system

Abstract

The system according to the embodiment aims to effectively utilize open data and web data to analyze and provide market data based on user questions. [Solution] A system according to an embodiment includes a collection unit, a learning unit, a reception unit, an analysis unit, and a provision unit. The collection unit collects data. The learning unit accumulates and learns the data collected by the collection unit. The reception unit receives questions from users. The analysis unit analyzes the data based on the questions received by the reception unit. The provision unit provides the analysis results obtained by the analysis unit.

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 have not effectively utilized open data and web data to analyze market data and provide it to users, and there is room for improvement.

[0005] The system according to the embodiment aims to effectively utilize open data and web data to analyze and provide market data based on user questions. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a learning unit, a reception unit, an analysis unit, and a provision unit. The collection unit collects data. The learning unit accumulates and learns the data collected by the collection unit. The reception unit receives questions from users. The analysis unit analyzes the data based on the questions received by the reception unit. The provision unit provides the analysis results obtained by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can effectively utilize open data and web data to analyze and provide market data based on user questions. [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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[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) A data analysis system according to an embodiment of the present invention uses a generation AI to accumulate and learn open data, such as data from government agencies, investor relations, financial statements, and DS.INSIGHT, as well as web data held by specific companies. This system enables the exchange of higher-resolution market data with the generation AI, allowing users to generate graphs and discover the analytical data they desire through the generation AI. For example, the data analysis system collects open data, such as data from government agencies, investor relations, financial statements, and DS.INSIGHT, as well as web data held by specific companies. The generation AI then accumulates and learns the collected data. The generation AI analyzes this data and provides the market data desired by the user. The user inputs a question to the generation AI in natural language, and the generation AI analyzes the input question and extracts relevant information from the accumulated data. The system then generates a graph based on the extracted information and provides it to the user. This system allows users to easily obtain and analyze market data. For example, a specific company's financial data and market trends can be visually confirmed in a graph. Furthermore, the generation AI responds to user questions in real time, enabling rapid data acquisition. Furthermore, generative AI can learn from users' past question history and provide more accurate answers, allowing data analysis systems to support business decision-making and improve competitiveness.

[0029] A data analysis system according to an embodiment includes a collection unit, a learning unit, a reception unit, an analysis unit, and a provision unit. The collection unit collects data. Examples of the collected data include, but are not limited to, text data, numerical data, and image data. The collection unit collects open data from government agencies, investor relations, financial statements, DS.INSIGHT, and other sources, as well as web data held by specific companies. The learning unit accumulates and learns the data collected by the collection unit. The accumulation and learning can be performed using, for example, deep learning or reinforcement learning, but is not limited to these examples. For example, the learning unit analyzes and learns the collected data using a generative AI. The reception unit accepts user questions. Examples of the question format include, but are not limited to, voice input and text input. For example, the reception unit accepts questions entered by the user in natural language. The analysis unit analyzes the data based on the questions accepted by the reception unit. The analysis can be performed using, for example, statistical analysis or a machine learning algorithm, but is not limited to these examples. For example, the analysis unit uses a generation AI to extract relevant information from the accumulated data. The provision unit provides the analysis results obtained by the analysis unit. The format of the provided results includes, but is not limited to, a report format or a graph format. For example, the provision unit uses the generation AI to generate a graph based on the extracted information and provide it to the user. This allows the data analysis system according to the embodiment to efficiently collect data, accumulate and learn data, accept questions, analyze data, and provide results.

[0030] The data analysis system includes a history learning unit that learns a user's past question history. The history learning unit learns the user's past question history. The question history includes, for example, a text log and an audio log, but is not limited to these examples. For example, the history learning unit analyzes and learns the content of questions previously asked by the user. The history learning unit can also analyze question trends based on the user's question history. For example, the history learning unit identifies patterns of questions frequently asked by the user and learns based on those patterns. Furthermore, the history learning unit can determine the priority of questions based on the user's question history. For example, the history learning unit evaluates the importance of questions previously asked by the user and prioritizes learning questions with high importance. In this way, learning the past question history enables more accurate answers.

[0031] The data analysis system includes a graph generation unit that generates graphs. The graph generation unit generates graphs based on data. Types of graphs that can be generated include, but are not limited to, bar graphs, line graphs, and pie charts. For example, the graph generation unit analyzes data using a generation AI to generate an appropriate graph. The graph generation unit can also generate customized graphs in response to user requests. For example, the graph generation unit generates graphs based on a data range and display format specified by the user. Furthermore, the graph generation unit has a function for visually displaying the generated graphs. For example, the graph generation unit displays the generated graphs on a screen so that the user can visually confirm them. This allows for visual confirmation of the data.

[0032] The data analysis system includes a real-time response unit that responds in real time. The real-time response unit responds to user questions in real time. Response formats include, but are not limited to, text responses and voice responses. For example, the real-time response unit uses a generation AI to analyze the user's questions and respond immediately. The real-time response unit can also provide an appropriate response by referring to the user's past question history. For example, the real-time response unit can provide relevant information based on the content of questions the user has previously asked. Furthermore, the real-time response unit can adjust the content of the response according to the user's current situation. For example, the real-time response unit can prioritize providing relevant information based on the user's current areas of interest. This enables rapid data acquisition.

[0033] The collection unit can collect data from government agencies, investor relations, financial statements, open data, and web data held by specific companies. For example, the collection unit collects data from public databases of government agencies. The collection unit can also collect data from corporate websites that provide investor relations information. The collection unit can also collect corporate financial statements and store them in a database. For example, the collection unit can automatically download corporate financial statements and store them in a database. The collection unit can also collect data from open data platforms such as DS.INSIGHT. For example, the collection unit can obtain data using the DS.INSIGHT API. This makes it possible to collect data from a variety of data sources.

[0034] The analysis unit can analyze the accumulated data based on the user's question and extract related information. The analysis unit can extract information related to the user's question using, for example, keyword extraction technology. The analysis unit can also identify topics related to the user's question using topic modeling technology. The analysis unit can also analyze the intent of the user's question and extract related information using natural language processing technology. For example, the analysis unit can analyze the user's question and search for related data. The analysis unit can also extract related information from a database based on the user's question. This makes it possible to provide appropriate information in response to the user's question.

[0035] When collecting data, the collection unit can analyze the user's past data usage history and select a collection method. The collection unit, for example, analyzes the user's past data usage history and selects the optimal data collection method. For example, the collection unit prioritizes collecting data sources that the user has frequently used in the past. The collection unit can also optimize data to be collected in a specific time period based on the user's past data usage history. For example, the collection unit prioritizes collecting data that the user frequently uses in a specific time period. The collection unit can also select the most efficient collection method based on the user's past data usage history. For example, the collection unit evaluates the reliability of data sources that the user has used in the past and prioritizes collecting reliable data sources. This enables optimal data collection based on the user's past data usage history.

[0036] The collection unit can perform filtering based on the user's current areas of interest when collecting data. For example, the collection unit analyzes the user's current areas of interest and prioritizes collecting related data. For example, the collection unit prioritizes collecting data related to areas in which the user is currently interested. The collection unit can also filter unnecessary data based on the user's current areas of interest. For example, the collection unit filters out data in areas in which the user is not currently interested so as not to collect it. The collection unit can also dynamically adjust the data to be collected when the user's areas of interest change. For example, the collection unit adjusts the type and amount of data to be collected when the user's areas of interest change. This makes it possible to collect data based on the user's areas of interest.

[0037] The collection unit can evaluate the reliability of data when collecting data and prioritize collecting highly reliable data. For example, the collection unit evaluates the reliability of a data source and prioritizes collecting highly reliable data. For example, the collection unit checks the consistency and accuracy of data to evaluate the reliability of the data source. The collection unit can also determine the priority of data to be collected based on the reliability of the data. For example, the collection unit prioritizes collecting highly reliable data and filters out unreliable data. The collection unit can also not collect unreliable data. For example, if the reliability of a data source is low, the collection unit sets the collection unit not to collect that data. This improves the quality of data by preferentially collecting highly reliable data.

[0038] When collecting data, the collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. The collection unit, for example, prioritizes collecting data related to the user's current location. For example, the collection unit collects relevant data based on the user's geographical location information. The collection unit can also filter unnecessary data based on the user's geographical location information. For example, the collection unit filters out data that is not related to the user's current location so as not to collect it. The collection unit can also dynamically adjust the data to be collected when the user's location information changes. For example, the collection unit adjusts the type and amount of data to be collected when the user's location information changes. This makes it possible to collect data based on the user's geographical location information.

[0039] When collecting data, the collection unit can analyze the user's social media activities and collect related data. For example, the collection unit analyzes the content of the user's posts on social media and collects related data. For example, the collection unit analyzes the content of the user's posts on social media and collects related data. The collection unit can also collect related data by referring to the activities of the user's friends on social media. For example, the collection unit collects related data based on information shared by the user's friends on social media. The collection unit can also collect related data based on the user's check-in information on social media. For example, the collection unit collects data related to places where the user checked in on social media. This makes it possible to collect data based on the user's social media activities.

[0040] The collection unit can customize the collection method by reflecting the user's past feedback when collecting data. The collection unit, for example, adjusts the type of data to be collected based on the user's past feedback. For example, the collection unit changes the type of data to be collected based on the user's feedback. The collection unit can also optimize the collection method based on the user's feedback. For example, the collection unit improves the collection method by reflecting the user's feedback. The collection unit can also determine the priority of data to be collected based on the user's feedback. For example, the collection unit prioritizes collecting data with high importance based on the user's feedback. This makes it possible to customize the collection method based on the user's past feedback.

[0041] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, selects an optimal learning algorithm based on past learning data. For example, the learning unit analyzes past learning data and selects an optimal algorithm. The learning unit can also adjust parameters of the learning algorithm from past learning data. For example, the learning unit optimizes parameters of the algorithm based on past learning data. The learning unit can also improve the accuracy of the learning algorithm by referring to past learning data. For example, the learning unit improves the accuracy of the algorithm based on past learning data. This makes it possible to optimize the learning algorithm based on past learning data.

[0042] The learning unit can analyze data fluctuations during learning and adjust the update frequency of the learning data. The learning unit, for example, analyzes data fluctuations and adjusts the update frequency of the learning data. For example, the learning unit increases the update frequency of the learning data when data fluctuations are large. The learning unit can also decrease the update frequency of the learning data when data fluctuations are small. For example, the learning unit sets a low update frequency when data fluctuations are small. The learning unit can also analyze data fluctuations in real time and dynamically adjust the update frequency of the learning data. For example, the learning unit monitors data fluctuations in real time and adjusts the update frequency as necessary. This makes it possible to adjust the update frequency of the learning data in accordance with data fluctuations.

