perform learning by referencing relevant market data for meetings during the learning process. For example, the learning unit can refer to market data related to the content of the meeting and perform learning. Furthermore, the learning unit can adjust its learning algorithm based on market data related to the meeting topics. In addition, the learning unit can dynamically perform learning by referencing relevant market data for meetings in real time. For example, the learning unit can monitor relevant market data for meetings in real time and perform learning based on that data. This allows for more appropriate learning by referencing relevant market data for meetings.

[0057] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0058] The data collection unit can analyze participants' past statements and select the most suitable collection method. For example, it can prioritize collecting information on topics that participants have frequently discussed in the past. It can also analyze participants' statements and select the most appropriate question format. Furthermore, based on participants' past statements, the data collection unit can suggest relevant topics and collect opinions. For instance, it can automatically suggest relevant topics and collect opinions based on participants' past statements. This allows for efficient opinion collection by selecting the most suitable collection method based on past statements.

[0059] The data collection unit can filter opinions based on participants' current projects and areas of interest. For example, it can prioritize collecting opinions related to projects participants are currently involved in. It can also suggest relevant topics and collect opinions based on participants' areas of interest. Furthermore, it can collect opinions at appropriate times, taking into account the progress of participants' projects. For example, it can monitor participants' project progress in real time and collect opinions at the right time. This allows for the collection of highly relevant opinions based on participants' interests.

[0060] The data collection unit can prioritize collecting highly relevant opinions by considering the geographical location of participants during the opinion gathering process. For example, if participants are in different regions, the data collection unit will prioritize collecting opinions related to those regions. Furthermore, based on the participants' geographical location, the data collection unit can collect opinions on region-specific issues and challenges. In addition, if participants are in a specific region, the data collection unit can prioritize collecting opinions relevant to the situation in that region. For example, the data collection unit can monitor participants' geographical location in real time and collect opinions on region-specific issues and challenges. This allows for the collection of opinions on region-specific issues and challenges by considering geographical location.

[0061] The data collection unit can analyze participants' social media activity and collect relevant opinions when gathering feedback. For example, it can analyze the content of participants' social media posts and collect relevant opinions. Furthermore, based on participants' social media activity history, the data collection unit can suggest topics of high interest and collect opinions. In addition, the data collection unit can gather relevant opinions by referencing the opinions of participants' social media followers and friends. For example, the data collection unit can monitor participants' social media posts in real time and collect relevant opinions. This allows for the collection of opinions based on participants' interests by analyzing their social media activity.

[0062] The analysis unit can adjust the level of detail of the analysis based on the importance of the opinions during the analysis. For example, the analysis unit can perform a detailed analysis and provide specific data for opinions of high importance. Conversely, the analysis unit can perform a simplified analysis and provide only an overview for opinions of low importance. Furthermore, the analysis unit can evaluate the importance of opinions in real time and dynamically adjust the level of detail of the analysis. For example, the analysis unit can monitor the importance of opinions in real time and adjust the level of detail of the analysis according to the importance. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the opinions.

[0063] The following briefly describes the processing flow for example form 1.

[0064] Step 1: The collection unit collects opinions. For example, the collection unit collects opinions expressed by participants in real time during a meeting. The collection unit can also collect opinions posted by participants through online platforms. Furthermore, the collection unit provides a function for posting opinions anonymously, creating an environment where participants can freely express their opinions. For example, the collection unit provides an interface for participants to post opinions anonymously, protecting personal information. The collection unit also has a function to automatically segment the collected opinions. For example, the collection unit creates segments based on the content of the opinions and groups related opinions together. Step 2: The analysis unit performs sentiment analysis on the opinions collected by the collection unit. The analysis unit analyzes the sentiment of the opinions using, for example, natural language processing technology, and grasps positive / negative feedback and changes in sentiment in real time. The analysis unit can also provide appropriate feedback based on the results of the sentiment analysis. For example, the analysis unit can display encouraging messages for positive opinions and offer solutions to problems for negative opinions. Step 3: The conversion unit converts the opinions analyzed by the analysis unit into text. The conversion unit, for example, uses speech recognition technology to convert the meeting audio into text in real time and automatically records it. The conversion unit also summarizes the opinions converted into text, making it possible to grasp the content of the meeting concisely. For example, the conversion unit extracts the important points of the meeting and displays them as a summary. Step 4: The learning unit learns from the text converted by the conversion unit. For example, the learning unit uses machine learning algorithms to learn from meeting data and make optimal suggestions and improvements for future meetings. The learning unit can also generate post-meeting action plans and follow up. For example, the learning unit can generate tasks based on the meeting content and assign them to responsible persons.

