system

Abstract

An object of a system according to an embodiment is to efficiently analyze IR information of listed companies and provide the IR information to investors in an optimal form.SOLUTION: A system according to an embodiment includes a text generation unit, a keyword extraction unit, a data arrangement unit, and a chat unit. The text generator generates text from video or audio content of a financial briefing meeting or a shareholders meeting of a listed company. The keyword extraction unit extracts important keywords and numbers from the data converted into text by the text conversion unit, and highlights them. The data organization unit organizes and analyzes the data extracted by the keyword extraction unit. The chat section can communicate with a person in charge of IR or a manager of a listed company online in a chat form.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] Conventional technologies are not sufficient to efficiently analyze IR information of listed companies and provide it to investors, and there is room for improvement.

[0005] The system according to the embodiment aims to efficiently analyze IR information of listed companies and provide it to investors in an optimal format. [Means for solving the problem]

[0006] The system according to the embodiment includes a text conversion unit, a keyword extraction unit, a data organization unit, and a chat unit. The text conversion unit converts video or audio content from financial results briefings or general shareholders' meetings of listed companies into text. The keyword extraction unit extracts and highlights important keywords and figures from the data converted into text by the text conversion unit. The data organization unit organizes and analyzes the data extracted by the keyword extraction unit. The chat unit allows online chat interaction with investor relations personnel and management of listed companies. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently analyze IR information of listed companies and provide it to investors in an optimal format. [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 communication service according to an embodiment of the present invention is a system that automatically analyzes IR information of listed companies and provides it to investors in an optimal format. This allows the communication service to efficiently collect and analyze IR information of listed companies and use it to make investment decisions.

[0029] A communication service according to an embodiment includes a text conversion unit, a keyword extraction unit, a data organization unit, and a chat unit. The text conversion unit converts video or audio content from a listed company's financial results briefing or shareholders' meeting into text. For example, the generation AI converts audio data into character data using speech recognition technology. The generation AI can also analyze video content and output it as text. The generation AI can also convert live streaming audio into text in real time. The keyword extraction unit extracts and highlights important keywords and numbers from the data converted into text by the text conversion unit. For example, the generation AI analyzes text data and extracts keywords based on frequency and contextual importance. The generation AI can also highlight extracted keywords by changing color, font, underlining, etc. The generation AI can also use a summary function to shorten long texts. The data organization unit organizes and analyzes the data extracted by the keyword extraction unit. For example, the generation AI classifies data and analyzes trends and patterns in the data using an analytical algorithm. The generation AI can also collect, organize, and analyze data such as industry information and mid-term business plans. The generation AI can also collect the latest news and trends related to a specific industry and provide them to investors. The chat section has a function that allows investors to interact with IR personnel and management of listed companies via online chat. For example, investors can freely ask questions based on their interests and concerns. The chat section also allows for human intervention according to the plan, allowing for more detailed information and expert advice. The chat section can also support formats such as text chat, voice chat, and video chat. This allows the communication service according to the embodiment to efficiently collect and analyze IR information of listed companies and use it to make investment decisions. For example, investors can review the contents of financial results briefings in text format and grasp important keywords and figures. Furthermore, by organizing and analyzing industry information and mid-term business plans, investors can evaluate overall industry trends and the future prospects of companies.In addition, by using the online chat function, you can obtain information directly from company representatives, allowing you to make investment decisions based on more reliable information.

[0030] The text conversion unit allows the generation AI to automatically add footnotes and references to the converted content, providing supplemental information to deepen understanding. For example, the generation AI analyzes the converted content and automatically adds relevant footnotes and references. For example, detailed explanations and related literature are inserted for specific terms and concepts. The text conversion unit also allows the generation AI to automatically provide supplemental information to the converted data. For example, sources and references are added for specific data and statistics. The text conversion unit also analyzes the converted content and automatically provides supplemental information to deepen understanding. For example, it links to research papers and articles related to a specific topic. This provides supplemental information to deepen understanding of the text.

[0031] The text conversion unit can have a function to automatically convert the text data into a different format. For example, the generation AI analyzes the text data and automatically converts it into a presentation slide format. For example, it summarizes important points and keywords in slides. The text conversion unit also has a function to automatically convert the text data into a report format. For example, it divides the text into chapters and organizes it using headings and bullet points. The text conversion unit also analyzes the text data and automatically converts it into a different format. For example, it converts the text into an infographic or dashboard format. This automatic conversion into a different format makes the data easier to use.

[0032] The text conversion unit can automatically translate the text data into different languages, making it possible to accommodate international investors. For example, the text conversion unit has a generation AI analyze the text data and automatically translate it into different languages. For example, it supports multiple languages ​​such as English, Japanese, and Chinese. The text conversion unit also automatically translates the text data to accommodate international investors. For example, it provides the translated text to a multilingual platform. The text conversion unit also has a function to analyze the text data converted by the generation AI and automatically translate it into different languages. For example, it displays the translated text in real time. This makes it possible to accommodate international investors by automatically translating it into different languages.

