System

Abstract

An object of a system according to an embodiment is to extract a useful hypothesis from data and provide the customer with the useful hypothesis.SOLUTION: A system includes a collection unit, an analysis unit, a hypothesis generation unit, and a provision unit. The collection unit collects data. The analysis unit analyzes the data collected by the collection unit. The hypothesis generator derives a hypothesis based on the data analyzed by the analyzer. The provider provides the customer with the hypothesis derived by the hypothesis generator.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies are not sufficient in efficiently extracting useful hypotheses from data and providing them to customers, and there is room for improvement.

[0005] The system according to the embodiment aims to extract useful hypotheses from data and provide them to clients. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a hypothesis generation unit, and a provision unit. The collection unit collects data. The analysis unit analyzes the data collected by the collection unit. The hypothesis generation unit derives hypotheses based on the data analyzed by the analysis unit. The provision unit provides the hypotheses derived by the hypothesis generation unit to a client. [Effects of the Invention]

[0007] The system according to the embodiment can extract useful hypotheses from data and provide them to the client. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A data analysis system according to an embodiment of the present invention utilizes generative AI to derive hypotheses from data. This data analysis system collects, analyzes, generates, and provides data to support customers in strengthening their business strategies and making effective decisions. For example, in a data analysis system, a customer provides data related to their industry. The customer then selects an external generative AI, which analyzes the provided data. The generative AI analyzes the data and derives hypotheses from it. For example, a hypothesis might be that a particular product sells better in a particular season, or that a particular customer demographic is highly interested in a particular service. The hypotheses derived by the generative AI are provided to customers. Customers can use these hypotheses to strengthen their business strategies and make effective decisions. Furthermore, generative AI focused on specific industries is also under consideration. For example, a generative AI specialized for the medical industry or the financial industry could be developed. This would enable more specialized and accurate hypotheses to be derived. For example, the hypotheses derived by the generative AI could be used to develop new marketing strategies or revise product development directions. Furthermore, the insights provided by the generative AI could be used to differentiate companies from their competitors. This allows the data analysis system to support the strengthening of customers' business strategies and effective decision-making. For example, it is possible to formulate a new marketing strategy or review the direction of product development based on hypotheses derived by generative AI. It is also possible to differentiate from competitors based on insights provided by generative AI. This allows the data analysis system to support the strengthening of customers' business strategies and effective decision-making.

[0029] A data analysis system according to an embodiment includes a collection unit, an analysis unit, a hypothesis generation unit, and a provision unit. The collection unit collects data. Examples of the data include, but are not limited to, numerical data, text data, and image data. The collection unit collects data such as sales data, customer behavior data, and market trends. The collection unit can also collect data in real time using sensors and APIs. For example, the collection unit can collect environmental data using sensors. The collection unit can also collect social media data using APIs. The analysis unit analyzes the data collected by the collection unit. The analysis can be performed using, for example, statistical analysis or a machine learning algorithm, but is not limited to these examples. For example, the analysis unit can analyze data trends using statistical analysis. The analysis unit can also analyze data patterns using a machine learning algorithm. The analysis unit can also analyze text data using natural language processing technology. The hypothesis generation unit derives hypotheses based on the data analyzed by the analysis unit. The hypotheses can be generated based on, for example, a predictive model or an estimation of causal relationships, but are not limited to these examples. For example, the hypothesis generation unit may use a predictive model to generate a hypothesis that a particular product sells well in a particular season. The hypothesis generation unit may also use causal relationship estimation to generate a hypothesis that a particular customer segment is highly interested in a particular service. The hypothesis generation unit may also use data mining technology to derive new hypotheses from data. The provision unit provides the hypotheses derived by the hypothesis generation unit to a customer. The provision may be, for example, in the form of a report or through a dashboard display, but is not limited to these examples. For example, the provision unit may provide the hypotheses in the form of a report. The provision unit may also provide the hypotheses in real time through a dashboard. The provision unit may also provide the hypotheses to a customer via email or notification. This allows the data analysis system according to the embodiment to strengthen a customer's business strategy and support effective decision-making.

[0030] The data analysis system further includes a generative AI focused on a specific industry. Examples of generative AI focused on a specific industry include the medical, manufacturing, and financial industries. For example, a generative AI specialized for the medical industry analyzes medical data and generates hypotheses related to medical care. A generative AI specialized for the manufacturing industry can analyze manufacturing data and generate hypotheses related to manufacturing. A generative AI specialized for the financial industry can analyze financial data and generate hypotheses related to finance. This makes it possible to derive more specialized and accurate hypotheses by using generative AI specialized for a specific industry. For example, a generative AI specialized for the medical industry can analyze medical data and generate a hypothesis that a specific treatment is effective for a specific patient. A generative AI specialized for the manufacturing industry can analyze manufacturing data and generate a hypothesis that a specific manufacturing process improves the quality of a specific product. A generative AI specialized for the financial industry can analyze financial data and generate a hypothesis that a specific investment strategy is effective under specific market conditions. This makes it possible to derive more specialized and accurate hypotheses by using generative AI specialized for a specific industry.

[0031] The providing unit can provide the hypothesis in real time through a dashboard. The providing unit, for example, provides the hypothesis in real time through a dashboard. The dashboard includes, for example, a graph display and a filtering function, but is not limited to these examples. For example, the providing unit provides the hypothesis in a graph display. The providing unit can also provide the hypothesis using a filtering function. The providing unit can also update the hypothesis in real time to provide the latest information. By providing the hypothesis in real time, the customer can make decisions quickly. For example, by providing the hypothesis in real time, the providing unit can help the customer to quickly formulate a marketing strategy. By providing the hypothesis in real time, the providing unit can help the customer to quickly review the direction of product development. By providing the hypothesis in real time, the providing unit can help the customer to make decisions quickly.

[0032] The providing unit can provide the hypothesis in a report format. For example, the providing unit provides the hypothesis in a report format. Report formats include, but are not limited to, PDF format and Excel format. For example, the providing unit can provide the hypothesis in PDF format. The providing unit can also provide the hypothesis in Excel format. The providing unit can also provide the hypothesis in a customized report format. By providing the hypothesis in report format, a customer can make decisions based on detailed information. For example, by providing the hypothesis in report format, a customer can plan a detailed marketing strategy. By providing the hypothesis in report format, a customer can review the direction of product development in detail. By providing the hypothesis in report format, a customer can make decisions based on detailed information.

[0033] The collection unit can collect sales data, customer behavior data, and market trend data. The collection unit, for example, collects sales data. The sales data includes, for example, sales data and sales data by product, but is not limited to these examples. For example, the collection unit collects sales data. The collection unit can also collect sales data by product. The collection unit can also collect customer behavior data. The customer behavior data includes, for example, website browsing history and purchase history, but is not limited to these examples. For example, the collection unit collects website browsing history. The collection unit can also collect purchase history. The collection unit can also collect market trend data. The market trend data includes, for example, market research data and social media trends, but is not limited to these examples. For example, the collection unit collects market research data. The collection unit can also collect social media trends. By collecting a variety of data, more diverse hypotheses can be generated. For example, by collecting sales data, customer behavior data, and market trend data, the collection unit can generate a hypothesis that a particular product sells well in a particular season. Also, by collecting sales data, customer behavior data, and market trend data, the collection unit can generate a hypothesis that a particular customer segment shows a high interest in a particular service. In this way, by collecting a variety of data, more diverse hypotheses can be generated.

[0034] The analysis unit can analyze the collected data and derive a hypothesis that a specific product will sell in a specific season. The analysis unit, for example, analyzes the collected data and derives a hypothesis that a specific product will sell in a specific season. Examples of specific products include, but are not limited to, seasonal products and standard products. For example, the analysis unit can derive a hypothesis that a seasonal product will sell in a specific season. The analysis unit can also derive a hypothesis that a standard product will sell in a specific season. Examples of specific seasons include, but are not limited to, spring, summer, fall, and winter. For example, the analysis unit can derive a hypothesis that a specific product will sell in spring. The analysis unit can also derive a hypothesis that a specific product will sell in summer. The analysis unit can also derive a hypothesis that a specific product will sell in fall. The analysis unit can also derive a hypothesis that a specific product will sell in winter. This makes it possible to understand seasonal product sales trends through data analysis. For example, the analysis unit can analyze the collected data and derive a hypothesis that a specific product will sell in a specific season, allowing customers to develop seasonal sales strategies. The analysis department also analyzes the collected data and draws hypotheses about which products sell best in which seasons, allowing customers to optimize their inventory management. This allows data analysis to identify seasonal product sales trends.

[0035] The collection unit can analyze the user's past data provision history and select the optimal collection method. The collection unit, for example, analyzes the user's past data provision history and selects the optimal collection method. The data provision history includes, for example, the number of times data has been provided in the past and the type of provided data, but is not limited to these examples. For example, the collection unit prioritizes collecting types of data that the user has frequently provided in the past. The collection unit can also prioritize selecting data provision methods (audio, text, etc.) that the user has used in the past. The collection unit can also select the optimal collection method for a specific time period based on the user's past data provision history. For example, the collection unit selects the optimal collection method based on the type of data the user has provided in the past. The collection unit can also select the optimal collection method based on the data provision methods the user has used in the past. The collection unit can also analyze the user's past data provision history and select the optimal collection method for a specific time period. In this way, efficient data collection is possible by selecting the optimal collection method based on the past data provision history. For example, the collection unit can analyze the user's past data provision history and select the optimal collection method, thereby collecting data in a way that is easy for the user to provide. Furthermore, the collection unit analyzes the user's past data provision history and selects the optimal collection method, thereby collecting data at a time when it is convenient for the user to provide the data. This allows for efficient data collection by selecting the optimal collection method based on the user's past data provision history.

[0036] The collection unit may filter data based on the user's current work situation or areas of interest when collecting data. For example, the collection unit may filter data based on the user's current work situation or areas of interest when collecting data. Examples of work situations include, but are not limited to, project progress and work priorities. For example, the collection unit may prioritize collecting data related to a project the user is currently working on. The collection unit may also collect only necessary data and eliminate unnecessary data based on the user's work priorities. Examples of areas of interest include, but are not limited to, technical fields and business fields. For example, the collection unit may filter and collect highly relevant data based on the user's areas of interest. The collection unit may also collect only necessary data and eliminate unnecessary data according to the user's work situation. Thus, filtering data based on the user's work situation or areas of interest allows efficient collection of only necessary data. For example, the collection unit may prioritize collecting relevant data based on the user's current work situation, allowing rapid provision of data required by the user. The collection unit may filter and collect highly relevant data based on the user's areas of interest, allowing efficient provision of data of interest to the user. This allows users to filter data based on their work situation and areas of interest, allowing them to efficiently collect only the data they need.

[0037] The collection unit can select an optimal collection means depending on the user's input method when collecting data. For example, the collection unit selects an optimal collection means depending on the user's input method (voice, text, image, etc.) when collecting data. Input methods include, but are not limited to, voice input, text input, and image input. For example, when the user uses voice input, the collection unit prioritizes collecting voice data. Furthermore, when the user uses text input, the collection unit can also prioritize collecting text data. Furthermore, when the user uses image input, the collection unit can also prioritize collecting image data. In this way, efficient data collection is possible by selecting an optimal collection means depending on the user's input method. For example, when the user uses voice input, the collection unit prioritizes collecting voice data, thereby collecting data in a manner that is easy for the user to provide. Furthermore, when the user uses text input, the collection unit prioritizes collecting text data, thereby collecting data in a manner that is easy for the user to provide. Furthermore, when the user uses image input, the collection unit prioritizes collecting image data, thereby collecting data in a manner that is easy for the user to provide. In this way, efficient data collection is possible by selecting an optimal collection means depending on the user's input method.

[0038] The collection unit can prioritize collecting highly relevant data based on the user's geographical location information when collecting data. For example, the collection unit prioritizes collecting highly relevant data by taking the user's geographical location information into consideration when collecting data. Geographical location information includes, but is not limited to, GPS data and address information. For example, when the user is in a specific area, the collection unit prioritizes collecting data related to that area. Furthermore, when the user is moving, the collection unit can also collect highly relevant data based on the user's current location. Furthermore, when the user is staying in a specific place, the collection unit can prioritize collecting data related to that place. In this way, highly relevant data can be efficiently collected by taking the user's geographical location information into consideration. For example, when the user is in a specific area, the collection unit prioritizes collecting data related to that area, thereby enabling the user to quickly provide the data required by the user. Furthermore, when the user is moving, the collection unit collects highly relevant data based on the user's current location, thereby enabling the user to efficiently provide the data required by the user. Furthermore, when the user is staying in a specific place, the collection unit prioritizes collecting data related to that place, thereby enabling the user to quickly provide the data required by the user. This allows for efficient collection of highly relevant data by taking into account the user's geographical location information.

[0039] The collection unit can analyze the user's social media activities and collect related data when collecting data. For example, the collection unit can analyze the user's social media activities and collect related data when collecting data. Social media activities include, but are not limited to, post content, the number of likes, and the number of followers. For example, the collection unit can collect related data based on information shared by the user on social media. The collection unit can also analyze the user's social media activities and collect related data. The collection unit can also collect related data by referring to the activities of the user's friends on social media. In this way, highly relevant data can be efficiently collected by analyzing the user's social media activities. For example, the collection unit can collect related data based on the information shared by the user on social media, thereby quickly providing data that the user is interested in. The collection unit can also analyze the user's social media activities and collect related data. In addition, the collection unit can collect related data by referring to the activities of the user's friends on social media, thereby quickly providing data that the user is interested in. In this way, highly relevant data can be efficiently collected by analyzing the user's social media activities.

