system

Abstract

The system according to this embodiment aims to predict future risks by utilizing past failure cases and to make strategic proposals. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a generation unit, and a proposal unit. The collection unit collects a large amount of historical data. The analysis unit analyzes the data collected by the collection unit. The generation unit generates a predictive model based on the analysis results obtained by the analysis unit. The proposal unit makes strategic proposals based on the predictive model generated by the generation unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is 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 an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult to fully utilize past failure cases to predict future risks and make strategic proposals.

[0005] The system according to the embodiment aims to utilize past failure cases to predict future risks and make strategic proposals.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a data collection unit, an analysis unit, a generation unit, and a proposal unit. The data collection unit collects a large amount of historical data. The analysis unit analyzes the data collected by the data collection unit. The generation unit generates a predictive model based on the analysis results obtained by the analysis unit. The proposal unit makes strategic proposals based on the predictive model generated by the generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can predict future risks by utilizing past failure cases and make strategic proposals. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) An AI agent system according to an embodiment of the present invention is a system that analyzes historical failure cases and provides a predictive model for preventing similar failures in the future. This AI agent system collects a large amount of historical data and performs pattern recognition and prediction using machine learning. Next, the AI ​​agent analyzes this data to improve the risk reduction rate, streamline strategic decision-making, and improve the accuracy of future predictions. Furthermore, it automatically generates strategic proposals for users such as strategists, risk managers, executives, and policymakers, learning from past failures and predicting future problems to reduce risk and support more effective decision-making. In this way, the AI ​​agent system can analyze historical failure cases and provide a predictive model for preventing similar failures in the future.

[0029] The AI ​​agent system according to this embodiment comprises a collection unit, an analysis unit, a generation unit, and a proposal unit. The collection unit collects large amounts of historical data. The collection unit collects data from, for example, world history, Japanese history, corporate history, and startup history. The collection unit can collect data in the form of, for example, text data, numerical data, and image data. The collection unit collects data from, for example, publicly available databases and archives on the internet. The collection unit can also collect data provided by companies and research institutions. The collection unit, for example, evaluates the reliability of the data during data collection and prioritizes the collection of highly reliable data. The analysis unit analyzes the data collected by the collection unit. The analysis unit, for example, uses machine learning to analyze the data and perform pattern recognition and prediction. The analysis unit can use machine learning algorithms such as supervised learning, unsupervised learning, and reinforcement learning. The analysis unit, for example, analyzes the correlation between data and discovers hidden patterns. The analysis unit applies different machine learning algorithms to obtain the optimal analysis result. The generation unit generates a predictive model based on the analysis results obtained by the analysis unit. The generation unit generates predictive models that, for example, improve risk reduction rates, streamline strategic decision-making, and enhance the accuracy of future predictions. The generation unit can generate predictive models such as regression models, classification models, and time series models. The generation unit evaluates the accuracy of past predictive models and selects the optimal model. The generation unit generates multiple predictive models, for example, by considering different scenarios. The proposal unit makes strategic proposals based on the predictive models generated by the generation unit. The proposal unit automatically generates strategic proposals for users such as strategists, risk managers, executives, and policymakers. The proposal unit helps reduce risk and support more effective decision-making by learning from past failures and predicting future problems. The proposal unit provides proposals in a format that is easy for users to understand, for example, by visually displaying the proposal content. As a result, the AI ​​agent system according to the embodiment can prevent similar failures in the future by collecting and analyzing large amounts of historical data, generating predictive models, and making strategic proposals.

[0030] The data collection unit collects large amounts of historical data. Specifically, it collects data from a wide range of fields, including world history, Japanese history, corporate history, and startup history. The collected data comes in diverse formats, such as text data, numerical data, and image data, enabling comprehensive information to be obtained. The data collection unit collects data not only from publicly available databases and archives on the internet, but also from companies and research institutions. Examples include historical documents and reports, corporate financial data, and startup growth records. When collecting data, the data collection unit evaluates the reliability of the data and prioritizes the collection of reliable data. Factors considered in the reliability evaluation include the data source, the frequency of data updates, and the data consistency. For example, academic papers and data from government agencies are considered highly reliable and are collected preferentially. The data collection unit also detects data duplication and missing data and cleans the data as needed. This maintains the quality of the collected data and ensures high accuracy in subsequent analysis and the generation of predictive models. Furthermore, the data collection unit can achieve real-time capabilities by adjusting the frequency and timing of data collection. For example, when important events or occurrences occur, data is collected quickly to improve the overall response speed of the system. This allows the data collection unit to collect data efficiently and effectively, improving the overall performance of the system.

[0031] The analysis department analyzes the data collected by the data collection department. Specifically, it uses machine learning to analyze the data and perform pattern recognition and prediction. The analysis department can use machine learning algorithms such as supervised learning, unsupervised learning, and reinforcement learning. For example, in supervised learning, a model is trained using past data and labels to make predictions on new data. In unsupervised learning, data clustering and dimensionality reduction are performed to discover hidden structures in the data. In reinforcement learning, an agent learns optimal behavior through interaction with the environment. The analysis department analyzes the correlations between data to discover hidden patterns. For example, it can analyze corporate growth patterns, market trends, and causal relationships of historical events. By applying different machine learning algorithms, the analysis department compares and considers multiple algorithms to obtain the optimal analysis results and selects the most suitable one. Furthermore, the analysis department improves the performance of the model by performing data preprocessing and feature engineering. For example, it performs data normalization, missing value imputation, and feature selection and generation. As a result, the analysis department can quickly and accurately analyze the collected data and grasp the surrounding risk situation in real time. Furthermore, the analysis department can utilize historical data and statistical information to conduct long-term risk assessments and trend analyses. For example, it can predict risk fluctuations in specific areas and time periods based on past flood data and formulate future countermeasures. The analysis department can also use anomaly detection algorithms to detect unusual patterns and abnormal data, issuing early warnings. As a result, the analysis department can not only grasp the situation in real time but also handle long-term risk management and anomaly detection, improving the reliability and safety of the entire system.

[0032] The generation unit generates predictive models based on the analysis results obtained by the analysis unit. Specifically, it generates predictive models that improve risk reduction rates, streamline strategic decision-making, and enhance the accuracy of future forecasts. The generation unit can generate predictive models such as regression models, classification models, and time series models. For example, it can use regression models to forecast company sales, classification models to identify market segments, and time series models to predict fluctuations in economic indicators. The generation unit evaluates the accuracy of past predictive models and selects the optimal model. For example, it evaluates the performance of models using cross-validation and holdout validation and selects the model with the highest accuracy. Furthermore, the generation unit generates multiple predictive models considering different scenarios. For example, it considers economic growth scenarios, recession scenarios, and technological innovation scenarios, and generates the optimal predictive model for each scenario. This allows the generation unit to make flexible forecasts that respond to various situations. In addition, the generation unit continuously monitors the performance of the generated predictive models and updates or retrains the models as needed. For example, it retrains the models when new data is collected or in response to changes in the environment, always providing forecasts based on the latest information. This allows the generation unit to produce highly accurate and reliable predictive models, thereby improving the overall system performance.

[0033] The proposal unit provides strategic recommendations based on predictive models generated by the generation unit. Specifically, it automatically generates strategic recommendations for users such as strategists, risk managers, executives, and policymakers. The proposal unit learns from past failures and predicts future problems to reduce risks and support more effective decision-making. For example, in corporate management strategy, it analyzes past market trends and the actions of competitors to propose the optimal strategy. In risk management, it predicts potential risks and proposes risk avoidance measures and emergency response measures. The proposal unit displays the content of its recommendations visually and provides them in a format that is easy for users to understand. For example, it uses graphs, charts, and heatmaps to visualize data and make the content of the recommendations intuitively understandable. The proposal unit also collects user feedback and continuously improves the accuracy and effectiveness of its recommendations. For example, it adjusts and improves the recommendation algorithm based on feedback from users who have received recommendations. Furthermore, the proposal unit can reliably transmit information using multiple communication methods. For example, it can quickly deliver important recommendations through email and notification systems. This allows the proposal unit to provide users with strategic recommendations quickly and reliably, preventing similar failures in the future.