[0033] The text conversion unit can have a function to automatically convert the text data into infographics that are easy to understand visually. For example, the generation AI in the text conversion unit analyzes the text data and automatically converts it into infographics that are easy to understand visually. For example, important data and keywords are displayed in graphs and charts. The text conversion unit also has a function to automatically convert the text data into infographics. For example, the text is visually represented using diagrams and icons. The text conversion unit also has a function to automatically convert the text data into infographics that are easy to understand visually. For example, the flow and relationships of data are illustrated. This automatic conversion into infographics that are easy to understand visually deepens understanding of the data.

[0034] The keyword extraction unit can automatically link related past data and trends to extracted keywords and numbers, providing background information. For example, the keyword extraction unit automatically links related past data and trends to keywords and numbers extracted by the generation AI. For example, it displays past performance data and market trends. The keyword extraction unit also builds a system that automatically provides related background information to extracted keywords and numbers. For example, it links related news articles and research papers. The keyword extraction unit also automatically links related past data and trends to keywords and numbers extracted by the generation AI. For example, it displays past financial results data and industry trends. This allows for linking related past data and trends to provide background information and deepen understanding.

[0035] The keyword extraction unit allows the generation AI to automatically generate graphs and charts based on the extracted keywords and numbers, thereby visually emphasizing the data. The keyword extraction unit, for example, automatically generates graphs and charts based on the keywords and numbers extracted by the generation AI. For example, sales figures and profit margins are displayed as bar graphs or pie charts. The keyword extraction unit also builds a system in which the generation AI automatically generates graphs and charts to visually emphasize the extracted keywords and numbers. For example, important data is displayed as a line graph. The keyword extraction unit also automatically generates graphs and charts based on the keywords and numbers extracted by the generation AI. For example, performance data is displayed as a heat map or scatter plot. In this way, generating graphs and charts can visually emphasize the data and deepen understanding.

[0036] The data reduction unit can automatically compare with industry leader companies and generate a report that clearly shows relative strengths and weaknesses. In the data reduction unit, for example, the generation AI analyzes industry information and automatically generates a report that clearly shows relative strengths and weaknesses in comparison with leader companies. For example, it compares sales and market share. The data reduction unit also has a function to automatically compare with industry leader companies and generate a report that clearly shows relative strengths and weaknesses. For example, it compares technological capabilities and brand power. In addition, the data reduction unit uses the generation AI to analyze industry information and generate a report that clearly shows relative strengths and weaknesses in comparison with leader companies. For example, it compares financial indicators and growth rates. This makes it possible to clearly show relative strengths and weaknesses by comparing with leader companies.

[0037] The data reduction unit can be equipped with a function for monitoring the progress of the mid-term management plan in real time and evaluating the degree of achievement of the plan. The data reduction unit, for example, has a function for the generation AI to monitor the progress of the mid-term management plan in real time and evaluate the degree of achievement of the plan. For example, it displays the goal achievement rate and progress status in a graph. The data reduction unit also builds a system for monitoring the progress of the mid-term management plan in real time and evaluates the degree of achievement of the plan. For example, it displays the progress status of each goal on a dashboard. The data reduction unit also has a function for the generation AI to monitor the progress of the mid-term management plan in real time and evaluate the degree of achievement of the plan. For example, it automatically collects progress data and generates an evaluation report. This makes it possible to monitor the progress of the mid-term management plan in real time and evaluate the degree of achievement of the plan, thereby understanding the progress of the plan.

[0038] The data reduction department can compare industry information and mid-term business plans with data from different regions and markets to provide analysis from a global perspective. For example, the generation AI in the data reduction department analyzes industry information and mid-term business plans and compares them with data from different regions and markets. For example, it compares trends in the Asian market with those in the European and American markets. The data reduction department also builds a system that collects data from different regions and markets and compares it with industry information and mid-term business plans. For example, it compares economic indicators and market trends by region. The data reduction department also analyzes industry information and mid-term business plans with the generation AI and provides analysis from a global perspective. For example, it compares them with competitors in different regions. This makes it possible to provide analysis from a global perspective by comparing them with data from different regions and markets.

[0039] The data reduction unit can automatically predict industry trends using the generation AI and generate reports showing future market trends. In the data reduction unit, for example, the generation AI analyzes industry information and automatically predicts trends. For example, it predicts future market trends based on past data and generates reports. The data reduction unit also has a function for predicting industry trends and generates reports showing future market trends. For example, it predicts technological innovations and changes in consumer behavior. In addition, the data reduction unit uses the generation AI to analyze industry information and automatically predict trends and generate reports showing future market trends. For example, it predicts demand forecasts and changes in the competitive environment. In this way, future market trends can be grasped by predicting industry trends and generating reports showing future market trends.

