system

Abstract

An object of the system according to the embodiment is to efficiently support various tasks in the PTA activity.SOLUTION: A system according to an embodiment includes a conference progress support unit, a minutes creation unit, an accounting management unit, a publicity magazine creation unit, and an image extraction unit. The conference progress support unit supports the progress of the conference using the generated AI. The minute creation part automatically creates minutes of the conference by using the generation AI. The account management unit performs budget allocation and account management using the generated AI. A public relation magazine preparation part automatically prepares a public relation magazine by using the generation AI. The image extraction unit extracts an image without deviation of a person from the photographic image of the event using the generation AI.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, PTA activities such as running meetings, taking minutes, managing accounts, creating newsletters, and managing event photos required time and effort, making it difficult to carry out these tasks efficiently.

[0005] The system according to the embodiment aims to efficiently support various tasks in PTA activities. [Means for solving the problem]

[0006] The system according to the embodiment comprises a meeting progress support unit, a minutes creation unit, an accounting management unit, a newsletter creation unit, and an image extraction unit. The meeting progress support unit uses a generation AI to support the progress of the meeting. The minutes creation unit uses a generation AI to automatically create meeting minutes. The accounting management unit uses a generation AI to allocate budgets and manage accounts. The newsletter creation unit uses a generation AI to automatically create newsletters. The image extraction unit uses a generation AI to extract images from photo images of the event without bias towards people. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently support various tasks in PTA activities. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also 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. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an 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 emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The PTA activity support system according to the embodiment of the present invention is a system that manages meetings, creates minutes, manages accounting such as budget allocation, creates newsletters, and extracts images of people from event photos without bias. As a result, the PTA activity support system can improve the efficiency and smooth operation of PTA activities.

[0029] A PTA activity support system according to an embodiment includes a meeting progress support unit, a minutes creation unit, an accounting management unit, a newsletter creation unit, and an image extraction unit. The meeting progress support unit uses a generation AI to support the progress of a meeting. For example, the generation AI automatically creates a meeting agenda, allowing the moderator to smoothly proceed with the meeting. The generation AI can also analyze comments made during a meeting in real time and suggest when to move on to the next topic. The minutes creation unit automatically creates meeting minutes using the generation AI. For example, the generation AI converts comments made during a meeting into text using voice recognition technology, organizes the content, and creates minutes. The generation AI creates minutes based on audio data from the meeting. The accounting management unit uses the generation AI to allocate budgets and manage accounts. For example, when income and expense data is entered, the generation AI suggests optimal budget allocation. The generation AI allocates the budget based on the income and expense data. The newsletter creation unit automatically creates newsletters using the generation AI. For example, when an event report or activity details are input, the generation AI generates a newsletter manuscript based on that. The generation AI creates a newsletter based on the text data of the event report and activity details. The image extraction unit uses the generation AI to extract images from event photo images without bias toward any particular person. For example, when event photos are input, the generation AI analyzes the photos and selects images without bias toward any particular person. The generation AI extracts unbiased images based on the event photo images. As a result, the PTA activity support system according to the embodiment can improve the efficiency and smooth operation of PTA activities. For example, meetings can proceed more smoothly, reducing the effort required to create minutes. In addition, budgets can be allocated appropriately, improving the quality of newsletters. Furthermore, fair selection of event photo images improves the transparency and reliability of PTA activities.

[0030] The meeting progress support unit can automatically generate a meeting agenda, allowing the facilitator to smoothly proceed with the meeting. For example, the meeting progress support unit uses a generation AI to automatically generate an agenda based on the purpose and agenda of the meeting. The generation AI can also analyze what is being said in real time while the meeting is in progress and suggest when to move on to the next topic. This allows the meeting to proceed smoothly.

[0031] The minutes-taking section uses voice recognition technology to convert statements made during meetings into text, and the generation AI can then organize the content to generate minutes. For example, the minutes-taking section uses voice recognition technology to convert statements made during meetings into text, and the generation AI then organizes the content to generate minutes. The generation AI creates minutes based on the audio data from the meeting. This can significantly reduce the effort required to create minutes.

[0032] When the accounting management department inputs income and expenditure data, the generation AI can propose the optimal budget allocation. For example, when the accounting management department inputs income and expenditure data, the generation AI can propose the optimal budget allocation. The generation AI allocates the budget based on the income and expenditure data. This improves the efficiency and transparency of accounting management.

[0033] When the newsletter creation department inputs event reports and activity details, the generation AI can generate a newsletter manuscript based on that. When the newsletter creation department inputs event reports and activity details, the generation AI can generate a newsletter manuscript based on that. The generation AI creates a newsletter based on the text data of the event reports and activity details. This reduces the effort required to create a newsletter and enables the creation of high-quality newsletters.