[0034] The data collection unit can collect data from world history, Japanese history, corporate history, and startup history. For example, the data collection unit can collect data from world history. For example, it can collect data on historical events and people. The data collection unit can also collect data from Japanese history. For example, it can collect data on historical events and culture in Japan. Furthermore, the data collection unit can collect data from corporate history. For example, it can collect data on the establishment, growth, and failure of companies. The data collection unit can also collect data from startup history. For example, it can collect data on the success and failure of startup companies. By collecting diverse historical data, it is possible to generate more comprehensive predictive models. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not. For example, when the data collection unit collects data from publicly available databases on the internet, it can use AI to evaluate the reliability of the data and prioritize the collection of reliable data.

[0035] The analysis unit can analyze collected data using machine learning to perform pattern recognition and prediction. For example, the analysis unit can analyze collected data using supervised learning. For example, the analysis unit can label the data, train a model, and perform pattern recognition. The analysis unit can also analyze collected data using unsupervised learning. For example, the analysis unit can cluster the data and discover hidden patterns. Furthermore, the analysis unit can analyze collected data using reinforcement learning. For example, the analysis unit can learn the optimal action from the data and make predictions. This improves the accuracy of pattern recognition and prediction of data by using machine learning. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input collected data into an AI, which can perform pattern recognition and prediction of the data.

[0036] The generation unit can generate predictive models that improve risk reduction rates, streamline strategic decision-making, and enhance the accuracy of future predictions based on the analysis results. For example, the generation unit can generate predictive models that improve risk reduction rates based on the analysis results. For example, the generation unit can generate predictive models that identify risk factors and propose risk reduction measures based on them. The generation unit can also generate predictive models that streamline strategic decision-making based on the analysis results. For example, the generation unit can generate predictive models that optimize the decision-making process and propose efficient strategies. Furthermore, the generation unit can generate predictive models that enhance the accuracy of future predictions based on the analysis results. For example, the generation unit can generate models that predict future events based on past data. By generating predictive models that improve risk reduction rates, streamline strategic decision-making, and enhance the accuracy of future predictions, the generation unit supports more effective decision-making. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input analysis results into AI, and the AI ​​can generate a predictive model.

[0037] The proposal unit can automatically generate strategic proposals for users such as strategists, risk managers, executives, and policymakers based on the generated predictive model. For example, the proposal unit can automatically generate strategic proposals for strategists. For example, the proposal unit can generate proposals that strategists can use as a reference when making decisions. The proposal unit can also automatically generate strategic proposals for risk managers. For example, the proposal unit can generate proposals that risk managers can use as a reference when assessing risks and taking countermeasures. Furthermore, the proposal unit can also automatically generate strategic proposals for executives. For example, the proposal unit can generate proposals that executives can use as a reference when formulating business strategies. The proposal unit can also automatically generate strategic proposals for policymakers. For example, the proposal unit can generate proposals that policymakers can use as a reference when formulating policies. In this way, by automatically generating strategic proposals, it supports user decision-making. Some or all of the above processes in the proposal unit may be performed using AI, for example, or without using AI. For example, the proposal department can input the generated predictive model into an AI, which can then automatically generate strategic proposals.

[0038] The proposal department can reduce risks and support more effective decision-making by learning from past failures and predicting future problems. For example, the proposal department can analyze past failure cases and predict future problems. For example, the proposal department can extract common patterns from past failure cases and predict future problems based on them. The proposal department can also make suggestions to reduce risks by predicting future problems. For example, the proposal department can propose countermeasures for predicted problems. Furthermore, the proposal department can support more effective decision-making by predicting future problems. For example, the proposal department can propose the optimal decision for predicted problems. In this way, by learning from past failures and predicting future problems, risks are reduced and more effective decision-making is supported. Some or all of the above processes in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can input past failure cases into AI, which can predict future problems and make suggestions based on them.

[0039] The data collection unit can evaluate the reliability of the data during collection and prioritize the collection of reliable data. For example, the data collection unit can evaluate the reliability of data sources and prioritize the collection of data from highly-rated sources. For example, the data collection unit can collect data from official institutions and reliable research institutions. The data collection unit can also verify the source of the data and prioritize the collection of data from official institutions. For example, the data collection unit can verify the source of the data and select reliable data. Furthermore, the data collection unit can check the update history of the data and prioritize the collection of reliable data that is frequently updated. For example, the data collection unit can check the update history of the data and collect the latest data. This improves data quality by evaluating the reliability of the data and prioritizing the collection of reliable data. Some or all of the above processes in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input the reliability of the data into AI, and the AI ​​can select reliable data.

[0040] The data collection unit can prioritize the collection of the latest data, taking into account the data update frequency during collection. For example, the data collection unit can check the data update frequency and prioritize the collection of the latest data. For example, the data collection unit can collect data from frequently updated data sources. The data collection unit can also prioritize the collection of data that is updated in real time. For example, the data collection unit can collect news articles and social media posts that are updated in real time. Furthermore, the data collection unit can also prioritize the collection of the latest data by comparing it with historical data. For example, the data collection unit can compare historical data with the latest data and select the latest data. This allows for analysis based on the latest information by prioritizing the collection of the latest data, taking into account the data update frequency. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the data update frequency into the AI, and the AI ​​can select the latest data.

[0041] The data collection unit can prioritize the collection of data from specific regions, taking into account the geographical distribution of the data during collection. For example, the data collection unit can prioritize the collection of data from a particular region. For example, the data collection unit can collect data on historical events and culture in a particular region. The data collection unit can also collect data without geographical bias. For example, the data collection unit can collect data from various regions in a balanced manner. Furthermore, the data collection unit can collect data from each region in a balanced manner. For example, the data collection unit can collect data from each region equally to construct a balanced dataset. This allows for analysis that takes into account region-specific risks by prioritizing the collection of data from specific regions, taking into account the geographical distribution of the data. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the geographical distribution of the data into the AI, which can then prioritize the collection of data from a specific region.

[0042] The data collection unit can select the optimal data collection method according to the data format at the time of collection. For example, in the case of text data, the data collection unit can use web scraping to collect it. For example, the data collection unit can collect text data from publicly available databases on the internet. In the case of image data, the data collection unit can also use image recognition technology to collect it. For example, the data collection unit can collect image data from the internet and analyze it using image recognition technology. Furthermore, in the case of audio data, the data collection unit can also use speech recognition technology to collect it. For example, the data collection unit can collect audio data and convert it into text data using speech recognition technology. This enables efficient data collection by selecting the optimal data collection method according to the data format. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the data format into AI, and the AI ​​can select the optimal data collection method.

[0043] The analysis unit can analyze data correlations in detail during analysis and discover hidden patterns. For example, the analysis unit can analyze data correlations and discover hidden patterns. For example, the analysis unit can calculate correlation coefficients to clarify the relationships between data. The analysis unit can also visualize data correlations and discover hidden patterns. For example, the analysis unit can create correlation matrices to visually show the relationships between data. Furthermore, the analysis unit can analyze data correlations using machine learning and discover hidden patterns. For example, the analysis unit can use machine learning algorithms to analyze data correlations and identify hidden patterns. This allows for deeper insights by analyzing data correlations in detail and discovering hidden patterns. Some or all of the above processes in the analysis unit may be performed using AI, for example, or not. For example, the analysis unit can input data correlations into AI, which can analyze the correlations and discover hidden patterns.

[0044] The analysis unit can obtain optimal analysis results by applying different machine learning algorithms during analysis. For example, the analysis unit can apply multiple algorithms and compare their performance. The analysis unit can also compare the performance of machine learning algorithms and select the optimal algorithm. For example, the analysis unit can evaluate the accuracy and computation time of each algorithm and select the optimal algorithm. Furthermore, the analysis unit can obtain optimal analysis results by combining different machine learning algorithms. For example, the analysis unit can use multiple algorithms in combination to perform analysis that leverages the strengths of each. This allows for the application of different machine learning algorithms to obtain optimal analysis results. Some or all of the above processes in the analysis unit may be performed using AI, or not using AI. For example, the analysis unit can input different machine learning algorithms into an AI, which can then select the optimal algorithm.

[0045] The analysis unit can analyze long-term trends by considering the temporal changes in data during analysis. For example, the analysis unit can analyze long-term trends by considering the temporal changes in data. For example, the analysis unit can visualize the temporal changes in data to reveal long-term trends. The analysis unit can also identify long-term trends by analyzing the temporal changes in data using machine learning. For example, the analysis unit can analyze time-series data to predict future trends. Furthermore, the analysis unit can compare data from different periods by considering the temporal changes in data. For example, the analysis unit can compare past data with current data to identify changes in trends. This improves the accuracy of future predictions by analyzing long-term trends while considering the temporal changes in data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the temporal changes in data into AI, and the AI ​​can analyze long-term trends.