[0040] The collection unit can customize the collection method by reflecting the user's past feedback when collecting data. For example, the collection unit customizes the collection method by reflecting the user's past feedback when collecting data. The feedback includes, for example, user comments and evaluation scores, but is not limited to these examples. For example, the collection unit optimizes the collection method based on feedback provided by the user in the past. The collection unit can also preferentially select a specific data collection means based on the user's past feedback. The collection unit can also customize the collection method by reflecting the user's feedback to suit the user's needs. In this way, the collection method can be optimized by reflecting the user's past feedback, enabling efficient data collection. For example, the collection unit can collect data in a way that is easy for the user to provide by optimizing the collection method based on the user's past feedback. The collection unit can also preferentially select a specific data collection means based on the user's past feedback. The collection unit can collect data in a way that is easy for the user to provide by reflecting the user's feedback. This allows for the collection method to be optimized and data to be collected efficiently by reflecting past user feedback.

[0041] The analysis unit can adjust the level of detail of the analysis based on the importance of the data during analysis. For example, the analysis unit adjusts the level of detail of the analysis based on the importance of the data during analysis. The importance of data includes, but is not limited to, business impact and data reliability. For example, the analysis unit performs a detailed analysis on data with high importance. The analysis unit can also perform a simplified analysis on data with low importance. The analysis unit can also dynamically adjust the level of detail of the analysis according to the importance of the data. This enables efficient data analysis by adjusting the level of detail of the analysis according to the importance of the data. For example, the analysis unit can perform a detailed analysis on data with high importance, thereby analyzing data with a large business impact in detail. The analysis unit can also perform a simplified analysis on data with low importance, thereby analyzing data efficiently. The analysis unit can also dynamically adjust the level of detail of the analysis according to the importance of the data, thereby analyzing data efficiently.

[0042] The analysis unit can apply different analysis algorithms depending on the data category during analysis. For example, the analysis unit applies different analysis algorithms depending on the data category during analysis. Data categories include, but are not limited to, text data, numerical data, and image data. For example, the analysis unit applies a sales forecasting algorithm to sales data. The analysis unit can also apply a behavior pattern analysis algorithm to customer behavior data. The analysis unit can also apply a trend prediction algorithm to market trend data. In this way, by applying an appropriate analysis algorithm depending on the data category, highly accurate analysis results can be provided. For example, the analysis unit can predict sales by applying a sales forecasting algorithm to sales data. In addition, the analysis unit can analyze customer behavior patterns by applying a behavior pattern analysis algorithm to customer behavior data. In addition, the analysis unit can predict market trends by applying a trend prediction algorithm to market trend data. In this way, by applying an appropriate analysis algorithm depending on the data category, highly accurate analysis results can be provided.

[0043] The analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results during analysis. For example, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results during analysis. Past analysis results include, but are not limited to, past reports and database records. For example, the analysis unit can optimize the analysis algorithm based on the user's past analysis results. The analysis unit can also extract specific patterns from the user's past analysis results to improve the accuracy of the analysis. The analysis unit can also dynamically adjust the accuracy of the analysis by referring to the user's past analysis results. In this way, the accuracy of the analysis can be improved by referring to the user's past analysis results. For example, the analysis unit can improve the accuracy of the analysis by optimizing the analysis algorithm based on the user's past analysis results. The analysis unit can improve the accuracy of the analysis by extracting specific patterns from the user's past analysis results to improve the accuracy of the analysis, thereby providing more accurate analysis results. The analysis unit can also dynamically adjust the accuracy of the analysis by referring to the user's past analysis results to provide more accurate analysis results. This allows the accuracy of the analysis to be improved by referring to the user's past analysis results.

[0044] The analysis unit can determine the analysis priority based on the time of data submission during analysis. The analysis unit, for example, determines the analysis priority based on the time of data submission during analysis. The time of data submission includes, for example, the submission date and the submission time, but is not limited to these examples. For example, the analysis unit prioritizes analysis of the most recent data. The analysis unit can also postpone analysis of data that was submitted earlier. The analysis unit can also dynamically adjust the analysis priority according to the time of data submission. In this way, by determining the analysis priority based on the time of data submission, the most recent data can be analyzed preferentially. For example, by analyzing the most recent data preferentially, the analysis unit can provide analysis results based on the most recent information. In addition, by postponing analysis of data that was submitted earlier, the analysis unit can efficiently analyze data. In addition, by dynamically adjusting the analysis priority according to the time of data submission, the analysis unit can efficiently analyze data. In this way, by determining the analysis priority based on the time of data submission, the most recent data can be analyzed preferentially.

[0045] The analysis unit can adjust the order of analysis based on the relevance of data during analysis. For example, the analysis unit adjusts the order of analysis based on the relevance of data during analysis. Data relevance includes, but is not limited to, correlation and causal relationship, for example. For example, the analysis unit prioritizes analysis of highly relevant data. The analysis unit can also postpone analysis of less relevant data. The analysis unit can also dynamically adjust the order of analysis according to the relevance of data. In this way, adjusting the order of analysis based on the relevance of data enables efficient data analysis. For example, the analysis unit can prioritize analysis of highly relevant data, thereby quickly analyzing highly relevant data. In addition, the analysis unit can postpone analysis of less relevant data, thereby efficiently analyzing data. In addition, the analysis unit can dynamically adjust the order of analysis according to the relevance of data, thereby efficiently analyzing data. In this way, adjusting the order of analysis based on the relevance of data enables efficient data analysis.

[0046] The analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise during analysis. For example, the analysis unit adjusts the use of technical terms in the analysis according to the user's level of expertise during analysis. Expertise levels include, but are not limited to, beginner, intermediate, and advanced. For example, if the user has expert knowledge, the analysis unit provides analysis results that use a lot of technical terms. Furthermore, if the user does not have expert knowledge, the analysis unit can provide analysis results in simple language. Furthermore, the analysis unit can dynamically adjust the use of technical terms in the analysis according to the user's level of expertise. In this way, by adjusting the use of technical terms in the analysis according to the user's level of expertise, analysis results that are easy for the user to understand can be provided. For example, if the user has expert knowledge, the analysis unit can provide specialized information by providing analysis results that use a lot of technical terms. Furthermore, if the user does not have expert knowledge, the analysis unit can provide analysis results in simple language to provide information that is easy for the user to understand. Furthermore, by dynamically adjusting the use of technical terms in the analysis according to the user's level of expertise, information that is easy for the user to understand can be provided. This allows the use of analytical terminology to be adjusted according to the user's level of expertise, making it possible to provide analysis results that are easy for the user to understand.

[0047] The hypothesis generation unit can improve the accuracy of a hypothesis based on the interrelationships of data when generating a hypothesis. For example, the hypothesis generation unit improves the accuracy of a hypothesis by taking into account the interrelationships of data when generating a hypothesis. Examples of the interrelationships of data include, but are not limited to, correlation analysis and network analysis. For example, the hypothesis generation unit analyzes the interrelationships of data to generate a highly accurate hypothesis. The hypothesis generation unit can also improve the reliability of the hypothesis by taking into account the interrelationships of data. The hypothesis generation unit can also dynamically adjust the accuracy of the hypothesis based on the interrelationships of data. In this way, a highly accurate hypothesis can be generated by taking into account the interrelationships of data. For example, the hypothesis generation unit can provide a highly reliable hypothesis by analyzing the interrelationships of data and generating a highly accurate hypothesis. In addition, the hypothesis generation unit can provide a more accurate hypothesis by improving the reliability of the hypothesis by taking into account the interrelationships of data. In this way, a highly accurate hypothesis can be generated by taking into account the interrelationships of data.

[0048] The hypothesis generation unit can generate a hypothesis by taking into account attribute information of the data submitter when generating a hypothesis. For example, the hypothesis generation unit generates a hypothesis by taking into account attribute information of the data submitter when generating a hypothesis. The attribute information includes, but is not limited to, age, gender, occupation, etc. For example, the hypothesis generation unit generates a hypothesis based on the attribute information of the data submitter. The hypothesis generation unit can also improve the reliability of the hypothesis by taking into account the attribute information of the submitter. The hypothesis generation unit can also dynamically adjust the accuracy of the hypothesis based on the attribute information of the submitter. In this way, a highly reliable hypothesis can be generated by taking into account the attribute information of the data submitter. For example, the hypothesis generation unit can provide a hypothesis based on the attributes of the data submitter by generating a hypothesis based on the attribute information of the data submitter. In addition, the hypothesis generation unit can improve the reliability of the hypothesis by taking into account the attribute information of the submitter, thereby providing a more accurate hypothesis. In addition, the hypothesis generation unit can dynamically adjust the accuracy of the hypothesis based on the attribute information of the submitter, thereby providing a more accurate hypothesis. In this way, a highly reliable hypothesis can be generated by taking into account the attribute information of the data submitter.

[0049] The hypothesis generation unit can weight hypotheses based on the frequency of data submission when generating hypotheses. For example, the hypothesis generation unit weights hypotheses based on the frequency of data submission when generating hypotheses. The submission frequency includes, but is not limited to, weekly, monthly, and yearly. For example, the hypothesis generation unit weights hypotheses based on data submitted frequently. The hypothesis generation unit can also lower the weight of data submitted infrequently. The hypothesis generation unit can also dynamically adjust the weight of hypotheses according to the frequency of data submission. In this way, by weighting hypotheses based on the frequency of data submission, hypotheses based on important data can be generated. For example, the hypothesis generation unit weights hypotheses based on data submitted frequently, thereby providing hypotheses based on frequently provided data. The hypothesis generation unit can also lower the weight of data submitted infrequently, thereby providing hypotheses based on data of low importance. The hypothesis generation unit can also dynamically adjust the weight of hypotheses according to the frequency of data submission. This allows hypotheses to be weighted based on the frequency of data submission, allowing hypotheses to be generated that are based on important data.

[0050] The hypothesis generation unit may generate hypotheses taking into account the geographical distribution of data when generating hypotheses. For example, the hypothesis generation unit generates hypotheses taking into account the geographical distribution of data when generating hypotheses. Geographical distribution includes, but is not limited to, data by region or data by country. For example, the hypothesis generation unit may analyze the geographical distribution of data and generate hypotheses taking into account the characteristics of each region. The hypothesis generation unit may also generate hypotheses related to a specific region based on the geographical distribution. The hypothesis generation unit may also improve the accuracy of the hypotheses by taking the geographical distribution into account. In this way, by taking the geographical distribution of data into account, hypotheses that reflect the characteristics of each region can be generated. For example, the hypothesis generation unit may analyze the geographical distribution of data and generate hypotheses taking into account the characteristics of each region, thereby providing hypotheses that reflect the characteristics of each region. In addition, by generating hypotheses related to a specific region based on the geographical distribution, hypotheses that reflect the characteristics of each region can be provided. In addition, the hypothesis generation unit may improve the accuracy of the hypotheses by taking the geographical distribution into account, thereby providing more accurate hypotheses. In this way, by taking the geographical distribution of data into account, hypotheses that reflect the characteristics of each region can be generated.

[0051] The hypothesis generation unit can improve the accuracy of the hypothesis by referring to literature related to the data when generating a hypothesis. For example, the hypothesis generation unit can improve the accuracy of the hypothesis by referring to literature related to the data when generating a hypothesis. Related literature includes, but is not limited to, academic papers and technical reports. For example, the hypothesis generation unit can improve the reliability of the hypothesis by referring to the related literature. The hypothesis generation unit can also improve the accuracy of the hypothesis based on the related literature. The hypothesis generation unit can also support the hypothesis by referring to the related literature. In this way, a highly reliable hypothesis can be generated by referring to the related literature. For example, the hypothesis generation unit can provide a highly reliable hypothesis by referring to the related literature and improving the reliability of the hypothesis. In addition, the hypothesis generation unit can provide a more accurate hypothesis by improving the accuracy of the hypothesis based on the related literature. In addition, the hypothesis generation unit can provide a more accurate hypothesis by referring to the related literature and supporting the hypothesis. In this way, a highly reliable hypothesis can be generated by referring to the related literature.

[0052] The hypothesis generation unit can generate a hypothesis taking into account the market value of the data when generating a hypothesis. For example, the hypothesis generation unit generates a hypothesis taking into account the market value of the data when generating a hypothesis. Market value includes, but is not limited to, sales forecasts and market shares. For example, the hypothesis generation unit generates a hypothesis based on data with high market value. The hypothesis generation unit can also lower the priority of hypothesis generation for data with low market value. The hypothesis generation unit can also weight the hypotheses according to the market value of the data. In this way, a hypothesis with high value can be generated by taking the market value of the data into account. For example, the hypothesis generation unit can provide a hypothesis with high value by generating a hypothesis based on data with high market value. In addition, the hypothesis generation unit can lower the priority of hypothesis generation for data with low market value, thereby providing a hypothesis based on data with low importance. In addition, the hypothesis generation unit can provide a hypothesis with high value by weighting the hypothesis according to the market value of the data. In this way, a hypothesis with high value can be generated by taking the market value of the data into account.