[0043] During learning, the learning unit can integrate information from different data sources to expand the learning data. For example, the learning unit integrates information from different data sources to expand the learning data. For example, the learning unit collects and integrates data from multiple data sources. The learning unit can also compare data from different data sources and select optimal data. For example, the learning unit compares data from different data sources and selects high-quality data. The learning unit can also increase the diversity of the learning data based on information from different data sources. For example, the learning unit collects data from different industries or fields and reflects it in the learning data. In this way, the diversity of the learning data is improved by integrating information from different data sources.

[0044] During learning, the learning unit can weight the learning data based on the time of data submission. The learning unit weights the learning data based on, for example, the time of data submission. For example, the learning unit assigns a high weight to the most recent data. The learning unit can also assign a low weight to older data. For example, the learning unit sets a low weight for older data. The learning unit can also dynamically adjust the weighting of the learning data based on the time of data submission. For example, the learning unit adjusts the weighting in real time based on the time of data submission. This makes it possible to weight the learning data based on the time of data submission.

[0045] The learning unit can adjust the learning algorithm by reflecting user feedback during learning. The learning unit, for example, adjusts parameters of the learning algorithm based on user feedback. For example, the learning unit analyzes user feedback and optimizes parameters of the algorithm. The learning unit can also improve the accuracy of the learning algorithm by reflecting user feedback. For example, the learning unit improves the accuracy of the algorithm based on user feedback. The learning unit can also optimize the learning algorithm based on user feedback. For example, the learning unit optimizes the algorithm by reflecting user feedback. This makes it possible to adjust the learning algorithm based on user feedback.

[0046] The learning unit can incorporate data from different industries during learning to increase the diversity of learning. For example, the learning unit incorporates data from different industries to increase the diversity of the learning data. For example, the learning unit collects data from multiple industries and reflects it in the learning data. The learning unit can also compare data from different industries and select the most suitable data. For example, the learning unit compares data from different industries and selects high-quality data. The learning unit can also improve the accuracy of the learning algorithm based on data from different industries. For example, the learning unit improves the accuracy of the algorithm based on data from different industries. In this way, by incorporating data from different industries, the diversity of learning is increased.

[0047] When accepting a question, the acceptance unit can select the optimal acceptance method by referring to the user's past question history. The acceptance unit, for example, analyzes the user's past question history and selects the optimal acceptance method. For example, the acceptance unit automatically displays questions that the user has frequently asked in the past as candidates. The acceptance unit can also preferentially suggest input methods (voice, text, etc.) that the user has used in the past. For example, the acceptance unit suggests the optimal acceptance method based on the input methods that the user has used in the past. The acceptance unit can also predict and suggest questions that will be asked in a specific time period based on the user's past question history. For example, the acceptance unit predicts and suggests questions that will be asked in a specific time period based on the user's past question history. This makes it possible to accept optimal questions based on the user's past question history.

[0048] When receiving questions, the reception unit can determine the priority of the questions based on the user's current areas of interest. For example, the reception unit analyzes the user's current areas of interest and prioritizes receiving related questions. For example, the reception unit prioritizes receiving questions related to areas in which the user is currently interested. The reception unit can also filter unnecessary questions based on the user's current areas of interest. For example, the reception unit filters out questions in areas in which the user is not currently interested and does not accept them. The reception unit can also dynamically adjust the questions to be received when the user's areas of interest change. For example, the reception unit adjusts the types and priorities of questions to be received when the user's areas of interest change. This makes it possible to determine the priority of questions based on the user's areas of interest.

[0049] When accepting a question, the acceptance unit can select the optimal acceptance means depending on the user's input method. For example, when the user inputs a question by voice, the acceptance unit accepts the question using voice recognition. For example, the acceptance unit uses voice recognition technology to convert the user's voice into text and accepts the question. Furthermore, when the user inputs a question by text, the acceptance unit can also accept the question using text analysis. For example, the acceptance unit uses text analysis technology to analyze the user's text input and accept the question. Furthermore, when the user inputs a question by image, the acceptance unit can also accept the question using image analysis. For example, the acceptance unit uses image analysis technology to analyze the user's image input and accept the question. This makes it possible to accept the question optimally depending on the user's input method.

[0050] When receiving a question, the reception unit can automatically suggest candidate locations by referring to the user's past travel history. The reception unit, for example, analyzes the user's past travel history and suggests optimal candidate locations. For example, the reception unit automatically displays places that the user has frequently visited in the past as candidate locations. The reception unit can also predict places that the user will visit on specific days of the week or time periods and suggest them as candidate locations. For example, the reception unit predicts and suggests places that the user will visit on specific days of the week or time periods based on the user's past travel history. The reception unit can also analyze the user's past travel patterns and suggest optimal candidate locations. For example, the reception unit analyzes the user's past travel patterns and identifies optimal candidate locations. This makes it possible to automatically suggest candidate locations based on the user's past travel history.

[0051] When receiving a question, the reception unit can make a suggestion based on the schedule by referring to the user's calendar information. The reception unit, for example, references the user's calendar information and makes a suggestion based on the schedule. For example, the reception unit references the schedule registered in the user's calendar and automatically sets the departure point and destination. The reception unit can also suggest locations related to a specific event as candidate locations from the user's calendar information. For example, the reception unit suggests a location related to a specific event based on the user's calendar information. The reception unit can also suggest an optimal route that matches the schedule based on the user's calendar information. For example, the reception unit references the user's calendar information and suggests an optimal route. This makes it possible to suggest a schedule based on the user's calendar information.

[0052] When receiving a question, the reception unit can analyze the user's social media activity and suggest related places. The reception unit, for example, analyzes the content of the user's social media posts and suggests related places. For example, the reception unit analyzes the content of the user's social media posts and suggests related places as candidate locations. The reception unit can also suggest related places by referring to the activity of the user's friends on social media. For example, the reception unit can suggest related places based on places where the user's friends have checked in on social media. The reception unit can also suggest related places based on the user's social media check-in information. For example, the reception unit can suggest related places based on places where the user has checked in on social media. This makes it possible to suggest related places based on the user's social media activity.

[0053] The analysis unit can adjust the level of detail of the analysis based on the importance of the data during analysis. The analysis unit, for example, evaluates the importance of the data and performs a detailed analysis on data with high importance. For example, the analysis unit performs a detailed analysis based on the importance of the data. The analysis unit can also perform a simplified analysis on data with low importance. For example, the analysis unit performs a simplified analysis on data with low importance. The analysis unit can also dynamically adjust the level of detail of the analysis based on the importance of the data. For example, the analysis unit adjusts the level of detail of the analysis in real time based on the importance of the data. This makes it possible to adjust the level of detail of the analysis according to the importance of the data.

[0054] During analysis, the analysis unit can apply different analysis algorithms depending on the category of data. The analysis unit, for example, selects the optimal analysis algorithm depending on the category of data. For example, the analysis unit applies a specific analysis algorithm to financial data. The analysis unit can also apply a different analysis algorithm to market data. For example, the analysis unit applies a different analysis algorithm to market data. The analysis unit can also select the optimal analysis algorithm depending on the category of data. For example, the analysis unit selects the optimal analysis algorithm depending on the category of data, such as text data, numerical data, or image data. This makes it possible to apply the optimal analysis algorithm depending on the category of data.

[0055] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The analysis unit, for example, adjusts the parameters of the analysis algorithm based on the user's past analysis results. For example, the analysis unit analyzes the user's past analysis results and optimizes the parameters of the algorithm. The analysis unit can also improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis unit improves the accuracy of the algorithm based on the user's past analysis results. The analysis unit can also optimize the analysis method by reflecting the user's past analysis results. For example, the analysis unit optimizes the analysis method based on the user's past analysis results. This makes it possible to improve the analysis accuracy based on the user's past analysis results.

[0056] During analysis, the analysis unit can determine the priority of analysis based on the time of data submission. The analysis unit determines the priority of analysis based on, for example, the time of data submission. For example, the analysis unit sets a high priority for the most recent data. The analysis unit can also set a low priority for older data. For example, the analysis unit sets a low priority for older data. The analysis unit can also dynamically adjust the priority of analysis based on the time of data submission. For example, the analysis unit adjusts the priority in real time based on the time of data submission. This makes it possible to determine the priority of analysis based on the time of data submission.

[0057] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the data. For example, the analysis unit evaluates the relevance of the data and prioritizes the analysis of highly relevant data. For example, the analysis unit prioritizes analysis based on the relevance of the data. The analysis unit can also postpone data with low relevance. For example, the analysis unit postpones data with low relevance. The analysis unit can also dynamically adjust the order of analysis based on the relevance of the data. For example, the analysis unit adjusts the order of analysis in real time based on the relevance of the data. This makes it possible to adjust the order of analysis based on the relevance of the data.

[0058] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. For example, the analysis unit evaluates the user's level of expertise and uses detailed technical terms if the user has specialized knowledge. For example, the analysis unit uses detailed technical terms based on the user's level of expertise. The analysis unit can also use simple terms if the user does not have specialized knowledge. For example, the analysis unit uses simple terms based on the user's level of expertise. The analysis unit can also dynamically adjust the use of technical terms in the analysis according to the user's level of expertise. For example, the analysis unit adjusts the use of technical terms based on the user's level of expertise. This makes it possible to use technical terms in the analysis according to the user's level of expertise.

[0059] The providing unit can adjust the level of detail of the information provided based on the importance of the information when providing the information. For example, the providing unit evaluates the importance of the information and provides detailed information for information with high importance. For example, the providing unit provides detailed information based on the importance of the information. The providing unit can also provide simplified information for information with low importance. For example, the providing unit provides simplified information for information with low importance. The providing unit can also dynamically adjust the level of detail of the information provided based on the importance of the information. For example, the providing unit adjusts the level of detail of the information provided in real time based on the importance of the information. This makes it possible to adjust the level of detail of the information provided according to the importance of the information.

[0060] The providing unit can apply different provision algorithms depending on the category of information when providing the information. The providing unit, for example, selects an optimal provision algorithm depending on the category of information. For example, the providing unit applies a specific provision algorithm to financial information. The providing unit can also apply a different provision algorithm to market information. For example, the providing unit applies a different provision algorithm to market information. The providing unit can also select an optimal provision algorithm depending on the category of information. For example, the providing unit selects an optimal provision algorithm depending on categories such as text information, numerical information, and image information. This makes it possible to apply an optimal provision algorithm depending on the category of information.

[0061] The providing unit can improve the accuracy of provision by referring to the user's past provision results when providing the data. The providing unit, for example, adjusts parameters of the provision algorithm based on the user's past provision results. For example, the providing unit analyzes the user's past provision results and optimizes parameters of the algorithm. The providing unit can also improve the accuracy of provision by referring to the user's past provision results. For example, the providing unit improves the accuracy of the algorithm based on the user's past provision results. The providing unit can also optimize the provision method by reflecting the user's past provision results. For example, the providing unit optimizes the provision method based on the user's past provision results. This makes it possible to improve the accuracy of provision based on the user's past provision results.