[0034] When an event photo is input into the image extraction unit, the generation AI analyzes the photo and selects images that are not biased toward any particular person. For example, when an event photo is input into the image extraction unit, the generation AI analyzes the photo and selects images that are not biased toward any particular person. The generation AI extracts unbiased images based on the event photos. This ensures fairness in the images used in public relations magazines and reports.

[0035] The meeting progress support unit can analyze the content of participants' remarks in real time as the meeting progresses, automatically generate summaries of the remarks, and present them to the facilitator. For example, the meeting progress support unit uses a generation AI to analyze the content of participants' remarks in real time as the meeting progresses, automatically generate summaries of the remarks, and present them to the facilitator. The generation AI converts the remarks into short summary sentences and displays them to the facilitator. This allows the meeting to proceed smoothly.

[0036] The meeting progress support unit monitors the frequency and duration of speech of participants as the meeting progresses, and can make suggestions to provide balanced speaking opportunities. For example, the generation AI of the meeting progress support unit monitors the frequency and duration of speech of participants as the meeting progresses, and makes suggestions to provide speaking opportunities to participants who speak less. The generation AI displays a message encouraging participants who speak less to speak. This makes it possible to provide balanced speaking opportunities.

[0037] The meeting progress support unit can link the meeting progress support function with the online conference system to provide similar support to remote participants. For example, the meeting progress support unit can link the meeting progress support function with the online conference system to provide summaries and suggestions of remarks to remote participants in real time. The generation AI analyzes the remarks of remote participants and displays summaries. This allows similar support to be provided to remote participants.

[0038] The meeting progress support unit allows the generation AI to automatically search for relevant materials and past minutes as the meeting progresses and present them as needed. For example, the meeting progress support unit allows the generation AI to automatically search for relevant materials and past minutes as the meeting progresses and present them to the facilitator. The generation AI displays past minutes related to the agenda. This makes it possible to automatically present relevant materials and past minutes as the meeting progresses.

[0039] The minutes-taking unit can translate statements made during meetings in real time and automatically generate minutes in multiple languages. For example, the minutes-taking unit uses a generation AI to translate statements made during meetings in real time and automatically generate minutes in multiple languages. The generation AI creates minutes in multiple languages, such as English, Japanese, and French. This makes it possible to automatically generate minutes in multiple languages.

[0040] The minutes-taking section allows the generation AI to automatically classify what is said during a meeting and organize the structure of the minutes. For example, the minutes-taking section allows the generation AI to automatically classify what is said during a meeting and organize the structure of the minutes. The generation AI classifies what is said by topic and records it in the minutes. This allows the structure of the minutes to be organized.

[0041] The minutes-taking section allows the generation AI to automatically refer to relevant laws and regulations and add appropriate descriptions when creating minutes. The minutes-taking section allows the generation AI to automatically refer to relevant laws and regulations and add appropriate descriptions when creating minutes. The generation AI records laws and regulations related to the agenda in the minutes. This allows the generation AI to automatically refer to relevant laws and regulations and add appropriate descriptions.

[0042] The minutes-taking unit allows the generation AI to automatically summarize the contents of the minutes and generate a summary version that can be reviewed in a short time. For example, the minutes-taking unit allows the generation AI to automatically summarize the contents of the minutes and generate a summary version that can be reviewed in a short time. The generation AI extracts the main points of the minutes and creates a summary version. This makes it possible to generate a summary version that can be reviewed in a short time.

[0043] The accounting management department can analyze past accounting data and provide predictions regarding future budget allocations. In the accounting management department, for example, a generation AI analyzes past accounting data and provides predictions regarding future budget allocations. The generation AI predicts budget allocations based on past income and expenditure data. This makes it possible to provide predictions regarding future budget allocations.

[0044] The accounting management department can make specific proposals for cost reduction based on the accounting data. In the accounting management department, for example, the generation AI analyzes the accounting data and makes specific proposals for cost reduction. The generation AI makes proposals for cutting wasteful expenditures. This makes it possible to make specific proposals for cost reduction.

[0045] The accounting management department can compare accounting data with data from other PTAs and similar organizations and perform benchmark analysis. For example, the generation AI in the accounting management department compares accounting data with data from other PTAs and similar organizations and performs benchmark analysis. The generation AI evaluates the organization's expenditures by comparing them with the expenditure trends of other organizations. This allows benchmark analysis to be performed by comparing with data from other PTAs and similar organizations.

[0046] The accounting management department can propose new ideas for fundraising based on accounting data. For example, the accounting management department has a generation AI that analyzes accounting data and proposes new ideas for fundraising. The generation AI makes suggestions for finding new sources of income. This makes it possible to propose new ideas for fundraising.