[0053] The providing unit can select an optimal providing method by referring to the user's past feedback when providing a hypothesis. For example, the providing unit selects the optimal providing method by referring to the user's past feedback when providing a hypothesis. The feedback includes, for example, user comments and evaluation scores, but is not limited to these examples. For example, the providing unit optimizes the providing method based on feedback previously provided by the user. The providing unit can also preferentially select a specific providing means based on the user's past feedback. The providing unit can also customize the providing method by reflecting the user's feedback to match the user's needs. In this way, the optimal providing method can be selected by referring to the user's past feedback. For example, the providing unit can provide a hypothesis in a way that is easy for the user to understand by optimizing the providing method based on the user's past feedback. In addition, the providing unit can provide a hypothesis in a way that is easy for the user to understand by preferentially selecting a specific providing means based on the user's past feedback. In addition, the providing unit can customize the providing method by reflecting the user's feedback to match the user's needs, and provide a hypothesis in a way that is easy for the user to understand. In this way, the optimal providing method can be selected by referring to the user's past feedback.

[0054] The providing unit can customize the provided content according to the user's current work situation when providing a hypothesis. For example, the providing unit customizes the provided content according to the user's current work situation when providing a hypothesis. The work situation includes, for example, the progress status of a project and the priority of the work, but is not limited to such examples. For example, the providing unit prioritizes providing hypotheses related to a project the user is currently working on. The providing unit can also provide only necessary hypotheses and eliminate unnecessary hypotheses according to the user's work situation. The providing unit can also dynamically customize the provided content based on the user's work situation. As a result, customizing the provided content according to the user's work situation makes it possible to efficiently provide only necessary hypotheses. For example, the providing unit prioritizes providing hypotheses related to a project the user is currently working on, making it possible to quickly provide hypotheses required by the user. As a result, the providing unit can provide only necessary hypotheses and eliminate unnecessary hypotheses according to the user's work situation, making it possible to efficiently provide hypotheses required by the user. As a result, the providing unit dynamically customizes the provided content based on the user's work situation, making it possible to quickly provide hypotheses required by the user.

[0055] The providing unit can improve the provision method by reflecting user feedback when providing a hypothesis. For example, the providing unit improves the provision method by reflecting user feedback when providing a hypothesis. Feedback includes, for example, user comments and evaluation scores, but is not limited to these examples. For example, the providing unit optimizes the provision method based on feedback provided by the user. The providing unit can also preferentially select a specific provision means based on the user feedback. The providing unit can also customize the provision method by reflecting user feedback to match the user's needs. In this way, the provision method can be optimized by reflecting user feedback, and a hypothesis tailored to the user's needs can be provided. For example, the providing unit can provide a hypothesis in a way that is easy for the user to understand by optimizing the provision method based on the user's feedback. In addition, the providing unit can provide a hypothesis in a way that is easy for the user to understand by preferentially selecting a specific provision means based on the user's feedback. In addition, the providing unit can customize the provision method by reflecting user feedback to match the user's needs, and provide a hypothesis in a way that is easy for the user to understand. In this way, the provision method can be optimized by reflecting user feedback, and a hypothesis tailored to the user's needs can be provided.

[0056] The providing unit can select the optimal providing method by taking into consideration device information of the user when providing a hypothesis. For example, the providing unit selects the optimal providing method by taking into consideration device information of the user when providing a hypothesis. Device information includes, but is not limited to, for example, a smartphone, a tablet, a PC, etc. For example, if the user is using a smartphone, the providing unit selects a providing method that matches the screen size. Furthermore, if the user is using a tablet, the providing unit can select a providing method optimized for a large screen. Furthermore, if the user is using a desktop, the providing unit can select a providing method that includes detailed information. In this way, the optimal providing method can be selected by taking into consideration device information of the user. For example, if the user is using a smartphone, the providing unit can select a providing method that matches the screen size to provide the hypothesis in a manner that is easy for the user to understand. Furthermore, if the user is using a tablet, the providing unit can select a providing method optimized for a large screen to provide the hypothesis in a manner that is easy for the user to understand. Furthermore, if the user is using a desktop, the providing unit can select a providing method that includes detailed information to provide the hypothesis in a manner that is easy for the user to understand. In this way, the optimal providing method can be selected by taking into consideration device information of the user.

[0057] The providing unit can provide the provided content in multiple languages ​​according to the user's language setting when providing a hypothesis. For example, when providing a hypothesis, the providing unit can provide the provided content in multiple languages ​​according to the user's language setting. Language settings include, but are not limited to, Japanese, English, and Spanish. For example, the providing unit can automatically set the language of the hypothesis based on the language setting of the user's device. The providing unit can also provide a language switching function when the user uses multiple languages. The providing unit can also provide the hypothesis in a specific language when the user selects that language. This makes the provided content multilingual according to the user's language setting, thereby providing a hypothesis that is easy for the user to understand. For example, the providing unit can automatically set the language of the hypothesis based on the language setting of the user's device, thereby providing the hypothesis in a language that is easy for the user to understand. The providing unit can also provide a language switching function when the user uses multiple languages, thereby providing the hypothesis in a language that is easy for the user to understand. The providing unit can also provide the hypothesis in a specific language when the user selects that language, thereby providing the hypothesis in that language. This allows the content to be provided in multiple languages ​​according to the user's language settings, making it possible to provide hypotheses that are easy for the user to understand.

[0058] The providing unit can customize the content to be provided based on the user's industry characteristics when providing hypotheses. For example, the providing unit customizes the content to be provided based on the user's industry characteristics when providing hypotheses. Industry characteristics include, but are not limited to, the medical industry, manufacturing industry, and financial industry. For example, the providing unit prioritizes providing hypotheses related to the industry to which the user belongs. The providing unit can also provide only necessary hypotheses and eliminate unnecessary hypotheses based on the industry characteristics. The providing unit can also dynamically customize the content to be provided based on the industry characteristics. As a result, industry-specific hypotheses can be provided by customizing the content to be provided based on the user's industry characteristics. For example, the providing unit prioritizes providing hypotheses related to the industry to which the user belongs, thereby quickly providing hypotheses needed by the user. As a result, the providing unit can provide only necessary hypotheses and eliminate unnecessary hypotheses based on the industry characteristics, thereby efficiently providing hypotheses needed by the user. As a result, the providing unit dynamically customizes the content to be provided based on the industry characteristics, thereby quickly providing hypotheses needed by the user. As a result, industry-specific hypotheses can be provided by customizing the content to be provided based on the user's industry characteristics.

[0059] A generative AI focused on a specific industry can improve the analytical accuracy of data in a specific industry by using an industry-specific generative AI. A generative AI focused on a specific industry can improve the analytical accuracy of data in a specific industry by using, for example, an industry-specific generative AI. Analysis accuracy includes, but is not limited to, data preprocessing and algorithm selection for improving accuracy. For example, a generative AI focused on a specific industry can improve the analytical accuracy of medical data by using a generative AI specialized for the medical industry. A generative AI focused on a specific industry can also improve the analytical accuracy of financial data by using a generative AI specialized for the financial industry. A generative AI focused on a specific industry can also improve the analytical accuracy of manufacturing data by using a generative AI specialized for the manufacturing industry. Thus, the analytical accuracy of data in a specific industry can be improved by using an industry-specific generative AI. For example, a generative AI focused on a specific industry can improve the analytical accuracy of medical data by using a generative AI specialized for the medical industry, thereby providing accurate analytical results related to healthcare. A generative AI focused on a specific industry can improve the analytical accuracy of financial data by using a generative AI specialized for the financial industry, thereby providing accurate analytical results related to finance. In addition, generative AI focused on a specific industry can provide accurate analytical results related to manufacturing by using generative AI specialized for the manufacturing industry to improve the accuracy of analytical data on manufacturing. As a result, by using industry-specific generative AI, the accuracy of analytical data in a specific industry can be improved.

[0060] A generative AI focused on a specific industry can improve the accuracy of hypothesis generation in a specific industry by using an industry-specific generative AI. A generative AI focused on a specific industry can improve the accuracy of hypothesis generation in a specific industry by using, for example, an industry-specific generative AI. The accuracy of hypothesis generation can include, but is not limited to, data preprocessing and algorithm selection for improving accuracy. For example, a generative AI focused on a specific industry can improve the accuracy of hypothesis generation from medical data by using a generative AI specialized for the medical industry. A generative AI focused on a specific industry can also improve the accuracy of hypothesis generation from financial data by using a generative AI specialized for the financial industry. A generative AI focused on a specific industry can also improve the accuracy of hypothesis generation from manufacturing data by using a generative AI specialized for the manufacturing industry. Thus, the accuracy of hypothesis generation in a specific industry can be improved by using an industry-specific generative AI. For example, a generative AI focused on a specific industry can improve the accuracy of hypothesis generation from medical data by using a generative AI specialized for the medical industry, thereby providing accurate hypotheses related to healthcare. Furthermore, a generative AI focused on a specific industry can provide accurate hypotheses related to finance by using a generative AI specialized for the financial industry to improve the accuracy of hypothesis generation from financial data. Also, a generative AI focused on a specific industry can provide accurate hypotheses related to manufacturing by using a generative AI specialized for the manufacturing industry to improve the accuracy of hypothesis generation from manufacturing data. In this way, by using industry-specific generative AI, the accuracy of hypothesis generation in a specific industry can be improved.

[0061] A generative AI focused on a specific industry can improve the efficiency of data collection in a specific industry by using an industry-specific generative AI. A generative AI focused on a specific industry can improve the efficiency of data collection in a specific industry by using, for example, an industry-specific generative AI. Data collection efficiency includes, but is not limited to, shortening collection time and comprehensiveness of data. For example, a generative AI focused on a specific industry can improve the efficiency of medical data collection by using a generative AI specialized for the medical industry. A generative AI focused on a specific industry can also improve the efficiency of financial data collection by using a generative AI specialized for the financial industry. A generative AI focused on a specific industry can also improve the efficiency of manufacturing data collection by using a generative AI specialized for the manufacturing industry. In this way, the efficiency of data collection in a specific industry can be improved by using an industry-specific generative AI. For example, a generative AI focused on a specific industry can improve the efficiency of medical data collection by using a generative AI specialized for the medical industry, thereby quickly collecting medical data. A generative AI focused on a specific industry can improve the efficiency of financial data collection by using a generative AI specialized for the financial industry, thereby quickly collecting financial data. In addition, generative AI focused on a specific industry can quickly collect manufacturing data by using generative AI specialized for the manufacturing industry to improve the efficiency of collecting manufacturing data. This makes it possible to improve the efficiency of data collection in a specific industry by using industry-specific generative AI.

[0062] A generative AI focused on a specific industry can provide analytical results of data in a specific industry using an industry-specific generative AI. A generative AI focused on a specific industry can, for example, use an industry-specific generative AI to provide analytical results of data in a specific industry. Analysis results include, but are not limited to, graph displays and text reports. For example, a generative AI focused on a specific industry can provide analytical results of medical data using a generative AI specialized for the medical industry. A generative AI focused on a specific industry can also provide analytical results of financial data using a generative AI specialized for the financial industry. A generative AI focused on a specific industry can also provide analytical results of manufacturing data using a generative AI specialized for the manufacturing industry. In this way, analytical results of data in a specific industry can be provided using an industry-specific generative AI. For example, a generative AI focused on a specific industry can provide analytical results of medical data using a generative AI specialized for the medical industry, thereby providing accurate analytical results related to healthcare. A generative AI focused on a specific industry can provide analytical results of financial data using a generative AI specialized for the financial industry, thereby providing accurate analytical results related to finance. In addition, generative AI focused on a specific industry can provide accurate analytical results related to manufacturing by using generative AI specialized for the manufacturing industry to provide analytical results on manufacturing data. This makes it possible to provide analytical results on data in a specific industry by using industry-specific generative AI.

[0063] A generation AI focused on a specific industry can provide hypothesis generation results for a specific industry using an industry-specific generation AI. A generation AI focused on a specific industry can provide hypothesis generation results for a specific industry using, for example, an industry-specific generation AI. Hypothesis generation results include, but are not limited to, graph displays and text reports. For example, a generation AI focused on a specific industry can provide hypothesis generation results from medical data using a generation AI specialized for the medical industry. A generation AI focused on a specific industry can also provide hypothesis generation results from financial data using a generation AI specialized for the financial industry. A generation AI focused on a specific industry can also provide hypothesis generation results from manufacturing data using a generation AI specialized for the manufacturing industry. In this way, hypothesis generation results for a specific industry can be provided using an industry-specific generation AI. For example, a generation AI focused on a specific industry can provide hypothesis generation results from medical data using a generation AI specialized for the medical industry, thereby providing accurate hypotheses related to healthcare. A generation AI focused on a specific industry can provide hypothesis generation results from financial data using a generation AI specialized for the financial industry, thereby providing accurate hypotheses related to finance. In addition, generative AI focused on a specific industry can provide accurate hypotheses about manufacturing by using generative AI specialized for the manufacturing industry to provide hypothesis generation results from manufacturing data. This makes it possible to provide hypothesis generation results for a specific industry by using industry-specific generative AI.