[0046] The analysis unit can perform comprehensive analysis by integrating different data sources during the analysis process. For example, the analysis unit can collect data from multiple data sources, integrate them, and analyze them. The analysis unit can also evaluate the reliability of data sources and prioritize the integration of highly reliable data. For example, the analysis unit can select and integrate data from highly reliable data sources. Furthermore, the analysis unit can unify the format of data sources to perform comprehensive analysis. For example, the analysis unit can convert data in different formats into a unified format and analyze it. This enables comprehensive analysis by integrating different data sources. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input different data sources into AI, and the AI ​​can integrate the data and perform comprehensive analysis.

[0047] The generation unit can evaluate the accuracy of past prediction models during generation and select the optimal model. For example, the generation unit can evaluate the accuracy of past prediction models and select the optimal model. For example, the generation unit can compare the performance of each prediction model and select the optimal model. The generation unit can also evaluate the performance of prediction models using machine learning and select the optimal model. For example, the generation unit can evaluate the accuracy of past prediction models and select the optimal model based on the evaluation results. Furthermore, the generation unit can continuously evaluate the performance of prediction models and select the optimal model. For example, the generation unit periodically evaluates the accuracy of prediction models and updates the models as needed. This allows the optimal prediction model to be selected by evaluating the accuracy of past prediction models. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the accuracy of past prediction models into AI, and the AI ​​can select the optimal model.

[0048] The generation unit can generate multiple predictive models by considering different scenarios during the generation process. For example, the generation unit can generate multiple predictive models by considering different scenarios. For example, the generation unit can set different parameters for each scenario and generate multiple predictive models. The generation unit can also analyze different scenarios using machine learning and generate multiple predictive models. For example, the generation unit can consider different scenarios and generate the optimal predictive model for each scenario. Furthermore, the generation unit can evaluate the performance of the predictive models by considering different scenarios. For example, the generation unit can evaluate the accuracy of the predictive models in each scenario and select the optimal model. In this way, multiple predictive models can be generated by considering different scenarios. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input different scenarios into AI, and the AI ​​can generate multiple predictive models.

[0049] The generation unit can generate a general-purpose predictive model by considering data from different industries and fields during the generation process. For example, the generation unit can generate a general-purpose predictive model by considering data from different industries and fields. For example, the generation unit can generate a general-purpose predictive model by considering the characteristics of each industry and field. The generation unit can also generate a general-purpose predictive model by analyzing data from different industries and fields using machine learning. For example, the generation unit can integrate data from different industries and fields and generate a general-purpose predictive model based on that. Furthermore, the generation unit can evaluate the performance of predictive models by considering data from different industries and fields. For example, the generation unit can evaluate the accuracy of predictive models in each industry and field and select the optimal model. This allows for the generation of a general-purpose predictive model by considering data from different industries and fields. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input data from different industries and fields into AI, and the AI ​​can generate a general-purpose predictive model.

[0050] The generation unit can visualize the results of the predictive model during generation and provide them in a format that is easy for users to understand. For example, the generation unit can visualize the results of the predictive model using graphs or charts. For example, the generation unit can create graphs or charts that visually show the prediction results. The generation unit can also provide the results of the predictive model in a dashboard format. For example, the generation unit can create a dashboard that allows users to grasp the prediction results at a glance. Furthermore, the generation unit can provide the results of the predictive model in an interactive format. For example, the generation unit can create an interactive dashboard that allows users to manipulate the prediction results. This makes it possible to provide the results of the predictive model in a format that is easy for users to understand by visualizing them. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the results of the predictive model into AI, and the AI ​​can visualize the results.

[0051] The proposal department can evaluate the effectiveness of past proposals and select the optimal proposal at the time of proposal submission. For example, the proposal department can evaluate the effectiveness of past proposals and select the optimal proposal. For example, the proposal department can compare the performance of each proposal and select the optimal proposal. The proposal department can also evaluate the performance of proposals using machine learning and select the optimal proposal. For example, the proposal department can evaluate the effectiveness of past proposals and select the optimal proposal based on the evaluation results. Furthermore, the proposal department can continuously evaluate the performance of proposals and select the optimal proposal. For example, the proposal department can periodically evaluate the effectiveness of proposals and update the proposal content as needed. This allows the proposal department to select the optimal proposal by evaluating the effectiveness of past proposals. Some or all of the above processes in the proposal department may be performed using AI, for example, or without AI. For example, the proposal department can input the effectiveness of past proposals into AI, and the AI ​​can select the optimal proposal.

[0052] The proposal department can provide customized proposals by considering the user's attribute information (job title, industry, experience, etc.) when making a proposal. For example, the proposal department can provide customized proposals according to the user's job title. For example, the proposal department can differentiate between proposals for managers and proposals for field staff. The proposal department can also provide customized proposals according to the user's industry. For example, the proposal department can differentiate between proposals for manufacturing companies and proposals for service companies. Furthermore, the proposal department can provide customized proposals according to the user's experience. For example, the proposal department can differentiate between proposals for beginners and proposals for experienced users. In this way, customized proposals can be made by considering the user's attribute information. Some or all of the above processing in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can input the user's attribute information into AI, and the AI ​​can generate customized proposals.

[0053] The proposal unit can make multiple proposals by considering different risk scenarios. For example, the proposal unit can make multiple proposals by considering different risk scenarios. For example, the proposal unit can provide different proposals for each risk scenario. The proposal unit can also analyze different risk scenarios using machine learning and make multiple proposals. For example, the proposal unit can generate the optimal proposal for each risk scenario. Furthermore, the proposal unit can evaluate the performance of proposals by considering different risk scenarios. For example, the proposal unit can evaluate the effectiveness of proposals in each risk scenario and select the optimal proposal. In this way, multiple proposals can be made by considering different risk scenarios. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not using AI. For example, the proposal unit can input different risk scenarios into AI, and the AI ​​can generate multiple proposals.

[0054] The proposal department can visually display the proposed content and provide it in a format that is easy for users to understand. For example, the proposal department can visually display the proposed content using graphs and charts. For example, the proposal department can create graphs and charts that visually represent the proposed content. The proposal department can also provide the proposed content in a dashboard format. For example, the proposal department can create a dashboard that allows users to grasp the proposed content at a glance. Furthermore, the proposal department can provide the proposed content in an interactive format. For example, the proposal department can create an interactive dashboard that allows users to interact with the proposed content. This allows the proposed content to be visually displayed and provided in a format that is easy for users to understand. Some or all of the above processing in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can input the proposed content into AI, and the AI ​​can visualize the content.

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

[0056] The data collection unit can select the optimal collection method depending on the format of the data to be collected. For example, in the case of text data, the data collection unit can use web scraping to collect the data. In the case of image data, the data collection unit can use image recognition technology to collect the data. Furthermore, in the case of audio data, the data collection unit can use speech recognition technology to collect the data. This enables efficient data collection by selecting the optimal collection method according to the data format.

[0057] The analysis department can apply different machine learning algorithms to the collected data to obtain optimal analysis results. For example, the analysis department can apply multiple algorithms and compare their performance. It can also evaluate the accuracy and computation time of each algorithm and select the optimal one. Furthermore, it can combine different machine learning algorithms to perform analysis that leverages the strengths of each. In this way, optimal analysis results can be obtained by applying different machine learning algorithms.

[0058] The generation unit can visualize the results of the generated predictive model and provide them in a format that is easy for users to understand. For example, the generation unit can create graphs and charts that visually represent the prediction results. It can also create dashboards that allow users to grasp the prediction results at a glance. Furthermore, it can create interactive dashboards that allow users to manipulate the prediction results. In this way, by visualizing the results of the predictive model, it can provide them in a format that is easy for users to understand.

[0059] The proposal team can visually display the proposal content and provide it in a format that is easy for users to understand. For example, the proposal team can create graphs and charts that visually represent the proposal content. They can also create dashboards that allow users to grasp the proposal content at a glance. Furthermore, they can create interactive dashboards that allow users to manipulate the proposal content. In this way, the proposal content can be visually displayed and provided in a format that is easy for users to understand.