[0047] The newsletter production department can analyze data from past newsletters and propose the most effective layout and design. For example, the generation AI in the newsletter production department can analyze data from past newsletters and propose the most effective layout and design. The generation AI makes proposals based on layouts that have received a good response from readers. This allows the department to propose the most effective layout and design.

[0048] The newsletter creation department can automatically proofread the contents of the newsletter and correct typos and grammatical errors. In the newsletter creation department, for example, the generation AI automatically proofreads the contents of the newsletter and corrects typos and grammatical errors. The generation AI automatically detects and corrects errors in sentences. This allows the contents of the newsletter to be automatically proofread and correct typos and grammatical errors.

[0049] The newsletter creation department can optimize the content of the newsletter for social media and automatically generate content for posting. In the newsletter creation department, for example, a generation AI optimizes the content of the newsletter for social media and automatically generates content for posting. The generation AI converts the content of the newsletter into short posts. This allows the content of the newsletter to be optimized for social media and the content for posting to be automatically generated.

[0050] The newsletter creation unit can convert the contents of the newsletter into audio or video and support distribution in multimedia format. For example, the newsletter creation unit uses a generation AI to convert the contents of the newsletter into audio or video and support distribution in multimedia format. The generation AI converts the contents of the newsletter into video with audio narration. This allows the contents of the newsletter to be converted into audio or video and support distribution in multimedia format.

[0051] The image extraction unit performs image analysis and can automatically select images so as not to be biased towards a particular person or group. For example, the image extraction unit uses a generation AI to analyze photo images of an event and automatically select images so as not to be biased towards a particular person or group. The generation AI selects images in which multiple people are evenly represented. This makes it possible to automatically select images so as not to be biased towards a particular person or group.

[0052] The image extraction unit analyzes the background and composition of the image and can perform optimal trimming. For example, the image extraction unit uses a generation AI to analyze the background and composition of a photo image of an event and perform optimal trimming. The generation AI trims the image so that important people and elements are placed in the center. This allows the background and composition of the image to be analyzed and optimal trimming to be performed.

[0053] The image extraction unit performs image analysis and can automatically select images that match the theme and atmosphere of the event. For example, the generation AI analyzes photo images of the event and automatically selects images that match the theme and atmosphere of the event. The generation AI selects images that are in line with the theme of the event. This makes it possible to automatically select images that match the theme and atmosphere of the event.

[0054] The image extraction unit can analyze image metadata and classify images based on the date and time of shooting and the location. For example, the generation AI analyzes image metadata and classifies images based on the date and time of shooting and the location. The generation AI classifies images for each different session of the event. This makes it possible to classify images based on the date and time of shooting and the location.

[0055] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0056] The PTA activity support system can further be equipped with a participant schedule adjustment unit, which obtains calendar information from each participant and proposes the optimal meeting date and time. For example, the generation AI can analyze the free time of all participants and automatically select the date and time when the largest number of participants can attend. The generation AI can also adjust schedules by prioritizing them according to the importance and urgency of the meeting. This makes meeting schedule adjustment more efficient and improves participant attendance rates.

[0057] The PTA activity support system can further include a participant opinion collection unit. The participant opinion collection unit collects opinions and questions from participants before the meeting and reflects them in the meeting agenda. For example, the generation AI can analyze opinions and questions submitted in advance and add important items to the agenda. The generation AI can also organize the collected opinions by category to enable efficient discussion during the meeting. This makes meeting preparations smoother and ensures discussions that reflect the opinions of participants.

[0058] The PTA activity support system can also be equipped with a meeting follow-up section, which automatically sends follow-up emails to participants after the meeting to share the minutes and the next agenda. For example, the generation AI can automatically generate minutes after the meeting and send them to participants by email. It can also propose an agenda for the next meeting and ask participants for confirmation. This will make post-meeting follow-up more efficient and smoother preparation for the next meeting.

[0059] The PTA activity support system can also be equipped with an accounting auditing department, which regularly audits accounting data to detect fraud and anomalies. For example, the generation AI can analyze income and expenditure data and automatically detect fraudulent transactions and abnormal expenditures. The generation AI can also compare data with past data to identify abnormal patterns and issue alerts. This improves the transparency and reliability of accounting and helps prevent fraud.

[0060] The PTA activity support system can further be equipped with a newsletter reader analysis unit. The newsletter reader analysis unit analyzes newsletter reader data to understand readers' interests and concerns. For example, the generation AI analyzes the newsletter's viewing history and click data to identify articles and themes that interest readers. The generation AI can also collect reader feedback and make suggestions to improve the newsletter's content. This ensures that the newsletter's content meets readers' needs and increases reader satisfaction.

[0061] The processing flow of the first embodiment will be briefly explained below.