[0064] A generation AI focused on a specific industry can provide data collection results in a specific industry using an industry-specific generation AI. A generation AI focused on a specific industry can provide data collection results in a specific industry using, for example, an industry-specific generation AI. Data collection results include, but are not limited to, graph displays and text reports. For example, a generation AI focused on a specific industry can provide medical data collection results using a generation AI specialized for the medical industry. A generation AI focused on a specific industry can also provide financial data collection results using a generation AI specialized for the financial industry. A generation AI focused on a specific industry can also provide manufacturing data collection results using a generation AI specialized for the manufacturing industry. In this way, data collection results in a specific industry can be provided using an industry-specific generation AI. For example, a generation AI focused on a specific industry can provide accurate medical data collection results by using a generation AI specialized for the medical industry to provide medical data collection results. A generation AI focused on a specific industry can provide accurate financial data collection results by using a generation AI specialized for the financial industry to provide financial data collection results. In addition, generative AI focused on a specific industry can provide accurate data collection results related to manufacturing by using generative AI specialized for the manufacturing industry to provide manufacturing data collection results. This makes it possible to provide data collection results for a specific industry by using industry-specific generative AI.

[0065] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0066] When collecting data, the collection unit can analyze the user's past data provision history and select the optimal collection method. For example, it can prioritize collection of types of data that the user has frequently provided in the past. It can also prioritize data provision methods (voice, text, etc.) that the user has used in the past. Furthermore, it can select the optimal collection method for a specific time period from the user's past data provision history. This enables efficient data collection by selecting the optimal collection method based on the past data provision history.

[0067] The hypothesis generation unit can improve the accuracy of hypotheses by taking into account the interrelationships of data. For example, it can analyze the interrelationships of data and generate hypotheses with high accuracy. It can also improve the reliability of hypotheses by taking into account the interrelationships of data. Furthermore, it can dynamically adjust the accuracy of hypotheses based on the interrelationships of data. In this way, it is possible to generate hypotheses with high accuracy by taking into account the interrelationships of data.

[0068] The analysis unit can apply different analysis algorithms depending on the data category. For example, a sales forecasting algorithm can be applied to sales data. A behavioral pattern analysis algorithm can also be applied to customer behavior data. Furthermore, a trend forecasting algorithm can be applied to market trend data. In this way, by applying the appropriate analysis algorithm depending on the data category, highly accurate analysis results can be provided.

[0069] When providing hypotheses, the providing unit can customize the content to be provided according to the user's current work situation. For example, it can provide hypotheses related to the project the user is currently working on with priority. It can also provide only necessary hypotheses and eliminate unnecessary hypotheses according to the user's work situation. Furthermore, it can dynamically customize the content to be provided based on the user's work situation. In this way, by customizing the content to be provided according to the user's work situation, it is possible to efficiently provide only necessary hypotheses.

[0070] When collecting data, the collection unit can prioritize collection of highly relevant data based on the user's geographical location information. For example, if the user is in a specific area, data related to that area can be prioritized. Also, if the user is moving, highly relevant data can be collected based on the user's current location. Furthermore, if the user is staying in a specific place, data related to that place can be prioritized. In this way, highly relevant data can be efficiently collected by taking the user's geographical location information into consideration.

[0071] The processing flow of the first embodiment will be briefly explained below.

[0072] Step 1: The collection unit collects data. The data includes numerical data, text data, image data, etc. The collection unit collects data such as sales data, customer behavior data, and market trends. The collection unit can also collect data in real time using sensors and APIs. For example, the collection unit can collect environmental data using sensors. The collection unit can also collect social media data using APIs. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis is performed using statistical analysis or machine learning algorithms. For example, the analysis unit analyzes trends in the data using statistical analysis. The analysis unit can also analyze patterns in the data using machine learning algorithms. The analysis unit can also analyze text data using natural language processing technology. Step 3: The hypothesis generation unit derives hypotheses based on the data analyzed by the analysis unit. The hypotheses are generated based on a predictive model and an inference of causal relationships. For example, the hypothesis generation unit uses a predictive model to generate a hypothesis that a particular product sells well in a particular season. The hypothesis generation unit can also use an inference of causal relationships to generate a hypothesis that a particular customer segment shows a high interest in a particular service. The hypothesis generation unit can also use data mining technology to derive new hypotheses from the data. Step 4: The provision unit provides the hypotheses derived by the hypothesis generation unit to the client. Provision is performed in the form of a report or a dashboard display. For example, the provision unit provides the hypotheses in the form of a report. The provision unit can also provide the hypotheses in real time through a dashboard. The provision unit can also provide the hypotheses to the client through email or notifications.

[0073] (Example 2) A data analysis system according to an embodiment of the present invention utilizes generative AI to derive hypotheses from data. This data analysis system collects, analyzes, generates, and provides data to support customers in strengthening their business strategies and making effective decisions. For example, in a data analysis system, a customer provides data related to their industry. The customer then selects an external generative AI, which analyzes the provided data. The generative AI analyzes the data and derives hypotheses from it. For example, a hypothesis might be that a particular product sells better in a particular season, or that a particular customer demographic is highly interested in a particular service. The hypotheses derived by the generative AI are provided to customers. Customers can use these hypotheses to strengthen their business strategies and make effective decisions. Furthermore, generative AI focused on specific industries is also under consideration. For example, a generative AI specialized for the medical industry or the financial industry could be developed. This would enable more specialized and accurate hypotheses to be derived. For example, the hypotheses derived by the generative AI could be used to develop new marketing strategies or revise product development directions. Furthermore, the insights provided by the generative AI could be used to differentiate companies from their competitors. This allows the data analysis system to support the strengthening of customers' business strategies and effective decision-making. For example, it is possible to formulate a new marketing strategy or review the direction of product development based on hypotheses derived by generative AI. It is also possible to differentiate from competitors based on insights provided by generative AI. This allows the data analysis system to support the strengthening of customers' business strategies and effective decision-making.

[0074] A data analysis system according to an embodiment includes a collection unit, an analysis unit, a hypothesis generation unit, and a provision unit. The collection unit collects data. Examples of the data include, but are not limited to, numerical data, text data, and image data. The collection unit collects data such as sales data, customer behavior data, and market trends. The collection unit can also collect data in real time using sensors and APIs. For example, the collection unit can collect environmental data using sensors. The collection unit can also collect social media data using APIs. The analysis unit analyzes the data collected by the collection unit. The analysis can be performed using, for example, statistical analysis or a machine learning algorithm, but is not limited to these examples. For example, the analysis unit can analyze data trends using statistical analysis. The analysis unit can also analyze data patterns using a machine learning algorithm. The analysis unit can also analyze text data using natural language processing technology. The hypothesis generation unit derives hypotheses based on the data analyzed by the analysis unit. The hypotheses can be generated based on, for example, a predictive model or an estimation of causal relationships, but are not limited to these examples. For example, the hypothesis generation unit may use a predictive model to generate a hypothesis that a particular product sells well in a particular season. The hypothesis generation unit may also use causal relationship estimation to generate a hypothesis that a particular customer segment is highly interested in a particular service. The hypothesis generation unit may also use data mining technology to derive new hypotheses from data. The provision unit provides the hypotheses derived by the hypothesis generation unit to a customer. The provision may be, for example, in the form of a report or through a dashboard display, but is not limited to these examples. For example, the provision unit may provide the hypotheses in the form of a report. The provision unit may also provide the hypotheses in real time through a dashboard. The provision unit may also provide the hypotheses to a customer via email or notification. This allows the data analysis system according to the embodiment to strengthen a customer's business strategy and support effective decision-making.

[0075] The data analysis system further includes a generative AI focused on a specific industry. Examples of generative AI focused on a specific industry include the medical, manufacturing, and financial industries. For example, a generative AI specialized for the medical industry analyzes medical data and generates hypotheses related to medical care. A generative AI specialized for the manufacturing industry can analyze manufacturing data and generate hypotheses related to manufacturing. A generative AI specialized for the financial industry can analyze financial data and generate hypotheses related to finance. This makes it possible to derive more specialized and accurate hypotheses by using generative AI specialized for a specific industry. For example, a generative AI specialized for the medical industry can analyze medical data and generate a hypothesis that a specific treatment is effective for a specific patient. A generative AI specialized for the manufacturing industry can analyze manufacturing data and generate a hypothesis that a specific manufacturing process improves the quality of a specific product. A generative AI specialized for the financial industry can analyze financial data and generate a hypothesis that a specific investment strategy is effective under specific market conditions. This makes it possible to derive more specialized and accurate hypotheses by using generative AI specialized for a specific industry.

[0076] The providing unit can provide the hypothesis in real time through a dashboard. The providing unit, for example, provides the hypothesis in real time through a dashboard. The dashboard includes, for example, a graph display and a filtering function, but is not limited to these examples. For example, the providing unit provides the hypothesis in a graph display. The providing unit can also provide the hypothesis using a filtering function. The providing unit can also update the hypothesis in real time to provide the latest information. By providing the hypothesis in real time, the customer can make decisions quickly. For example, by providing the hypothesis in real time, the providing unit can help the customer to quickly formulate a marketing strategy. By providing the hypothesis in real time, the providing unit can help the customer to quickly review the direction of product development. By providing the hypothesis in real time, the providing unit can help the customer to make decisions quickly.

[0077] The providing unit can provide the hypothesis in a report format. For example, the providing unit provides the hypothesis in a report format. Report formats include, but are not limited to, PDF format and Excel format. For example, the providing unit can provide the hypothesis in PDF format. The providing unit can also provide the hypothesis in Excel format. The providing unit can also provide the hypothesis in a customized report format. By providing the hypothesis in report format, a customer can make decisions based on detailed information. For example, by providing the hypothesis in report format, a customer can plan a detailed marketing strategy. By providing the hypothesis in report format, a customer can review the direction of product development in detail. By providing the hypothesis in report format, a customer can make decisions based on detailed information.

[0078] The collection unit can collect sales data, customer behavior data, and market trend data. The collection unit, for example, collects sales data. The sales data includes, for example, sales data and sales data by product, but is not limited to these examples. For example, the collection unit collects sales data. The collection unit can also collect sales data by product. The collection unit can also collect customer behavior data. The customer behavior data includes, for example, website browsing history and purchase history, but is not limited to these examples. For example, the collection unit collects website browsing history. The collection unit can also collect purchase history. The collection unit can also collect market trend data. The market trend data includes, for example, market research data and social media trends, but is not limited to these examples. For example, the collection unit collects market research data. The collection unit can also collect social media trends. By collecting a variety of data, more diverse hypotheses can be generated. For example, by collecting sales data, customer behavior data, and market trend data, the collection unit can generate a hypothesis that a particular product sells well in a particular season. Also, by collecting sales data, customer behavior data, and market trend data, the collection unit can generate a hypothesis that a particular customer segment shows a high interest in a particular service. In this way, by collecting a variety of data, more diverse hypotheses can be generated.

[0079] The analysis unit can analyze the collected data and derive a hypothesis that a specific product will sell in a specific season. The analysis unit, for example, analyzes the collected data and derives a hypothesis that a specific product will sell in a specific season. Examples of specific products include, but are not limited to, seasonal products and standard products. For example, the analysis unit can derive a hypothesis that a seasonal product will sell in a specific season. The analysis unit can also derive a hypothesis that a standard product will sell in a specific season. Examples of specific seasons include, but are not limited to, spring, summer, fall, and winter. For example, the analysis unit can derive a hypothesis that a specific product will sell in spring. The analysis unit can also derive a hypothesis that a specific product will sell in summer. The analysis unit can also derive a hypothesis that a specific product will sell in fall. The analysis unit can also derive a hypothesis that a specific product will sell in winter. This makes it possible to understand seasonal product sales trends through data analysis. For example, the analysis unit can analyze the collected data and derive a hypothesis that a specific product will sell in a specific season, allowing customers to develop seasonal sales strategies. The analysis department also analyzes the collected data and draws hypotheses about which products sell best in which seasons, allowing customers to optimize their inventory management. This allows data analysis to identify seasonal product sales trends.

[0080] The collection unit can estimate a user's emotion and adjust the timing of data collection based on the estimated user's emotion. For example, the collection unit can estimate a user's emotion and adjust the timing of data collection based on the estimated user's emotion. The user's emotion can be estimated using, for example, facial expression recognition or text analysis, but is not limited to these examples. For example, the collection unit can estimate a user's emotion using facial expression recognition. The collection unit can also estimate a user's emotion using text analysis. The collection unit can also estimate a user's emotion using voice analysis. For example, if the user is feeling stressed, the collection unit can reduce the frequency of data collection to reduce the user's burden. If the user is relaxed, the collection unit can increase the frequency of data collection to collect more data. If the user is in a hurry, the collection unit can adjust the timing of data collection to quickly collect necessary data. In this way, by adjusting the timing of data collection according to the user's emotion, the burden on the user can be reduced. For example, the collection unit can estimate a user's emotion and adjust the timing of data collection based on the estimated user's emotion, thereby providing data without the user feeling stressed. Furthermore, the collection unit estimates the user's emotions and adjusts the timing of data collection based on the estimated user emotions, thereby enabling efficient data collection when the user is relaxed. This reduces the burden on the user by adjusting the timing of data collection according to the user's emotions.