[0065] (Example of form 2) The Idea Dashboard with AI Agent according to an embodiment of the present invention is an innovative AI agent solution for dramatically improving the efficiency and productivity of meetings and discussions. This AI agent solution collects opinions in real time and automatically segments them. Next, it performs sentiment analysis on the collected opinions to grasp positive / negative feedback and changes in emotion in real time. Furthermore, it converts meeting audio into text in real time and records it automatically. This allows for later review of the meeting content. The AI ​​agent also learns from the meeting data and makes optimal suggestions and improvements for future meetings. This can overcome the "dislike of meetings" culture in Japanese companies and improve meeting productivity. For example, the AI ​​agent collects opinions in real time during a meeting. Participants can post their opinions anonymously, providing an environment where they can speak freely. For example, if a participant posts, "I have an opinion on the progress of this project," the AI ​​agent collects that opinion and automatically segments it. Next, it performs sentiment analysis on the collected opinions. The AI ​​agent analyzes the participants' statements and grasps positive / negative feedback and changes in emotion in real time. For example, if a participant says, "This project is progressing smoothly," the AI ​​agent will analyze this as positive feedback. Furthermore, it will convert the meeting audio into text in real time and record it automatically. This allows for later review of the meeting content. For example, if a question is asked during the meeting, "What is the next step?", the question and answer will be recorded as text. The AI ​​agent also learns from the meeting data and makes optimal suggestions and improvements for future meetings. For example, if there was a suggestion in the previous meeting that "we would like a more detailed report on the project's progress," the next meeting will include a suggestion that reflects this suggestion. This system can overcome the "aversion to meetings" culture in Japanese companies and improve meeting productivity. For example, it can extract excellent, previously unpublished opinions and ideas in real time after the meeting, such as "We should have done this" or "I would have done it this way."Furthermore, by automatically summarizing meeting content, generating tasks, and performing follow-up, it's possible to clarify post-meeting action plans. This dramatically improves meeting efficiency and productivity, leading to improved overall business efficiency within the company. In short, Idea Dashboard with AI Agent can dramatically improve the efficiency and productivity of meetings and discussions.

[0066] The Idea Dashboard with AI Agent according to this embodiment comprises a collection unit, an analysis unit, a conversion unit, and a learning unit. The collection unit collects opinions. For example, the collection unit collects opinions spoken by participants during a meeting in real time. The collection unit can also collect opinions posted by participants through an online platform. Furthermore, the collection unit provides a function for posting opinions anonymously, creating an environment where participants can freely express their opinions. For example, the collection unit provides an interface for participants to post opinions anonymously, protecting personal information. The collection unit also has a function to automatically segment the collected opinions. For example, the collection unit creates segments based on the content of the opinions and groups related opinions. The analysis unit performs sentiment analysis on the opinions collected by the collection unit. For example, the analysis unit uses natural language processing technology to analyze the sentiment of the opinions and grasps positive / negative feedback and changes in sentiment in real time. Furthermore, the analysis unit can provide appropriate feedback based on the results of the sentiment analysis. For example, the analysis unit displays encouraging messages for positive opinions and offers solutions for negative opinions. The conversion unit converts the opinions analyzed by the analysis unit into text. The conversion unit, for example, uses speech recognition technology to convert meeting audio into text in real time and automatically records it. The conversion unit also summarizes the converted opinions to make the meeting content easy to understand. For example, the conversion unit extracts the key points of the meeting and displays them as a summary. The learning unit learns from the text converted by the conversion unit. The learning unit, for example, uses machine learning algorithms to learn from meeting data and makes optimal suggestions and improvements for future meetings. The learning unit can also generate post-meeting action plans and perform follow-up. For example, the learning unit generates tasks based on the meeting content and assigns them to responsible persons. As a result, the Idea Dashboard with AI Agent according to this embodiment can efficiently collect opinions, analyze sentiment, convert text, and learn.

[0067] The collection unit collects opinions. For example, it collects opinions spoken by participants during meetings in real time. Specifically, it uses microphones and speech recognition devices installed in the meeting room to capture participants' speech with high accuracy and collects it as audio data. The collection unit can also collect opinions posted by participants through an online platform. The online platform is equipped with chat and comment functions, and participants can post their opinions in text format. Furthermore, the collection unit provides a function to post opinions anonymously, creating an environment where participants can freely express their opinions. For example, the collection unit provides an interface for participants to post opinions anonymously, protecting personal information. The anonymous posting function is an important element for enabling participants to freely express their opinions and is essential for ensuring diversity of opinions. The collection unit also has a function to automatically segment the collected opinions. For example, the collection unit creates segments based on the content of the opinions and groups related opinions. Segmentation is an important process for facilitating the organization and analysis of opinions and helps to efficiently grasp the content of opinions. This allows the collection unit to efficiently collect and organize diverse opinions. Furthermore, the data collection unit can securely store the collected data and, as needed, integrate with other systems and departments. For example, collected opinion data can be stored on a cloud server, making it accessible to the analysis and transformation units. The data collection unit can also adjust the frequency and accuracy of data collection, enabling flexible responses to specific situations and conditions. This allows the data collection unit to efficiently and effectively collect opinions and improve the overall system performance.

[0068] The analysis unit performs sentiment analysis on the opinions collected by the collection unit. For example, the analysis unit uses natural language processing techniques to analyze the sentiment of opinions, enabling it to grasp positive / negative feedback and changes in sentiment in real time. Specifically, it uses sentiment analysis algorithms to analyze the collected text data and classify the sentiment of each opinion. This allows it to identify positive, negative, and neutral opinions. Furthermore, the analysis unit can provide appropriate feedback based on the sentiment analysis results. For example, it can display encouraging messages for positive opinions and offer solutions for negative opinions. In addition, the analysis unit can track changes in the sentiment of opinions, enabling it to grasp the progress of the meeting and participant reactions in real time. This allows it to evaluate the atmosphere of the meeting and participant satisfaction, and adjust the meeting's progress as needed. The analysis unit can also utilize historical data and statistical information to analyze long-term sentiment trends. For example, based on past meeting data, it can predict fluctuations in participants' sentiments regarding specific themes or agenda items and plan countermeasures for the next meeting. Furthermore, the analysis unit can use anomaly detection algorithms to detect unusual patterns and abnormal data, enabling it to issue warnings early. This allows the analysis unit to handle not only real-time sentiment analysis but also long-term sentiment management and anomaly detection, thereby improving the overall reliability and safety of the system.