[0062] Step 1: The meeting progress support unit uses generation AI to support the progress of the meeting. For example, generation AI can automatically generate a meeting agenda, allowing the moderator to smoothly proceed with the meeting. Generation AI can also analyze comments made during the meeting in real time and suggest when to move on to the next agenda item. Step 2: The minutes-taking unit uses the generation AI to automatically create meeting minutes. For example, the generation AI converts what is said during the meeting into text using voice recognition technology, then organizes the content to create minutes. The generation AI creates minutes based on the audio data from the meeting. Step 3: The accounting management department uses the generation AI to allocate the budget and manage accounting. For example, when income and expenditure data is entered, the generation AI proposes the optimal budget allocation. The generation AI allocates the budget based on the income and expenditure data. Step 4: The newsletter creation department uses the generation AI to automatically create the newsletter. For example, when an event report or activity details are input, the generation AI generates the manuscript for the newsletter based on that information. The generation AI creates the newsletter based on the text data of the event report or activity details. Step 5: The image extraction unit uses the generation AI to extract images from the event photos without bias towards any particular person. For example, when an event photo is input, the generation AI analyzes the photo and selects images without bias towards any particular person. The generation AI extracts unbiased images based on the event photos.

[0063] (Example 2) The PTA activity support system according to the embodiment of the present invention is a system that manages meetings, creates minutes, manages accounting such as budget allocation, creates newsletters, and extracts images of people from event photos without bias. As a result, the PTA activity support system can improve the efficiency and smooth operation of PTA activities.

[0064] A PTA activity support system according to an embodiment includes a meeting progress support unit, a minutes creation unit, an accounting management unit, a newsletter creation unit, and an image extraction unit. The meeting progress support unit uses a generation AI to support the progress of a meeting. For example, the generation AI automatically creates a meeting agenda, allowing the moderator to smoothly proceed with the meeting. The generation AI can also analyze comments made during a meeting in real time and suggest when to move on to the next topic. The minutes creation unit automatically creates meeting minutes using the generation AI. For example, the generation AI converts comments made during a meeting into text using voice recognition technology, organizes the content, and creates minutes. The generation AI creates minutes based on audio data from the meeting. The accounting management unit uses the generation AI to allocate budgets and manage accounts. For example, when income and expense data is entered, the generation AI suggests optimal budget allocation. The generation AI allocates the budget based on the income and expense data. The newsletter creation unit automatically creates newsletters using the generation AI. For example, when an event report or activity details are input, the generation AI generates a newsletter manuscript based on that. The generation AI creates a newsletter based on the text data of the event report and activity details. The image extraction unit uses the generation AI to extract images from event photo images without bias toward any particular person. For example, when event photos are input, the generation AI analyzes the photos and selects images without bias toward any particular person. The generation AI extracts unbiased images based on the event photo images. As a result, the PTA activity support system according to the embodiment can improve the efficiency and smooth operation of PTA activities. For example, meetings can proceed more smoothly, reducing the effort required to create minutes. In addition, budgets can be allocated appropriately, improving the quality of newsletters. Furthermore, fair selection of event photo images improves the transparency and reliability of PTA activities.

[0065] The meeting progress support unit can automatically generate a meeting agenda, allowing the facilitator to smoothly proceed with the meeting. For example, the meeting progress support unit uses a generation AI to automatically generate an agenda based on the purpose and agenda of the meeting. The generation AI can also analyze what is being said in real time while the meeting is in progress and suggest when to move on to the next topic. This allows the meeting to proceed smoothly.

[0066] The minutes-taking section uses voice recognition technology to convert statements made during meetings into text, and the generation AI can then organize the content to generate minutes. For example, the minutes-taking section uses voice recognition technology to convert statements made during meetings into text, and the generation AI then organizes the content to generate minutes. The generation AI creates minutes based on the audio data from the meeting. This can significantly reduce the effort required to create minutes.

[0067] When the accounting management department inputs income and expenditure data, the generation AI can propose the optimal budget allocation. For example, when the accounting management department inputs income and expenditure data, the generation AI can propose the optimal budget allocation. The generation AI allocates the budget based on the income and expenditure data. This improves the efficiency and transparency of accounting management.

[0068] When the newsletter creation department inputs event reports and activity details, the generation AI can generate a newsletter manuscript based on that. When the newsletter creation department inputs event reports and activity details, the generation AI can generate a newsletter manuscript based on that. The generation AI creates a newsletter based on the text data of the event reports and activity details. This reduces the effort required to create a newsletter and enables the creation of high-quality newsletters.