[0081] The collection unit can analyze the user's past data provision history and select the optimal collection method. The collection unit, for example, analyzes the user's past data provision history and selects the optimal collection method. The data provision history includes, for example, the number of times data has been provided in the past and the type of provided data, but is not limited to these examples. For example, the collection unit prioritizes collecting types of data that the user has frequently provided in the past. The collection unit can also prioritize selecting data provision methods (audio, text, etc.) that the user has used in the past. The collection unit can also select the optimal collection method for a specific time period based on the user's past data provision history. For example, the collection unit selects the optimal collection method based on the type of data the user has provided in the past. The collection unit can also select the optimal collection method based on the data provision methods the user has used in the past. The collection unit can also analyze the user's past data provision history and select the optimal collection method for a specific time period. In this way, efficient data collection is possible by selecting the optimal collection method based on the past data provision history. For example, the collection unit can analyze the user's past data provision history and select the optimal collection method, thereby collecting data in a way that is easy for the user to provide. Furthermore, the collection unit analyzes the user's past data provision history and selects the optimal collection method, thereby collecting data at a time when it is convenient for the user to provide the data. This allows for efficient data collection by selecting the optimal collection method based on the user's past data provision history.

[0082] The collection unit may filter data based on the user's current work situation or areas of interest when collecting data. For example, the collection unit may filter data based on the user's current work situation or areas of interest when collecting data. Examples of work situations include, but are not limited to, project progress and work priorities. For example, the collection unit may prioritize collecting data related to a project the user is currently working on. The collection unit may also collect only necessary data and eliminate unnecessary data based on the user's work priorities. Examples of areas of interest include, but are not limited to, technical fields and business fields. For example, the collection unit may filter and collect highly relevant data based on the user's areas of interest. The collection unit may also collect only necessary data and eliminate unnecessary data according to the user's work situation. Thus, filtering data based on the user's work situation or areas of interest allows efficient collection of only necessary data. For example, the collection unit may prioritize collecting relevant data based on the user's current work situation, allowing rapid provision of data required by the user. The collection unit may filter and collect highly relevant data based on the user's areas of interest, allowing efficient provision of data of interest to the user. This allows users to filter data based on their work situation and areas of interest, allowing them to efficiently collect only the data they need.

[0083] The collection unit can select an optimal collection means depending on the user's input method when collecting data. For example, the collection unit selects an optimal collection means depending on the user's input method (voice, text, image, etc.) when collecting data. Input methods include, but are not limited to, voice input, text input, and image input. For example, when the user uses voice input, the collection unit prioritizes collecting voice data. Furthermore, when the user uses text input, the collection unit can also prioritize collecting text data. Furthermore, when the user uses image input, the collection unit can also prioritize collecting image data. In this way, efficient data collection is possible by selecting an optimal collection means depending on the user's input method. For example, when the user uses voice input, the collection unit prioritizes collecting voice data, thereby collecting data in a manner that is easy for the user to provide. Furthermore, when the user uses text input, the collection unit prioritizes collecting text data, thereby collecting data in a manner that is easy for the user to provide. Furthermore, when the user uses image input, the collection unit prioritizes collecting image data, thereby collecting data in a manner that is easy for the user to provide. In this way, efficient data collection is possible by selecting an optimal collection means depending on the user's input method.

[0084] The collection unit can estimate the user's emotions and determine the priority of data to be collected based on the estimated user emotions. The collection unit, for example, estimates the user's emotions and determines the priority of data to be collected based on the estimated user emotions. The user's emotions are estimated using, for example, facial expression recognition or text analysis, but are not limited to these examples. For example, the collection unit estimates the user's emotions using facial expression recognition. The collection unit can also estimate the user's emotions using text analysis. The collection unit can also estimate the user's emotions using voice analysis. For example, when the user is feeling stressed, the collection unit prioritizes collecting data of high importance. When the user is relaxed, the collection unit can also collect data of low importance. When the user is in a hurry, the collection unit can prioritize collecting data that can be collected quickly. In this way, by determining the priority of data according to the user's emotions, important data can be collected preferentially. For example, when the collection unit estimates the user's emotions and determines the priority of data to be collected based on the estimated user emotions, important data can be provided to the user without causing stress. Furthermore, the collection unit estimates the user's emotions and determines the priority of data to be collected based on the estimated user emotions, thereby enabling efficient collection of data when the user is relaxed. Thus, by determining the priority of data according to the user's emotions, important data can be preferentially collected.

[0085] The collection unit can prioritize collecting highly relevant data based on the user's geographical location information when collecting data. For example, the collection unit prioritizes collecting highly relevant data by taking the user's geographical location information into consideration when collecting data. Geographical location information includes, but is not limited to, GPS data and address information. For example, when the user is in a specific area, the collection unit prioritizes collecting data related to that area. Furthermore, when the user is moving, the collection unit can also collect highly relevant data based on the user's current location. Furthermore, when the user is staying in a specific place, the collection unit can prioritize collecting data related to that place. In this way, highly relevant data can be efficiently collected by taking the user's geographical location information into consideration. For example, when the user is in a specific area, the collection unit prioritizes collecting data related to that area, thereby enabling the user to quickly provide the data required by the user. Furthermore, when the user is moving, the collection unit collects highly relevant data based on the user's current location, thereby enabling the user to efficiently provide the data required by the user. Furthermore, when the user is staying in a specific place, the collection unit prioritizes collecting data related to that place, thereby enabling the user to quickly provide the data required by the user. This allows for efficient collection of highly relevant data by taking into account the user's geographical location information.

[0086] The collection unit can analyze the user's social media activities and collect related data when collecting data. For example, the collection unit can analyze the user's social media activities and collect related data when collecting data. Social media activities include, but are not limited to, post content, the number of likes, and the number of followers. For example, the collection unit can collect related data based on information shared by the user on social media. The collection unit can also analyze the user's social media activities and collect related data. The collection unit can also collect related data by referring to the activities of the user's friends on social media. In this way, highly relevant data can be efficiently collected by analyzing the user's social media activities. For example, the collection unit can collect related data based on the information shared by the user on social media, thereby quickly providing data that the user is interested in. The collection unit can also analyze the user's social media activities and collect related data. In addition, the collection unit can collect related data by referring to the activities of the user's friends on social media, thereby quickly providing data that the user is interested in. In this way, highly relevant data can be efficiently collected by analyzing the user's social media activities.

[0087] The collection unit can customize the collection method by reflecting the user's past feedback when collecting data. For example, the collection unit customizes the collection method by reflecting the user's past feedback when collecting data. The feedback includes, for example, user comments and evaluation scores, but is not limited to these examples. For example, the collection unit optimizes the collection method based on feedback provided by the user in the past. The collection unit can also preferentially select a specific data collection means based on the user's past feedback. The collection unit can also customize the collection method by reflecting the user's feedback to suit the user's needs. In this way, the collection method can be optimized by reflecting the user's past feedback, enabling efficient data collection. For example, the collection unit can collect data in a way that is easy for the user to provide by optimizing the collection method based on the user's past feedback. The collection unit can also preferentially select a specific data collection means based on the user's past feedback. The collection unit can collect data in a way that is easy for the user to provide by reflecting the user's feedback. This allows for the collection method to be optimized and data to be collected efficiently by reflecting past user feedback.

[0088] The analysis unit can estimate the user's emotion and adjust the method of presentation of the analysis based on the estimated user's emotion. For example, the analysis unit can estimate the user's emotion and adjust the method of presentation of the analysis based on the estimated user's emotion. The user's emotion can be estimated using, for example, facial expression recognition or text analysis, but is not limited to these examples. For example, the analysis unit can estimate the user's emotion using facial expression recognition. The analysis unit can also estimate the user's emotion using text analysis. The analysis unit can also estimate the user's emotion using voice analysis. For example, the analysis unit can provide a simple, highly visible analysis result when the user is nervous. The analysis unit can also provide a detailed analysis result when the user is relaxed. The analysis unit can also provide a concise analysis result when the user is in a hurry. In this way, by adjusting the method of presentation of the analysis according to the user's emotion, it is possible to provide an analysis result that is easy for the user to understand. For example, the analysis unit can estimate the user's emotion and adjust the method of presentation of the analysis based on the estimated user's emotion, it is possible to provide an analysis result that is easy for the user to understand even when the user is nervous. Furthermore, the analysis unit estimates the user's emotions and adjusts the way the analysis is presented based on the estimated user emotions, making it possible to provide detailed analysis results even when the user is relaxed. This makes it possible to provide analysis results that are easy for the user to understand by adjusting the way the analysis is presented according to the user's emotions.

[0089] The analysis unit can adjust the level of detail of the analysis based on the importance of the data during analysis. For example, the analysis unit adjusts the level of detail of the analysis based on the importance of the data during analysis. The importance of data includes, but is not limited to, business impact and data reliability. For example, the analysis unit performs a detailed analysis on data with high importance. The analysis unit can also perform a simplified analysis on data with low importance. The analysis unit can also dynamically adjust the level of detail of the analysis according to the importance of the data. This enables efficient data analysis by adjusting the level of detail of the analysis according to the importance of the data. For example, the analysis unit can perform a detailed analysis on data with high importance, thereby analyzing data with a large business impact in detail. The analysis unit can also perform a simplified analysis on data with low importance, thereby analyzing data efficiently. The analysis unit can also dynamically adjust the level of detail of the analysis according to the importance of the data, thereby analyzing data efficiently.

[0090] The analysis unit can apply different analysis algorithms depending on the data category during analysis. For example, the analysis unit applies different analysis algorithms depending on the data category during analysis. Data categories include, but are not limited to, text data, numerical data, and image data. For example, the analysis unit applies a sales forecasting algorithm to sales data. The analysis unit can also apply a behavior pattern analysis algorithm to customer behavior data. The analysis unit can also apply a trend prediction algorithm to market trend data. In this way, by applying an appropriate analysis algorithm depending on the data category, highly accurate analysis results can be provided. For example, the analysis unit can predict sales by applying a sales forecasting algorithm to sales data. In addition, the analysis unit can analyze customer behavior patterns by applying a behavior pattern analysis algorithm to customer behavior data. In addition, the analysis unit can predict market trends by applying a trend prediction algorithm to market trend data. In this way, by applying an appropriate analysis algorithm depending on the data category, highly accurate analysis results can be provided.

[0091] The analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results during analysis. For example, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results during analysis. Past analysis results include, but are not limited to, past reports and database records. For example, the analysis unit can optimize the analysis algorithm based on the user's past analysis results. The analysis unit can also extract specific patterns from the user's past analysis results to improve the accuracy of the analysis. The analysis unit can also dynamically adjust the accuracy of the analysis by referring to the user's past analysis results. In this way, the accuracy of the analysis can be improved by referring to the user's past analysis results. For example, the analysis unit can improve the accuracy of the analysis by optimizing the analysis algorithm based on the user's past analysis results. The analysis unit can improve the accuracy of the analysis by extracting specific patterns from the user's past analysis results to improve the accuracy of the analysis, thereby providing more accurate analysis results. The analysis unit can also dynamically adjust the accuracy of the analysis by referring to the user's past analysis results to provide more accurate analysis results. This allows the accuracy of the analysis to be improved by referring to the user's past analysis results.

[0092] The analysis unit can estimate the user's emotion and adjust the length of the analysis based on the estimated user's emotion. The analysis unit, for example, estimates the user's emotion and adjusts the length of the analysis based on the estimated user's emotion. The user's emotion is estimated using, for example, facial expression recognition or text analysis, but is not limited to these examples. For example, the analysis unit can estimate the user's emotion using facial expression recognition. The analysis unit can also estimate the user's emotion using text analysis. The analysis unit can also estimate the user's emotion using voice analysis. For example, the analysis unit can provide a short and to-the-point analysis result when the user is in a hurry. The analysis unit can provide a detailed analysis result when the user is relaxed. The analysis unit can also provide an analysis result with visually stimulating effects when the user is excited. In this way, by adjusting the length of the analysis according to the user's emotion, it is possible to provide an optimal analysis result for the user. For example, the analysis unit can estimate the user's emotion and adjust the length of the analysis based on the estimated user's emotion, it is possible to provide an analysis result that is to the point even when the user is in a hurry. Furthermore, the analysis unit estimates the user's emotions and adjusts the length of the analysis based on the estimated user emotions, making it possible to provide detailed analysis results even when the user is relaxed. This allows the analysis unit to adjust the length of the analysis according to the user's emotions, making it possible to provide the user with optimal analysis results.

[0093] The analysis unit can determine the analysis priority based on the time of data submission during analysis. The analysis unit, for example, determines the analysis priority based on the time of data submission during analysis. The time of data submission includes, for example, the submission date and the submission time, but is not limited to these examples. For example, the analysis unit prioritizes analysis of the most recent data. The analysis unit can also postpone analysis of data that was submitted earlier. The analysis unit can also dynamically adjust the analysis priority according to the time of data submission. In this way, by determining the analysis priority based on the time of data submission, the most recent data can be analyzed preferentially. For example, by analyzing the most recent data preferentially, the analysis unit can provide analysis results based on the most recent information. In addition, by postponing analysis of data that was submitted earlier, the analysis unit can efficiently analyze data. In addition, by dynamically adjusting the analysis priority according to the time of data submission, the analysis unit can efficiently analyze data. In this way, by determining the analysis priority based on the time of data submission, the most recent data can be analyzed preferentially.