[0069] The conversion unit converts the opinions analyzed by the analysis unit into text. For example, the conversion unit uses speech recognition technology to convert meeting audio into text in real time and automatically record it. Specifically, it uses a high-precision speech recognition engine to transcribe speech during the meeting in real time and generate organized text data for each speaker. The conversion unit also summarizes the converted opinions, making the meeting content easily understandable. For example, it uses natural language processing technology to extract key points from the meeting and display them as a summary. This allows participants to quickly grasp the main points of the meeting and understand important information without missing anything. Furthermore, the conversion unit saves the text data in a searchable format for easy later reference. For example, it organizes meeting minutes using keyword search and tagging functions, allowing for quick retrieval of necessary information. This enables the conversion unit to efficiently manage meeting records and promote information sharing and utilization. The conversion unit can also support multiple languages, functioning effectively in international meetings and multilingual environments. For example, the speech recognition engine can recognize speech in different languages ​​and convert it into corresponding text. This allows the conversion unit to have high flexibility and adaptability even in a global business environment.

[0070] The learning unit learns from the text converted by the conversion unit. For example, the learning unit uses machine learning algorithms to learn from meeting data and make optimal suggestions and improvements for future meetings. Specifically, it analyzes participant speaking patterns and opinion trends based on past meeting data, providing information useful for meeting progress and agenda setting. The learning unit can also generate post-meeting action plans and conduct follow-up. For example, it can generate tasks based on the meeting content and assign them to responsible parties. This ensures that decisions made in the meeting are implemented and that follow-up is effective. Furthermore, the learning unit collects participant feedback and provides data for continuously improving the quality of meetings. For example, it analyzes feedback provided by participants after meetings to derive areas for improvement and new suggestions for future meetings. The learning unit can also monitor the progress of meetings and participant reactions in real time and adjust the meeting progress as needed. This allows the learning unit to maximize meeting efficiency and effectiveness and improve participant satisfaction. Additionally, the learning unit can conduct long-term data analysis and contribute to improving the meeting culture and communication throughout the organization. For example, by analyzing past meeting data, the learning department can analyze communication patterns and opinion trends across the entire organization, providing information useful for strategic decision-making. This allows the learning department to contribute to improving the overall performance of the organization.

[0071] The collection unit allows participants to post opinions anonymously. For example, the collection unit provides an interface for participants to post opinions anonymously, protecting personal information. Furthermore, to ensure anonymity, the collection unit can automatically remove personally identifiable information from posted opinions. For example, the collection unit analyzes the content of opinions and detects and removes personal information such as names and addresses. The collection unit can also take measures to maintain anonymity when sharing anonymously posted opinions with other participants. For example, when sharing opinions, the collection unit replaces the poster's ID with a randomly generated number. This provides an environment where participants can freely post their opinions.

[0072] The analysis unit can grasp positive / negative feedback and emotional changes in real time. For example, the analysis unit uses natural language processing technology to analyze participants' statements and detect changes in emotion. Furthermore, the analysis unit can provide appropriate feedback based on the results of the emotion analysis. For example, the analysis unit displays encouraging messages for positive opinions and offers solutions for negative opinions. In addition, the analysis unit can analyze nonverbal information such as tone of voice and facial expressions in order to grasp emotional changes in real time. For example, the analysis unit detects changes in emotion by raising or lowering the tone of voice and estimates emotions from the participant's facial expressions using facial recognition technology. This allows for the provision of appropriate feedback by grasping emotional changes in real time.

[0073] The conversion unit can convert meeting audio into text in real time and record it automatically. For example, it uses speech recognition technology to convert meeting speeches into text in real time. The conversion unit also automatically records the converted text for later review. For example, it can extract key points from the meeting and display them as a summary. Furthermore, the conversion unit saves the converted text in a searchable format, allowing for quick retrieval of necessary information. For example, the conversion unit can automatically generate meeting minutes for later review by participants. This allows for review of the meeting content afterward.

[0074] The learning unit can learn from meeting data and make optimal suggestions and improvements for future meetings. For example, the learning unit can use machine learning algorithms to learn from past meeting data and extract suggestions and areas for improvement for the next meeting. The learning unit can also generate post-meeting action plans and follow up. For example, the learning unit can generate tasks based on the meeting content and assign them to responsible parties. Furthermore, the learning unit can monitor the progress of meetings and suggest improvements in real time. For example, the learning unit can analyze the frequency and content of contributions during meetings and make suggestions to balance the discussion. This can improve the productivity of meetings.