[0069] When an event photo is input into the image extraction unit, the generation AI analyzes the photo and selects images that are not biased toward any particular person. For example, when an event photo is input into the image extraction unit, the generation AI analyzes the photo and selects images that are not biased toward any particular person. The generation AI extracts unbiased images based on the event photos. This ensures fairness in the images used in public relations magazines and reports.

[0070] The meeting progress support unit can analyze the content of participants' remarks in real time as the meeting progresses, automatically generate summaries of the remarks, and present them to the facilitator. For example, the meeting progress support unit uses a generation AI to analyze the content of participants' remarks in real time as the meeting progresses, automatically generate summaries of the remarks, and present them to the facilitator. The generation AI converts the remarks into short summary sentences and displays them to the facilitator. This allows the meeting to proceed smoothly.

[0071] The meeting progress support unit monitors the frequency and duration of speech of participants as the meeting progresses, and can make suggestions to provide balanced speaking opportunities. For example, the generation AI of the meeting progress support unit monitors the frequency and duration of speech of participants as the meeting progresses, and makes suggestions to provide speaking opportunities to participants who speak less. The generation AI displays a message encouraging participants who speak less to speak. This makes it possible to provide balanced speaking opportunities.

[0072] The meeting progress support unit uses the emotion estimation function to analyze the emotional state of participants in real time and propose appropriate responses according to the progress of the meeting. For example, the meeting progress support unit uses the emotion estimation function to analyze participants' facial expressions and voices and predict their emotional state in real time. If a participant appears nervous, the generation AI makes suggestions to help them relax. This makes it possible to respond appropriately according to the participants' emotional state.

[0073] The meeting progress support unit can link the meeting progress support function with the online conference system to provide similar support to remote participants. For example, the meeting progress support unit can link the meeting progress support function with the online conference system to provide summaries and suggestions of remarks to remote participants in real time. The generation AI analyzes the remarks of remote participants and displays summaries. This allows similar support to be provided to remote participants.

[0074] The meeting progress support unit allows the generation AI to automatically search for relevant materials and past minutes as the meeting progresses and present them as needed. For example, the meeting progress support unit allows the generation AI to automatically search for relevant materials and past minutes as the meeting progresses and present them to the facilitator. The generation AI displays past minutes related to the agenda. This makes it possible to automatically present relevant materials and past minutes as the meeting progresses.

[0075] The meeting progress support unit can use the emotion estimation function to analyze the emotions of participants during the meeting and make interactive suggestions to bring out positive emotions. For example, the meeting progress support unit can use the emotion estimation function to analyze the emotions of participants during the meeting and make suggestions to bring out positive emotions. If a participant is feeling tense, the generation AI makes suggestions to help them relax. This makes it possible to make interactive suggestions to bring out positive emotions.

[0076] The minutes-taking unit can translate statements made during meetings in real time and automatically generate minutes in multiple languages. For example, the minutes-taking unit uses a generation AI to translate statements made during meetings in real time and automatically generate minutes in multiple languages. The generation AI creates minutes in multiple languages, such as English, Japanese, and French. This makes it possible to automatically generate minutes in multiple languages.

[0077] The minutes-taking section allows the generation AI to automatically classify what is said during a meeting and organize the structure of the minutes. For example, the minutes-taking section allows the generation AI to automatically classify what is said during a meeting and organize the structure of the minutes. The generation AI classifies what is said by topic and records it in the minutes. This allows the structure of the minutes to be organized.

[0078] The minutes creation unit can use the emotion estimation function to analyze the emotions of speakers and generate minutes that reflect changes in emotions. For example, the minutes creation unit can use the emotion estimation function to analyze the emotions of speakers during a meeting and generate minutes that reflect changes in emotions. The generation AI records the emotional state of the speaker in the minutes. This makes it possible to generate minutes that reflect changes in emotions.

[0079] The minutes-taking section allows the generation AI to automatically refer to relevant laws and regulations and add appropriate descriptions when creating minutes. The minutes-taking section allows the generation AI to automatically refer to relevant laws and regulations and add appropriate descriptions when creating minutes. The generation AI records laws and regulations related to the agenda in the minutes. This allows the generation AI to automatically refer to relevant laws and regulations and add appropriate descriptions.

[0080] The minutes-taking unit allows the generation AI to automatically summarize the contents of the minutes and generate a summary version that can be reviewed in a short time. For example, the minutes-taking unit allows the generation AI to automatically summarize the contents of the minutes and generate a summary version that can be reviewed in a short time. The generation AI extracts the main points of the minutes and creates a summary version. This makes it possible to generate a summary version that can be reviewed in a short time.

[0081] The minutes-taking unit can use the emotion estimation function to analyze the emotional reactions of participants to the contents of the minutes and suggest improvements to the minutes. The minutes-taking unit can, for example, use the emotion estimation function to analyze the emotional reactions of participants to the contents of the minutes and suggest improvements to the minutes. The generation AI improves the contents of the minutes based on the emotional reactions of participants. This makes it possible to suggest improvements to the minutes.