[0094] The analysis unit can adjust the order of analysis based on the relevance of data during analysis. For example, the analysis unit adjusts the order of analysis based on the relevance of data during analysis. Data relevance includes, but is not limited to, correlation and causal relationship, for example. For example, the analysis unit prioritizes analysis of highly relevant data. The analysis unit can also postpone analysis of less relevant data. The analysis unit can also dynamically adjust the order of analysis according to the relevance of data. In this way, adjusting the order of analysis based on the relevance of data enables efficient data analysis. For example, the analysis unit can prioritize analysis of highly relevant data, thereby quickly analyzing highly relevant data. In addition, the analysis unit can postpone analysis of less relevant data, thereby efficiently analyzing data. In addition, the analysis unit can dynamically adjust the order of analysis according to the relevance of data, thereby efficiently analyzing data. In this way, adjusting the order of analysis based on the relevance of data enables efficient data analysis.

[0095] The analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise during analysis. For example, the analysis unit adjusts the use of technical terms in the analysis according to the user's level of expertise during analysis. Expertise levels include, but are not limited to, beginner, intermediate, and advanced. For example, if the user has expert knowledge, the analysis unit provides analysis results that use a lot of technical terms. Furthermore, if the user does not have expert knowledge, the analysis unit can provide analysis results in simple language. Furthermore, the analysis unit can dynamically adjust the use of technical terms in the analysis according to the user's level of expertise. In this way, by adjusting the use of technical terms in the analysis according to the user's level of expertise, analysis results that are easy for the user to understand can be provided. For example, if the user has expert knowledge, the analysis unit can provide specialized information by providing analysis results that use a lot of technical terms. Furthermore, if the user does not have expert knowledge, the analysis unit can provide analysis results in simple language to provide information that is easy for the user to understand. Furthermore, by dynamically adjusting the use of technical terms in the analysis according to the user's level of expertise, information that is easy for the user to understand can be provided. This allows the use of analytical terminology to be adjusted according to the user's level of expertise, making it possible to provide analysis results that are easy for the user to understand.

[0096] The hypothesis generation unit can estimate the user's emotion and adjust the hypothesis generation method based on the estimated user's emotion. For example, the hypothesis generation unit can estimate the user's emotion and adjust the hypothesis generation method based on the estimated user's emotion. The user's emotion can be estimated using, for example, facial expression recognition or text analysis, but is not limited to these examples. For example, the hypothesis generation unit can estimate the user's emotion using facial expression recognition. The hypothesis generation unit can also estimate the user's emotion using text analysis. The hypothesis generation unit can also estimate the user's emotion using voice analysis. For example, the hypothesis generation unit can generate a detailed hypothesis when the user is relaxed. The hypothesis generation unit can also generate a concise hypothesis when the user is in a hurry. The hypothesis generation unit can also generate a hypothesis with a visually stimulating effect when the user is excited. In this way, by adjusting the hypothesis generation method according to the user's emotion, it is possible to generate an optimal hypothesis for the user. For example, the hypothesis generation unit can estimate the user's emotion and adjust the hypothesis generation method based on the estimated user's emotion, thereby providing a detailed hypothesis even when the user is relaxed. Furthermore, the hypothesis generation unit estimates the user's emotions and adjusts the hypothesis generation method based on the estimated user emotions, thereby providing concise hypotheses even when the user is in a hurry. In this way, by adjusting the hypothesis generation method according to the user's emotions, it is possible to generate hypotheses that are optimal for the user.

[0097] The hypothesis generation unit can improve the accuracy of a hypothesis based on the interrelationships of data when generating a hypothesis. For example, the hypothesis generation unit improves the accuracy of a hypothesis by taking into account the interrelationships of data when generating a hypothesis. Examples of the interrelationships of data include, but are not limited to, correlation analysis and network analysis. For example, the hypothesis generation unit analyzes the interrelationships of data to generate a highly accurate hypothesis. The hypothesis generation unit can also improve the reliability of the hypothesis by taking into account the interrelationships of data. The hypothesis generation unit can also dynamically adjust the accuracy of the hypothesis based on the interrelationships of data. In this way, a highly accurate hypothesis can be generated by taking into account the interrelationships of data. For example, the hypothesis generation unit can provide a highly reliable hypothesis by analyzing the interrelationships of data and generating a highly accurate hypothesis. In addition, the hypothesis generation unit can provide a more accurate hypothesis by improving the reliability of the hypothesis by taking into account the interrelationships of data. In this way, a highly accurate hypothesis can be generated by taking into account the interrelationships of data.

[0098] The hypothesis generation unit can generate a hypothesis by taking into account attribute information of the data submitter when generating a hypothesis. For example, the hypothesis generation unit generates a hypothesis by taking into account attribute information of the data submitter when generating a hypothesis. The attribute information includes, but is not limited to, age, gender, occupation, etc. For example, the hypothesis generation unit generates a hypothesis based on the attribute information of the data submitter. The hypothesis generation unit can also improve the reliability of the hypothesis by taking into account the attribute information of the submitter. The hypothesis generation unit can also dynamically adjust the accuracy of the hypothesis based on the attribute information of the submitter. In this way, a highly reliable hypothesis can be generated by taking into account the attribute information of the data submitter. For example, the hypothesis generation unit can provide a hypothesis based on the attributes of the data submitter by generating a hypothesis based on the attribute information of the data submitter. In addition, the hypothesis generation unit can improve the reliability of the hypothesis by taking into account the attribute information of the submitter, thereby providing a more accurate hypothesis. In addition, the hypothesis generation unit can dynamically adjust the accuracy of the hypothesis based on the attribute information of the submitter, thereby providing a more accurate hypothesis. In this way, a highly reliable hypothesis can be generated by taking into account the attribute information of the data submitter.

[0099] The hypothesis generation unit can weight hypotheses based on the frequency of data submission when generating hypotheses. For example, the hypothesis generation unit weights hypotheses based on the frequency of data submission when generating hypotheses. The submission frequency includes, but is not limited to, weekly, monthly, and yearly. For example, the hypothesis generation unit weights hypotheses based on data submitted frequently. The hypothesis generation unit can also lower the weight of data submitted infrequently. The hypothesis generation unit can also dynamically adjust the weight of hypotheses according to the frequency of data submission. In this way, by weighting hypotheses based on the frequency of data submission, hypotheses based on important data can be generated. For example, the hypothesis generation unit weights hypotheses based on data submitted frequently, thereby providing hypotheses based on frequently provided data. The hypothesis generation unit can also lower the weight of data submitted infrequently, thereby providing hypotheses based on data of low importance. The hypothesis generation unit can also dynamically adjust the weight of hypotheses according to the frequency of data submission. This allows hypotheses to be weighted based on the frequency of data submission, allowing hypotheses to be generated that are based on important data.

[0100] The hypothesis generation unit can estimate the user's emotion and adjust the display method of the hypothesis based on the estimated user's emotion. The hypothesis generation unit, for example, estimates the user's emotion and adjusts the display method of the hypothesis based on the estimated user's emotion. The user's emotion is estimated using, for example, facial expression recognition or text analysis, but is not limited to these examples. For example, the hypothesis generation unit estimates the user's emotion using facial expression recognition. The hypothesis generation unit can also estimate the user's emotion using text analysis. The hypothesis generation unit can also estimate the user's emotion using voice analysis. For example, the hypothesis generation unit provides a simple, highly visible display method when the user is nervous. The hypothesis generation unit can also provide a display method including detailed information when the user is relaxed. The hypothesis generation unit can also provide a display method that focuses on the main points when the user is in a hurry. In this way, by adjusting the display method of the hypothesis according to the user's emotion, it is possible to provide a hypothesis that is easy for the user to understand. For example, the hypothesis generation unit estimates the user's emotion and adjusts the display method of the hypothesis based on the estimated user's emotion, it is possible to provide a hypothesis that is easy for the user to understand even when the user is nervous. Furthermore, the hypothesis generation unit estimates the user's emotions and adjusts the display method of hypotheses based on the estimated user emotions, thereby making it possible to provide detailed hypotheses even when the user is relaxed. This makes it possible to provide hypotheses that are easy for the user to understand by adjusting the display method of hypotheses according to the user's emotions.

[0101] The hypothesis generation unit may generate hypotheses taking into account the geographical distribution of data when generating hypotheses. For example, the hypothesis generation unit generates hypotheses taking into account the geographical distribution of data when generating hypotheses. Geographical distribution includes, but is not limited to, data by region or data by country. For example, the hypothesis generation unit may analyze the geographical distribution of data and generate hypotheses taking into account the characteristics of each region. The hypothesis generation unit may also generate hypotheses related to a specific region based on the geographical distribution. The hypothesis generation unit may also improve the accuracy of the hypotheses by taking the geographical distribution into account. In this way, by taking the geographical distribution of data into account, hypotheses that reflect the characteristics of each region can be generated. For example, the hypothesis generation unit may analyze the geographical distribution of data and generate hypotheses taking into account the characteristics of each region, thereby providing hypotheses that reflect the characteristics of each region. In addition, by generating hypotheses related to a specific region based on the geographical distribution, hypotheses that reflect the characteristics of each region can be provided. In addition, the hypothesis generation unit may improve the accuracy of the hypotheses by taking the geographical distribution into account, thereby providing more accurate hypotheses. In this way, by taking the geographical distribution of data into account, hypotheses that reflect the characteristics of each region can be generated.

[0102] The hypothesis generation unit can improve the accuracy of the hypothesis by referring to literature related to the data when generating a hypothesis. For example, the hypothesis generation unit can improve the accuracy of the hypothesis by referring to literature related to the data when generating a hypothesis. Related literature includes, but is not limited to, academic papers and technical reports. For example, the hypothesis generation unit can improve the reliability of the hypothesis by referring to the related literature. The hypothesis generation unit can also improve the accuracy of the hypothesis based on the related literature. The hypothesis generation unit can also support the hypothesis by referring to the related literature. In this way, a highly reliable hypothesis can be generated by referring to the related literature. For example, the hypothesis generation unit can provide a highly reliable hypothesis by referring to the related literature and improving the reliability of the hypothesis. In addition, the hypothesis generation unit can provide a more accurate hypothesis by improving the accuracy of the hypothesis based on the related literature. In addition, the hypothesis generation unit can provide a more accurate hypothesis by referring to the related literature and supporting the hypothesis. In this way, a highly reliable hypothesis can be generated by referring to the related literature.

[0103] The hypothesis generation unit can generate a hypothesis taking into account the market value of the data when generating a hypothesis. For example, the hypothesis generation unit generates a hypothesis taking into account the market value of the data when generating a hypothesis. Market value includes, but is not limited to, sales forecasts and market shares. For example, the hypothesis generation unit generates a hypothesis based on data with high market value. The hypothesis generation unit can also lower the priority of hypothesis generation for data with low market value. The hypothesis generation unit can also weight the hypotheses according to the market value of the data. In this way, a hypothesis with high value can be generated by taking the market value of the data into account. For example, the hypothesis generation unit can provide a hypothesis with high value by generating a hypothesis based on data with high market value. In addition, the hypothesis generation unit can lower the priority of hypothesis generation for data with low market value, thereby providing a hypothesis based on data with low importance. In addition, the hypothesis generation unit can provide a hypothesis with high value by weighting the hypothesis according to the market value of the data. In this way, a hypothesis with high value can be generated by taking the market value of the data into account.

[0104] The providing unit can estimate the user's emotions and adjust the method of providing hypotheses based on the estimated user emotions. The providing unit, for example, estimates the user's emotions and adjusts the method of providing hypotheses based on the estimated user emotions. The user's emotions are estimated using, for example, facial expression recognition or text analysis, but are not limited to these examples. For example, the providing unit estimates the user's emotions using facial expression recognition. The providing unit can also estimate the user's emotions using text analysis. The providing unit can also estimate the user's emotions using voice analysis. For example, if the user is nervous, the providing unit selects a simple, highly visible method of providing hypotheses. If the user is relaxed, the providing unit can select a method of providing hypotheses that includes detailed information. If the user is in a hurry, the providing unit can select a method of providing hypotheses that focuses on the main points. In this way, by adjusting the method of providing hypotheses according to the user's emotions, hypotheses that are easy for the user to understand can be provided. For example, the providing unit estimates the user's emotions and adjusts the method of providing hypotheses based on the estimated user emotions, hypotheses that are easy for the user to understand even when the user is nervous. Furthermore, the providing unit estimates the user's emotions and adjusts the method of providing hypotheses based on the estimated user emotions, thereby making it possible to provide detailed hypotheses even when the user is relaxed. This makes it possible to provide hypotheses that are easy for the user to understand by adjusting the method of providing hypotheses according to the user's emotions.

[0105] The providing unit can select an optimal providing method by referring to the user's past feedback when providing a hypothesis. For example, the providing unit selects the optimal providing method by referring to the user's past feedback when providing a hypothesis. The feedback includes, for example, user comments and evaluation scores, but is not limited to these examples. For example, the providing unit optimizes the providing method based on feedback previously provided by the user. The providing unit can also preferentially select a specific providing means based on the user's past feedback. The providing unit can also customize the providing method by reflecting the user's feedback to match the user's needs. In this way, the optimal providing method can be selected by referring to the user's past feedback. For example, the providing unit can provide a hypothesis in a way that is easy for the user to understand by optimizing the providing method based on the user's past feedback. In addition, the providing unit can provide a hypothesis in a way that is easy for the user to understand by preferentially selecting a specific providing means based on the user's past feedback. In addition, the providing unit can customize the providing method by reflecting the user's feedback to match the user's needs, and provide a hypothesis in a way that is easy for the user to understand. In this way, the optimal providing method can be selected by referring to the user's past feedback.