[0075] The collection unit can automatically segment the collected opinions. For example, it can create segments based on the content of the opinions and group related opinions together. The collection unit can also visually display the segmented opinions so that participants can grasp the overall picture of the opinions. For example, the collection unit can color-code the opinions by category to make them visually easy to understand. Furthermore, the collection unit can support the progress of the discussion based on the segmented opinions. For example, the collection unit can prioritize opinions related to a specific segment and make suggestions to deepen the discussion. This allows for the efficient organization of opinions.

[0076] The summarization unit can automatically summarize the content of a meeting. For example, it can extract the key points of a meeting and display them as a summary. The summarization unit can also share the summarized content with participants, allowing them to grasp the meeting's content concisely. For example, the summarization unit can automatically generate a summary after the meeting and send it to participants via email. Furthermore, the summarization unit can create an agenda for the next meeting based on the summarized content. For example, it can summarize the important topics discussed in the previous meeting and add them to the agenda as items to be revisited in the next meeting. This allows for a concise understanding of the meeting's content.

[0077] The learning department can generate and follow up on tasks. For example, it can generate tasks based on meeting content and assign them to individuals. It can also monitor task progress and follow up. For instance, it can periodically check task progress and send reminders if delays occur. Furthermore, it can record task completion status and report it at the next meeting. For example, it can automatically generate a list of completed tasks and use it as a report for the next meeting. This clarifies the action plan after the meeting.

[0078] The data collection unit can estimate the user's emotions and adjust the timing of opinion collection based on the estimated emotions. For example, if the user is feeling stressed, the data collection unit can temporarily suspend opinion collection and resume it when the user is relaxed. Furthermore, if the user is showing positive emotions, the data collection unit can facilitate opinion collection and encourage active discussion. Additionally, if the user is tired, the data collection unit can shorten the time spent collecting opinions to reduce the burden. For example, the data collection unit can monitor the user's emotions in real time and adjust the timing of opinion collection according to changes in emotions. This allows for the collection of more appropriate opinions by adjusting the timing of opinion collection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0079] The data collection unit can analyze participants' past statements and select the most suitable collection method. For example, it can prioritize collecting information on topics that participants have frequently discussed in the past. It can also analyze participants' statements and select the most appropriate question format. Furthermore, based on participants' past statements, the data collection unit can suggest relevant topics and collect opinions. For instance, it can automatically suggest relevant topics and collect opinions based on participants' past statements. This allows for efficient opinion collection by selecting the most suitable collection method based on past statements.

[0080] The data collection unit can filter opinions based on participants' current projects and areas of interest. For example, it can prioritize collecting opinions related to projects participants are currently involved in. It can also suggest relevant topics and collect opinions based on participants' areas of interest. Furthermore, it can collect opinions at appropriate times, taking into account the progress of participants' projects. For example, it can monitor participants' project progress in real time and collect opinions at the right time. This allows for the collection of highly relevant opinions based on participants' interests.

[0081] The data collection unit can estimate the user's emotions and determine the priority of opinions to collect based on the estimated emotions. For example, if the user is expressing positive emotions, the data collection unit will prioritize collecting those opinions. Conversely, if the user is expressing negative emotions, the data collection unit can quickly collect those opinions and use them to help solve problems. Furthermore, the data collection unit can grasp changes in the user's emotions in real time and dynamically adjust the priority of opinions. For example, the data collection unit monitors the user's emotions in real time and adjusts the priority of opinions according to changes in emotions. This allows for the priority collection of important opinions by determining the priority of opinions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0082] The data collection unit can prioritize collecting highly relevant opinions by considering the geographical location of participants during the opinion gathering process. For example, if participants are in different regions, the data collection unit will prioritize collecting opinions related to those regions. Furthermore, based on the participants' geographical location, the data collection unit can collect opinions on region-specific issues and challenges. In addition, if participants are in a specific region, the data collection unit can prioritize collecting opinions relevant to the situation in that region. For example, the data collection unit can monitor participants' geographical location in real time and collect opinions on region-specific issues and challenges. This allows for the collection of opinions on region-specific issues and challenges by considering geographical location.

[0083] The data collection unit can analyze participants' social media activity and collect relevant opinions when gathering feedback. For example, it can analyze the content of participants' social media posts and collect relevant opinions. Furthermore, based on participants' social media activity history, the data collection unit can suggest topics of high interest and collect opinions. In addition, the data collection unit can gather relevant opinions by referencing the opinions of participants' social media followers and friends. For example, the data collection unit can monitor participants' social media posts in real time and collect relevant opinions. This allows for the collection of opinions based on participants' interests by analyzing their social media activity.

[0084] The analysis unit can estimate the user's emotions and adjust the presentation of the analysis based on the estimated emotions. For example, if the user is showing positive emotions, the analysis unit can display the analysis results using graphs or charts with bright colors. Conversely, if the user is showing negative emotions, the analysis unit can display the analysis results using graphs or charts with calm colors. Furthermore, the analysis unit can grasp changes in the user's emotions in real time and dynamically adjust the presentation of the analysis results. For example, the analysis unit can monitor the user's emotions in real time and adjust the presentation of the analysis results according to changes in emotions. This allows for the provision of more appropriate analysis results by adjusting the presentation of the analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0085] The analysis unit can adjust the level of detail of the analysis based on the importance of the opinions during the analysis. For example, the analysis unit can perform a detailed analysis and provide specific data for opinions of high importance. Conversely, the analysis unit can perform a simplified analysis and provide only an overview for opinions of low importance. Furthermore, the analysis unit can evaluate the importance of opinions in real time and dynamically adjust the level of detail of the analysis. For example, the analysis unit can monitor the importance of opinions in real time and adjust the level of detail of the analysis according to the importance. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the opinions.