[0062] The providing unit can determine the priority of provision based on the time of submission of the information at the time of provision. The providing unit determines the priority of provision based on, for example, the time of submission of the information. For example, the providing unit sets a high priority for the most recent information. The providing unit can also set a low priority for older information. For example, the providing unit sets a low priority for older information. The providing unit can also dynamically adjust the priority of provision based on the time of submission of the information. For example, the providing unit adjusts the priority in real time based on the time of submission of the information. This makes it possible to determine the priority of provision based on the time of submission of the information.

[0063] The providing unit can adjust the order of provision based on the relevance of the information at the time of provision. For example, the providing unit evaluates the relevance of the information and provides highly relevant information preferentially. For example, the providing unit provides information preferentially based on the relevance of the information. The providing unit can also postpone information with low relevance. For example, the providing unit postpones information with low relevance. The providing unit can also dynamically adjust the order of provision based on the relevance of the information. For example, the providing unit adjusts the order of provision in real time based on the relevance of the information. This makes it possible to adjust the order of provision based on the relevance of the information.

[0064] The providing unit can adjust the use of provided terminology according to the user's level of expertise when providing the information. For example, the providing unit evaluates the user's level of expertise, and uses detailed terminology if the user has expertise. For example, the providing unit uses detailed terminology based on the user's level of expertise. The providing unit can also use simple terminology if the user does not have expertise. For example, the providing unit uses simple terminology based on the user's level of expertise. The providing unit can also dynamically adjust the use of provided terminology according to the user's level of expertise. For example, the providing unit adjusts the use of terminology based on the user's level of expertise. This makes it possible to use provided terminology according to the user's level of expertise.

[0065] During history learning, the history learning unit can optimize the learning algorithm by referring to past question histories. The history learning unit, for example, selects an optimal learning algorithm based on past question histories. For example, the history learning unit analyzes past question histories and selects an optimal algorithm. The history learning unit can also adjust parameters of the learning algorithm based on past question histories. For example, the history learning unit optimizes parameters of the algorithm based on past question histories. The history learning unit can also improve the accuracy of the learning algorithm by referring to past question histories. For example, the history learning unit improves the accuracy of the algorithm based on past question histories. This makes it possible to optimize the learning algorithm based on past question histories.

[0066] During history learning, the history learning unit can analyze fluctuations in user questions and adjust the update frequency of the learning data. The history learning unit, for example, analyzes fluctuations in user questions and adjusts the update frequency of the learning data. For example, the history learning unit increases the update frequency of the learning data when there is a large fluctuation in questions. The history learning unit can also decrease the update frequency of the learning data when there is a small fluctuation in questions. For example, the history learning unit sets a low update frequency when there is a small fluctuation in questions. The history learning unit can also analyze fluctuations in questions in real time and dynamically adjust the update frequency of the learning data. For example, the history learning unit monitors fluctuations in questions in real time and adjusts the update frequency as necessary. This makes it possible to adjust the update frequency of the learning data in accordance with fluctuations in user questions.

[0067] During history learning, the history learning unit can weight the learning data based on the time when the question was submitted. The history learning unit weights the learning data based on, for example, the time when the question was submitted. For example, the history learning unit assigns a high weight to the most recent question. The history learning unit can also assign a low weight to an older question. For example, the history learning unit sets a low weight to an older question. The history learning unit can also dynamically adjust the weighting of the learning data based on the time when the question was submitted. For example, the history learning unit adjusts the weighting in real time based on the time when the question was submitted. This makes it possible to weight the learning data based on the time when the question was submitted.

[0068] The history learning unit can adjust the learning algorithm by reflecting user feedback during history learning. The history learning unit, for example, adjusts the parameters of the learning algorithm based on user feedback. For example, the history learning unit analyzes user feedback and optimizes the parameters of the algorithm. The history learning unit can also improve the accuracy of the learning algorithm by reflecting user feedback. For example, the history learning unit improves the accuracy of the algorithm based on user feedback. The history learning unit can also optimize the learning algorithm based on user feedback. For example, the history learning unit optimizes the algorithm by reflecting user feedback. This makes it possible to adjust the learning algorithm based on user feedback.

[0069] The graph generation unit can adjust the level of detail of the graph based on the importance of the data when generating the graph. For example, the graph generation unit evaluates the importance of the data and generates a detailed graph for data with high importance. For example, the graph generation unit generates a detailed graph based on the importance of the data. The graph generation unit can also generate a simplified graph for data with low importance. For example, the graph generation unit generates a simplified graph for data with low importance. The graph generation unit can also dynamically adjust the level of detail of the graph based on the importance of the data. For example, the graph generation unit adjusts the level of detail of the graph in real time based on the importance of the data. This makes it possible to adjust the level of detail of the graph according to the importance of the data.

[0070] The graph generation unit can apply different graph generation algorithms depending on the data category when generating a graph. The graph generation unit, for example, selects an optimal graph generation algorithm depending on the data category. For example, the graph generation unit applies a specific graph generation algorithm to financial data. The graph generation unit can also apply a different graph generation algorithm to market data. For example, the graph generation unit applies a different graph generation algorithm to market data. The graph generation unit can also select an optimal graph generation algorithm depending on the data category. For example, the graph generation unit selects an optimal graph generation algorithm depending on the category, such as text data, numerical data, or image data. This makes it possible to apply an optimal graph generation algorithm depending on the data category.

[0071] When generating a graph, the graph generation unit can improve the accuracy of the graph by referring to the user's past graph generation results. The graph generation unit, for example, adjusts parameters of the graph generation algorithm based on the user's past graph generation results. For example, the graph generation unit analyzes the user's past graph generation results and optimizes parameters of the algorithm. The graph generation unit can also improve the accuracy of the graph by referring to the user's past graph generation results. For example, the graph generation unit improves the accuracy of the algorithm based on the user's past graph generation results. The graph generation unit can also optimize the graph generation method by reflecting the user's past graph generation results. For example, the graph generation unit optimizes the graph generation method based on the user's past graph generation results. This makes it possible to improve the accuracy of the graph based on the user's past graph generation results.

[0072] The graph generation unit can determine the priority of a graph based on the time of data submission when generating a graph. The graph generation unit determines the priority of a graph based on, for example, the time of data submission. For example, the graph generation unit sets a high priority for the most recent data. The graph generation unit can also set a low priority for older data. For example, the graph generation unit sets a low priority for older data. The graph generation unit can also dynamically adjust the priority of a graph based on the time of data submission. For example, the graph generation unit adjusts the priority in real time based on the time of data submission. This makes it possible to determine the priority of a graph based on the time of data submission.

[0073] The graph generation unit can adjust the order of the graph based on the relevance of the data when generating the graph. For example, the graph generation unit evaluates the relevance of the data and prioritizes graphing highly relevant data. For example, the graph generation unit prioritizes generating graphs based on the relevance of the data. The graph generation unit can also postpone data with low relevance. For example, the graph generation unit postpones data with low relevance. The graph generation unit can also dynamically adjust the order of the graph based on the relevance of the data. For example, the graph generation unit adjusts the order of the graph in real time based on the relevance of the data. This makes it possible to adjust the order of the graph based on the relevance of the data.

[0074] The graph generation unit can adjust the use of technical terms in the graph according to the user's level of expertise when generating the graph. For example, the graph generation unit evaluates the user's level of expertise and uses detailed technical terms if the user has technical expertise. For example, the graph generation unit uses detailed technical terms based on the user's level of expertise. The graph generation unit can also use simple terms if the user does not have technical expertise. For example, the graph generation unit uses simple terms based on the user's level of expertise. The graph generation unit can also dynamically adjust the use of technical terms in the graph according to the user's level of expertise. For example, the graph generation unit adjusts the use of technical terms based on the user's level of expertise. This makes it possible to use technical terms in the graph according to the user's level of expertise.

[0075] The real-time response unit can select the optimal response method by referring to the user's past response history when making a real-time response. The real-time response unit selects the optimal response method based on, for example, the user's past response history. For example, the real-time response unit analyzes the user's past response history and selects the optimal response method. The real-time response unit can also select a quick response method from the user's past response history. For example, the real-time response unit selects a quick response method based on the user's past response history. The real-time response unit can also improve the accuracy of the response by referring to the user's past response history. For example, the real-time response unit improves the accuracy of the response based on the user's past response history. This makes it possible to select the optimal response method based on the user's past response history.

[0076] The real-time response unit can determine the priority of responses based on the user's current areas of interest during real-time responses. For example, the real-time response unit analyzes the user's current areas of interest and prioritizes relevant responses. For example, the real-time response unit prioritizes responses related to areas in which the user is currently interested. The real-time response unit can also filter unnecessary responses based on the user's current areas of interest. For example, the real-time response unit filters out and does not provide responses in areas in which the user is not currently interested. The real-time response unit can also dynamically adjust the priority of responses when the user's areas of interest change. For example, the real-time response unit adjusts the priority of responses when the user's areas of interest change. This makes it possible to determine the priority of responses based on the user's areas of interest.

[0077] The real-time response unit can select the optimal response means depending on the user's input method when making a real-time response. For example, when the user inputs a question by voice, the real-time response unit responds using voice recognition. For example, the real-time response unit uses voice recognition technology to convert the user's voice into text and respond. Furthermore, when the user inputs a question by text, the real-time response unit can also respond using text analysis. For example, the real-time response unit uses text analysis technology to analyze the user's text input and respond. Furthermore, when the user inputs a question by image, the real-time response unit can also respond using image analysis. For example, the real-time response unit uses image analysis technology to analyze the user's image input and respond. This makes it possible to select the optimal response means depending on the user's input method.

[0078] When providing a real-time response, the real-time response unit can prioritize highly relevant responses by taking into account the user's geographical location information. The real-time response unit, for example, prioritizes providing information related to the user's current location. For example, the real-time response unit provides relevant information based on the user's geographical location information. The real-time response unit can also filter unnecessary information based on the user's geographical location information. For example, the real-time response unit filters out information that is not related to the user's current location so that it is not provided. The real-time response unit can also dynamically adjust the content of the response when the user's location information changes. For example, the real-time response unit adjusts the type and amount of information to be provided when the user's location information changes. This enables a highly relevant response based on the user's geographical location information.

[0079] The real-time response unit can analyze the user's social media activity and provide a relevant response during the real-time response. For example, the real-time response unit analyzes the user's social media posting content and provides relevant information. For example, the real-time response unit analyzes the user's social media posting content and provides relevant information. The real-time response unit can also provide a relevant response by referring to the activities of the user's friends on social media. For example, the real-time response unit can provide a relevant response based on information shared by the user's friends on social media. The real-time response unit can also provide a relevant response based on the user's social media check-in information. For example, the real-time response unit can provide information related to places where the user checked in on social media. This makes it possible to provide a relevant response based on the user's social media activity.