[0106] The providing unit can customize the provided content according to the user's current work situation when providing a hypothesis. For example, the providing unit customizes the provided content according to the user's current work situation when providing a hypothesis. The work situation includes, for example, the progress status of a project and the priority of the work, but is not limited to such examples. For example, the providing unit prioritizes providing hypotheses related to a project the user is currently working on. The providing unit can also provide only necessary hypotheses and eliminate unnecessary hypotheses according to the user's work situation. The providing unit can also dynamically customize the provided content based on the user's work situation. As a result, customizing the provided content according to the user's work situation makes it possible to efficiently provide only necessary hypotheses. For example, the providing unit prioritizes providing hypotheses related to a project the user is currently working on, making it possible to quickly provide hypotheses required by the user. As a result, the providing unit can provide only necessary hypotheses and eliminate unnecessary hypotheses according to the user's work situation, making it possible to efficiently provide hypotheses required by the user. As a result, the providing unit dynamically customizes the provided content based on the user's work situation, making it possible to quickly provide hypotheses required by the user.

[0107] The providing unit can improve the provision method by reflecting user feedback when providing a hypothesis. For example, the providing unit improves the provision method by reflecting user feedback when providing a hypothesis. Feedback includes, for example, user comments and evaluation scores, but is not limited to these examples. For example, the providing unit optimizes the provision method based on feedback provided by the user. The providing unit can also preferentially select a specific provision means based on the user feedback. The providing unit can also customize the provision method by reflecting user feedback to match the user's needs. In this way, the provision method can be optimized by reflecting user feedback, and a hypothesis tailored to the user's needs can be provided. For example, the providing unit can provide a hypothesis in a way that is easy for the user to understand by optimizing the provision method based on the user's feedback. In addition, the providing unit can provide a hypothesis in a way that is easy for the user to understand by preferentially selecting a specific provision means based on the user's feedback. In addition, the providing unit can customize the provision method by reflecting user feedback to match the user's needs, and provide a hypothesis in a way that is easy for the user to understand. In this way, the provision method can be optimized by reflecting user feedback, and a hypothesis tailored to the user's needs can be provided.

[0108] The providing unit can estimate the user's emotion and adjust the order in which hypotheses are provided based on the estimated user's emotion. The providing unit, for example, estimates the user's emotion and adjusts the order in which hypotheses are provided based on the estimated user's emotion. The user's emotion is estimated using, for example, facial expression recognition or text analysis, but is not limited to these examples. For example, the providing unit estimates the user's emotion using facial expression recognition. The providing unit can also estimate the user's emotion using text analysis. The providing unit can also estimate the user's emotion using voice analysis. For example, when the user is nervous, the providing unit prioritizes providing hypotheses with high importance. When the user is relaxed, the providing unit can also provide hypotheses with low importance. When the user is in a hurry, the providing unit can prioritize providing hypotheses that can be provided quickly. In this way, by adjusting the order in which hypotheses are provided according to the user's emotion, important hypotheses can be provided preferentially. For example, when the providing unit estimates the user's emotion and adjusts the order in which hypotheses are provided based on the estimated user's emotion, important hypotheses can be provided even when the user is nervous. Furthermore, the providing unit estimates the user's emotions and adjusts the order in which hypotheses are provided based on the estimated user emotions, thereby enabling the provision of hypotheses with low importance even when the user is relaxed. This allows important hypotheses to be provided preferentially by adjusting the order in which hypotheses are provided according to the user's emotions.

[0109] The providing unit can select the optimal providing method by taking into consideration device information of the user when providing a hypothesis. For example, the providing unit selects the optimal providing method by taking into consideration device information of the user when providing a hypothesis. Device information includes, but is not limited to, for example, a smartphone, a tablet, a PC, etc. For example, if the user is using a smartphone, the providing unit selects a providing method that matches the screen size. Furthermore, if the user is using a tablet, the providing unit can select a providing method optimized for a large screen. Furthermore, if the user is using a desktop, the providing unit can select a providing method that includes detailed information. In this way, the optimal providing method can be selected by taking into consideration device information of the user. For example, if the user is using a smartphone, the providing unit can select a providing method that matches the screen size to provide the hypothesis in a manner that is easy for the user to understand. Furthermore, if the user is using a tablet, the providing unit can select a providing method optimized for a large screen to provide the hypothesis in a manner that is easy for the user to understand. Furthermore, if the user is using a desktop, the providing unit can select a providing method that includes detailed information to provide the hypothesis in a manner that is easy for the user to understand. In this way, the optimal providing method can be selected by taking into consideration device information of the user.

[0110] The providing unit can provide the provided content in multiple languages ​​according to the user's language setting when providing a hypothesis. For example, when providing a hypothesis, the providing unit can provide the provided content in multiple languages ​​according to the user's language setting. Language settings include, but are not limited to, Japanese, English, and Spanish. For example, the providing unit can automatically set the language of the hypothesis based on the language setting of the user's device. The providing unit can also provide a language switching function when the user uses multiple languages. The providing unit can also provide the hypothesis in a specific language when the user selects that language. This makes the provided content multilingual according to the user's language setting, thereby providing a hypothesis that is easy for the user to understand. For example, the providing unit can automatically set the language of the hypothesis based on the language setting of the user's device, thereby providing the hypothesis in a language that is easy for the user to understand. The providing unit can also provide a language switching function when the user uses multiple languages, thereby providing the hypothesis in a language that is easy for the user to understand. The providing unit can also provide the hypothesis in a specific language when the user selects that language, thereby providing the hypothesis in that language. This allows the content to be provided in multiple languages ​​according to the user's language settings, making it possible to provide hypotheses that are easy for the user to understand.

[0111] The providing unit can customize the content to be provided based on the user's industry characteristics when providing hypotheses. For example, the providing unit customizes the content to be provided based on the user's industry characteristics when providing hypotheses. Industry characteristics include, but are not limited to, the medical industry, manufacturing industry, and financial industry. For example, the providing unit prioritizes providing hypotheses related to the industry to which the user belongs. The providing unit can also provide only necessary hypotheses and eliminate unnecessary hypotheses based on the industry characteristics. The providing unit can also dynamically customize the content to be provided based on the industry characteristics. As a result, industry-specific hypotheses can be provided by customizing the content to be provided based on the user's industry characteristics. For example, the providing unit prioritizes providing hypotheses related to the industry to which the user belongs, thereby quickly providing hypotheses needed by the user. As a result, the providing unit can provide only necessary hypotheses and eliminate unnecessary hypotheses based on the industry characteristics, thereby efficiently providing hypotheses needed by the user. As a result, the providing unit dynamically customizes the content to be provided based on the industry characteristics, thereby quickly providing hypotheses needed by the user. As a result, industry-specific hypotheses can be provided by customizing the content to be provided based on the user's industry characteristics.

[0112] A generation AI focused on a specific industry can estimate a user's emotions and select an industry-specific generation AI based on the estimated user emotions. A generation AI focused on a specific industry can, for example, estimate a user's emotions and select an industry-specific generation AI based on the estimated user emotions. User emotions can be estimated using, for example, facial expression recognition or text analysis, but these examples are not limited to these. For example, a generation AI focused on a specific industry can estimate a user's emotions using facial expression recognition. A generation AI focused on a specific industry can also estimate a user's emotions using text analysis. A generation AI focused on a specific industry can also estimate a user's emotions using voice analysis. For example, a generation AI focused on a specific industry can select a simple, highly visible industry-specific generation AI if the user is nervous. A generation AI focused on a specific industry can also select an industry-specific generation AI that includes detailed information if the user is relaxed. A generation AI focused on a specific industry can also select an industry-specific generation AI that can provide information quickly if the user is in a hurry. This allows the system to provide the optimal generation AI for the user by selecting an industry-specific generation AI according to the user's emotions. For example, a generation AI focused on a specific industry can estimate the user's emotions and select an industry-specific generation AI based on the estimated user's emotions, thereby providing a generation AI with high visibility even when the user is nervous. Furthermore, a generation AI focused on a specific industry can estimate the user's emotions and select an industry-specific generation AI based on the estimated user's emotions, thereby providing a generation AI that includes detailed information even when the user is relaxed. This allows the system to provide the optimal generation AI for the user by selecting an industry-specific generation AI according to the user's emotions.

[0113] A generative AI focused on a specific industry can improve the analytical accuracy of data in a specific industry by using an industry-specific generative AI. A generative AI focused on a specific industry can improve the analytical accuracy of data in a specific industry by using, for example, an industry-specific generative AI. Analysis accuracy includes, but is not limited to, data preprocessing and algorithm selection for improving accuracy. For example, a generative AI focused on a specific industry can improve the analytical accuracy of medical data by using a generative AI specialized for the medical industry. A generative AI focused on a specific industry can also improve the analytical accuracy of financial data by using a generative AI specialized for the financial industry. A generative AI focused on a specific industry can also improve the analytical accuracy of manufacturing data by using a generative AI specialized for the manufacturing industry. Thus, the analytical accuracy of data in a specific industry can be improved by using an industry-specific generative AI. For example, a generative AI focused on a specific industry can improve the analytical accuracy of medical data by using a generative AI specialized for the medical industry, thereby providing accurate analytical results related to healthcare. A generative AI focused on a specific industry can improve the analytical accuracy of financial data by using a generative AI specialized for the financial industry, thereby providing accurate analytical results related to finance. In addition, generative AI focused on a specific industry can provide accurate analytical results related to manufacturing by using generative AI specialized for the manufacturing industry to improve the accuracy of analytical data on manufacturing. As a result, by using industry-specific generative AI, the accuracy of analytical data in a specific industry can be improved.

[0114] A generative AI focused on a specific industry can improve the accuracy of hypothesis generation in a specific industry by using an industry-specific generative AI. A generative AI focused on a specific industry can improve the accuracy of hypothesis generation in a specific industry by using, for example, an industry-specific generative AI. The accuracy of hypothesis generation can include, but is not limited to, data preprocessing and algorithm selection for improving accuracy. For example, a generative AI focused on a specific industry can improve the accuracy of hypothesis generation from medical data by using a generative AI specialized for the medical industry. A generative AI focused on a specific industry can also improve the accuracy of hypothesis generation from financial data by using a generative AI specialized for the financial industry. A generative AI focused on a specific industry can also improve the accuracy of hypothesis generation from manufacturing data by using a generative AI specialized for the manufacturing industry. Thus, the accuracy of hypothesis generation in a specific industry can be improved by using an industry-specific generative AI. For example, a generative AI focused on a specific industry can improve the accuracy of hypothesis generation from medical data by using a generative AI specialized for the medical industry, thereby providing accurate hypotheses related to healthcare. Furthermore, a generative AI focused on a specific industry can provide accurate hypotheses related to finance by using a generative AI specialized for the financial industry to improve the accuracy of hypothesis generation from financial data. Also, a generative AI focused on a specific industry can provide accurate hypotheses related to manufacturing by using a generative AI specialized for the manufacturing industry to improve the accuracy of hypothesis generation from manufacturing data. In this way, by using industry-specific generative AI, the accuracy of hypothesis generation in a specific industry can be improved.

[0115] A generative AI focused on a specific industry can improve the efficiency of data collection in a specific industry by using an industry-specific generative AI. A generative AI focused on a specific industry can improve the efficiency of data collection in a specific industry by using, for example, an industry-specific generative AI. Data collection efficiency includes, but is not limited to, shortening collection time and comprehensiveness of data. For example, a generative AI focused on a specific industry can improve the efficiency of medical data collection by using a generative AI specialized for the medical industry. A generative AI focused on a specific industry can also improve the efficiency of financial data collection by using a generative AI specialized for the financial industry. A generative AI focused on a specific industry can also improve the efficiency of manufacturing data collection by using a generative AI specialized for the manufacturing industry. In this way, the efficiency of data collection in a specific industry can be improved by using an industry-specific generative AI. For example, a generative AI focused on a specific industry can improve the efficiency of medical data collection by using a generative AI specialized for the medical industry, thereby quickly collecting medical data. A generative AI focused on a specific industry can improve the efficiency of financial data collection by using a generative AI specialized for the financial industry, thereby quickly collecting financial data. In addition, generative AI focused on a specific industry can quickly collect manufacturing data by using generative AI specialized for the manufacturing industry to improve the efficiency of collecting manufacturing data. This makes it possible to improve the efficiency of data collection in a specific industry by using industry-specific generative AI.

[0116] A generation AI focused on a specific industry can estimate a user's emotions and adjust the delivery method of the industry-specific generation AI based on the estimated user emotions. For example, a generation AI focused on a specific industry can estimate a user's emotions and adjust the delivery method of the industry-specific generation AI based on the estimated user emotions. User emotions can be estimated using, for example, facial expression recognition or text analysis, but are not limited to these examples. For example, a generation AI focused on a specific industry can estimate a user's emotions using facial expression recognition. A generation AI focused on a specific industry can also estimate a user's emotions using text analysis. A generation AI focused on a specific industry can also estimate a user's emotions using voice analysis. For example, a generation AI focused on a specific industry can select a simple, highly visible delivery method if the user is nervous. A generation AI focused on a specific industry can select a delivery method that includes detailed information if the user is relaxed. A generation AI focused on a specific industry can also select a delivery method that focuses on the main points if the user is in a hurry. This allows the delivery method of the industry-specific generation AI to be adjusted according to the user's emotions, thereby selecting the optimal delivery method for the user. For example, a generative AI focused on a specific industry can estimate a user's emotions and adjust the delivery method of the industry-specific generative AI based on the estimated user emotions, thereby providing a highly visible delivery method even when the user is nervous.Furthermore, a generative AI focused on a specific industry can estimate a user's emotions and adjust the delivery method of the industry-specific generative AI based on the estimated user emotions, thereby providing a delivery method that includes detailed information even when the user is relaxed.In this way, by adjusting the delivery method of the industry-specific generative AI according to the user's emotions, the optimal delivery method for the user can be selected.