[0040] The chat unit can have a function to automatically analyze chat history and extract and provide useful information from past interactions. For example, the chat unit uses a generation AI to analyze chat history and automatically extract useful information from past interactions. For example, related information is provided based on past questions and answers. The chat unit also builds a system that analyzes chat history, extracts useful information, and provides it. For example, it extracts important points from past interactions and presents them to the user. The chat unit also has a function to use a generation AI to analyze chat history and automatically extract and provide useful information from past interactions. For example, it provides related materials and links based on past interactions. This enables more effective information provision by analyzing chat history and extracting and providing useful information from past interactions.

[0041] The chat unit can have a function to automatically summarize chat content and highlight important points. For example, the generation AI in the chat unit analyzes chat content and automatically summarizes it. For example, it may condense long messages into a few lines. The chat unit may also build a system that summarizes chat content and highlights important points. For example, it may highlight important keywords and phrases. The chat unit may also have a function to analyze chat content and automatically summarize it and highlight important points. For example, it may highlight the summary content. This makes it easier to understand the information by summarizing chat content and highlighting important points.

[0042] The chat unit enables the chat function to support voice calls and video calls, thereby providing a wider variety of communication methods. For example, the chat unit uses a generation AI to analyze the chat function and enable it to support voice calls and video calls. For example, a function to switch from text chat to voice calls or video calls is added. The chat unit also builds a system to support voice and video calls. For example, it uses voice recognition and video analysis technology to analyze the content of calls in real time. The chat unit also analyzes the chat function using a generation AI and enables it to support voice and video calls. For example, it provides an interface that allows the user to select voice calls or video calls. This allows it to support voice and video calls, thereby providing a wider variety of communication methods.

[0043] The chat unit can translate chat content into different languages ​​in real time, facilitating communication with international investors. For example, the chat unit uses a generation AI to analyze chat content and translate it into different languages ​​in real time. For example, it supports multiple languages ​​such as English, Japanese, and Chinese. The chat unit also translates chat content in real time, building a system that facilitates communication with international investors. For example, it displays translated messages in real time. The chat unit also has a function where the generation AI analyzes chat content and translates it into different languages ​​in real time. For example, it provides translated messages to a multilingual platform. This allows chat content to be translated into different languages ​​in real time, facilitating communication with international investors.

[0044] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0045] The text conversion unit allows the generation AI to automatically add footnotes and references to the converted content, providing supplementary information for deeper understanding. For example, the generation AI analyzes the converted content and automatically adds relevant footnotes and references. Detailed explanations and related literature can be inserted for specific terms and concepts. It is also possible to add sources and references for specific data and statistics. Furthermore, by linking to research papers and articles related to specific topics, supplementary information can be provided to deepen understanding of the text.

[0046] The text conversion unit can be equipped with a function to automatically convert the converted data into different formats. For example, the generation AI can analyze the converted data and automatically convert it into a presentation slide format. Important points and keywords can be summarized in the slides. It can also be equipped with a function to automatically convert the converted data into a report format. The text can be divided into chapters and organized using headings and bullet points. Furthermore, converting the text into infographics or dashboard formats makes the data easier to use.

[0047] The text conversion unit can automatically translate the converted data into different languages, making it possible to accommodate international investors. For example, the generation AI analyzes the converted data and automatically translates it into different languages. It can support multiple languages, including English, Japanese, and Chinese. It is also possible to provide the translated text on a multilingual platform. Furthermore, the translated text can be displayed in real time, making it possible to accommodate international investors.

[0048] The text conversion unit can be equipped with a function to automatically convert the converted text data into infographics that are easy to understand visually. For example, the generation AI analyzes the converted text data and automatically converts it into infographics that are easy to understand visually. Important data and keywords can be displayed in graphs and charts. It is also possible to visually represent text using diagrams and icons. Furthermore, by illustrating the flow and relationships of data, it is possible to automatically convert it into infographics that are easy to understand visually.

[0049] The keyword extraction unit can automatically link related past data and trends to extracted keywords and figures to provide background information. For example, related past data and trends can be automatically linked to keywords and figures extracted by the generation AI. Past performance data and market trends can be displayed. It is also possible to build a system that provides background information by linking related news articles and research papers. Furthermore, displaying past financial data and industry trends can provide background information and deepen understanding.

[0050] The data reduction unit can automatically compare companies with industry leaders and generate reports that clearly show their relative strengths and weaknesses. For example, the generation AI analyzes industry information and automatically generates a report that clearly shows their relative strengths and weaknesses compared to the leader. It is possible to compare sales and market share. It is also possible to compare technological capabilities and brand power. Furthermore, by comparing financial indicators and growth rates, it is possible to clearly show their relative strengths and weaknesses compared to the leader.

[0051] The processing flow of the first embodiment will be briefly explained below.