[0080] The real-time response unit can customize the response method by reflecting the user's past feedback when making a real-time response. The real-time response unit, for example, adjusts the content of the response based on the user's past feedback. For example, the real-time response unit analyzes the user's feedback and optimizes the content of the response. The real-time response unit can also optimize the response method based on the user's feedback. For example, the real-time response unit improves the response method by reflecting the user's feedback. The real-time response unit can also determine the priority of responses based on the user's feedback. For example, the real-time response unit prioritizes responses with higher importance based on the user's feedback. This makes it possible to customize the response method based on the user's past feedback.

[0081] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0082] The analysis unit can integrate information from different data sources to perform analysis. For example, financial data and market data can be integrated to perform analysis, providing more comprehensive results. The analysis unit can also integrate data from different industries to perform analysis. For example, data from the manufacturing and service industries can be integrated to perform analysis, revealing correlations between industries. The analysis unit can also integrate data in different formats to perform analysis. For example, text data and numerical data can be integrated to perform analysis, providing results from a more multifaceted perspective.

[0083] The providing unit may provide information taking into account the user's geographical location information. For example, if the user is in a particular area, information related to that area may be preferentially provided. The providing unit may also provide information based on the user's movement history. For example, information related to places the user has previously visited may be provided. Furthermore, the providing unit may adjust the format of information based on the user's current location. For example, if the user is moving, concise, visually easy-to-understand information may be provided, and if the user is stationary, detailed text information may be provided.

[0084] The collection unit can analyze the user's social media activities and collect related data. For example, the collection unit can collect related data based on information shared by the user on social media. The collection unit can also collect data by referring to the social media activities of the user's friends. For example, the collection unit can collect related data based on information shared by the user's friends. The collection unit can also collect data based on the user's check-in information on social media. For example, the collection unit can collect data related to the places where the user checked in.

[0085] The learning unit can incorporate data from different industries to increase the diversity of learning. For example, data from the manufacturing and service industries can be incorporated for learning, enabling learning from a more multifaceted perspective. The learning unit can also incorporate data from different regions for learning. For example, domestic data and overseas data can be incorporated for learning, enabling learning from a global perspective. Furthermore, the learning unit can incorporate data in different formats for learning. For example, text data and numerical data can be incorporated for learning, enabling learning from a more diverse range of data sources.

[0086] The reception unit can make suggestions based on the schedule by referring to the user's calendar information. For example, it can provide related information based on the schedule registered in the user's calendar. The reception unit can also suggest locations related to specific events from the user's calendar information. For example, if the user has a meeting scheduled, it can suggest locations and information related to the meeting. Furthermore, the reception unit can also suggest the optimal route to match the schedule based on the user's calendar information. For example, if the user has multiple schedules, it can suggest the optimal route for each schedule.

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

[0088] Step 1: The collection department collects data. The collected data includes text data, numerical data, and image data. The collection department collects open data from government agencies, IR, financial statements, DS.INSIGHT, etc., as well as web data held by specific companies. Step 2: The learning unit accumulates and learns the data collected by the collection unit. Accumulation and learning is performed using methods such as deep learning and reinforcement learning. For example, the learning unit uses generative AI to analyze and learn from the collected data. Step 3: The reception unit receives a question from the user. The question may be input by voice or text. For example, the reception unit receives a question input by the user in natural language. Step 4: The analysis unit analyzes the data based on the questions received by the reception unit. The analysis is performed using methods such as statistical analysis and machine learning algorithms. For example, the analysis unit uses generative AI to extract relevant information from the accumulated data. Step 5: The providing unit provides the analysis results obtained by the analysis unit. The results can be provided in the form of a report or graph. For example, the providing unit may use a generation AI to generate a graph based on the extracted information and provide it to the user.

[0089] (Example 2) A data analysis system according to an embodiment of the present invention uses a generation AI to accumulate and learn open data, such as data from government agencies, investor relations, financial statements, and DS.INSIGHT, as well as web data held by specific companies. This system enables the exchange of higher-resolution market data with the generation AI, allowing users to generate graphs and discover the analytical data they desire through the generation AI. For example, the data analysis system collects open data, such as data from government agencies, investor relations, financial statements, and DS.INSIGHT, as well as web data held by specific companies. The generation AI then accumulates and learns the collected data. The generation AI analyzes this data and provides the market data desired by the user. The user inputs a question to the generation AI in natural language, and the generation AI analyzes the input question and extracts relevant information from the accumulated data. The system then generates a graph based on the extracted information and provides it to the user. This system allows users to easily obtain and analyze market data. For example, a specific company's financial data and market trends can be visually confirmed in a graph. Furthermore, the generation AI responds to user questions in real time, enabling rapid data acquisition. Furthermore, generative AI can learn from users' past question history and provide more accurate answers, allowing data analysis systems to support business decision-making and improve competitiveness.

[0090] A data analysis system according to an embodiment includes a collection unit, a learning unit, a reception unit, an analysis unit, and a provision unit. The collection unit collects data. Examples of the collected data include, but are not limited to, text data, numerical data, and image data. The collection unit collects open data from government agencies, investor relations, financial statements, DS.INSIGHT, and other sources, as well as web data held by specific companies. The learning unit accumulates and learns the data collected by the collection unit. The accumulation and learning can be performed using, for example, deep learning or reinforcement learning, but is not limited to these examples. For example, the learning unit analyzes and learns the collected data using a generative AI. The reception unit accepts user questions. Examples of the question format include, but are not limited to, voice input and text input. For example, the reception unit accepts questions entered by the user in natural language. The analysis unit analyzes the data based on the questions accepted by the reception unit. The analysis can be performed using, for example, statistical analysis or a machine learning algorithm, but is not limited to these examples. For example, the analysis unit uses a generation AI to extract relevant information from the accumulated data. The provision unit provides the analysis results obtained by the analysis unit. The format of the provided results includes, but is not limited to, a report format or a graph format. For example, the provision unit uses the generation AI to generate a graph based on the extracted information and provide it to the user. This allows the data analysis system according to the embodiment to efficiently collect data, accumulate and learn data, accept questions, analyze data, and provide results.

[0091] The data analysis system includes a history learning unit that learns a user's past question history. The history learning unit learns the user's past question history. The question history includes, for example, a text log and an audio log, but is not limited to these examples. For example, the history learning unit analyzes and learns the content of questions previously asked by the user. The history learning unit can also analyze question trends based on the user's question history. For example, the history learning unit identifies patterns of questions frequently asked by the user and learns based on those patterns. Furthermore, the history learning unit can determine the priority of questions based on the user's question history. For example, the history learning unit evaluates the importance of questions previously asked by the user and prioritizes learning questions with high importance. In this way, learning the past question history enables more accurate answers.

[0092] The data analysis system includes a graph generation unit that generates graphs. The graph generation unit generates graphs based on data. Types of graphs that can be generated include, but are not limited to, bar graphs, line graphs, and pie charts. For example, the graph generation unit analyzes data using a generation AI to generate an appropriate graph. The graph generation unit can also generate customized graphs in response to user requests. For example, the graph generation unit generates graphs based on a data range and display format specified by the user. Furthermore, the graph generation unit has a function for visually displaying the generated graphs. For example, the graph generation unit displays the generated graphs on a screen so that the user can visually confirm them. This allows for visual confirmation of the data.

[0093] The data analysis system includes a real-time response unit that responds in real time. The real-time response unit responds to user questions in real time. Response formats include, but are not limited to, text responses and voice responses. For example, the real-time response unit uses a generation AI to analyze the user's questions and respond immediately. The real-time response unit can also provide an appropriate response by referring to the user's past question history. For example, the real-time response unit can provide relevant information based on the content of questions the user has previously asked. Furthermore, the real-time response unit can adjust the content of the response according to the user's current situation. For example, the real-time response unit can prioritize providing relevant information based on the user's current areas of interest. This enables rapid data acquisition.

[0094] The collection unit can collect data from government agencies, investor relations, financial statements, open data, and web data held by specific companies. For example, the collection unit collects data from public databases of government agencies. The collection unit can also collect data from corporate websites that provide investor relations information. The collection unit can also collect corporate financial statements and store them in a database. For example, the collection unit can automatically download corporate financial statements and store them in a database. The collection unit can also collect data from open data platforms such as DS.INSIGHT. For example, the collection unit can obtain data using the DS.INSIGHT API. This makes it possible to collect data from a variety of data sources.

[0095] The analysis unit can analyze the accumulated data based on the user's question and extract related information. The analysis unit can extract information related to the user's question using, for example, keyword extraction technology. The analysis unit can also identify topics related to the user's question using topic modeling technology. The analysis unit can also analyze the intent of the user's question and extract related information using natural language processing technology. For example, the analysis unit can analyze the user's question and search for related data. The analysis unit can also extract related information from a database based on the user's question. This makes it possible to provide appropriate information in response to the user's question.

[0096] The collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated user emotions. For example, the collection unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the collection unit calculates an emotion score based on changes in facial expressions. The collection unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the collection unit analyzes the tone and speed of the voice and calculates an emotion score. The collection unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the collection unit calculates an emotion score based on heart rate fluctuations. This enables data collection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input image data of a user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0097] When collecting data, the collection unit can analyze the user's past data usage history and select a collection method. The collection unit, for example, analyzes the user's past data usage history and selects the optimal data collection method. For example, the collection unit prioritizes collecting data sources that the user has frequently used in the past. The collection unit can also optimize data to be collected in a specific time period based on the user's past data usage history. For example, the collection unit prioritizes collecting data that the user frequently uses in a specific time period. The collection unit can also select the most efficient collection method based on the user's past data usage history. For example, the collection unit evaluates the reliability of data sources that the user has used in the past and prioritizes collecting reliable data sources. This enables optimal data collection based on the user's past data usage history.

[0098] The collection unit can perform filtering based on the user's current areas of interest when collecting data. For example, the collection unit analyzes the user's current areas of interest and prioritizes collecting related data. For example, the collection unit prioritizes collecting data related to areas in which the user is currently interested. The collection unit can also filter unnecessary data based on the user's current areas of interest. For example, the collection unit filters out data in areas in which the user is not currently interested so as not to collect it. The collection unit can also dynamically adjust the data to be collected when the user's areas of interest change. For example, the collection unit adjusts the type and amount of data to be collected when the user's areas of interest change. This makes it possible to collect data based on the user's areas of interest.

[0099] The collection unit can evaluate the reliability of data when collecting data and prioritize collecting highly reliable data. For example, the collection unit evaluates the reliability of a data source and prioritizes collecting highly reliable data. For example, the collection unit checks the consistency and accuracy of data to evaluate the reliability of the data source. The collection unit can also determine the priority of data to be collected based on the reliability of the data. For example, the collection unit prioritizes collecting highly reliable data and filters out unreliable data. The collection unit can also not collect unreliable data. For example, if the reliability of a data source is low, the collection unit sets the collection unit not to collect that data. This improves the quality of data by preferentially collecting highly reliable data.