[0117] A generative AI focused on a specific industry can provide analytical results of data in a specific industry using an industry-specific generative AI. A generative AI focused on a specific industry can, for example, use an industry-specific generative AI to provide analytical results of data in a specific industry. Analysis results include, but are not limited to, graph displays and text reports. For example, a generative AI focused on a specific industry can provide analytical results of medical data using a generative AI specialized for the medical industry. A generative AI focused on a specific industry can also provide analytical results of financial data using a generative AI specialized for the financial industry. A generative AI focused on a specific industry can also provide analytical results of manufacturing data using a generative AI specialized for the manufacturing industry. In this way, analytical results of data in a specific industry can be provided using an industry-specific generative AI. For example, a generative AI focused on a specific industry can provide analytical results of medical data using a generative AI specialized for the medical industry, thereby providing accurate analytical results related to healthcare. A generative AI focused on a specific industry can provide analytical results of financial data using a generative AI specialized for the financial industry, thereby providing accurate analytical results related to finance. In addition, generative AI focused on a specific industry can provide accurate analytical results related to manufacturing by using generative AI specialized for the manufacturing industry to provide analytical results on manufacturing data. This makes it possible to provide analytical results on data in a specific industry by using industry-specific generative AI.

[0118] A generation AI focused on a specific industry can provide hypothesis generation results for a specific industry using an industry-specific generation AI. A generation AI focused on a specific industry can provide hypothesis generation results for a specific industry using, for example, an industry-specific generation AI. Hypothesis generation results include, but are not limited to, graph displays and text reports. For example, a generation AI focused on a specific industry can provide hypothesis generation results from medical data using a generation AI specialized for the medical industry. A generation AI focused on a specific industry can also provide hypothesis generation results from financial data using a generation AI specialized for the financial industry. A generation AI focused on a specific industry can also provide hypothesis generation results from manufacturing data using a generation AI specialized for the manufacturing industry. In this way, hypothesis generation results for a specific industry can be provided using an industry-specific generation AI. For example, a generation AI focused on a specific industry can provide hypothesis generation results from medical data using a generation AI specialized for the medical industry, thereby providing accurate hypotheses related to healthcare. A generation AI focused on a specific industry can provide hypothesis generation results from financial data using a generation AI specialized for the financial industry, thereby providing accurate hypotheses related to finance. In addition, generative AI focused on a specific industry can provide accurate hypotheses about manufacturing by using generative AI specialized for the manufacturing industry to provide hypothesis generation results from manufacturing data. This makes it possible to provide hypothesis generation results for a specific industry by using industry-specific generative AI.

[0119] A generation AI focused on a specific industry can provide data collection results in a specific industry using an industry-specific generation AI. A generation AI focused on a specific industry can provide data collection results in a specific industry using, for example, an industry-specific generation AI. Data collection results include, but are not limited to, graph displays and text reports. For example, a generation AI focused on a specific industry can provide medical data collection results using a generation AI specialized for the medical industry. A generation AI focused on a specific industry can also provide financial data collection results using a generation AI specialized for the financial industry. A generation AI focused on a specific industry can also provide manufacturing data collection results using a generation AI specialized for the manufacturing industry. In this way, data collection results in a specific industry can be provided using an industry-specific generation AI. For example, a generation AI focused on a specific industry can provide accurate medical data collection results by using a generation AI specialized for the medical industry to provide medical data collection results. A generation AI focused on a specific industry can provide accurate financial data collection results by using a generation AI specialized for the financial industry to provide financial data collection results. In addition, generative AI focused on a specific industry can provide accurate data collection results related to manufacturing by using generative AI specialized for the manufacturing industry to provide manufacturing data collection results. This makes it possible to provide data collection results for a specific industry by using industry-specific generative AI. === Hard Collateral 1-1 === Each of the multiple elements including the collection unit, analysis unit, hypothesis generation unit, and provision unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects data using sensors or APIs of the smart device 14, and the data is analyzed by the specific processing unit 290 of the data processing device 12. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the collected data using statistical analysis or machine learning algorithms. The hypothesis generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates hypotheses based on the analyzed data. The provision unit is realized by the control unit 46A of the smart device 14 and provides the generated hypotheses to the customer in the form of a report or dashboard display. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned collection unit, analysis unit, hypothesis generation unit, and provision unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects data using sensors or APIs of the smart glasses 214, and the data is analyzed by the specific processing unit 290 of the data processing device 12. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the collected data using statistical analysis or machine learning algorithms. The hypothesis generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates hypotheses based on the analyzed data. The provision unit is realized by the control unit 46A of the smart glasses 214 and provides the generated hypotheses to the customer in the form of a report or dashboard display. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned collection unit, analysis unit, hypothesis generation unit, and provision unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects data using sensors or APIs of the headset type terminal 314, and the data is analyzed by the specific processing unit 290 of the data processing device 12. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the collected data using statistical analysis or machine learning algorithms. The hypothesis generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates hypotheses based on the analyzed data. The provision unit is realized by the control unit 46A of the headset type terminal 314 and provides the generated hypotheses to the customer in report format or dashboard display. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned collection unit, analysis unit, hypothesis generation unit, and provision unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects data using sensors or APIs of the robot 414, and the data is analyzed by the specific processing unit 290 of the data processing device 12. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the collected data using statistical analysis or machine learning algorithms. The hypothesis generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates hypotheses based on the analyzed data. The provision unit is realized by the control unit 46A of the robot 414 and provides the generated hypotheses to the customer in the form of a report or dashboard display.

[0120] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0121] When analyzing data, the analysis unit can estimate the user's emotions and adjust the analysis priority based on the estimated emotions. For example, if the user is feeling stressed, the analysis unit can prioritize analysis of important data and provide results quickly. If the user is relaxed, the analysis unit can perform a detailed analysis and provide comprehensive results. Furthermore, if the user is in a hurry, the analysis unit can provide concise analysis results that focus on the main points. In this way, by adjusting the analysis priority according to the user's emotions, it is possible to provide the user with the optimal analysis results.

[0122] When collecting data, the collection unit can analyze the user's past data provision history and select the optimal collection method. For example, it can prioritize collection of types of data that the user has frequently provided in the past. It can also prioritize data provision methods (voice, text, etc.) that the user has used in the past. Furthermore, it can select the optimal collection method for a specific time period from the user's past data provision history. This enables efficient data collection by selecting the optimal collection method based on the past data provision history.

[0123] The provision unit can estimate the user's emotions and adjust the method of providing hypotheses based on the estimated emotions. For example, if the user is nervous, the provision unit can select a simple, highly visible provision method. If the user is relaxed, the provision unit can select a provision method that includes detailed information. Furthermore, if the user is in a hurry, the provision unit can select a provision method that focuses on the main points. In this way, by adjusting the method of providing hypotheses according to the user's emotions, hypotheses that are easy for the user to understand can be provided.

[0124] The hypothesis generation unit can improve the accuracy of hypotheses by taking into account the interrelationships of data. For example, it can analyze the interrelationships of data and generate hypotheses with high accuracy. It can also improve the reliability of hypotheses by taking into account the interrelationships of data. Furthermore, it can dynamically adjust the accuracy of hypotheses based on the interrelationships of data. In this way, it is possible to generate hypotheses with high accuracy by taking into account the interrelationships of data.

[0125] The collection unit can estimate the user's emotions and determine the priority of data to be collected based on the estimated emotions. For example, if the user is feeling stressed, it can prioritize collection of data of high importance. Also, if the user is relaxed, it can collect data including data of low importance. Furthermore, if the user is in a hurry, it can also prioritize collection of data that can be collected quickly. In this way, by determining the priority of data according to the user's emotions, it is possible to prioritize collection of important data.

[0126] The analysis unit can apply different analysis algorithms depending on the data category. For example, a sales forecasting algorithm can be applied to sales data. A behavioral pattern analysis algorithm can also be applied to customer behavior data. Furthermore, a trend forecasting algorithm can be applied to market trend data. In this way, by applying the appropriate analysis algorithm depending on the data category, highly accurate analysis results can be provided.

[0127] When providing hypotheses, the providing unit can customize the content to be provided according to the user's current work situation. For example, it can provide hypotheses related to the project the user is currently working on with priority. It can also provide only necessary hypotheses and eliminate unnecessary hypotheses according to the user's work situation. Furthermore, it can dynamically customize the content to be provided based on the user's work situation. In this way, by customizing the content to be provided according to the user's work situation, it is possible to efficiently provide only necessary hypotheses.

[0128] The hypothesis generation unit can estimate the user's emotions and adjust the hypothesis generation method based on the estimated emotions. For example, if the user is relaxed, a detailed hypothesis can be generated. If the user is in a hurry, a concise hypothesis can be generated. Furthermore, if the user is excited, a hypothesis with a visually stimulating effect can be generated. In this way, by adjusting the hypothesis generation method according to the user's emotions, it is possible to generate the optimal hypothesis for the user.

[0129] When collecting data, the collection unit can prioritize collection of highly relevant data based on the user's geographical location information. For example, if the user is in a specific area, data related to that area can be prioritized. Also, if the user is moving, highly relevant data can be collected based on the user's current location. Furthermore, if the user is staying in a specific place, data related to that place can be prioritized. In this way, highly relevant data can be efficiently collected by taking the user's geographical location information into consideration.

[0130] A generation AI focused on a specific industry can infer the user's emotions and select an industry-specific generation AI based on the inferred emotions. For example, if the user is nervous, a simple, highly visible industry-specific generation AI can be selected. Alternatively, if the user is relaxed, an industry-specific generation AI containing detailed information can be selected. Furthermore, if the user is in a hurry, an industry-specific generation AI that can provide information quickly can be selected. In this way, by selecting an industry-specific generation AI according to the user's emotions, it is possible to provide the optimal generation AI for the user.

[0131] The processing flow of the second embodiment will be briefly explained below.

[0132] Step 1: The collection unit collects data. The data includes numerical data, text data, image data, etc. The collection unit collects data such as sales data, customer behavior data, and market trends. The collection unit can also collect data in real time using sensors and APIs. For example, the collection unit can collect environmental data using sensors. The collection unit can also collect social media data using APIs. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis is performed using statistical analysis or machine learning algorithms. For example, the analysis unit analyzes trends in the data using statistical analysis. The analysis unit can also analyze patterns in the data using machine learning algorithms. The analysis unit can also analyze text data using natural language processing technology. Step 3: The hypothesis generation unit derives hypotheses based on the data analyzed by the analysis unit. The hypotheses are generated based on a predictive model and an inference of causal relationships. For example, the hypothesis generation unit uses a predictive model to generate a hypothesis that a particular product sells well in a particular season. The hypothesis generation unit can also use an inference of causal relationships to generate a hypothesis that a particular customer segment shows a high interest in a particular service. The hypothesis generation unit can also use data mining technology to derive new hypotheses from the data. Step 4: The provision unit provides the hypotheses derived by the hypothesis generation unit to the client. Provision is performed in the form of a report or a dashboard display. For example, the provision unit provides the hypotheses in the form of a report. The provision unit can also provide the hypotheses in real time through a dashboard. The provision unit can also provide the hypotheses to the client through email or notifications.

[0133] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0136] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0137] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0138] 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.

[0139] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0140] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0144] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0147] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0153] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0154] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0155] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0156] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0157] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0159] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0160] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0161] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0162] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0163] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0164] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0165] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0166] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0167] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0168] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0169] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0170] 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.

[0171] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0172] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0173] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0175] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0176] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0177] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0178] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0179] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0180] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0181] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0182] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0183] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0184] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0185] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0186] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0187] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0188] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0189] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0190] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0191] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0192] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0193] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0194] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0195] 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.

[0196] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0197] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0198] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0199] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0200] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0201] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0202] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0203] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0204] [Explanation of symbols]

[0205] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects data; an analysis unit that analyzes the data collected by the collection unit; a hypothesis generation unit that derives hypotheses based on the data analyzed by the analysis unit; a providing unit that provides the hypotheses derived by the hypothesis generating unit to a customer. A system characterized by:

2. Equipped with generative AI focused on specific industries 2. The system of claim 1.

3. The providing unit Provide hypotheses in real time through a dashboard 2. The system of claim 1.

4. The providing unit Present your hypotheses in a report format 2. The system of claim 1.

5. The collecting unit Collect sales data, customer behavior data, and market trend data 2. The system of claim 1.

6. The analysis unit Analyze the collected data and derive hypotheses about which products sell better in certain seasons.

2. The system of claim 1.

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

8. The collecting unit Analyze users' past data provision history and select the optimal collection method 2. The system of claim 1.

9. The collecting unit Filtering data based on the user's current work situation or areas of interest as it is collected 2. The system of claim 1.

10. The collecting unit When collecting data, select the optimal collection method depending on the user's input method 2. The system of claim 1.

Images