[0086] The analysis unit can apply different analysis algorithms depending on the category of the opinion during analysis. For example, for technical opinions, the analysis unit can apply a technical analysis algorithm to provide detailed technical data. Similarly, for management opinions, the analysis unit can apply a management analysis algorithm to provide management data. Furthermore, the analysis unit can classify opinion categories in real time and dynamically apply the appropriate analysis algorithm. For example, the analysis unit can classify opinion categories in real time, select an appropriate analysis algorithm, and apply it. This allows for the application of highly accurate analysis results by applying the appropriate analysis algorithm according to the opinion category.

[0087] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated emotions. For example, if the user is in a hurry, the analysis unit can provide a short, concise analysis. Conversely, if the user is relaxed, the analysis unit can provide a detailed analysis. Furthermore, the analysis unit can grasp changes in the user's emotions in real time and dynamically adjust the length of the analysis. For example, the analysis unit monitors the user's emotions in real time and adjusts the length of the analysis according to the changes in emotions. This allows for the provision of analysis results of appropriate length by adjusting the length of the analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0088] The analysis unit can determine the priority of analysis based on when the opinions were submitted. For example, the analysis unit can prioritize the analysis of the most recent opinions and provide real-time feedback. It can also postpone the analysis of older opinions. Furthermore, the analysis unit can grasp the timing of opinion submissions in real time and dynamically adjust the analysis priority. For example, the analysis unit can monitor the timing of opinion submissions in real time and adjust the analysis priority according to the submission timing. This allows for the rapid analysis of the most recent opinions by determining the analysis priority based on the timing of opinion submission.

[0089] The analysis unit can adjust the order of analysis based on the relevance of the opinions during the analysis process. For example, the analysis unit can prioritize the analysis of highly relevant opinions and provide rapid feedback. Furthermore, the analysis unit can postpone the analysis of less relevant opinions. In addition, the analysis unit can evaluate the relevance of opinions in real time and dynamically adjust the order of analysis. For example, the analysis unit can monitor the relevance of opinions in real time and adjust the order of analysis according to the relevance. This allows for prioritizing the analysis of highly relevant opinions by adjusting the order of analysis based on their relevance.

[0090] The conversion unit can estimate the user's emotions and adjust the representation of the conversion based on the estimated emotions. For example, if the user is showing positive emotions, the conversion unit can display the conversion result using text in bright colors. Conversely, if the user is showing negative emotions, the conversion unit can display the conversion result using text in calm colors. Furthermore, the conversion unit can grasp changes in the user's emotions in real time and dynamically adjust the representation of the conversion result. For example, the conversion unit monitors the user's emotions in real time and adjusts the representation of the conversion result according to the changes in emotions. This allows for the provision of more appropriate conversion results by adjusting the representation of the conversion according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0091] The conversion unit can adjust the level of detail in the conversion based on the importance of the audio during the conversion process. For example, for high-importance audio, the conversion unit performs detailed text conversion to provide specific content. Conversely, for low-importance audio, the conversion unit can perform simplified text conversion to provide only an overview. Furthermore, the conversion unit can evaluate the importance of the audio in real time and dynamically adjust the level of detail in the conversion. For example, the conversion unit monitors the importance of the audio in real time and adjusts the level of detail in the conversion according to its importance. This allows for efficient conversion by adjusting the level of detail in the conversion based on the importance of the audio.

[0092] The conversion unit can apply different conversion algorithms depending on the audio category during conversion. For example, for technical audio, the conversion unit can apply a technical conversion algorithm and provide detailed technical data. Similarly, for business-related audio, the conversion unit can apply a business conversion algorithm and provide business data. Furthermore, the conversion unit can classify audio categories in real time and dynamically apply the appropriate conversion algorithm. For example, the conversion unit can classify audio categories in real time, select an appropriate conversion algorithm, and apply it. This allows for highly accurate conversion results by applying the appropriate conversion algorithm according to the audio category.

[0093] The translation unit can estimate the user's emotions and adjust the length of the translation based on the estimated emotions. For example, if the user is in a hurry, the translation unit can provide a short, concise translation. Conversely, if the user is relaxed, the translation unit can provide a detailed translation. Furthermore, the translation unit can grasp changes in the user's emotions in real time and dynamically adjust the length of the translation. For example, the translation unit monitors the user's emotions in real time and adjusts the length of the translation according to the changes in emotions. This allows for the provision of a translation of appropriate length by adjusting the length according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0094] The conversion unit can determine conversion priorities based on the submission date of the audio during the conversion process. For example, the conversion unit can prioritize the conversion of the most recent audio and provide real-time feedback. It can also postpone the conversion of older audio. Furthermore, the conversion unit can grasp the submission date of the audio in real time and dynamically adjust the conversion priority. For example, the conversion unit monitors the submission date of the audio in real time and adjusts the conversion priority according to the submission date. This allows for the rapid conversion of the most recent audio by determining the conversion priority based on the submission date of the audio.