[0052] Step 1: The text conversion unit converts video or audio content from a listed company's financial results briefing or general shareholders' meeting into text. For example, the generation AI uses speech recognition technology to convert audio data into text data. The generation AI can also analyze video content and output it as text. The generation AI can also convert live streaming audio into text in real time. Step 2: The keyword extraction unit extracts and highlights important keywords and numbers from the data converted by the text conversion unit. For example, the generation AI analyzes the text data and extracts keywords based on frequency and contextual importance. The generation AI can also highlight the extracted keywords by changing the color or font, underlining, etc. The generation AI can also use a summary function to summarize long texts in a shorter form. Step 3: The data organizer organizes and analyzes the data extracted by the keyword extractor. For example, the generation AI classifies the data and uses analytical algorithms to analyze trends and patterns in the data. The generation AI can also collect, organize, and analyze data such as industry information and medium-term management plans. The generation AI can also collect the latest news and trends related to a specific industry and provide them to investors. Step 4: The chat section has a function that allows investors to communicate online with IR personnel and management of listed companies through chat. For example, investors can freely ask questions based on their interests and concerns. The chat section also allows for human intervention according to the plan, allowing investors to receive more detailed information and expert advice. The chat section can also support text chat, voice chat, video chat, and other formats.

[0053] (Example 2) The communication service according to an embodiment of the present invention is a system that automatically analyzes IR information of listed companies and provides it to investors in an optimal format. This allows the communication service to efficiently collect and analyze IR information of listed companies and use it to make investment decisions.

[0054] A communication service according to an embodiment includes a text conversion unit, a keyword extraction unit, a data organization unit, and a chat unit. The text conversion unit converts video or audio content from a listed company's financial results briefing or shareholders' meeting into text. For example, the generation AI converts audio data into character data using speech recognition technology. The generation AI can also analyze video content and output it as text. The generation AI can also convert live streaming audio into text in real time. The keyword extraction unit extracts and highlights important keywords and numbers from the data converted into text by the text conversion unit. For example, the generation AI analyzes text data and extracts keywords based on frequency and contextual importance. The generation AI can also highlight extracted keywords by changing color, font, underlining, etc. The generation AI can also use a summary function to shorten long texts. The data organization unit organizes and analyzes the data extracted by the keyword extraction unit. For example, the generation AI classifies data and analyzes trends and patterns in the data using an analytical algorithm. The generation AI can also collect, organize, and analyze data such as industry information and mid-term business plans. The generation AI can also collect the latest news and trends related to a specific industry and provide them to investors. The chat section has a function that allows investors to interact with IR personnel and management of listed companies via online chat. For example, investors can freely ask questions based on their interests and concerns. The chat section also allows for human intervention according to the plan, allowing for more detailed information and expert advice. The chat section can also support formats such as text chat, voice chat, and video chat. This allows the communication service according to the embodiment to efficiently collect and analyze IR information of listed companies and use it to make investment decisions. For example, investors can review the contents of financial results briefings in text format and grasp important keywords and figures. Furthermore, by organizing and analyzing industry information and mid-term business plans, investors can evaluate overall industry trends and the future prospects of companies.In addition, by using the online chat function, you can obtain information directly from company representatives, allowing you to make investment decisions based on more reliable information.

[0055] The text converter can estimate the speaker's emotions and add tags to the text that indicate changes in emotion. For example, the text converter uses a generative AI to analyze video and audio content and estimate the speaker's emotions in real time. For example, it analyzes the speaker's tone of voice, speed, and facial expressions and adds tags to the text that indicate changes in emotion. The text converter also automatically adds tags to the converted content that indicate the intensity and type of the speaker's emotion. For example, emotions such as joy, sadness, and surprise are quantified and inserted into the text. The text converter also uses an emotion estimation function to add tags to the text that indicate changes in the speaker's emotion. For example, by adding an "emphasis" tag to parts the speaker wants to emphasize, important points are made clear. In this way, adding tags that indicate changes in the speaker's emotion deepens understanding of the text.

[0056] The text conversion unit allows the generation AI to automatically add footnotes and references to the converted content, providing supplemental information to deepen understanding. For example, the generation AI analyzes the converted content and automatically adds relevant footnotes and references. For example, detailed explanations and related literature are inserted for specific terms and concepts. The text conversion unit also allows the generation AI to automatically provide supplemental information to the converted data. For example, sources and references are added for specific data and statistics. The text conversion unit also analyzes the converted content and automatically provides supplemental information to deepen understanding. For example, it links to research papers and articles related to a specific topic. This provides supplemental information to deepen understanding of the text.