[0100] The collection unit can estimate the user's emotions and determine the priority of data to be collected based on the estimated user emotions. For example, the collection unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the collection unit calculates an emotion score based on changes in facial expressions. The collection unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the collection unit analyzes the tone and speed of the voice and calculates an emotion score. The collection unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the collection unit calculates an emotion score based on heart rate fluctuations. This makes it possible to determine the priority of data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input image data of a user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0101] When collecting data, the collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. The collection unit, for example, prioritizes collecting data related to the user's current location. For example, the collection unit collects relevant data based on the user's geographical location information. The collection unit can also filter unnecessary data based on the user's geographical location information. For example, the collection unit filters out data that is not related to the user's current location so as not to collect it. The collection unit can also dynamically adjust the data to be collected when the user's location information changes. For example, the collection unit adjusts the type and amount of data to be collected when the user's location information changes. This makes it possible to collect data based on the user's geographical location information.

[0102] When collecting data, the collection unit can analyze the user's social media activities and collect related data. For example, the collection unit analyzes the content of the user's posts on social media and collects related data. For example, the collection unit analyzes the content of the user's posts on social media and collects related data. The collection unit can also collect related data by referring to the activities of the user's friends on social media. For example, the collection unit collects related data based on information shared by the user's friends on social media. The collection unit can also collect related data based on the user's check-in information on social media. For example, the collection unit collects data related to places where the user checked in on social media. This makes it possible to collect data based on the user's social media activities.

[0103] The collection unit can customize the collection method by reflecting the user's past feedback when collecting data. The collection unit, for example, adjusts the type of data to be collected based on the user's past feedback. For example, the collection unit changes the type of data to be collected based on the user's feedback. The collection unit can also optimize the collection method based on the user's feedback. For example, the collection unit improves the collection method by reflecting the user's feedback. The collection unit can also determine the priority of data to be collected based on the user's feedback. For example, the collection unit prioritizes collecting data with high importance based on the user's feedback. This makes it possible to customize the collection method based on the user's past feedback.

[0104] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. For example, the learning unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the learning unit calculates an emotion score based on changes in facial expressions. The learning unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the learning unit analyzes the tone and speed of the voice and calculates an emotion score. The learning unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the learning unit calculates an emotion score based on heart rate fluctuations. This enables the selection of training data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the learning unit can be performed using, for example, AI, or without AI. For example, the learning unit can input image data of a user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0105] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, selects an optimal learning algorithm based on past learning data. For example, the learning unit analyzes past learning data and selects an optimal algorithm. The learning unit can also adjust parameters of the learning algorithm from past learning data. For example, the learning unit optimizes parameters of the algorithm based on past learning data. The learning unit can also improve the accuracy of the learning algorithm by referring to past learning data. For example, the learning unit improves the accuracy of the algorithm based on past learning data. This makes it possible to optimize the learning algorithm based on past learning data.

[0106] The learning unit can analyze data fluctuations during learning and adjust the update frequency of the learning data. The learning unit, for example, analyzes data fluctuations and adjusts the update frequency of the learning data. For example, the learning unit increases the update frequency of the learning data when data fluctuations are large. The learning unit can also decrease the update frequency of the learning data when data fluctuations are small. For example, the learning unit sets a low update frequency when data fluctuations are small. The learning unit can also analyze data fluctuations in real time and dynamically adjust the update frequency of the learning data. For example, the learning unit monitors data fluctuations in real time and adjusts the update frequency as necessary. This makes it possible to adjust the update frequency of the learning data in accordance with data fluctuations.

[0107] During learning, the learning unit can integrate information from different data sources to expand the learning data. For example, the learning unit integrates information from different data sources to expand the learning data. For example, the learning unit collects and integrates data from multiple data sources. The learning unit can also compare data from different data sources and select optimal data. For example, the learning unit compares data from different data sources and selects high-quality data. The learning unit can also increase the diversity of the learning data based on information from different data sources. For example, the learning unit collects data from different industries or fields and reflects it in the learning data. In this way, the diversity of the learning data is improved by integrating information from different data sources.

[0108] The learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated user emotions. For example, the learning unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the learning unit calculates an emotion score based on changes in facial expressions. The learning unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the learning unit analyzes the tone and speed of the voice and calculates an emotion score. The learning unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the learning unit calculates an emotion score based on heart rate fluctuations. This makes it possible to adjust the frequency of learning according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the learning unit can be performed using, for example, AI, or without AI. For example, the learning unit can input image data of a user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0109] During learning, the learning unit can weight the learning data based on the time of data submission. The learning unit weights the learning data based on, for example, the time of data submission. For example, the learning unit assigns a high weight to the most recent data. The learning unit can also assign a low weight to older data. For example, the learning unit sets a low weight for older data. The learning unit can also dynamically adjust the weighting of the learning data based on the time of data submission. For example, the learning unit adjusts the weighting in real time based on the time of data submission. This makes it possible to weight the learning data based on the time of data submission.

[0110] The learning unit can adjust the learning algorithm by reflecting user feedback during learning. The learning unit, for example, adjusts parameters of the learning algorithm based on user feedback. For example, the learning unit analyzes user feedback and optimizes parameters of the algorithm. The learning unit can also improve the accuracy of the learning algorithm by reflecting user feedback. For example, the learning unit improves the accuracy of the algorithm based on user feedback. The learning unit can also optimize the learning algorithm based on user feedback. For example, the learning unit optimizes the algorithm by reflecting user feedback. This makes it possible to adjust the learning algorithm based on user feedback.

[0111] The learning unit can incorporate data from different industries during learning to increase the diversity of learning. For example, the learning unit incorporates data from different industries to increase the diversity of the learning data. For example, the learning unit collects data from multiple industries and reflects it in the learning data. The learning unit can also compare data from different industries and select the most suitable data. For example, the learning unit compares data from different industries and selects high-quality data. The learning unit can also improve the accuracy of the learning algorithm based on data from different industries. For example, the learning unit improves the accuracy of the algorithm based on data from different industries. In this way, by incorporating data from different industries, the diversity of learning is increased.

[0112] The reception unit can estimate the user's emotion and adjust the method for receiving questions based on the estimated user's emotion. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on changes in facial expression. The reception unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the reception unit analyzes the tone and speed of the voice and calculates an emotion score. The reception unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on heart rate fluctuations. This makes it possible to adjust the method for receiving questions based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the reception unit can be performed using, for example, AI, or without AI. For example, the reception unit can input image data of a user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0113] When accepting a question, the acceptance unit can select the optimal acceptance method by referring to the user's past question history. The acceptance unit, for example, analyzes the user's past question history and selects the optimal acceptance method. For example, the acceptance unit automatically displays questions that the user has frequently asked in the past as candidates. The acceptance unit can also preferentially suggest input methods (voice, text, etc.) that the user has used in the past. For example, the acceptance unit suggests the optimal acceptance method based on the input methods that the user has used in the past. The acceptance unit can also predict and suggest questions that will be asked in a specific time period based on the user's past question history. For example, the acceptance unit predicts and suggests questions that will be asked in a specific time period based on the user's past question history. This makes it possible to accept optimal questions based on the user's past question history.

[0114] When receiving questions, the reception unit can determine the priority of the questions based on the user's current areas of interest. For example, the reception unit analyzes the user's current areas of interest and prioritizes receiving related questions. For example, the reception unit prioritizes receiving questions related to areas in which the user is currently interested. The reception unit can also filter unnecessary questions based on the user's current areas of interest. For example, the reception unit filters out questions in areas in which the user is not currently interested and does not accept them. The reception unit can also dynamically adjust the questions to be received when the user's areas of interest change. For example, the reception unit adjusts the types and priorities of questions to be received when the user's areas of interest change. This makes it possible to determine the priority of questions based on the user's areas of interest.

[0115] When accepting a question, the acceptance unit can select the optimal acceptance means depending on the user's input method. For example, when the user inputs a question by voice, the acceptance unit accepts the question using voice recognition. For example, the acceptance unit uses voice recognition technology to convert the user's voice into text and accepts the question. Furthermore, when the user inputs a question by text, the acceptance unit can also accept the question using text analysis. For example, the acceptance unit uses text analysis technology to analyze the user's text input and accept the question. Furthermore, when the user inputs a question by image, the acceptance unit can also accept the question using image analysis. For example, the acceptance unit uses image analysis technology to analyze the user's image input and accept the question. This makes it possible to accept the question optimally depending on the user's input method.

[0116] The reception unit can estimate the user's emotion and adjust the design of the input interface based on the estimated user emotion. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on changes in facial expression. The reception unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the reception unit analyzes the tone and speed of the voice and calculates an emotion score. The reception unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on heart rate fluctuations. This enables the design of the input interface to be adjusted according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the reception unit can be performed using, for example, AI, or without AI. For example, the reception unit can input image data of a user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0117] When receiving a question, the reception unit can automatically suggest candidate locations by referring to the user's past travel history. The reception unit, for example, analyzes the user's past travel history and suggests optimal candidate locations. For example, the reception unit automatically displays places that the user has frequently visited in the past as candidate locations. The reception unit can also predict places that the user will visit on specific days of the week or time periods and suggest them as candidate locations. For example, the reception unit predicts and suggests places that the user will visit on specific days of the week or time periods based on the user's past travel history. The reception unit can also analyze the user's past travel patterns and suggest optimal candidate locations. For example, the reception unit analyzes the user's past travel patterns and identifies optimal candidate locations. This makes it possible to automatically suggest candidate locations based on the user's past travel history.

[0118] When receiving a question, the reception unit can make a suggestion based on the schedule by referring to the user's calendar information. The reception unit, for example, references the user's calendar information and makes a suggestion based on the schedule. For example, the reception unit references the schedule registered in the user's calendar and automatically sets the departure point and destination. The reception unit can also suggest locations related to a specific event as candidate locations from the user's calendar information. For example, the reception unit suggests a location related to a specific event based on the user's calendar information. The reception unit can also suggest an optimal route that matches the schedule based on the user's calendar information. For example, the reception unit references the user's calendar information and suggests an optimal route. This makes it possible to suggest a schedule based on the user's calendar information.

[0119] When receiving a question, the reception unit can analyze the user's social media activity and suggest related places. The reception unit, for example, analyzes the content of the user's social media posts and suggests related places. For example, the reception unit analyzes the content of the user's social media posts and suggests related places as candidate locations. The reception unit can also suggest related places by referring to the activity of the user's friends on social media. For example, the reception unit can suggest related places based on places where the user's friends have checked in on social media. The reception unit can also suggest related places based on the user's social media check-in information. For example, the reception unit can suggest related places based on places where the user has checked in on social media. This makes it possible to suggest related places based on the user's social media activity.