[0095] The conversion unit can adjust the order of conversion based on the relevance of the audio during the conversion process. For example, the conversion unit can prioritize the conversion of highly relevant audio and provide rapid feedback. Furthermore, the conversion unit can postpone the conversion of less relevant audio. In addition, the conversion unit can evaluate the relevance of the audio in real time and dynamically adjust the order of conversion. For example, the conversion unit can monitor the relevance of the audio in real time and adjust the order of conversion according to the relevance. This allows for the prioritization of highly relevant audio by adjusting the order of conversion based on the relevance of the audio.

[0096] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is showing positive emotions, the learning unit will prioritize learning data related to those emotions. Conversely, if the user is showing negative emotions, the learning unit will quickly learn data related to those emotions and use it to solve problems. Furthermore, the learning unit can grasp changes in the user's emotions in real time and dynamically adjust the selection of training data. For example, the learning unit can monitor the user's emotions in real time and adjust the selection of training data according to changes in emotions. This allows for the learning of more appropriate data by selecting training data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0097] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data and perform efficient learning. Furthermore, the learning unit can analyze past learning data and adjust the parameters of the learning algorithm. In addition, the learning unit can dynamically optimize the learning algorithm by referring to past learning data in real time. For example, the learning unit can monitor past learning data in real time and adjust the learning algorithm based on optimization criteria. This allows for efficient optimization of the learning algorithm by referring to past learning data.

[0098] The learning unit can apply different learning methods to each meeting category during the learning process. For example, for technical meetings, the learning unit can apply a technical learning method to learn detailed technical data. Similarly, for management meetings, the learning unit can apply a management learning method to learn management data. Furthermore, the learning unit can classify meeting categories in real time and dynamically apply the appropriate learning method. For example, the learning unit can classify meeting categories in real time, select and apply the appropriate learning method. This allows for the application of the appropriate learning method according to the meeting category, thereby providing highly accurate learning results.

[0099] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is showing positive emotions, the learning unit will increase the learning frequency. Conversely, if the user is showing negative emotions, the learning unit can decrease the learning frequency to reduce the burden. Furthermore, the learning unit can grasp changes in the user's emotions in real time and dynamically adjust the learning frequency. For example, the learning unit can monitor the user's emotions in real time and adjust the learning frequency in response to changes in emotions. This allows learning to be performed at an appropriate frequency by adjusting the learning frequency according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0100] The learning unit can weight the training data based on the submission date of the meeting during training. For example, the learning unit can prioritize learning the most recent meeting data and give it a higher weight. Conversely, it can give older meeting data a lower weight. Furthermore, the learning unit can grasp the meeting submission date in real time and dynamically adjust the weighting of the training data. For example, the learning unit can monitor the meeting submission date in real time and adjust the weighting of the training data according to the submission date. This allows the learning unit to prioritize learning the most recent data by weighting the training data based on the meeting submission date.

[0101] The learning unit can perform learning by referencing relevant market data for meetings during the learning process. For example, the learning unit can refer to market data related to the content of the meeting and perform learning. Furthermore, the learning unit can adjust its learning algorithm based on market data related to the meeting topics. In addition, the learning unit can dynamically perform learning by referencing relevant market data for meetings in real time. For example, the learning unit can monitor relevant market data for meetings in real time and perform learning based on that data. This allows for more appropriate learning by referencing relevant market data for meetings.

[0102] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0103] The data collection unit can estimate the user's emotions and adjust the timing of opinion collection based on those emotions. For example, if the user is feeling stressed, the data collection unit can temporarily suspend opinion collection and resume it when the user is relaxed. Furthermore, if the user is showing positive emotions, the data collection unit can facilitate opinion collection and encourage active discussion. Additionally, if the user is tired, the data collection unit can shorten the time spent collecting opinions to reduce their burden. For instance, the data collection unit can monitor the user's emotions in real time and adjust the timing of opinion collection according to changes in those emotions. This allows for the collection of more appropriate opinions by adjusting the timing of opinion collection according to the user's emotions.

[0104] The analysis unit can estimate the user's emotions and adjust the presentation of the analysis based on the estimated emotions. For example, if the user is showing positive emotions, the analysis unit can display the analysis results using graphs and charts with bright colors. Conversely, if the user is showing negative emotions, the analysis unit can display the analysis results using graphs and charts with calm colors. Furthermore, the analysis unit can grasp changes in the user's emotions in real time and dynamically adjust the presentation of the analysis results. For example, the analysis unit monitors the user's emotions in real time and adjusts the presentation of the analysis results according to changes in emotions. This allows for the provision of more appropriate analysis results by adjusting the presentation of the analysis according to the user's emotions.

[0105] The conversion unit can estimate the user's emotions and adjust the way the conversion is presented based on those emotions. For example, if the user is expressing positive emotions, the conversion unit can display the conversion result using text in bright colors. Conversely, if the user is expressing negative emotions, the conversion unit can display the conversion result using text in calm colors. Furthermore, the conversion unit can grasp changes in the user's emotions in real time and dynamically adjust the way the conversion result is presented. For example, the conversion unit can monitor the user's emotions in real time and adjust the way the conversion result is presented in response to changes in emotions. This allows for the provision of more appropriate conversion results by adjusting the way the conversion is presented according to the user's emotions.