[0057] The text conversion unit can have a function to automatically convert the text data into a different format. For example, the generation AI analyzes the text data and automatically converts it into a presentation slide format. For example, it summarizes important points and keywords in slides. The text conversion unit also has a function to automatically convert the text data into a report format. For example, it divides the text into chapters and organizes it using headings and bullet points. The text conversion unit also analyzes the text data and automatically converts it into a different format. For example, it converts the text into an infographic or dashboard format. This automatic conversion into a different format makes the data easier to use.

[0058] The text conversion unit can automatically translate the text data into different languages, making it possible to accommodate international investors. For example, the text conversion unit has a generation AI analyze the text data and automatically translate it into different languages. For example, it supports multiple languages ​​such as English, Japanese, and Chinese. The text conversion unit also automatically translates the text data to accommodate international investors. For example, it provides the translated text to a multilingual platform. The text conversion unit also has a function to analyze the text data converted by the generation AI and automatically translate it into different languages. For example, it displays the translated text in real time. This makes it possible to accommodate international investors by automatically translating it into different languages.

[0059] The text conversion unit can have a function to automatically convert the text data into infographics that are easy to understand visually. For example, the generation AI in the text conversion unit analyzes the text data and automatically converts it into infographics that are easy to understand visually. For example, important data and keywords are displayed in graphs and charts. The text conversion unit also has a function to automatically convert the text data into infographics. For example, the text is visually represented using diagrams and icons. The text conversion unit also has a function to automatically convert the text data into infographics that are easy to understand visually. For example, the flow and relationships of data are illustrated. This automatic conversion into infographics that are easy to understand visually deepens understanding of the data.

[0060] The text conversion unit can use the emotion estimation function to collect the user's emotional response to the text data in real time and dynamically adjust the content of the text. The text conversion unit, for example, uses the emotion estimation function to collect the user's emotional response to the text data in real time. For example, the text conversion unit analyzes the user's facial expressions and voice and calculates an emotion score. The text conversion unit also builds a system that dynamically adjusts the content of the text based on the user's emotional response data. For example, it highlights parts with strong positive emotions. The text conversion unit also collects emotion estimation data in real time and dynamically adjusts the content of the text. For example, it changes the expression of the text in response to changes in the user's emotions. This makes it possible to provide more appropriate information by dynamically adjusting the content of the text based on the user's emotional response.

[0061] The keyword extraction unit can automatically link related past data and trends to extracted keywords and numbers, providing background information. For example, the keyword extraction unit automatically links related past data and trends to keywords and numbers extracted by the generation AI. For example, it displays past performance data and market trends. The keyword extraction unit also builds a system that automatically provides related background information to extracted keywords and numbers. For example, it links related news articles and research papers. The keyword extraction unit also automatically links related past data and trends to keywords and numbers extracted by the generation AI. For example, it displays past financial results data and industry trends. This allows for linking related past data and trends to provide background information and deepen understanding.

[0062] The keyword extraction unit allows the generation AI to automatically generate graphs and charts based on the extracted keywords and numbers, thereby visually emphasizing the data. The keyword extraction unit, for example, automatically generates graphs and charts based on the keywords and numbers extracted by the generation AI. For example, sales figures and profit margins are displayed as bar graphs or pie charts. The keyword extraction unit also builds a system in which the generation AI automatically generates graphs and charts to visually emphasize the extracted keywords and numbers. For example, important data is displayed as a line graph. The keyword extraction unit also automatically generates graphs and charts based on the keywords and numbers extracted by the generation AI. For example, performance data is displayed as a heat map or scatter plot. In this way, generating graphs and charts can visually emphasize the data and deepen understanding.

[0063] The keyword extraction unit can use the emotion estimation function to analyze the user's emotional response to the extracted keywords and numbers and generate a summary that elicits a positive response. The keyword extraction unit, for example, uses the emotion estimation function to analyze the user's emotional response to the extracted keywords and numbers. For example, it analyzes the user's facial expressions and voice and calculates an emotion score. The keyword extraction unit also builds a system that generates a summary that elicits a positive response based on the user's emotional response data. For example, it highlights parts that show strong positive emotions. The keyword extraction unit also collects emotion estimation data in real time and generates a summary that elicits a positive response. For example, it changes the expression of the summary according to changes in the user's emotions. In this way, a positive response can be elicited by generating a summary based on the user's emotional response.

[0064] The data reduction unit can use the emotion estimation function to evaluate market sentiment toward a company's strategy when analyzing industry information or a medium-term management plan. For example, the data reduction unit uses the emotion estimation function to evaluate market sentiment when the generation AI analyzes industry information or a medium-term management plan. For example, it analyzes news articles and social media posts and calculates a market sentiment score. The data reduction unit also uses the emotion estimation function to build a system that evaluates market sentiment toward a company's strategy. For example, it highlights strategies with strong positive sentiment. The data reduction unit also evaluates market sentiment based on emotion estimation data when the generation AI analyzes industry information or a medium-term management plan. For example, it collects users' emotional reactions in real time and reflects them in the evaluation of the strategy. In this way, the effectiveness of a strategy can be understood by evaluating market sentiment toward a company's strategy.

