system

Abstract

The system according to this embodiment aims to efficiently carry out the hypothesis testing process. [Solution] The system according to the embodiment comprises a reception unit, a hypothesis generation unit, a verification unit, a feedback unit, and a reward setting unit. The reception unit receives a hypothesis verification task. The hypothesis generation unit generates a hypothesis for the task received by the reception unit. The verification unit verifies the hypothesis generated by the hypothesis generation unit. The feedback unit feeds back the verification results obtained by the verification unit to the system. The reward setting unit sets a reward based on the results fed back by the feedback unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, the process of hypothesis verification is not efficiently performed and there is room for improvement.

[0005] The system according to the embodiment aims to efficiently perform the process of hypothesis verification.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a hypothesis generation unit, a verification unit, a feedback unit, and a reward setting unit. The reception unit receives a hypothesis testing task. The hypothesis generation unit generates a hypothesis for the task received by the reception unit. The verification unit verifies the hypothesis generated by the hypothesis generation unit. The feedback unit feeds back the verification results obtained by the verification unit to the system. The reward setting unit sets a reward based on the results fed back by the feedback unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently carry out the hypothesis testing process. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) An advanced scientific and technological simulation system according to an embodiment of the present invention is a mechanism that provides a community site for hypothesis testing challenges and rewards. In this system, users post hypothesis testing challenges to the community site, and an AI agent generates multiple hypotheses for those challenges. The generated hypotheses are published on the community site, and rewards are set. Companies use the simulation AI on a subscription basis, and the usage fees become the source of rewards. The results of hypothesis testing are fed back into the system and used to improve the accuracy of the simulator. This realizes the creation of a sustainable ecosystem, where companies can utilize cutting-edge simulation technology, and researchers and students can participate in hypothesis testing and earn rewards, thereby accelerating scientific discovery. Through this initiative, we aim to make a significant contribution to the development of human knowledge and technology. For example, a user posts a hypothesis testing challenge to the community site. Next, an AI agent generates multiple hypotheses for that challenge. The generated hypotheses are published on the community site, and rewards are set. Companies use the simulation AI on a subscription basis, and the usage fees become the source of rewards. The results of hypothesis testing are fed back into the system and used to improve the accuracy of the simulator. This will enable the creation of a sustainable ecosystem, accelerating scientific discovery by allowing companies to leverage cutting-edge simulation technology and enabling researchers and students to participate in hypothesis testing and receive rewards. Through this initiative, we aim to make a significant contribution to the advancement of human knowledge and technology. This will allow advanced scientific and technological simulation systems to efficiently handle the entire process, from receiving hypothesis testing challenges to setting rewards.

[0029] The advanced scientific and technological simulation system according to this embodiment comprises a reception unit, a hypothesis generation unit, a verification unit, a feedback unit, and a reward setting unit. The reception unit receives hypothesis testing tasks. The reception unit provides, for example, a community site for users to post hypothesis testing tasks. The hypothesis generation unit generates hypotheses for the hypothesis testing tasks. The hypothesis generation unit generates multiple hypotheses, for example, using an AI agent. The verification unit verifies the hypotheses generated by the hypothesis generation unit. The verification unit verifies the hypotheses, for example, researchers or students. The feedback unit feeds back the verification results obtained by the verification unit to the system. The feedback unit feeds back the verification results to the system and uses them to improve the accuracy of the simulator. The reward setting unit sets rewards based on the results fed back by the feedback unit. The reward setting unit sets rewards according to the difficulty level of the hypotheses and automatically increases the reward amount over time for unverified hypotheses. As a result, the advanced scientific and technological simulation system according to this embodiment can efficiently perform a series of processes from receiving hypothesis testing tasks to setting rewards.

[0030] The reception department accepts hypothesis testing tasks. Specifically, it provides a community site for users to post hypothesis testing tasks. The community site has an easy-to-access interface and provides functions such as posting, viewing, and commenting on hypothesis testing tasks. When posting a hypothesis testing task, users can enter detailed descriptions of the task, background information, and expected results. The community site also organizes the posted hypothesis testing tasks by category, making it easy for other users to find tasks of interest. Furthermore, the reception department has a function to automatically analyze the content of the posted hypothesis testing tasks and classify them into the appropriate category. This allows users to efficiently post hypothesis testing tasks and share information with other users.