[0060] The proposal department can provide customized proposals by considering the user's attribute information (job title, industry, experience, etc.) when making a proposal. For example, it can differentiate between proposals for managers and proposals for on-site staff depending on the user's job title. It can also differentiate between proposals for manufacturing and proposals for service industries depending on the user's industry. Furthermore, it can differentiate between proposals for beginners and proposals for experienced users depending on the user's experience. In this way, customized proposals can be made by considering the user's attribute information.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The data collection unit collects large amounts of historical data. The data collection unit collects data from sources such as world history, Japanese history, corporate history, and startup history. The data collection unit can collect data in various formats, such as text data, numerical data, and image data. The data collection unit collects data from publicly available databases and archives on the internet, for example. The data collection unit can also collect data provided by companies and research institutions. The data collection unit evaluates the reliability of the data during the data collection process and prioritizes the collection of highly reliable data. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit analyzes the data using machine learning, for example, to perform pattern recognition and prediction. The analysis unit can use machine learning algorithms such as supervised learning, unsupervised learning, and reinforcement learning. The analysis unit can analyze the correlation between data and discover hidden patterns, for example. The analysis unit can apply different machine learning algorithms to obtain the optimal analysis results, for example. Step 3: The generation unit generates a predictive model based on the analysis results obtained by the analysis unit. The generation unit generates predictive models that, for example, improve risk reduction rates, streamline strategic decision-making, and improve the accuracy of future predictions. The generation unit can generate predictive models such as regression models, classification models, and time series models. The generation unit can, for example, evaluate the accuracy of past predictive models and select the optimal model. The generation unit can, for example, generate multiple predictive models considering different scenarios. Step 4: The proposal unit makes strategic proposals based on the predictive model generated by the generation unit. The proposal unit automatically generates strategic proposals for users such as strategists, risk managers, executives, and policymakers. The proposal unit helps reduce risks and support more effective decision-making by, for example, learning from past failures and predicting future problems. The proposal unit presents the proposals in a visually understandable format for the user.

[0063] (Example of form 2) An AI agent system according to an embodiment of the present invention is a system that analyzes historical failure cases and provides a predictive model for preventing similar failures in the future. This AI agent system collects a large amount of historical data and performs pattern recognition and prediction using machine learning. Next, the AI ​​agent analyzes this data to improve the risk reduction rate, streamline strategic decision-making, and improve the accuracy of future predictions. Furthermore, it automatically generates strategic proposals for users such as strategists, risk managers, executives, and policymakers, learning from past failures and predicting future problems to reduce risk and support more effective decision-making. In this way, the AI ​​agent system can analyze historical failure cases and provide a predictive model for preventing similar failures in the future.

[0064] The AI ​​agent system according to this embodiment comprises a collection unit, an analysis unit, a generation unit, and a proposal unit. The collection unit collects large amounts of historical data. The collection unit collects data from, for example, world history, Japanese history, corporate history, and startup history. The collection unit can collect data in the form of, for example, text data, numerical data, and image data. The collection unit collects data from, for example, publicly available databases and archives on the internet. The collection unit can also collect data provided by companies and research institutions. The collection unit, for example, evaluates the reliability of the data during data collection and prioritizes the collection of highly reliable data. The analysis unit analyzes the data collected by the collection unit. The analysis unit, for example, uses machine learning to analyze the data and perform pattern recognition and prediction. The analysis unit can use machine learning algorithms such as supervised learning, unsupervised learning, and reinforcement learning. The analysis unit, for example, analyzes the correlation between data and discovers hidden patterns. The analysis unit applies different machine learning algorithms to obtain the optimal analysis result. The generation unit generates a predictive model based on the analysis results obtained by the analysis unit. The generation unit generates predictive models that, for example, improve risk reduction rates, streamline strategic decision-making, and enhance the accuracy of future predictions. The generation unit can generate predictive models such as regression models, classification models, and time series models. The generation unit evaluates the accuracy of past predictive models and selects the optimal model. The generation unit generates multiple predictive models, for example, by considering different scenarios. The proposal unit makes strategic proposals based on the predictive models generated by the generation unit. The proposal unit automatically generates strategic proposals for users such as strategists, risk managers, executives, and policymakers. The proposal unit helps reduce risk and support more effective decision-making by learning from past failures and predicting future problems. The proposal unit provides proposals in a format that is easy for users to understand, for example, by visually displaying the proposal content. As a result, the AI ​​agent system according to the embodiment can prevent similar failures in the future by collecting and analyzing large amounts of historical data, generating predictive models, and making strategic proposals.

[0065] The data collection unit collects large amounts of historical data. Specifically, it collects data from a wide range of fields, including world history, Japanese history, corporate history, and startup history. The collected data comes in diverse formats, such as text data, numerical data, and image data, enabling comprehensive information to be obtained. The data collection unit collects data not only from publicly available databases and archives on the internet, but also from companies and research institutions. Examples include historical documents and reports, corporate financial data, and startup growth records. When collecting data, the data collection unit evaluates the reliability of the data and prioritizes the collection of reliable data. Factors considered in the reliability evaluation include the data source, the frequency of data updates, and the data consistency. For example, academic papers and data from government agencies are considered highly reliable and are collected preferentially. The data collection unit also detects data duplication and missing data and cleans the data as needed. This maintains the quality of the collected data and ensures high accuracy in subsequent analysis and the generation of predictive models. Furthermore, the data collection unit can achieve real-time capabilities by adjusting the frequency and timing of data collection. For example, when important events or occurrences occur, data is collected quickly to improve the overall response speed of the system. This allows the data collection unit to collect data efficiently and effectively, improving the overall performance of the system.

[0066] The analysis department analyzes the data collected by the data collection department. Specifically, it uses machine learning to analyze the data and perform pattern recognition and prediction. The analysis department can use machine learning algorithms such as supervised learning, unsupervised learning, and reinforcement learning. For example, in supervised learning, a model is trained using past data and labels to make predictions on new data. In unsupervised learning, data clustering and dimensionality reduction are performed to discover hidden structures in the data. In reinforcement learning, an agent learns optimal behavior through interaction with the environment. The analysis department analyzes the correlations between data to discover hidden patterns. For example, it can analyze corporate growth patterns, market trends, and causal relationships of historical events. By applying different machine learning algorithms, the analysis department compares and considers multiple algorithms to obtain the optimal analysis results and selects the most suitable one. Furthermore, the analysis department improves the performance of the model by performing data preprocessing and feature engineering. For example, it performs data normalization, missing value imputation, and feature selection and generation. As a result, the analysis department can quickly and accurately analyze the collected data and grasp the surrounding risk situation in real time. Furthermore, the analysis department can utilize historical data and statistical information to conduct long-term risk assessments and trend analyses. For example, it can predict risk fluctuations in specific areas and time periods based on past flood data and formulate future countermeasures. The analysis department can also use anomaly detection algorithms to detect unusual patterns and abnormal data, issuing early warnings. As a result, the analysis department can not only grasp the situation in real time but also handle long-term risk management and anomaly detection, improving the reliability and safety of the entire system.

[0067] The generation unit generates predictive models based on the analysis results obtained by the analysis unit. Specifically, it generates predictive models that improve risk reduction rates, streamline strategic decision-making, and enhance the accuracy of future forecasts. The generation unit can generate predictive models such as regression models, classification models, and time series models. For example, it can use regression models to forecast company sales, classification models to identify market segments, and time series models to predict fluctuations in economic indicators. The generation unit evaluates the accuracy of past predictive models and selects the optimal model. For example, it evaluates the performance of models using cross-validation and holdout validation and selects the model with the highest accuracy. Furthermore, the generation unit generates multiple predictive models considering different scenarios. For example, it considers economic growth scenarios, recession scenarios, and technological innovation scenarios, and generates the optimal predictive model for each scenario. This allows the generation unit to make flexible forecasts that respond to various situations. In addition, the generation unit continuously monitors the performance of the generated predictive models and updates or retrains the models as needed. For example, it retrains the models when new data is collected or in response to changes in the environment, always providing forecasts based on the latest information. This allows the generation unit to produce highly accurate and reliable predictive models, thereby improving the overall system performance.