[0120] The analysis unit can estimate the user's emotion and adjust the analysis method based on the estimated user's emotion. For example, the analysis unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on changes in facial expression. The analysis unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the analysis unit analyzes the tone and speed of the voice and calculates an emotion score. The analysis unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on heart rate fluctuations. This makes it possible to adjust the analysis method according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input image data of a user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0121] The analysis unit can adjust the level of detail of the analysis based on the importance of the data during analysis. The analysis unit, for example, evaluates the importance of the data and performs a detailed analysis on data with high importance. For example, the analysis unit performs a detailed analysis based on the importance of the data. The analysis unit can also perform a simplified analysis on data with low importance. For example, the analysis unit performs a simplified analysis on data with low importance. The analysis unit can also dynamically adjust the level of detail of the analysis based on the importance of the data. For example, the analysis unit adjusts the level of detail of the analysis in real time based on the importance of the data. This makes it possible to adjust the level of detail of the analysis according to the importance of the data.

[0122] During analysis, the analysis unit can apply different analysis algorithms depending on the category of data. The analysis unit, for example, selects the optimal analysis algorithm depending on the category of data. For example, the analysis unit applies a specific analysis algorithm to financial data. The analysis unit can also apply a different analysis algorithm to market data. For example, the analysis unit applies a different analysis algorithm to market data. The analysis unit can also select the optimal analysis algorithm depending on the category of data. For example, the analysis unit selects the optimal analysis algorithm depending on the category of data, such as text data, numerical data, or image data. This makes it possible to apply the optimal analysis algorithm depending on the category of data.

[0123] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The analysis unit, for example, adjusts the parameters of the analysis algorithm based on the user's past analysis results. For example, the analysis unit analyzes the user's past analysis results and optimizes the parameters of the algorithm. The analysis unit can also improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis unit improves the accuracy of the algorithm based on the user's past analysis results. The analysis unit can also optimize the analysis method by reflecting the user's past analysis results. For example, the analysis unit optimizes the analysis method based on the user's past analysis results. This makes it possible to improve the analysis accuracy based on the user's past analysis results.

[0124] The analysis unit can estimate the user's emotions and determine the priority of analysis based on the estimated user emotions. For example, the analysis unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on changes in facial expression. The analysis unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the analysis unit analyzes the tone and speed of the voice and calculates an emotion score. The analysis unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on heart rate fluctuations. This makes it possible to determine the priority of analysis based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input image data of a user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0125] During analysis, the analysis unit can determine the priority of analysis based on the time of data submission. The analysis unit determines the priority of analysis based on, for example, the time of data submission. For example, the analysis unit sets a high priority for the most recent data. The analysis unit can also set a low priority for older data. For example, the analysis unit sets a low priority for older data. The analysis unit can also dynamically adjust the priority of analysis based on the time of data submission. For example, the analysis unit adjusts the priority in real time based on the time of data submission. This makes it possible to determine the priority of analysis based on the time of data submission.

[0126] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the data. For example, the analysis unit evaluates the relevance of the data and prioritizes the analysis of highly relevant data. For example, the analysis unit prioritizes analysis based on the relevance of the data. The analysis unit can also postpone data with low relevance. For example, the analysis unit postpones data with low relevance. The analysis unit can also dynamically adjust the order of analysis based on the relevance of the data. For example, the analysis unit adjusts the order of analysis in real time based on the relevance of the data. This makes it possible to adjust the order of analysis based on the relevance of the data.

[0127] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. For example, the analysis unit evaluates the user's level of expertise and uses detailed technical terms if the user has specialized knowledge. For example, the analysis unit uses detailed technical terms based on the user's level of expertise. The analysis unit can also use simple terms if the user does not have specialized knowledge. For example, the analysis unit uses simple terms based on the user's level of expertise. The analysis unit can also dynamically adjust the use of technical terms in the analysis according to the user's level of expertise. For example, the analysis unit adjusts the use of technical terms based on the user's level of expertise. This makes it possible to use technical terms in the analysis according to the user's level of expertise.

[0128] The providing unit can estimate the user's emotion and adjust the presentation method of the information to be provided based on the estimated user's emotion. For example, the providing unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the providing unit calculates an emotion score based on changes in facial expression. The providing unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the providing unit analyzes the tone and speed of the voice and calculates an emotion score. The providing unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the providing unit calculates an emotion score based on heart rate fluctuations. This makes it possible to adjust the presentation method of information according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the providing unit can be performed using, for example, AI, or without AI. For example, the providing unit can input image data of a user taken with a camera into the generating AI and have the generating AI estimate the user's emotions.

[0129] The providing unit can adjust the level of detail of the information provided based on the importance of the information when providing the information. For example, the providing unit evaluates the importance of the information and provides detailed information for information with high importance. For example, the providing unit provides detailed information based on the importance of the information. The providing unit can also provide simplified information for information with low importance. For example, the providing unit provides simplified information for information with low importance. The providing unit can also dynamically adjust the level of detail of the information provided based on the importance of the information. For example, the providing unit adjusts the level of detail of the information provided in real time based on the importance of the information. This makes it possible to adjust the level of detail of the information provided according to the importance of the information.

[0130] The providing unit can apply different provision algorithms depending on the category of information when providing the information. The providing unit, for example, selects an optimal provision algorithm depending on the category of information. For example, the providing unit applies a specific provision algorithm to financial information. The providing unit can also apply a different provision algorithm to market information. For example, the providing unit applies a different provision algorithm to market information. The providing unit can also select an optimal provision algorithm depending on the category of information. For example, the providing unit selects an optimal provision algorithm depending on categories such as text information, numerical information, and image information. This makes it possible to apply an optimal provision algorithm depending on the category of information.

[0131] The providing unit can improve the accuracy of provision by referring to the user's past provision results when providing the data. The providing unit, for example, adjusts parameters of the provision algorithm based on the user's past provision results. For example, the providing unit analyzes the user's past provision results and optimizes parameters of the algorithm. The providing unit can also improve the accuracy of provision by referring to the user's past provision results. For example, the providing unit improves the accuracy of the algorithm based on the user's past provision results. The providing unit can also optimize the provision method by reflecting the user's past provision results. For example, the providing unit optimizes the provision method based on the user's past provision results. This makes it possible to improve the accuracy of provision based on the user's past provision results.

[0132] The providing unit can estimate the user's emotions and determine the priority of information to be provided based on the estimated user emotions. For example, the providing unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the providing unit calculates an emotion score based on changes in facial expression. The providing unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the providing unit analyzes the tone and speed of the voice and calculates the emotion score. The providing unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the providing unit calculates the emotion score based on heart rate fluctuations. This makes it possible to determine the priority of information according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the providing unit can be performed using, for example, AI, or without AI. For example, the providing unit can input image data of a user taken with a camera into the generating AI and have the generating AI estimate the user's emotions.

[0133] The providing unit can determine the priority of provision based on the time of submission of the information at the time of provision. The providing unit determines the priority of provision based on, for example, the time of submission of the information. For example, the providing unit sets a high priority for the most recent information. The providing unit can also set a low priority for older information. For example, the providing unit sets a low priority for older information. The providing unit can also dynamically adjust the priority of provision based on the time of submission of the information. For example, the providing unit adjusts the priority in real time based on the time of submission of the information. This makes it possible to determine the priority of provision based on the time of submission of the information.

[0134] The providing unit can adjust the order of provision based on the relevance of the information at the time of provision. For example, the providing unit evaluates the relevance of the information and provides highly relevant information preferentially. For example, the providing unit provides information preferentially based on the relevance of the information. The providing unit can also postpone information with low relevance. For example, the providing unit postpones information with low relevance. The providing unit can also dynamically adjust the order of provision based on the relevance of the information. For example, the providing unit adjusts the order of provision in real time based on the relevance of the information. This makes it possible to adjust the order of provision based on the relevance of the information.

[0135] The providing unit can adjust the use of provided terminology according to the user's level of expertise when providing the information. For example, the providing unit evaluates the user's level of expertise, and uses detailed terminology if the user has expertise. For example, the providing unit uses detailed terminology based on the user's level of expertise. The providing unit can also use simple terminology if the user does not have expertise. For example, the providing unit uses simple terminology based on the user's level of expertise. The providing unit can also dynamically adjust the use of provided terminology according to the user's level of expertise. For example, the providing unit adjusts the use of terminology based on the user's level of expertise. This makes it possible to use provided terminology according to the user's level of expertise.

[0136] The history learning unit can estimate the user's emotions and select training data based on the estimated user emotions. For example, the history learning unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the history learning unit calculates an emotion score based on changes in facial expressions. The history learning unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the history learning unit analyzes the tone and speed of the voice and calculates an emotion score. The history learning unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the history learning unit calculates an emotion score based on heart rate fluctuations. This makes it possible to select training data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the history learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the history learning unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0137] During history learning, the history learning unit can optimize the learning algorithm by referring to past question histories. The history learning unit, for example, selects an optimal learning algorithm based on past question histories. For example, the history learning unit analyzes past question histories and selects an optimal algorithm. The history learning unit can also adjust parameters of the learning algorithm based on past question histories. For example, the history learning unit optimizes parameters of the algorithm based on past question histories. The history learning unit can also improve the accuracy of the learning algorithm by referring to past question histories. For example, the history learning unit improves the accuracy of the algorithm based on past question histories. This makes it possible to optimize the learning algorithm based on past question histories.

[0138] During history learning, the history learning unit can analyze fluctuations in user questions and adjust the update frequency of the learning data. The history learning unit, for example, analyzes fluctuations in user questions and adjusts the update frequency of the learning data. For example, the history learning unit increases the update frequency of the learning data when there is a large fluctuation in questions. The history learning unit can also decrease the update frequency of the learning data when there is a small fluctuation in questions. For example, the history learning unit sets a low update frequency when there is a small fluctuation in questions. The history learning unit can also analyze fluctuations in questions in real time and dynamically adjust the update frequency of the learning data. For example, the history learning unit monitors fluctuations in questions in real time and adjusts the update frequency as necessary. This makes it possible to adjust the update frequency of the learning data in accordance with fluctuations in user questions.

[0139] The history learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated user emotions. For example, the history learning unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the history learning unit calculates an emotion score based on changes in facial expressions. The history learning unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the history learning unit analyzes the tone and speed of the voice and calculates an emotion score. The history learning unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the history learning unit calculates an emotion score based on heart rate fluctuations. This makes it possible to adjust the frequency of learning according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the history learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the history learning unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0140] During history learning, the history learning unit can weight the learning data based on the time when the question was submitted. The history learning unit weights the learning data based on, for example, the time when the question was submitted. For example, the history learning unit assigns a high weight to the most recent question. The history learning unit can also assign a low weight to an older question. For example, the history learning unit sets a low weight to an older question. The history learning unit can also dynamically adjust the weighting of the learning data based on the time when the question was submitted. For example, the history learning unit adjusts the weighting in real time based on the time when the question was submitted. This makes it possible to weight the learning data based on the time when the question was submitted.