[0082] The accounting management department can analyze past accounting data and provide predictions regarding future budget allocations. In the accounting management department, for example, a generation AI analyzes past accounting data and provides predictions regarding future budget allocations. The generation AI predicts budget allocations based on past income and expenditure data. This makes it possible to provide predictions regarding future budget allocations.

[0083] The accounting management department can make specific proposals for cost reduction based on the accounting data. In the accounting management department, for example, the generation AI analyzes the accounting data and makes specific proposals for cost reduction. The generation AI makes proposals for cutting wasteful expenditures. This makes it possible to make specific proposals for cost reduction.

[0084] The accounting management department can use the emotion estimation function to analyze the emotions of stakeholders regarding budget allocation and propose the optimal allocation. The accounting management department can, for example, use the emotion estimation function to analyze the emotions of stakeholders regarding budget allocation and propose the optimal allocation. The generation AI adjusts the budget allocation based on the emotional reactions of stakeholders. This makes it possible to propose the optimal budget allocation.

[0085] The accounting management department can compare accounting data with data from other PTAs and similar organizations and perform benchmark analysis. For example, the generation AI in the accounting management department compares accounting data with data from other PTAs and similar organizations and performs benchmark analysis. The generation AI evaluates the organization's expenditures by comparing them with the expenditure trends of other organizations. This allows benchmark analysis to be performed by comparing with data from other PTAs and similar organizations.

[0086] The accounting management department can propose new ideas for fundraising based on accounting data. For example, the accounting management department has a generation AI that analyzes accounting data and proposes new ideas for fundraising. The generation AI makes suggestions for finding new sources of income. This makes it possible to propose new ideas for fundraising.

[0087] The accounting management department can use the emotion estimation function to monitor the emotions of stakeholders regarding budget allocation in real time and adjust the allocation. The accounting management department can use the emotion estimation function to monitor the emotions of stakeholders regarding budget allocation in real time and adjust the allocation. The generation AI adjusts the budget allocation based on the emotional reactions of stakeholders. This makes it possible to monitor the emotions of stakeholders regarding budget allocation in real time and adjust the allocation.

[0088] The newsletter production department can analyze data from past newsletters and propose the most effective layout and design. For example, the generation AI in the newsletter production department can analyze data from past newsletters and propose the most effective layout and design. The generation AI makes proposals based on layouts that have received a good response from readers. This allows the department to propose the most effective layout and design.

[0089] The newsletter creation department can automatically proofread the contents of the newsletter and correct typos and grammatical errors. In the newsletter creation department, for example, the generation AI automatically proofreads the contents of the newsletter and corrects typos and grammatical errors. The generation AI automatically detects and corrects errors in sentences. This allows the contents of the newsletter to be automatically proofread and correct typos and grammatical errors.

[0090] The newsletter production department can use the emotion estimation function to analyze readers' emotional reactions to the content of the newsletter and suggest improvements to the content. The newsletter production department can, for example, use the emotion estimation function to analyze readers' emotional reactions to the content of the newsletter and suggest improvements to the content. The generation AI improves the content of the newsletter based on the readers' emotional reactions. This makes it possible to analyze readers' emotional reactions to the content of the newsletter and suggest improvements to the content.

[0091] The newsletter creation department can optimize the content of the newsletter for social media and automatically generate content for posting. In the newsletter creation department, for example, a generation AI optimizes the content of the newsletter for social media and automatically generates content for posting. The generation AI converts the content of the newsletter into short posts. This allows the content of the newsletter to be optimized for social media and the content for posting to be automatically generated.

[0092] The newsletter creation unit can convert the contents of the newsletter into audio or video and support distribution in multimedia format. For example, the newsletter creation unit uses a generation AI to convert the contents of the newsletter into audio or video and support distribution in multimedia format. The generation AI converts the contents of the newsletter into video with audio narration. This allows the contents of the newsletter to be converted into audio or video and support distribution in multimedia format.

[0093] The newsletter production department can use the emotion estimation function to monitor readers' emotions regarding the contents of the newsletter in real time and reflect them in the content of the next issue. The newsletter production department can use the emotion estimation function to monitor readers' emotions regarding the contents of the newsletter in real time and reflect them in the content of the next issue. The generation AI improves the content of the next issue based on the readers' emotional reactions. This allows readers' emotions regarding the contents of the newsletter to be monitored in real time and reflected in the content of the next issue.