[0065] The data reduction unit can automatically compare with industry leader companies and generate a report that clearly shows relative strengths and weaknesses. In the data reduction unit, for example, the generation AI analyzes industry information and automatically generates a report that clearly shows relative strengths and weaknesses in comparison with leader companies. For example, it compares sales and market share. The data reduction unit also has a function to automatically compare with industry leader companies and generate a report that clearly shows relative strengths and weaknesses. For example, it compares technological capabilities and brand power. In addition, the data reduction unit uses the generation AI to analyze industry information and generate a report that clearly shows relative strengths and weaknesses in comparison with leader companies. For example, it compares financial indicators and growth rates. This makes it possible to clearly show relative strengths and weaknesses by comparing with leader companies.

[0066] The data reduction unit can be equipped with a function for monitoring the progress of the mid-term management plan in real time and evaluating the degree of achievement of the plan. The data reduction unit, for example, has a function for the generation AI to monitor the progress of the mid-term management plan in real time and evaluate the degree of achievement of the plan. For example, it displays the goal achievement rate and progress status in a graph. The data reduction unit also builds a system for monitoring the progress of the mid-term management plan in real time and evaluates the degree of achievement of the plan. For example, it displays the progress status of each goal on a dashboard. The data reduction unit also has a function for the generation AI to monitor the progress of the mid-term management plan in real time and evaluate the degree of achievement of the plan. For example, it automatically collects progress data and generates an evaluation report. This makes it possible to monitor the progress of the mid-term management plan in real time and evaluate the degree of achievement of the plan, thereby understanding the progress of the plan.

[0067] The data reduction department can compare industry information and mid-term business plans with data from different regions and markets to provide analysis from a global perspective. For example, the generation AI in the data reduction department analyzes industry information and mid-term business plans and compares them with data from different regions and markets. For example, it compares trends in the Asian market with those in the European and American markets. The data reduction department also builds a system that collects data from different regions and markets and compares it with industry information and mid-term business plans. For example, it compares economic indicators and market trends by region. The data reduction department also analyzes industry information and mid-term business plans with the generation AI and provides analysis from a global perspective. For example, it compares them with competitors in different regions. This makes it possible to provide analysis from a global perspective by comparing them with data from different regions and markets.

[0068] The data reduction unit can automatically predict industry trends using the generation AI and generate reports showing future market trends. In the data reduction unit, for example, the generation AI analyzes industry information and automatically predicts trends. For example, it predicts future market trends based on past data and generates reports. The data reduction unit also has a function for predicting industry trends and generates reports showing future market trends. For example, it predicts technological innovations and changes in consumer behavior. In addition, the data reduction unit uses the generation AI to analyze industry information and automatically predict trends and generate reports showing future market trends. For example, it predicts demand forecasts and changes in the competitive environment. In this way, future market trends can be grasped by predicting industry trends and generating reports showing future market trends.

[0069] The data reduction unit can use the emotion estimation function to collect investors' emotional reactions to industry information and medium-term management plans, and dynamically adjust the analysis results based on the collected data. The data reduction unit, for example, uses the emotion estimation function to collect investors' emotional reactions to industry information and medium-term management plans. For example, it analyzes investors' facial expressions and voices to calculate an emotion score. The data reduction unit also builds a system that dynamically adjusts the analysis results based on the investors' emotional reaction data. For example, it highlights areas with strong positive emotions. The data reduction unit also collects emotion estimation data in real time, and dynamically adjusts the analysis results based on investors' emotional reactions to industry information and medium-term management plans. For example, it updates the analysis results in response to changes in investors' emotions. This makes it possible to provide more appropriate information by dynamically adjusting the analysis results based on investors' emotional reactions.

[0070] The chat unit can have a function in which the generation AI performs sentiment analysis on the chat content in real time and suggests an appropriate response. For example, the chat unit has the generation AI analyze the chat content and perform sentiment analysis in real time. For example, it analyzes the tone and content of the user's message and calculates an sentiment score. The chat unit also builds a system that suggests appropriate responses based on the results of the sentiment analysis. For example, if the user is feeling anxious, it suggests a message to reassure them. The chat unit also has a function in which the generation AI analyzes the chat content, performs sentiment analysis in real time, and suggests appropriate responses. For example, it automatically generates responses based on the user's emotions. This enables more effective communication by performing sentiment analysis on the chat content in real time and suggesting appropriate responses.

[0071] The chat unit can have a function to automatically analyze chat history and extract and provide useful information from past interactions. For example, the chat unit uses a generation AI to analyze chat history and automatically extract useful information from past interactions. For example, related information is provided based on past questions and answers. The chat unit also builds a system that analyzes chat history, extracts useful information, and provides it. For example, it extracts important points from past interactions and presents them to the user. The chat unit also has a function to use a generation AI to analyze chat history and automatically extract and provide useful information from past interactions. For example, it provides related materials and links based on past interactions. This enables more effective information provision by analyzing chat history and extracting and providing useful information from past interactions.