[0141] The history learning unit can adjust the learning algorithm by reflecting user feedback during history learning. The history learning unit, for example, adjusts the parameters of the learning algorithm based on user feedback. For example, the history learning unit analyzes user feedback and optimizes the parameters of the algorithm. The history learning unit can also improve the accuracy of the learning algorithm by reflecting user feedback. For example, the history learning unit improves the accuracy of the algorithm based on user feedback. The history learning unit can also optimize the learning algorithm based on user feedback. For example, the history learning unit optimizes the algorithm by reflecting user feedback. This makes it possible to adjust the learning algorithm based on user feedback.

[0142] The graph generation unit can estimate the user's emotion and adjust the graph representation method based on the estimated user's emotion. For example, the graph generation unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the graph generation unit calculates an emotion score based on changes in facial expression. The graph generation unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the graph generation unit analyzes the tone and speed of the voice and calculates an emotion score. The graph generation unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the graph generation unit calculates an emotion score based on heart rate fluctuations. This makes it possible to adjust the graph representation method according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the graph generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the graph generation unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0143] The graph generation unit can adjust the level of detail of the graph based on the importance of the data when generating the graph. For example, the graph generation unit evaluates the importance of the data and generates a detailed graph for data with high importance. For example, the graph generation unit generates a detailed graph based on the importance of the data. The graph generation unit can also generate a simplified graph for data with low importance. For example, the graph generation unit generates a simplified graph for data with low importance. The graph generation unit can also dynamically adjust the level of detail of the graph based on the importance of the data. For example, the graph generation unit adjusts the level of detail of the graph in real time based on the importance of the data. This makes it possible to adjust the level of detail of the graph according to the importance of the data.

[0144] The graph generation unit can apply different graph generation algorithms depending on the data category when generating a graph. The graph generation unit, for example, selects an optimal graph generation algorithm depending on the data category. For example, the graph generation unit applies a specific graph generation algorithm to financial data. The graph generation unit can also apply a different graph generation algorithm to market data. For example, the graph generation unit applies a different graph generation algorithm to market data. The graph generation unit can also select an optimal graph generation algorithm depending on the data category. For example, the graph generation unit selects an optimal graph generation algorithm depending on the category, such as text data, numerical data, or image data. This makes it possible to apply an optimal graph generation algorithm depending on the data category.

[0145] When generating a graph, the graph generation unit can improve the accuracy of the graph by referring to the user's past graph generation results. The graph generation unit, for example, adjusts parameters of the graph generation algorithm based on the user's past graph generation results. For example, the graph generation unit analyzes the user's past graph generation results and optimizes parameters of the algorithm. The graph generation unit can also improve the accuracy of the graph by referring to the user's past graph generation results. For example, the graph generation unit improves the accuracy of the algorithm based on the user's past graph generation results. The graph generation unit can also optimize the graph generation method by reflecting the user's past graph generation results. For example, the graph generation unit optimizes the graph generation method based on the user's past graph generation results. This makes it possible to improve the accuracy of the graph based on the user's past graph generation results.

[0146] The graph generation unit can estimate the user's emotions and determine the priority of graphs based on the estimated user emotions. For example, the graph generation unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the graph generation unit calculates an emotion score based on changes in facial expressions. The graph generation unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the graph generation unit analyzes the tone and speed of the voice and calculates an emotion score. The graph generation unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the graph generation unit calculates an emotion score based on heart rate fluctuations. This makes it possible to determine the priority of graphs based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the graph generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the graph generation unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0147] The graph generation unit can determine the priority of a graph based on the time of data submission when generating a graph. The graph generation unit determines the priority of a graph based on, for example, the time of data submission. For example, the graph generation unit sets a high priority for the most recent data. The graph generation unit can also set a low priority for older data. For example, the graph generation unit sets a low priority for older data. The graph generation unit can also dynamically adjust the priority of a graph based on the time of data submission. For example, the graph generation unit adjusts the priority in real time based on the time of data submission. This makes it possible to determine the priority of a graph based on the time of data submission.

[0148] The graph generation unit can adjust the order of the graph based on the relevance of the data when generating the graph. For example, the graph generation unit evaluates the relevance of the data and prioritizes graphing highly relevant data. For example, the graph generation unit prioritizes generating graphs based on the relevance of the data. The graph generation unit can also postpone data with low relevance. For example, the graph generation unit postpones data with low relevance. The graph generation unit can also dynamically adjust the order of the graph based on the relevance of the data. For example, the graph generation unit adjusts the order of the graph in real time based on the relevance of the data. This makes it possible to adjust the order of the graph based on the relevance of the data.

[0149] The graph generation unit can adjust the use of technical terms in the graph according to the user's level of expertise when generating the graph. For example, the graph generation unit evaluates the user's level of expertise and uses detailed technical terms if the user has technical expertise. For example, the graph generation unit uses detailed technical terms based on the user's level of expertise. The graph generation unit can also use simple terms if the user does not have technical expertise. For example, the graph generation unit uses simple terms based on the user's level of expertise. The graph generation unit can also dynamically adjust the use of technical terms in the graph according to the user's level of expertise. For example, the graph generation unit adjusts the use of technical terms based on the user's level of expertise. This makes it possible to use technical terms in the graph according to the user's level of expertise.

[0150] The real-time response unit can estimate the user's emotion and adjust the response method based on the estimated user emotion. For example, the real-time response unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the real-time response unit calculates an emotion score based on changes in facial expression. The real-time response unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the real-time response unit analyzes the tone and speed of the voice and calculates an emotion score. The real-time response unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the real-time response unit calculates an emotion score based on heart rate fluctuations. This makes it possible to adjust the response method according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the real-time response unit may be performed using, for example, AI, or may be performed without using AI. For example, the real-time response unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0151] The real-time response unit can select the optimal response method by referring to the user's past response history when making a real-time response. The real-time response unit selects the optimal response method based on, for example, the user's past response history. For example, the real-time response unit analyzes the user's past response history and selects the optimal response method. The real-time response unit can also select a quick response method from the user's past response history. For example, the real-time response unit selects a quick response method based on the user's past response history. The real-time response unit can also improve the accuracy of the response by referring to the user's past response history. For example, the real-time response unit improves the accuracy of the response based on the user's past response history. This makes it possible to select the optimal response method based on the user's past response history.

[0152] The real-time response unit can determine the priority of responses based on the user's current areas of interest during real-time responses. For example, the real-time response unit analyzes the user's current areas of interest and prioritizes relevant responses. For example, the real-time response unit prioritizes responses related to areas in which the user is currently interested. The real-time response unit can also filter unnecessary responses based on the user's current areas of interest. For example, the real-time response unit filters out and does not provide responses in areas in which the user is not currently interested. The real-time response unit can also dynamically adjust the priority of responses when the user's areas of interest change. For example, the real-time response unit adjusts the priority of responses when the user's areas of interest change. This makes it possible to determine the priority of responses based on the user's areas of interest.

[0153] The real-time response unit can select the optimal response means depending on the user's input method when making a real-time response. For example, when the user inputs a question by voice, the real-time response unit responds using voice recognition. For example, the real-time response unit uses voice recognition technology to convert the user's voice into text and respond. Furthermore, when the user inputs a question by text, the real-time response unit can also respond using text analysis. For example, the real-time response unit uses text analysis technology to analyze the user's text input and respond. Furthermore, when the user inputs a question by image, the real-time response unit can also respond using image analysis. For example, the real-time response unit uses image analysis technology to analyze the user's image input and respond. This makes it possible to select the optimal response means depending on the user's input method.

[0154] The real-time response unit can estimate the user's emotions and prioritize responses based on the estimated user emotions. For example, the real-time response unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the real-time response unit can calculate an emotion score based on changes in facial expressions. The real-time response unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the real-time response unit can analyze the tone and speed of the voice and calculate an emotion score. The real-time response unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the real-time response unit can calculate an emotion score based on heart rate fluctuations. This makes it possible to prioritize responses based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the real-time response unit may be performed using, for example, AI, or may be performed without using AI. For example, the real-time response unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0155] When providing a real-time response, the real-time response unit can prioritize highly relevant responses by taking into account the user's geographical location information. The real-time response unit, for example, prioritizes providing information related to the user's current location. For example, the real-time response unit provides relevant information based on the user's geographical location information. The real-time response unit can also filter unnecessary information based on the user's geographical location information. For example, the real-time response unit filters out information that is not related to the user's current location so that it is not provided. The real-time response unit can also dynamically adjust the content of the response when the user's location information changes. For example, the real-time response unit adjusts the type and amount of information to be provided when the user's location information changes. This enables a highly relevant response based on the user's geographical location information.

[0156] The real-time response unit can analyze the user's social media activity and provide a relevant response during the real-time response. For example, the real-time response unit analyzes the user's social media posting content and provides relevant information. For example, the real-time response unit analyzes the user's social media posting content and provides relevant information. The real-time response unit can also provide a relevant response by referring to the activities of the user's friends on social media. For example, the real-time response unit can provide a relevant response based on information shared by the user's friends on social media. The real-time response unit can also provide a relevant response based on the user's social media check-in information. For example, the real-time response unit can provide information related to places where the user checked in on social media. This makes it possible to provide a relevant response based on the user's social media activity.