[0068] The proposal unit provides strategic recommendations based on predictive models generated by the generation unit. Specifically, it automatically generates strategic recommendations for users such as strategists, risk managers, executives, and policymakers. The proposal unit learns from past failures and predicts future problems to reduce risks and support more effective decision-making. For example, in corporate management strategy, it analyzes past market trends and the actions of competitors to propose the optimal strategy. In risk management, it predicts potential risks and proposes risk avoidance measures and emergency response measures. The proposal unit displays the content of its recommendations visually and provides them in a format that is easy for users to understand. For example, it uses graphs, charts, and heatmaps to visualize data and make the content of the recommendations intuitively understandable. The proposal unit also collects user feedback and continuously improves the accuracy and effectiveness of its recommendations. For example, it adjusts and improves the recommendation algorithm based on feedback from users who have received recommendations. Furthermore, the proposal unit can reliably transmit information using multiple communication methods. For example, it can quickly deliver important recommendations through email and notification systems. This allows the proposal unit to provide users with strategic recommendations quickly and reliably, preventing similar failures in the future.

[0069] The data collection unit can collect data from world history, Japanese history, corporate history, and startup history. For example, the data collection unit can collect data from world history. For example, it can collect data on historical events and people. The data collection unit can also collect data from Japanese history. For example, it can collect data on historical events and culture in Japan. Furthermore, the data collection unit can collect data from corporate history. For example, it can collect data on the establishment, growth, and failure of companies. The data collection unit can also collect data from startup history. For example, it can collect data on the success and failure of startup companies. By collecting diverse historical data, it is possible to generate more comprehensive predictive models. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not. For example, when the data collection unit collects data from publicly available databases on the internet, it can use AI to evaluate the reliability of the data and prioritize the collection of reliable data.

[0070] The analysis unit can analyze collected data using machine learning to perform pattern recognition and prediction. For example, the analysis unit can analyze collected data using supervised learning. For example, the analysis unit can label the data, train a model, and perform pattern recognition. The analysis unit can also analyze collected data using unsupervised learning. For example, the analysis unit can cluster the data and discover hidden patterns. Furthermore, the analysis unit can analyze collected data using reinforcement learning. For example, the analysis unit can learn the optimal action from the data and make predictions. This improves the accuracy of pattern recognition and prediction of data by using machine learning. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input collected data into an AI, which can perform pattern recognition and prediction of the data.

[0071] The generation unit can generate predictive models that improve risk reduction rates, streamline strategic decision-making, and enhance the accuracy of future predictions based on the analysis results. For example, the generation unit can generate predictive models that improve risk reduction rates based on the analysis results. For example, the generation unit can generate predictive models that identify risk factors and propose risk reduction measures based on them. The generation unit can also generate predictive models that streamline strategic decision-making based on the analysis results. For example, the generation unit can generate predictive models that optimize the decision-making process and propose efficient strategies. Furthermore, the generation unit can generate predictive models that enhance the accuracy of future predictions based on the analysis results. For example, the generation unit can generate models that predict future events based on past data. By generating predictive models that improve risk reduction rates, streamline strategic decision-making, and enhance the accuracy of future predictions, the generation unit supports more effective decision-making. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input analysis results into AI, and the AI ​​can generate a predictive model.

[0072] The proposal unit can automatically generate strategic proposals for users such as strategists, risk managers, executives, and policymakers based on the generated predictive model. For example, the proposal unit can automatically generate strategic proposals for strategists. For example, the proposal unit can generate proposals that strategists can use as a reference when making decisions. The proposal unit can also automatically generate strategic proposals for risk managers. For example, the proposal unit can generate proposals that risk managers can use as a reference when assessing risks and taking countermeasures. Furthermore, the proposal unit can also automatically generate strategic proposals for executives. For example, the proposal unit can generate proposals that executives can use as a reference when formulating business strategies. The proposal unit can also automatically generate strategic proposals for policymakers. For example, the proposal unit can generate proposals that policymakers can use as a reference when formulating policies. In this way, by automatically generating strategic proposals, it supports user decision-making. Some or all of the above processes in the proposal unit may be performed using AI, for example, or without using AI. For example, the proposal department can input the generated predictive model into an AI, which can then automatically generate strategic proposals.

[0073] The proposal department can reduce risks and support more effective decision-making by learning from past failures and predicting future problems. For example, the proposal department can analyze past failure cases and predict future problems. For example, the proposal department can extract common patterns from past failure cases and predict future problems based on them. The proposal department can also make suggestions to reduce risks by predicting future problems. For example, the proposal department can propose countermeasures for predicted problems. Furthermore, the proposal department can support more effective decision-making by predicting future problems. For example, the proposal department can propose the optimal decision for predicted problems. In this way, by learning from past failures and predicting future problems, risks are reduced and more effective decision-making is supported. Some or all of the above processes in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can input past failure cases into AI, which can predict future problems and make suggestions based on them.

[0074] The data collection unit can estimate the user's emotions and determine the priority of data to collect based on the estimated emotions. For example, if the user is feeling anxious, the data collection unit will prioritize collecting reliable data. For example, it will collect data from reliable data sources. Also, if the user is excited, the data collection unit can prioritize collecting the latest data. For example, it will collect the latest research findings and news articles. Furthermore, if the user is relaxed, the data collection unit can collect a wide range of data in a balanced manner. For example, it will collect data from various data sources to build a balanced dataset. This allows for more appropriate data collection by prioritizing data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not using AI. For example, the data collection unit can input the user's emotions into an AI, which can then prioritize data based on those emotions.

[0075] The data collection unit can evaluate the reliability of the data during collection and prioritize the collection of reliable data. For example, the data collection unit can evaluate the reliability of data sources and prioritize the collection of data from highly-rated sources. For example, the data collection unit can collect data from official institutions and reliable research institutions. The data collection unit can also verify the source of the data and prioritize the collection of data from official institutions. For example, the data collection unit can verify the source of the data and select reliable data. Furthermore, the data collection unit can check the update history of the data and prioritize the collection of reliable data that is frequently updated. For example, the data collection unit can check the update history of the data and collect the latest data. This improves data quality by evaluating the reliability of the data and prioritizing the collection of reliable data. Some or all of the above processes in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input the reliability of the data into AI, and the AI ​​can select reliable data.

[0076] The data collection unit can prioritize the collection of the latest data, taking into account the data update frequency during collection. For example, the data collection unit can check the data update frequency and prioritize the collection of the latest data. For example, the data collection unit can collect data from frequently updated data sources. The data collection unit can also prioritize the collection of data that is updated in real time. For example, the data collection unit can collect news articles and social media posts that are updated in real time. Furthermore, the data collection unit can also prioritize the collection of the latest data by comparing it with historical data. For example, the data collection unit can compare historical data with the latest data and select the latest data. This allows for analysis based on the latest information by prioritizing the collection of the latest data, taking into account the data update frequency. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the data update frequency into the AI, and the AI ​​can select the latest data.

[0077] The data collection unit can estimate the user's emotions and adjust the scope of data collected based on the estimated emotions. For example, if the user is feeling anxious, the data collection unit can narrow the scope to reliable data. For example, the data collection unit can collect data from reliable data sources. Also, if the user is excited, the data collection unit can broaden the scope to include the latest data. For example, the data collection unit can collect the latest research findings and news articles. Furthermore, if the user is relaxed, the data collection unit can collect a wide range of data. For example, the data collection unit can collect data from various data sources to build a balanced dataset. This allows for more appropriate data collection by adjusting the scope of data based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's emotions into an AI, which can then adjust the scope of data based on the emotions.

[0078] The data collection unit can prioritize the collection of data from specific regions, taking into account the geographical distribution of the data during collection. For example, the data collection unit can prioritize the collection of data from a particular region. For example, the data collection unit can collect data on historical events and culture in a particular region. The data collection unit can also collect data without geographical bias. For example, the data collection unit can collect data from various regions in a balanced manner. Furthermore, the data collection unit can collect data from each region in a balanced manner. For example, the data collection unit can collect data from each region equally to construct a balanced dataset. This allows for analysis that takes into account region-specific risks by prioritizing the collection of data from specific regions, taking into account the geographical distribution of the data. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the geographical distribution of the data into the AI, which can then prioritize the collection of data from a specific region.