[0072] The chat unit can have a function to automatically summarize chat content and highlight important points. For example, the generation AI in the chat unit analyzes chat content and automatically summarizes it. For example, it may condense long messages into a few lines. The chat unit may also build a system that summarizes chat content and highlights important points. For example, it may highlight important keywords and phrases. The chat unit may also have a function to analyze chat content and automatically summarize it and highlight important points. For example, it may highlight the summary content. This makes it easier to understand the information by summarizing chat content and highlighting important points.

[0073] The chat unit enables the chat function to support voice calls and video calls, thereby providing a wider variety of communication methods. For example, the chat unit uses a generation AI to analyze the chat function and enable it to support voice calls and video calls. For example, a function to switch from text chat to voice calls or video calls is added. The chat unit also builds a system to support voice and video calls. For example, it uses voice recognition and video analysis technology to analyze the content of calls in real time. The chat unit also analyzes the chat function using a generation AI and enables it to support voice and video calls. For example, it provides an interface that allows the user to select voice calls or video calls. This allows it to support voice and video calls, thereby providing a wider variety of communication methods.

[0074] The chat unit can translate chat content into different languages ​​in real time, facilitating communication with international investors. For example, the chat unit uses a generation AI to analyze chat content and translate it into different languages ​​in real time. For example, it supports multiple languages ​​such as English, Japanese, and Chinese. The chat unit also translates chat content in real time, building a system that facilitates communication with international investors. For example, it displays translated messages in real time. The chat unit also has a function where the generation AI analyzes chat content and translates it into different languages ​​in real time. For example, it provides translated messages to a multilingual platform. This allows chat content to be translated into different languages ​​in real time, facilitating communication with international investors.

[0075] The chat unit can use the emotion estimation function to monitor the emotions of users during chat in real time and encourage human intervention at appropriate times. The chat unit, for example, uses the emotion estimation function to monitor the emotions of users during chat in real time. For example, it analyzes the user's facial expressions and voice and calculates an emotion score. The chat unit also builds a system that encourages human intervention at appropriate times based on the user's emotional response data. For example, support staff intervene if the user feels anxious. The chat unit also collects emotion estimation data in real time, monitors the user's emotions during chat, and encourages human intervention at appropriate times. For example, support staff responds according to changes in the user's emotions. This enables more effective support by monitoring the user's emotions in real time and encouraging human intervention at appropriate times.

[0076] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0077] The text conversion unit allows the generation AI to automatically add footnotes and references to the converted content, providing supplementary information for deeper understanding. For example, the generation AI analyzes the converted content and automatically adds relevant footnotes and references. Detailed explanations and related literature can be inserted for specific terms and concepts. It is also possible to add sources and references for specific data and statistics. Furthermore, by linking to research papers and articles related to specific topics, supplementary information can be provided to deepen understanding of the text.

[0078] The text conversion unit can be equipped with a function to automatically convert the converted data into different formats. For example, the generation AI can analyze the converted data and automatically convert it into a presentation slide format. Important points and keywords can be summarized in the slides. It can also be equipped with a function to automatically convert the converted data into a report format. The text can be divided into chapters and organized using headings and bullet points. Furthermore, converting the text into infographics or dashboard formats makes the data easier to use.

[0079] The text conversion unit can automatically translate the converted data into different languages, making it possible to accommodate international investors. For example, the generation AI analyzes the converted data and automatically translates it into different languages. It can support multiple languages, including English, Japanese, and Chinese. It is also possible to provide the translated text on a multilingual platform. Furthermore, the translated text can be displayed in real time, making it possible to accommodate international investors.

[0080] The text conversion unit can be equipped with a function to automatically convert the converted text data into infographics that are easy to understand visually. For example, the generation AI analyzes the converted text data and automatically converts it into infographics that are easy to understand visually. Important data and keywords can be displayed in graphs and charts. It is also possible to visually represent text using diagrams and icons. Furthermore, by illustrating the flow and relationships of data, it is possible to automatically convert it into infographics that are easy to understand visually.

[0081] The text conversion unit can use the emotion estimation function to collect the user's emotional response to the text data in real time and dynamically adjust the content of the text. For example, the emotion estimation function can be used to collect the user's emotional response to the text data in real time. The user's facial expressions and voice can be analyzed to calculate an emotion score. It is also possible to build a system that dynamically adjusts the content of the text based on the user's emotional response data. By highlighting parts with strong positive emotions, more appropriate information can be provided.

[0082] The keyword extraction unit can automatically link related past data and trends to extracted keywords and figures to provide background information. For example, related past data and trends can be automatically linked to keywords and figures extracted by the generation AI. Past performance data and market trends can be displayed. It is also possible to build a system that provides background information by linking related news articles and research papers. Furthermore, displaying past financial data and industry trends can provide background information and deepen understanding.