[0157] The real-time response unit can customize the response method by reflecting the user's past feedback when making a real-time response. The real-time response unit, for example, adjusts the content of the response based on the user's past feedback. For example, the real-time response unit analyzes the user's feedback and optimizes the content of the response. The real-time response unit can also optimize the response method based on the user's feedback. For example, the real-time response unit improves the response method by reflecting the user's feedback. The real-time response unit can also determine the priority of responses based on the user's feedback. For example, the real-time response unit prioritizes responses with higher importance based on the user's feedback. This makes it possible to customize the response method based on the user's past feedback. === Hard Collateral 1-1 === Each of the multiple elements including the collection unit, learning unit, reception unit, analysis unit, provision unit, history learning unit, graph generation unit, real-time response unit, and emotion estimation function described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects data using the camera 42 and microphone 38B of the smart device 14 and analyzes the collected data by the specific processing unit 290 of the data processing device 12. The learning unit accumulates and learns the collected data by the specific processing unit 290 of the data processing device 12. The reception unit receives a user's question by the control unit 46A of the smart device 14. The analysis unit analyzes data based on the user's question by the specific processing unit 290 of the data processing device 12. The provision unit provides the analysis result by the control unit 46A of the smart device 14. The history learning unit learns the user's past question history by the specific processing unit 290 of the data processing device 12. The graph generation unit generates a graph based on the data by the specific processing unit 290 of the data processing device 12. The real-time response unit responds to user questions in real time using the control unit 46A of the smart device 14. The emotion estimation function estimates the user's emotion using the camera 42 and microphone 38B of the smart device 14, and adjusts the timing of data collection based on the emotion using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the collection unit, learning unit, reception unit, analysis unit, provision unit, history learning unit, graph generation unit, real-time response unit, and emotion estimation function described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects data using the camera 42 and microphone 238 of the smart glasses 214 and analyzes the collected data by the specific processing unit 290 of the data processing device 12. The learning unit accumulates and learns the collected data by the specific processing unit 290 of the data processing device 12. The reception unit receives a user's question by the control unit 46A of the smart glasses 214. The analysis unit analyzes data based on the user's question by the specific processing unit 290 of the data processing device 12. The provision unit provides the analysis result by the control unit 46A of the smart glasses 214. The history learning unit learns the user's past question history by the specific processing unit 290 of the data processing device 12. The graph generation unit generates a graph based on the data by the specific processing unit 290 of the data processing device 12. The real-time response unit responds to user questions in real time using the control unit 46A of the smart glasses 214. The emotion estimation function estimates the user's emotion using the camera 42 and microphone 238 of the smart glasses 214, and adjusts the timing of data collection based on the emotion using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the collection unit, learning unit, reception unit, analysis unit, provision unit, history learning unit, graph generation unit, real-time response unit, and emotion estimation function described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects data using the camera 42 and microphone 238 of the headset type terminal 314 and analyzes the collected data by the specific processing unit 290 of the data processing device 12. The learning unit accumulates and learns the collected data by the specific processing unit 290 of the data processing device 12. The reception unit receives a user's question by the control unit 46A of the headset type terminal 314. The analysis unit analyzes the data based on the user's question by the specific processing unit 290 of the data processing device 12. The provision unit provides the analysis result by the control unit 46A of the headset type terminal 314. The history learning unit learns the user's past question history by the specific processing unit 290 of the data processing device 12. The graph generation unit generates a graph based on the data by the specific processing unit 290 of the data processing device 12. The real-time response unit responds to user questions in real time using the control unit 46A of the headset terminal 314. The emotion estimation function estimates the user's emotion using the camera 42 and microphone 238 of the headset terminal 314, and adjusts the timing of data collection based on the emotion using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, learning unit, reception unit, analysis unit, provision unit, history learning unit, graph generation unit, real-time response unit, and emotion estimation function described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects data using the camera 42 and microphone 238 of the robot 414 and analyzes the collected data by the specific processing unit 290 of the data processing device 12. The learning unit accumulates and learns the collected data by the specific processing unit 290 of the data processing device 12. The reception unit receives a user's question by the control unit 46A of the robot 414. The analysis unit analyzes the data based on the user's question by the specific processing unit 290 of the data processing device 12. The provision unit provides the analysis result by the control unit 46A of the robot 414. The history learning unit learns the user's past question history by the specific processing unit 290 of the data processing device 12. The graph generation unit generates a graph based on the data by the specific processing unit 290 of the data processing device 12. The real-time response unit responds to user questions in real time using the control unit 46A of the robot 414. The emotion estimation function estimates the user's emotion using the camera 42 and microphone 238 of the robot 414, and adjusts the timing of data collection based on the emotion using the specific processing unit 290 of the data processing device 12.

[0158] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0159] The analysis unit can estimate the user's emotions and adjust the analysis method based on the estimated user's emotions. For example, if the user is feeling stressed, the analysis unit can perform a simple analysis, and if the user is relaxed, the analysis unit can perform a detailed analysis. The analysis unit can also adjust the display method of the analysis results according to the user's emotions. For example, if the user is excited, the analysis unit can prioritize displaying a visually easy-to-understand graph, and if the user is calm, the analysis unit can provide a detailed text report. Furthermore, the analysis unit can determine the priority of the analysis based on the user's emotions. For example, if the user is feeling anxious, the analysis unit can prioritize the priority of the analysis in order to respond quickly.

[0160] The providing unit can estimate the user's emotions and adjust the presentation method of the information to be provided based on the estimated user's emotions. For example, if the user is tired, concise, visually easy-to-understand information can be provided, and if the user is concentrating, detailed text information can be provided. The providing unit can also determine the priority of information according to the user's emotions. For example, if the user is nervous, important information can be provided first, and if the user is relaxed, supplementary information can be provided. Furthermore, the providing unit can adjust the format of information based on the user's emotions. For example, if the user is excited, information can be provided using interactive graphs or animations.

[0161] The collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated user's emotions. For example, if the user is feeling stressed, data collection can be temporarily stopped, and if the user is relaxed, data collection can be resumed. The collection unit can also adjust the type of data to be collected according to the user's emotions. For example, if the user is excited, real-time updated data can be preferentially collected, and if the user is calm, past data can be collected. Furthermore, the collection unit can adjust the frequency of data collection based on the user's emotions. For example, if the user is feeling anxious, data can be collected frequently, and if the user is relaxed, data collection can be reduced in frequency.

[0162] The learning unit can estimate the user's emotions and select learning data based on the estimated user's emotions. For example, if the user is feeling stressed, learning can be performed using a simple data set, and if the user is relaxed, learning can be performed using a complex data set. The learning unit can also adjust the frequency of learning according to the user's emotions. For example, if the user is excited, learning can be performed frequently, and if the user is calm, learning can be performed less frequently. Furthermore, the learning unit can adjust the parameters of the learning algorithm based on the user's emotions. For example, if the user is feeling anxious, the parameters of the learning algorithm can be set conservatively, and if the user is relaxed, the parameters can be set aggressively.

[0163] The reception unit can estimate the user's emotions and adjust the method of receiving questions based on the estimated user's emotions. For example, if the user is feeling stressed, a simple question format can be provided, and if the user is relaxed, a detailed question format can be provided. The reception unit can also determine the priority of questions according to the user's emotions. For example, if the user is nervous, important questions can be given priority, and if the user is relaxed, supplementary questions can be given priority. Furthermore, the reception unit can adjust the format of questions based on the user's emotions. For example, if the user is excited, an interactive question format can be provided, and if the user is calm, a text-based question format can be provided.

[0164] The analysis unit can integrate information from different data sources to perform analysis. For example, financial data and market data can be integrated to perform analysis, providing more comprehensive results. The analysis unit can also integrate data from different industries to perform analysis. For example, data from the manufacturing and service industries can be integrated to perform analysis, revealing correlations between industries. The analysis unit can also integrate data in different formats to perform analysis. For example, text data and numerical data can be integrated to perform analysis, providing results from a more multifaceted perspective.

[0165] The providing unit may provide information taking into account the user's geographical location information. For example, if the user is in a particular area, information related to that area may be preferentially provided. The providing unit may also provide information based on the user's movement history. For example, information related to places the user has previously visited may be provided. Furthermore, the providing unit may adjust the format of information based on the user's current location. For example, if the user is moving, concise, visually easy-to-understand information may be provided, and if the user is stationary, detailed text information may be provided.

[0166] The collection unit can analyze the user's social media activities and collect related data. For example, the collection unit can collect related data based on information shared by the user on social media. The collection unit can also collect data by referring to the social media activities of the user's friends. For example, the collection unit can collect related data based on information shared by the user's friends. The collection unit can also collect data based on the user's check-in information on social media. For example, the collection unit can collect data related to the places where the user checked in.

[0167] The learning unit can incorporate data from different industries to increase the diversity of learning. For example, data from the manufacturing and service industries can be incorporated for learning, enabling learning from a more multifaceted perspective. The learning unit can also incorporate data from different regions for learning. For example, domestic data and overseas data can be incorporated for learning, enabling learning from a global perspective. Furthermore, the learning unit can incorporate data in different formats for learning. For example, text data and numerical data can be incorporated for learning, enabling learning from a more diverse range of data sources.

[0168] The reception unit can make suggestions based on the schedule by referring to the user's calendar information. For example, it can provide related information based on the schedule registered in the user's calendar. The reception unit can also suggest locations related to specific events from the user's calendar information. For example, if the user has a meeting scheduled, it can suggest locations and information related to the meeting. Furthermore, the reception unit can also suggest the optimal route to match the schedule based on the user's calendar information. For example, if the user has multiple schedules, it can suggest the optimal route for each schedule.

[0169] The processing flow of the second embodiment will be briefly explained below.

[0170] Step 1: The collection department collects data. The collected data includes text data, numerical data, and image data. The collection department collects open data from government agencies, IR, financial statements, DS.INSIGHT, etc., as well as web data held by specific companies. Step 2: The learning unit accumulates and learns the data collected by the collection unit. Accumulation and learning is performed using methods such as deep learning and reinforcement learning. For example, the learning unit uses generative AI to analyze and learn from the collected data. Step 3: The reception unit receives a question from the user. The question may be input by voice or text. For example, the reception unit receives a question input by the user in natural language. Step 4: The analysis unit analyzes the data based on the questions received by the reception unit. The analysis is performed using methods such as statistical analysis and machine learning algorithms. For example, the analysis unit uses generative AI to extract relevant information from the accumulated data. Step 5: The providing unit provides the analysis results obtained by the analysis unit. The results can be provided in the form of a report or graph. For example, the providing unit may use a generation AI to generate a graph based on the extracted information and provide it to the user.

[0171] 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.

[0172] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<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.

[0173] 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.

[0174] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0175] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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).

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0185] 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. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0191] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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).

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0201] 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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0207] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0208] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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).

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0218] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. 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 the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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).

[0228] 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.

[0229] 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."

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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.

[0242] [Explanation of symbols]

[0243] 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 collection unit that collects data; a learning unit that accumulates and learns the data collected by the collection unit; a reception unit that receives questions from users; an analysis unit that analyzes data based on the question received by the reception unit; a providing unit that provides the analysis results obtained by the analysis unit; Equipped with A system characterized by:

2. It has a history learning unit that learns the user's past question history.

2. The system of claim 1.

3. A graph generation unit is provided to generate graphs.

2. The system of claim 1.

4. Equipped with a real-time response section that responds in real time 2. The system of claim 1.

5. The collecting unit Collects government, IR, financial statements, open data, and web data held by specific companies.

2. The system of claim 1.

6. The analysis unit Analyze accumulated data based on user questions and extract relevant information 2. The system of claim 1.

7. The collecting unit Inferring user emotions and adjusting the timing of data collection based on the estimated user emotions 2. The system of claim 1.

8. The collecting unit When collecting data, analyze the user's past data usage history and select the collection method.

2. The system of claim 1.

9. The collecting unit Filtering data collection based on the user's current interests 2. The system of claim 1.

Images