[0079] The data collection unit can select the optimal data collection method according to the data format at the time of collection. For example, in the case of text data, the data collection unit can use web scraping to collect it. For example, the data collection unit can collect text data from publicly available databases on the internet. In the case of image data, the data collection unit can also use image recognition technology to collect it. For example, the data collection unit can collect image data from the internet and analyze it using image recognition technology. Furthermore, in the case of audio data, the data collection unit can also use speech recognition technology to collect it. For example, the data collection unit can collect audio data and convert it into text data using speech recognition technology. This enables efficient data collection by selecting the optimal data collection method according to the data format. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the data format into AI, and the AI ​​can select the optimal data collection method.

[0080] The analysis unit can estimate the user's emotions and adjust the focus of the analysis based on the estimated emotions. For example, if the user is feeling anxious, the analysis unit can focus on analyzing risk factors. For example, the analysis unit can identify risk factors and propose risk reduction measures based on them. Also, if the user is excited, the analysis unit can focus on analyzing success factors. For example, the analysis unit can identify success factors and propose success strategies based on them. Furthermore, if the user is relaxed, the analysis unit can focus on analyzing overall patterns. For example, the analysis unit can analyze the overall patterns of the data and make comprehensive recommendations based on them. This allows for more appropriate analysis by adjusting the focus of the analysis based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's emotions into the AI, which can then adjust the focus of the analysis based on those emotions.

[0081] The analysis unit can analyze data correlations in detail during analysis and discover hidden patterns. For example, the analysis unit can analyze data correlations and discover hidden patterns. For example, the analysis unit can calculate correlation coefficients to clarify the relationships between data. The analysis unit can also visualize data correlations and discover hidden patterns. For example, the analysis unit can create correlation matrices to visually show the relationships between data. Furthermore, the analysis unit can analyze data correlations using machine learning and discover hidden patterns. For example, the analysis unit can use machine learning algorithms to analyze data correlations and identify hidden patterns. This allows for deeper insights by analyzing data correlations in detail and discovering hidden patterns. Some or all of the above processes in the analysis unit may be performed using AI, for example, or not. For example, the analysis unit can input data correlations into AI, which can analyze the correlations and discover hidden patterns.

[0082] The analysis unit can obtain optimal analysis results by applying different machine learning algorithms during analysis. For example, the analysis unit can apply multiple algorithms and compare their performance. The analysis unit can also compare the performance of machine learning algorithms and select the optimal algorithm. For example, the analysis unit can evaluate the accuracy and computation time of each algorithm and select the optimal algorithm. Furthermore, the analysis unit can obtain optimal analysis results by combining different machine learning algorithms. For example, the analysis unit can use multiple algorithms in combination to perform analysis that leverages the strengths of each. This allows for the application of different machine learning algorithms to obtain optimal analysis results. Some or all of the above processes in the analysis unit may be performed using AI, or not using AI. For example, the analysis unit can input different machine learning algorithms into an AI, which can then select the optimal algorithm.

[0083] The analysis unit can estimate the user's emotions and adjust how the analysis results are displayed based on the estimated emotions. For example, if the user is feeling anxious, the analysis unit can provide a simple and highly visible display method. For example, it can highlight and concisely display important information. If the user is excited, the analysis unit can also provide a display method that includes detailed information. For example, it can display detailed data and graphs to help the user understand more deeply. Furthermore, if the user is relaxed, the analysis unit can provide a display method that shows overall patterns. For example, it can display graphs and charts that show overall trends and patterns. By adjusting how the analysis results are displayed based on the user's emotions, the results can be provided in a format that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's emotions into the AI, which can then adjust how the analysis results are displayed based on those emotions.

[0084] The analysis unit can analyze long-term trends by considering the temporal changes in data during analysis. For example, the analysis unit can analyze long-term trends by considering the temporal changes in data. For example, the analysis unit can visualize the temporal changes in data to reveal long-term trends. The analysis unit can also identify long-term trends by analyzing the temporal changes in data using machine learning. For example, the analysis unit can analyze time-series data to predict future trends. Furthermore, the analysis unit can compare data from different periods by considering the temporal changes in data. For example, the analysis unit can compare past data with current data to identify changes in trends. This improves the accuracy of future predictions by analyzing long-term trends while considering the temporal changes in data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the temporal changes in data into AI, and the AI ​​can analyze long-term trends.

[0085] The analysis unit can perform comprehensive analysis by integrating different data sources during the analysis process. For example, the analysis unit can collect data from multiple data sources, integrate them, and analyze them. The analysis unit can also evaluate the reliability of data sources and prioritize the integration of highly reliable data. For example, the analysis unit can select and integrate data from highly reliable data sources. Furthermore, the analysis unit can unify the format of data sources to perform comprehensive analysis. For example, the analysis unit can convert data in different formats into a unified format and analyze it. This enables comprehensive analysis by integrating different data sources. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input different data sources into AI, and the AI ​​can integrate the data and perform comprehensive analysis.

[0086] The generation unit can estimate the user's emotions and adjust the parameters of the predictive model it generates based on the estimated emotions. For example, if the user is feeling anxious, the generation unit can set parameters that emphasize risk reduction. For example, the generation unit generates a predictive model that emphasizes risk factors. The generation unit can also set parameters that emphasize success factors if the user is excited. For example, the generation unit generates a predictive model that emphasizes success factors. Furthermore, if the user is relaxed, the generation unit can set parameters that consider overall balance. For example, the generation unit generates a predictive model that considers both risk and success factors. This allows for more accurate predictions by adjusting the parameters of the predictive model based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the user's emotions into the AI, which can then adjust the parameters of the predictive model based on those emotions.

[0087] The generation unit can evaluate the accuracy of past prediction models during generation and select the optimal model. For example, the generation unit can evaluate the accuracy of past prediction models and select the optimal model. For example, the generation unit can compare the performance of each prediction model and select the optimal model. The generation unit can also evaluate the performance of prediction models using machine learning and select the optimal model. For example, the generation unit can evaluate the accuracy of past prediction models and select the optimal model based on the evaluation results. Furthermore, the generation unit can continuously evaluate the performance of prediction models and select the optimal model. For example, the generation unit periodically evaluates the accuracy of prediction models and updates the models as needed. This allows the optimal prediction model to be selected by evaluating the accuracy of past prediction models. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the accuracy of past prediction models into AI, and the AI ​​can select the optimal model.

[0088] The generation unit can generate multiple predictive models by considering different scenarios during the generation process. For example, the generation unit can generate multiple predictive models by considering different scenarios. For example, the generation unit can set different parameters for each scenario and generate multiple predictive models. The generation unit can also analyze different scenarios using machine learning and generate multiple predictive models. For example, the generation unit can consider different scenarios and generate the optimal predictive model for each scenario. Furthermore, the generation unit can evaluate the performance of the predictive models by considering different scenarios. For example, the generation unit can evaluate the accuracy of the predictive models in each scenario and select the optimal model. In this way, multiple predictive models can be generated by considering different scenarios. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input different scenarios into AI, and the AI ​​can generate multiple predictive models.

[0089] The generation unit can estimate the user's emotions and adjust the scope of the predictive model it generates based on the estimated emotions. For example, if the user is feeling anxious, the generation unit can set a scope that emphasizes risk reduction. For example, the generation unit generates a predictive model that emphasizes risk factors. The generation unit can also set a scope that emphasizes success factors if the user is excited. For example, the generation unit generates a predictive model that emphasizes success factors. Furthermore, if the user is relaxed, the generation unit can set a scope that considers the overall balance. For example, the generation unit generates a predictive model that considers both risk and success factors. This allows for more accurate predictions by adjusting the scope of the predictive model based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the user's emotions into the AI, which can then adjust the scope of the predictive model based on those emotions.

[0090] The generation unit can generate a general-purpose predictive model by considering data from different industries and fields during the generation process. For example, the generation unit can generate a general-purpose predictive model by considering data from different industries and fields. For example, the generation unit can generate a general-purpose predictive model by considering the characteristics of each industry and field. The generation unit can also generate a general-purpose predictive model by analyzing data from different industries and fields using machine learning. For example, the generation unit can integrate data from different industries and fields and generate a general-purpose predictive model based on that. Furthermore, the generation unit can evaluate the performance of predictive models by considering data from different industries and fields. For example, the generation unit can evaluate the accuracy of predictive models in each industry and field and select the optimal model. This allows for the generation of a general-purpose predictive model by considering data from different industries and fields. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input data from different industries and fields into AI, and the AI ​​can generate a general-purpose predictive model.