[0094] The image extraction unit performs image analysis and can automatically select images so as not to be biased towards a particular person or group. For example, the image extraction unit uses a generation AI to analyze photo images of an event and automatically select images so as not to be biased towards a particular person or group. The generation AI selects images in which multiple people are evenly represented. This makes it possible to automatically select images so as not to be biased towards a particular person or group.

[0095] The image extraction unit analyzes the background and composition of the image and can perform optimal trimming. For example, the image extraction unit uses a generation AI to analyze the background and composition of a photo image of an event and perform optimal trimming. The generation AI trims the image so that important people and elements are placed in the center. This allows the background and composition of the image to be analyzed and optimal trimming to be performed.

[0096] The image extraction unit can use the emotion estimation function to analyze the emotions of people in the image and preferentially select images with positive emotions. The image extraction unit can, for example, use the emotion estimation function to analyze the emotions of people in the image and preferentially select images with positive emotions. The generation AI selects images with a lot of smiling faces. This makes it possible to preferentially select images with positive emotions.

[0097] The image extraction unit performs image analysis and can automatically select images that match the theme and atmosphere of the event. For example, the generation AI analyzes photo images of the event and automatically selects images that match the theme and atmosphere of the event. The generation AI selects images that are in line with the theme of the event. This makes it possible to automatically select images that match the theme and atmosphere of the event.

[0098] The image extraction unit can analyze image metadata and classify images based on the date and time of shooting and the location. For example, the generation AI analyzes image metadata and classifies images based on the date and time of shooting and the location. The generation AI classifies images for each different session of the event. This makes it possible to classify images based on the date and time of shooting and the location.

[0099] The image extraction unit uses the emotion estimation function to analyze the emotions of people in images in real time and select the most suitable image. The image extraction unit, for example, uses the emotion estimation function to analyze the emotions of people in images in real time and select the most suitable image. The generation AI selects images with a high proportion of positive emotions. This makes it possible to analyze the emotions of people in images in real time and select the most suitable image.

[0100] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0101] The PTA activity support system can further be equipped with a participant schedule adjustment unit, which obtains calendar information from each participant and proposes the optimal meeting date and time. For example, the generation AI can analyze the free time of all participants and automatically select the date and time when the largest number of participants can attend. The generation AI can also adjust schedules by prioritizing them according to the importance and urgency of the meeting. This makes meeting schedule adjustment more efficient and improves participant attendance rates.

[0102] The PTA activity support system can further include a participant opinion collection unit. The participant opinion collection unit collects opinions and questions from participants before the meeting and reflects them in the meeting agenda. For example, the generation AI can analyze opinions and questions submitted in advance and add important items to the agenda. The generation AI can also organize the collected opinions by category to enable efficient discussion during the meeting. This makes meeting preparations smoother and ensures discussions that reflect the opinions of participants.

[0103] The PTA activity support system can also be equipped with a meeting follow-up section, which automatically sends follow-up emails to participants after the meeting to share the minutes and the next agenda. For example, the generation AI can automatically generate minutes after the meeting and send them to participants by email. It can also propose an agenda for the next meeting and ask participants for confirmation. This will make post-meeting follow-up more efficient and smoother preparation for the next meeting.

[0104] The PTA activity support system can also be equipped with an accounting auditing department, which regularly audits accounting data to detect fraud and anomalies. For example, the generation AI can analyze income and expenditure data and automatically detect fraudulent transactions and abnormal expenditures. The generation AI can also compare data with past data to identify abnormal patterns and issue alerts. This improves the transparency and reliability of accounting and helps prevent fraud.

[0105] The PTA activity support system can further be equipped with a newsletter reader analysis unit. The newsletter reader analysis unit analyzes newsletter reader data to understand readers' interests and concerns. For example, the generation AI analyzes the newsletter's viewing history and click data to identify articles and themes that interest readers. The generation AI can also collect reader feedback and make suggestions to improve the newsletter's content. This ensures that the newsletter's content meets readers' needs and increases reader satisfaction.

[0106] The PTA activity support system also uses an emotion estimation function to analyze participants' emotions during meetings in real time and propose appropriate responses depending on the progress of the meeting. For example, the generative AI analyzes participants' facial expressions and voices to estimate emotions such as tension or dissatisfaction. If participants are tense, it will make suggestions to help them relax, and if they are dissatisfied, it will identify the cause and present a solution. This makes it possible to respond appropriately to participants' emotional state, improving the atmosphere of the meeting.

[0107] The PTA activity support system can also use emotion estimation functionality to analyze the emotions of speakers when creating minutes, generating minutes that reflect changes in emotion. For example, the generation AI can analyze the emotions of speakers during a meeting and reflect changes in emotion in what is said. If a speaker has strong emotions, that emotion is recorded in the minutes, clarifying the background of the discussion. This generates minutes that reflect changes in emotion, leading to a deeper understanding of the discussion.