[0083] The keyword extraction unit can use the emotion estimation function to analyze the user's emotional response to the extracted keywords and numbers and generate summaries that elicit positive responses. For example, the emotion estimation function can be used to analyze the user's emotional response to the extracted keywords and numbers. The user's facial expressions and voice can be analyzed to calculate an emotion score. It is also possible to build a system that generates summaries that elicit positive responses based on the user's emotional response data. By highlighting parts with strong positive emotions, summaries can be generated that reflect the user's emotional changes.

[0084] The data reduction unit can automatically compare companies with industry leaders and generate reports that clearly show their relative strengths and weaknesses. For example, the generation AI analyzes industry information and automatically generates a report that clearly shows their relative strengths and weaknesses compared to the leader. It is possible to compare sales and market share. It is also possible to compare technological capabilities and brand power. Furthermore, by comparing financial indicators and growth rates, it is possible to clearly show their relative strengths and weaknesses compared to the leader.

[0085] The data reduction unit can use the emotion estimation function to collect investors' emotional reactions to industry information and mid-term management plans, and dynamically adjust the analysis results based on that information. For example, the emotion estimation function can be used to collect investors' emotional reactions to industry information and mid-term management plans. The emotion scores can be calculated by analyzing the investors' facial expressions and voices. It is also possible to build a system that dynamically adjusts the analysis results based on the investors' emotional reaction data. By highlighting areas with strong positive emotions, it is possible to provide analysis results that correspond to changes in investors' emotions.

[0086] The chat section can be equipped with a function that allows the generation AI to perform real-time emotional analysis of chat content and suggest appropriate responses. For example, the generation AI can analyze chat content and perform emotional analysis in real time. It can analyze the tone and content of the user's message and calculate an emotional score. It is also possible to build a system that suggests appropriate responses based on the results of the emotional analysis. If the user is feeling anxious, it can suggest a reassuring message. Furthermore, automatically generating responses according to the user's emotions enables more effective communication.

[0087] The processing flow of the second embodiment will be briefly explained below.

[0088] Step 1: The text conversion unit converts video or audio content from a listed company's financial results briefing or general shareholders' meeting into text. For example, the generation AI uses speech recognition technology to convert audio data into text data. The generation AI can also analyze video content and output it as text. The generation AI can also convert live streaming audio into text in real time. Step 2: The keyword extraction unit extracts and highlights important keywords and numbers from the data converted by the text conversion unit. For example, the generation AI analyzes the text data and extracts keywords based on frequency and contextual importance. The generation AI can also highlight the extracted keywords by changing the color or font, underlining, etc. The generation AI can also use a summary function to summarize long texts in a shorter form. Step 3: The data organizer organizes and analyzes the data extracted by the keyword extractor. For example, the generation AI classifies the data and uses analytical algorithms to analyze trends and patterns in the data. The generation AI can also collect, organize, and analyze data such as industry information and medium-term management plans. The generation AI can also collect the latest news and trends related to a specific industry and provide them to investors. Step 4: The chat section has a function that allows investors to communicate online with IR personnel and management of listed companies through chat. For example, investors can freely ask questions based on their interests and concerns. The chat section also allows for human intervention according to the plan, allowing investors to receive more detailed information and expert advice. The chat section can also support text chat, voice chat, video chat, and other formats.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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).

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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).

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0123] 7, a 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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."

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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, to avoid confusion and 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.

[0155] 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]

[0156] 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 text conversion department that converts video or audio content from financial results briefings or general shareholders' meetings of listed companies into text; a keyword extraction unit that extracts important keywords and numbers from the data converted into text by the text conversion unit and highlights them; a data organizing unit that organizes and analyzes the data extracted by the keyword extracting unit; It also has a chat section where users can communicate online with IR staff and managers of listed companies. A system characterized by:

2. The text conversion unit Estimate the speaker's emotions and add tags to the text to indicate changes in emotions 2. The system of claim 1.

3. The text conversion unit Automatically translate text data into different languages ​​to accommodate international investors 2. The system of claim 1.

4. The keyword extraction unit Automatically link relevant historical data and trends to extracted keywords and figures to provide context 2. The system of claim 1.

5. The data reduction unit Evaluate market sentiment toward a company's strategy when analyzing industry information and mid-term business plans 2. The system of claim 1.

6. The chat section The AI ​​generative system analyzes the sentiment of chat content in real time and suggests appropriate responses.

2. The system of claim 1.

7. The text conversion unit Collecting users' emotional responses to textual data in real time and dynamically adjusting the content of the text 2. The system of claim 1.

8. The chat section Monitor users' emotions in real time during chats and prompt human intervention at the appropriate time 2. The system of claim 1.

Images