[0091] The generation unit can visualize the results of the predictive model during generation and provide them in a format that is easy for users to understand. For example, the generation unit can visualize the results of the predictive model using graphs or charts. For example, the generation unit can create graphs or charts that visually show the prediction results. The generation unit can also provide the results of the predictive model in a dashboard format. For example, the generation unit can create a dashboard that allows users to grasp the prediction results at a glance. Furthermore, the generation unit can provide the results of the predictive model in an interactive format. For example, the generation unit can create an interactive dashboard that allows users to manipulate the prediction results. This makes it possible to provide the results of the predictive model in a format that is easy for users to understand by visualizing them. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the results of the predictive model into AI, and the AI ​​can visualize the results.

[0092] The suggestion unit can estimate the user's emotions and adjust the suggestions based on those emotions. For example, if the user is feeling anxious, the suggestion unit will make suggestions that focus on risk reduction. For example, the suggestion unit will make suggestions that emphasize risk factors. Also, if the user is excited, the suggestion unit can make suggestions that focus on success factors. For example, the suggestion unit will make suggestions that emphasize success factors. Furthermore, if the user is relaxed, the suggestion unit can make suggestions that consider overall balance. For example, the suggestion unit will make suggestions that consider both risks and success factors. By adjusting the suggestions based on the user's emotions, more appropriate suggestions become possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using AI or not using AI. For example, the suggestion unit can input the user's emotions into the AI, and the AI ​​can adjust the suggestions based on those emotions.

[0093] The proposal department can evaluate the effectiveness of past proposals and select the optimal proposal at the time of proposal submission. For example, the proposal department can evaluate the effectiveness of past proposals and select the optimal proposal. For example, the proposal department can compare the performance of each proposal and select the optimal proposal. The proposal department can also evaluate the performance of proposals using machine learning and select the optimal proposal. For example, the proposal department can evaluate the effectiveness of past proposals and select the optimal proposal based on the evaluation results. Furthermore, the proposal department can continuously evaluate the performance of proposals and select the optimal proposal. For example, the proposal department can periodically evaluate the effectiveness of proposals and update the proposal content as needed. This allows the proposal department to select the optimal proposal by evaluating the effectiveness of past proposals. Some or all of the above processes in the proposal department may be performed using AI, for example, or without AI. For example, the proposal department can input the effectiveness of past proposals into AI, and the AI ​​can select the optimal proposal.

[0094] The proposal department can provide customized proposals by considering the user's attribute information (job title, industry, experience, etc.) when making a proposal. For example, the proposal department can provide customized proposals according to the user's job title. For example, the proposal department can differentiate between proposals for managers and proposals for field staff. The proposal department can also provide customized proposals according to the user's industry. For example, the proposal department can differentiate between proposals for manufacturing companies and proposals for service companies. Furthermore, the proposal department can provide customized proposals according to the user's experience. For example, the proposal department can differentiate between proposals for beginners and proposals for experienced users. In this way, customized proposals can be made by considering the user's attribute information. Some or all of the above processing in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can input the user's attribute information into AI, and the AI ​​can generate customized proposals.

[0095] The suggestion unit can estimate the user's emotions and prioritize suggestions based on those emotions. For example, if the user is feeling anxious, the suggestion unit will prioritize suggestions that focus on risk reduction. For example, it will prioritize suggestions that emphasize risk factors. Also, if the user is excited, the suggestion unit can prioritize suggestions that focus on success factors. For example, it will prioritize suggestions that emphasize success factors. Furthermore, if the user is relaxed, the suggestion unit can prioritize suggestions that consider overall balance. For example, it will prioritize suggestions that consider both risks and success factors. This allows for more appropriate suggestions by prioritizing suggestions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the suggestion unit may be performed using AI, for example, or without AI. For example, the proposal department can input the user's emotions into the AI, which can then determine the priority of proposals based on those emotions.

[0096] The proposal unit can make multiple proposals by considering different risk scenarios. For example, the proposal unit can make multiple proposals by considering different risk scenarios. For example, the proposal unit can provide different proposals for each risk scenario. The proposal unit can also analyze different risk scenarios using machine learning and make multiple proposals. For example, the proposal unit can generate the optimal proposal for each risk scenario. Furthermore, the proposal unit can evaluate the performance of proposals by considering different risk scenarios. For example, the proposal unit can evaluate the effectiveness of proposals in each risk scenario and select the optimal proposal. In this way, multiple proposals can be made by considering different risk scenarios. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not using AI. For example, the proposal unit can input different risk scenarios into AI, and the AI ​​can generate multiple proposals.

[0097] The proposal department can visually display the proposed content and provide it in a format that is easy for users to understand. For example, the proposal department can visually display the proposed content using graphs and charts. For example, the proposal department can create graphs and charts that visually represent the proposed content. The proposal department can also provide the proposed content in a dashboard format. For example, the proposal department can create a dashboard that allows users to grasp the proposed content at a glance. Furthermore, the proposal department can provide the proposed content in an interactive format. For example, the proposal department can create an interactive dashboard that allows users to interact with the proposed content. This allows the proposed content to be visually displayed and provided in a format that is easy for users to understand. Some or all of the above processing in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can input the proposed content into AI, and the AI ​​can visualize the content.

[0098] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0099] The data collection unit can estimate the user's emotions and evaluate the reliability of the data to be collected based on those emotions. For example, if the user is feeling anxious, the unit will prioritize collecting data from reliable data sources. If the user is excited, the unit will prioritize collecting the most recent data. Furthermore, if the user is relaxed, the unit will collect a wide range of data in a balanced manner. This allows for more appropriate data collection by evaluating the reliability of the data based on the user's emotions.

[0100] The analytics department can estimate the user's emotions when analyzing collected data and adjust the focus of the analysis based on those estimated emotions. For example, if the user is feeling anxious, the analytics department can focus on analyzing risk factors. If the user is excited, it can focus on analyzing success factors. Furthermore, if the user is relaxed, it can focus on analyzing overall patterns. By adjusting the focus of the analysis based on the user's emotions, more appropriate analysis becomes possible.

[0101] The generation unit can estimate the user's emotions when generating a predictive model and adjust the model's parameters based on those emotions. For example, if the user is feeling anxious, the generation unit will set parameters that focus on risk reduction. If the user is excited, it can set parameters that focus on success factors. Furthermore, if the user is relaxed, it can set parameters that consider overall balance. By adjusting the predictive model's parameters based on the user's emotions, more accurate predictions can be made.

[0102] The proposal function can estimate the user's emotions when making strategic recommendations based on the generated predictive model, and adjust the recommendations based on those emotions. For example, if the user is feeling anxious, the proposal function will focus on risk reduction. If the user is excited, it can focus on success factors. Furthermore, if the user is relaxed, it can make recommendations that consider overall balance. By adjusting the recommendations based on the user's emotions, more appropriate recommendations can be made.

[0103] The proposal team can estimate user emotions when making strategic recommendations based on the generated predictive model, and prioritize recommendations based on those emotions. For example, if a user is feeling anxious, the proposal team will prioritize recommendations that focus on risk reduction. If a user is excited, it can prioritize recommendations that focus on success factors. Furthermore, if a user is relaxed, it can prioritize recommendations that consider overall balance. By prioritizing recommendations based on user emotions, more appropriate recommendations can be made.

[0104] The data collection unit can select the optimal collection method depending on the format of the data to be collected. For example, in the case of text data, the data collection unit can use web scraping to collect the data. In the case of image data, the data collection unit can use image recognition technology to collect the data. Furthermore, in the case of audio data, the data collection unit can use speech recognition technology to collect the data. This enables efficient data collection by selecting the optimal collection method according to the data format.

[0105] The analysis department can apply different machine learning algorithms to the collected data to obtain optimal analysis results. For example, the analysis department can apply multiple algorithms and compare their performance. It can also evaluate the accuracy and computation time of each algorithm and select the optimal one. Furthermore, it can combine different machine learning algorithms to perform analysis that leverages the strengths of each. In this way, optimal analysis results can be obtained by applying different machine learning algorithms.

[0106] The generation unit can visualize the results of the generated predictive model and provide them in a format that is easy for users to understand. For example, the generation unit can create graphs and charts that visually represent the prediction results. It can also create dashboards that allow users to grasp the prediction results at a glance. Furthermore, it can create interactive dashboards that allow users to manipulate the prediction results. In this way, by visualizing the results of the predictive model, it can provide them in a format that is easy for users to understand.