[0106] The learning unit can estimate the user's emotions and select training data based on those estimated emotions. For example, if the user is showing positive emotions, the learning unit will prioritize learning data related to those emotions. Conversely, if the user is showing negative emotions, the learning unit will quickly learn data related to those emotions and use that information to help solve problems. Furthermore, the learning unit can grasp changes in the user's emotions in real time and dynamically adjust the selection of training data. For example, the learning unit can monitor the user's emotions in real time and adjust the selection of training data according to those changes. This allows the learning unit to learn more appropriate data by selecting training data according to the user's emotions.

[0107] The learning unit can estimate the user's emotions and adjust the learning frequency based on those emotions. For example, if the user is showing positive emotions, the learning unit will increase the learning frequency. Conversely, if the user is showing negative emotions, the learning unit can decrease the learning frequency to reduce the burden. Furthermore, the learning unit can grasp changes in the user's emotions in real time and dynamically adjust the learning frequency. For example, the learning unit can monitor the user's emotions in real time and adjust the learning frequency in response to changes in those emotions. This allows for learning at an appropriate frequency by adjusting the learning frequency according to the user's emotions.

[0108] The data collection unit can analyze participants' past statements and select the most suitable collection method. For example, it can prioritize collecting information on topics that participants have frequently discussed in the past. It can also analyze participants' statements and select the most appropriate question format. Furthermore, based on participants' past statements, the data collection unit can suggest relevant topics and collect opinions. For instance, it can automatically suggest relevant topics and collect opinions based on participants' past statements. This allows for efficient opinion collection by selecting the most suitable collection method based on past statements.

[0109] The data collection unit can filter opinions based on participants' current projects and areas of interest. For example, it can prioritize collecting opinions related to projects participants are currently involved in. It can also suggest relevant topics and collect opinions based on participants' areas of interest. Furthermore, it can collect opinions at appropriate times, taking into account the progress of participants' projects. For example, it can monitor participants' project progress in real time and collect opinions at the right time. This allows for the collection of highly relevant opinions based on participants' interests.

[0110] The data collection unit can prioritize collecting highly relevant opinions by considering the geographical location of participants during the opinion gathering process. For example, if participants are in different regions, the data collection unit will prioritize collecting opinions related to those regions. Furthermore, based on the participants' geographical location, the data collection unit can collect opinions on region-specific issues and challenges. In addition, if participants are in a specific region, the data collection unit can prioritize collecting opinions relevant to the situation in that region. For example, the data collection unit can monitor participants' geographical location in real time and collect opinions on region-specific issues and challenges. This allows for the collection of opinions on region-specific issues and challenges by considering geographical location.

[0111] The data collection unit can analyze participants' social media activity and collect relevant opinions when gathering feedback. For example, it can analyze the content of participants' social media posts and collect relevant opinions. Furthermore, based on participants' social media activity history, the data collection unit can suggest topics of high interest and collect opinions. In addition, the data collection unit can gather relevant opinions by referencing the opinions of participants' social media followers and friends. For example, the data collection unit can monitor participants' social media posts in real time and collect relevant opinions. This allows for the collection of opinions based on participants' interests by analyzing their social media activity.

[0112] The analysis unit can adjust the level of detail of the analysis based on the importance of the opinions during the analysis. For example, the analysis unit can perform a detailed analysis and provide specific data for opinions of high importance. Conversely, the analysis unit can perform a simplified analysis and provide only an overview for opinions of low importance. Furthermore, the analysis unit can evaluate the importance of opinions in real time and dynamically adjust the level of detail of the analysis. For example, the analysis unit can monitor the importance of opinions in real time and adjust the level of detail of the analysis according to the importance. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the opinions.

[0113] The following briefly describes the processing flow for example form 2.

[0114] Step 1: The collection unit collects opinions. For example, the collection unit collects opinions expressed by participants in real time during a meeting. The collection unit can also collect opinions posted by participants through online platforms. Furthermore, the collection unit provides a function for posting opinions anonymously, creating an environment where participants can freely express their opinions. For example, the collection unit provides an interface for participants to post opinions anonymously, protecting personal information. The collection unit also has a function to automatically segment the collected opinions. For example, the collection unit creates segments based on the content of the opinions and groups related opinions together. Step 2: The analysis unit performs sentiment analysis on the opinions collected by the collection unit. The analysis unit analyzes the sentiment of the opinions using, for example, natural language processing technology, and grasps positive / negative feedback and changes in sentiment in real time. The analysis unit can also provide appropriate feedback based on the results of the sentiment analysis. For example, the analysis unit can display encouraging messages for positive opinions and offer solutions to problems for negative opinions. Step 3: The conversion unit converts the opinions analyzed by the analysis unit into text. The conversion unit, for example, uses speech recognition technology to convert the meeting audio into text in real time and automatically records it. The conversion unit also summarizes the opinions converted into text, making it possible to grasp the content of the meeting concisely. For example, the conversion unit extracts the important points of the meeting and displays them as a summary. Step 4: The learning unit learns from the text converted by the conversion unit. For example, the learning unit uses machine learning algorithms to learn from meeting data and make optimal suggestions and improvements for future meetings. The learning unit can also generate post-meeting action plans and follow up. For example, the learning unit can generate tasks based on the meeting content and assign them to responsible persons.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] Each of the multiple elements described above, including the collection unit, analysis unit, conversion unit, and learning unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit is implemented by the computer 36 of the smart device 14 and collects opinions spoken by participants during a meeting in real time. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs sentiment analysis on the collected opinions. The conversion unit is implemented by the processor 46 of the smart device 14 and converts the meeting audio into text in real time. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns from the meeting data to make optimal suggestions and improvements for future meetings. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0119] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0124] 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).