[0108] The PTA activity support system can also use its emotion estimation function to analyze readers' emotional reactions to the content of the newsletter and suggest ways to improve it. For example, the generative AI can analyze readers' emotional reactions and identify articles and themes that receive a lot of positive reactions. If there are a lot of negative reactions, it can identify the cause and suggest ways to improve them. This allows the content of the newsletter to be improved based on readers' emotions, increasing reader satisfaction.

[0109] The PTA activity support system also uses an emotion estimation function, allowing the accounting management department to analyze the emotions of those involved regarding budget allocation and propose optimal allocations. For example, the generative AI analyzes the emotional reactions of those involved and evaluates their satisfaction with the budget allocation. If satisfaction is low, it identifies the cause and proposes adjusting the budget allocation. This allows for optimal budget allocation based on the emotions of those involved, improving satisfaction.

[0110] The PTA activity support system also uses an emotion estimation function, allowing the image extraction unit to analyze the emotions of people in images in real time and select the most appropriate image. For example, the generative AI analyzes the facial expressions of people in images and selects images that show a lot of positive emotions. By prioritizing images with lots of smiling faces and happy expressions, the atmosphere of the event can be better conveyed. This makes it possible to select the most appropriate image based on emotions.

[0111] The processing flow of the second embodiment will be briefly explained below.

[0112] Step 1: The meeting progress support unit uses generation AI to support the progress of the meeting. For example, generation AI can automatically generate a meeting agenda, allowing the moderator to smoothly proceed with the meeting. Generation AI can also analyze comments made during the meeting in real time and suggest when to move on to the next agenda item. Step 2: The minutes-taking unit uses the generation AI to automatically create meeting minutes. For example, the generation AI converts what is said during the meeting into text using voice recognition technology, then organizes the content to create minutes. The generation AI creates minutes based on the audio data from the meeting. Step 3: The accounting management department uses the generation AI to allocate the budget and manage accounting. For example, when income and expenditure data is entered, the generation AI proposes the optimal budget allocation. The generation AI allocates the budget based on the income and expenditure data. Step 4: The newsletter creation department uses the generation AI to automatically create the newsletter. For example, when an event report or activity details are input, the generation AI generates the manuscript for the newsletter based on that information. The generation AI creates the newsletter based on the text data of the event report or activity details. Step 5: The image extraction unit uses the generation AI to extract images from the event photos without bias towards any particular person. For example, when an event photo is input, the generation AI analyzes the photo and selects images without bias towards any particular person. The generation AI extracts unbiased images based on the event photos.

[0113] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0114] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0115] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0116] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0117] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0118] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0119] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, 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. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0120] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0122] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0123] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0124] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0125] The storage 32 stores a data generation model 58 and an 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 emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0126] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0127] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0128] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0129] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0130] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0131] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0132] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0133] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0134] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. 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. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0135] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0137] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0138] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0139] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0140] The storage 32 stores a data generation model 58 and an 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 emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0141] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0142] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0145] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0146] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0147] 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.

[0148] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0149] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. 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. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0150] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0152] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0153] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0154] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0155] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0156] The storage 32 stores a data generation model 58 and an 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 emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0157] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0158] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0159] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0160] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0161] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0162] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0163] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0164] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0165] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0166] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0167] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0168] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0169] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0170] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0171] 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.

[0172] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0173] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0174] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific process may be a single processor.

[0175] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0176] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0177] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0178] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0179] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0180] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A meeting progress support unit that uses generative AI to support the progress of meetings; A minutes-taking section that automatically creates meeting minutes using generative AI, The accounting management department uses generative AI to allocate budgets and manage accounting, and A newsletter creation department that automatically creates newsletters using generative AI; An image extraction unit that uses generation AI to extract images of people from photo images of the event without bias. A system characterized by:

2. The minutes preparation department Speech recognition technology is used to convert statements made during meetings into text, and the AI ​​then organizes the content to generate minutes.

2. The system of claim 1.

3. The conference progress support unit Integrate meeting support functions with online meeting systems to provide similar support to remote participants.

2. The system of claim 1.

4. The accounting management department Analyze historical accounting data and provide forecasts for future budget allocations 2. The system of claim 1.

5. The newsletter production department: Analyzing data from past newsletters and proposing the most effective layout and design 2. The system of claim 1.

6. The image extraction unit Analyzes the emotions of people in images and prioritizes images with positive emotions 2. The system of claim 1.

7. The conference progress support unit Analyze participants' emotional states in real time and suggest appropriate responses as the meeting progresses 2. The system of claim 1.

8. The minutes preparation department Analyzes the emotions of speakers and generates minutes that reflect changes in emotions 2. The system of claim 1.

Images