[0107] The proposal team can visually display the proposal content and provide it in a format that is easy for users to understand. For example, the proposal team can create graphs and charts that visually represent the proposal content. They can also create dashboards that allow users to grasp the proposal content at a glance. Furthermore, they can create interactive dashboards that allow users to manipulate the proposal content. In this way, the proposal content can be visually displayed and provided in a format that is easy for users to understand.

[0108] The proposal department can provide customized proposals by considering the user's attribute information (job title, industry, experience, etc.) when making a proposal. For example, it can differentiate between proposals for managers and proposals for on-site staff depending on the user's job title. It can also differentiate between proposals for manufacturing and proposals for service industries depending on the user's industry. Furthermore, it can differentiate between proposals for beginners and proposals for experienced users depending on the user's experience. In this way, customized proposals can be made by considering the user's attribute information.

[0109] The following briefly describes the processing flow for example form 2.

[0110] Step 1: The data collection unit collects large amounts of historical data. The data collection unit collects data from sources such as world history, Japanese history, corporate history, and startup history. The data collection unit can collect data in various formats, such as text data, numerical data, and image data. The data collection unit collects data from publicly available databases and archives on the internet, for example. The data collection unit can also collect data provided by companies and research institutions. The data collection unit evaluates the reliability of the data during the data collection process and prioritizes the collection of highly reliable data. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit analyzes the data using machine learning, for example, to perform pattern recognition and prediction. The analysis unit can use machine learning algorithms such as supervised learning, unsupervised learning, and reinforcement learning. The analysis unit can analyze the correlation between data and discover hidden patterns, for example. The analysis unit can apply different machine learning algorithms to obtain the optimal analysis results, for example. Step 3: The generation unit generates a predictive model based on the analysis results obtained by the analysis unit. The generation unit generates predictive models that, for example, improve risk reduction rates, streamline strategic decision-making, and improve the accuracy of future predictions. The generation unit can generate predictive models such as regression models, classification models, and time series models. The generation unit can, for example, evaluate the accuracy of past predictive models and select the optimal model. The generation unit can, for example, generate multiple predictive models considering different scenarios. Step 4: The proposal unit makes strategic proposals based on the predictive model generated by the generation unit. The proposal unit automatically generates strategic proposals for users such as strategists, risk managers, executives, and policymakers. The proposal unit helps reduce risks and support more effective decision-making by, for example, learning from past failures and predicting future problems. The proposal unit presents the proposals in a visually understandable format for the user.

[0111] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0112] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0113] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0114] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, and proposal unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart device 14 and collects data from publicly available databases and archives on the internet. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the data using machine learning to perform pattern recognition and prediction. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a predictive model based on the analysis results. The proposal unit is implemented by the control unit 46A of the smart device 14 and makes strategic proposals based on the generated predictive model. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0115] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0116] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0117] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0118] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0119] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0121] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0122] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0123] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0124] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0125] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0126] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0127] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0128] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0129] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, and proposal unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart glasses 214 and collects data from publicly available databases and archives on the internet. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the data using machine learning to perform pattern recognition and prediction. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a predictive model based on the analysis results. The proposal unit is implemented by the control unit 46A of the smart glasses 214 and makes strategic proposals based on the generated predictive model. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

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

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

[0133] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0134] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

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

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

[0137] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0138] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

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

[0140] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0141] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0142] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

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

[0144] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0145] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, and proposal unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the headset terminal 314 and collects data from publicly available databases and archives on the internet. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the data using machine learning to perform pattern recognition and prediction. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a predictive model based on the analysis results. The proposal unit is implemented by the control unit 46A of the headset terminal 314 and makes strategic proposals based on the generated predictive model. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0147] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0148] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0149] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0150] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0151] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0153] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0154] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0155] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0156] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0157] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0158] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0159] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0160] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0161] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0162] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0163] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, and proposal unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the robot 414 and collects data from publicly available databases and archives on the internet. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the data using machine learning to perform pattern recognition and prediction. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a predictive model based on the analysis results. The proposal unit is implemented by the control unit 46A of the robot 414 and makes strategic proposals based on the generated predictive model. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0164] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0165] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0166] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0167] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0168] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0169] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0171] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0172] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0173] 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.

[0174] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0175] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0176] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0177] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0178] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0179] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0180] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0181] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0182] (Note 1) The collection department collects large amounts of historical data, An analysis unit analyzes the data collected by the aforementioned collection unit, A generation unit that generates a predictive model based on the analysis results obtained by the analysis unit, A proposal unit that makes strategic proposals based on the predictive model generated by the generation unit, Equipped with A system characterized by the following features. (Note 2) The aforementioned collection unit is We collect data from world history, Japanese history, corporate history, and startup history. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit is The collected data is analyzed using machine learning to perform pattern recognition and prediction. The system described in Appendix 1, characterized by the features described herein. (Note 4) The generating unit is Based on the analysis results, we generate predictive models that improve risk reduction rates, streamline strategic decision-making, and enhance the accuracy of future predictions. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned proposal section is, Based on the generated predictive model, strategic proposals are automatically created for users such as strategists, risk managers, executives, and policymakers. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned proposal section is, By learning from past failures and predicting future problems, we can reduce risks and support more effective decision-making. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is It estimates the user's emotions and prioritizes the data to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is During data collection, the reliability of the data is evaluated, and reliable data is prioritized for collection. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When collecting data, the most recent data is collected first, taking into account the frequency of data updates. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is We estimate the user's emotions and adjust the scope of data collected based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is During data collection, the geographical distribution of the data is taken into consideration, and data from specific regions is prioritized for collection. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is During data collection, the optimal collection method is selected according to the data format. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit is It estimates the user's emotions and adjusts the focus of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit is During analysis, we thoroughly examine the correlations between data to uncover hidden patterns. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit is During analysis, different machine learning algorithms are applied to obtain the optimal analysis results. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit is It estimates the user's emotions and adjusts how the analysis results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit is During analysis, we consider the temporal changes in the data to analyze long-term trends. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit is During analysis, different data sources are integrated to perform a comprehensive analysis. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is It estimates the user's emotions and adjusts the parameters of the predictive model generated based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is During generation, the accuracy of past prediction models is evaluated, and the optimal model is selected. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is During generation, multiple predictive models are generated, taking different scenarios into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is It estimates user sentiment and adjusts the scope of the predictive model generated based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is During generation, a general-purpose predictive model is created by considering data from different industries and fields. The system described in Appendix 1, characterized by the features described herein. (Note 24) The generating unit is During generation, the results of the predictive model are visualized and provided in a format that is easy for users to understand. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned proposal section is, It estimates the user's emotions and adjusts the suggestions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned proposal section is, When making a proposal, we evaluate the effectiveness of past proposals and select the most suitable one. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned proposal section is, When making a proposal, we take into account the user's attribute information to create a customized proposal. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned proposal section is, It estimates the user's emotions and determines the priority of suggestions based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned proposal section is, When making a proposal, consider different risk scenarios and provide multiple options. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned proposal section is, The proposal is presented visually and in a format that is easy for users to understand. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The collection department collects large amounts of historical data, An analysis unit analyzes the data collected by the aforementioned collection unit, A generation unit that generates a predictive model based on the analysis results obtained by the analysis unit, A proposal unit that makes strategic proposals based on the predictive model generated by the generation unit, Equipped with A system characterized by the following features.

2. The aforementioned collection unit is We collect data from world history, Japanese history, corporate history, and startup history. The system according to feature 1.

3. The aforementioned analysis unit is The collected data is analyzed using machine learning to perform pattern recognition and prediction. The system according to feature 1.

4. The generating unit is Based on the analysis results, we generate predictive models that improve risk reduction rates, streamline strategic decision-making, and enhance the accuracy of future predictions. The system according to feature 1.

5. The aforementioned proposal section is, Based on the generated predictive model, strategic proposals are automatically created for users such as strategists, risk managers, executives, and policymakers. The system according to feature 1.

6. The aforementioned proposal section is, By learning from past failures and predicting future problems, we can reduce risks and support more effective decision-making. The system according to feature 1.

7. The aforementioned collection unit is It estimates the user's emotions and prioritizes the data to collect based on those estimated emotions. The system according to feature 1.

8. The aforementioned collection unit is During data collection, the reliability of the data is evaluated, and reliable data is prioritized for collection. The system according to feature 1.

Images