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.).

[0131] 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.

[0132] 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.

[0133] 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.

[0134] Each of the multiple elements described above, including the collection unit, analysis unit, conversion unit, and learning unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit is implemented by the computer 36 of the smart glasses 214 and collects opinions spoken by participants during a meeting in real time. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs sentiment analysis on the collected opinions. The conversion unit is implemented by the processor 46 of the smart glasses 214 and converts the meeting audio into text in real time. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns from the meeting data to make optimal suggestions and improvements for future meetings. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0135] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0140] 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).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] Each of the multiple elements described above, including the collection unit, analysis unit, conversion unit, and learning unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit is implemented by the computer 36 of the headset terminal 314 and collects opinions spoken by participants during a meeting in real time. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs sentiment analysis on the collected opinions. The conversion unit is implemented by the processor 46 of the headset terminal 314 and converts the meeting audio into text in real time. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns from the meeting data to make optimal suggestions and improvements for future meetings. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0151] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0156] 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).

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.).

[0164] 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.

[0165] 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.

[0166] 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.

[0167] Each of the multiple elements described above, including the collection unit, analysis unit, conversion unit, and learning unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the collection unit is implemented by the computer 36 of the robot 414 and collects opinions spoken by participants during a meeting in real time. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs sentiment analysis on the collected opinions. The conversion unit is implemented by the processor 46 of the robot 414 and converts the meeting audio into text in real time. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns from the meeting data to make optimal suggestions and improvements for future meetings. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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."

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] (Note 1) The opinion collection department, An analysis unit that performs sentiment analysis on the opinions collected by the collection unit, A conversion unit that converts the opinions analyzed by the analysis unit into text, A learning unit that learns the text converted by the conversion unit, Equipped with A system characterized by the following features. (Note 2) The aforementioned collection unit is Participants can post their opinions anonymously. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, Track positive / negative feedback and emotional changes in real time. The system described in Appendix 1, characterized by the features described herein. (Note 4) The conversion unit is Convert meeting audio to text in real time and record it automatically. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned learning unit, Learn from meeting data to make optimal suggestions and improvements for future meetings. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned collection unit is The collected opinions are automatically segmented. The system described in Appendix 1, characterized by the features described herein. (Note 7) The conversion unit is Automatically summarize the meeting content. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned learning unit, Task generation and follow-up The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is We estimate the user's emotions and adjust the timing of opinion collection based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is We will analyze the participants' past statements and select the most suitable data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When collecting opinions, filter them based on the participants' current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is It estimates user sentiment and determines the priority of opinions to collect based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned collection unit is When collecting opinions, the geographical location of participants will be taken into consideration to prioritize the collection of most relevant opinions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned collection unit is When collecting opinions, we analyze participants' social media activity and gather relevant opinions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, The system estimates the user's emotions and adjusts the representation of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, During the analysis, adjust the level of detail based on the importance of each opinion. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of the opinion. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, It estimates the user's emotions and adjusts the length of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, During the analysis, the priority of the analysis will be determined based on when the opinions were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned analysis unit, During the analysis, the order of analysis will be adjusted based on the relevance of the opinions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The conversion unit is It estimates the user's emotions and adjusts the way the transformation is expressed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The conversion unit is During conversion, adjust the level of detail based on the importance of the audio. The system described in Appendix 1, characterized by the features described herein. (Note 23) The conversion unit is During conversion, different conversion algorithms are applied depending on the audio category. The system described in Appendix 1, characterized by the features described herein. (Note 24) The conversion unit is It estimates the user's emotions and adjusts the length of the conversion based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The conversion unit is During conversion, the conversion priority is determined based on when the audio was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 26) The conversion unit is During conversion, the order of conversion is adjusted based on the relevance of the audio. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned learning unit, During the learning process, different learning methods are applied to each category of meeting. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned learning unit, During training, the training data is weighted based on the submission timing of the conference. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned learning unit, During the learning process, the system will refer to relevant market data related to the conference. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0187] 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. The opinion collection department, An analysis unit that performs sentiment analysis on the opinions collected by the collection unit, A conversion unit that converts the opinions analyzed by the analysis unit into text, A learning unit that learns the text converted by the conversion unit, Equipped with A system characterized by the following features.

2. The aforementioned collection unit is Participants can post their opinions anonymously. The system according to feature 1.

3. The aforementioned analysis unit, Track positive / negative feedback and emotional changes in real time. The system according to feature 1.

4. The conversion unit is Convert meeting audio to text in real time and record it automatically. The system according to feature 1.

5. The aforementioned learning unit, Learn from meeting data to make optimal suggestions and improvements for future meetings. The system according to feature 1.

6. The aforementioned collection unit is The collected opinions are automatically segmented. The system according to feature 1.

7. The conversion unit is Automatically summarize the meeting content. The system according to feature 1.

8. The aforementioned learning unit, Task generation and follow-up The system according to feature 1.

Images