[0031] The hypothesis generation unit generates hypotheses for a hypothesis testing task. Specifically, it generates multiple hypotheses using an AI agent. The AI ​​agent analyzes the content of the hypothesis testing task using natural language processing technology and generates hypotheses based on relevant information. For example, the AI ​​agent refers to past research data and literature information to generate multiple appropriate hypotheses for the hypothesis testing task. The generated hypotheses are scored to evaluate their reliability and validity and presented to the user. The user can select the most appropriate hypothesis from those presented and send it to the testing unit. In this way, the hypothesis generation unit can efficiently generate hypotheses and support the user's hypothesis testing process.

[0032] The verification unit verifies the hypotheses generated by the hypothesis generation unit. Specifically, researchers and students verify the hypotheses. The verification unit provides the tools and resources necessary for conducting experiments and simulations to verify the hypotheses. For example, the verification unit is equipped with advanced simulation software and experimental equipment, allowing users to collect and analyze the data necessary to verify the hypotheses. The verification unit also has a function to automatically record the hypothesis verification results and send them to the feedback unit. In this way, the verification unit can efficiently verify hypotheses and support the user's research activities.

[0033] The feedback unit feeds the verification results obtained by the verification unit back into the system. Specifically, it feeds the verification results back into the system and uses them to improve the accuracy of the simulator. The feedback unit improves the accuracy of the simulator by analyzing the verification results and adjusting the simulator's parameters. The feedback unit also has a function to save the verification results to a database, making them accessible to other users. In this way, the feedback unit can contribute to improving the accuracy of the entire system and support the user's research activities.

[0034] The reward setting unit sets rewards based on the feedback received by the feedback unit. Specifically, it sets rewards according to the difficulty of the hypothesis and automatically increases the reward amount over time for untested hypotheses. The reward setting unit has an algorithm for evaluating the difficulty of hypotheses and determines the reward amount based on the complexity of the hypothesis and the resources required for verification. In addition, the reward setting unit has a function to evaluate the user's contribution and the quality of the verification results and adjust the reward amount accordingly. This allows the reward setting unit to increase user motivation and efficiently advance hypothesis testing tasks.

[0035] The reception desk can provide a community site for users to post hypothesis testing tasks. For example, the reception desk can make it easy for users to post hypothesis testing tasks. The reception desk can include posting functions, commenting functions, and rating functions. This allows users to easily post hypothesis testing tasks.

[0036] The hypothesis generation unit can generate multiple hypotheses using an AI agent. For example, the hypothesis generation unit efficiently generates multiple hypotheses using an AI agent. The AI ​​agent can generate hypotheses using machine learning algorithms and natural language processing techniques. This allows the AI ​​agent to efficiently generate multiple hypotheses.

[0037] The verification section allows researchers and students to test hypotheses. For example, the verification section accelerates scientific discovery by enabling researchers and students to test hypotheses. Researchers and students can test hypotheses according to their field of expertise, academic year, and major. This accelerates scientific discovery by enabling researchers and students to test hypotheses.

[0038] The feedback unit can feed back verification results to the system and use them to improve the simulator's accuracy. For example, the feedback unit can feed back verification results to the system and use them to improve the simulator's accuracy. The simulator can improve its accuracy depending on the simulation target and the method of accuracy improvement. This allows for improved simulator accuracy through feedback of verification results.

[0039] The reward setting unit sets rewards according to the difficulty of the hypothesis and can automatically increase the reward amount for untested hypotheses over time. For example, the reward setting unit enhances motivation for hypothesis testing by setting rewards according to the difficulty of the hypothesis and by automatically increasing the reward amount for untested hypotheses. The difficulty of a hypothesis is evaluated based on the complexity and feasibility of the hypothesis. The automatic increase in the reward amount is based on the rate of increase over time and the upper limit of the increase. This enhances motivation for hypothesis testing by setting rewards according to the difficulty of the hypothesis and by automatically increasing the reward amount for untested hypotheses.

[0040] The Subscription Service allows companies to use simulation AI on a subscription basis. For example, by enabling companies to use simulation AI on a subscription basis, the Subscription Service helps build a sustainable ecosystem. The subscription model operates based on usage fees, contract periods, and the services provided. This allows companies to use simulation AI on a subscription basis, thereby building a sustainable ecosystem.

[0041] The Community Site Management Department can publish hypothesis testing tasks and set rewards. For example, the Community Site Management Department can encourage user participation by publishing hypothesis testing tasks and setting rewards. The publication of hypothesis testing tasks is determined based on the timing and scope of publication. This process, including publishing hypothesis testing tasks and setting rewards, encourages user participation.

[0042] The simulator accuracy improvement unit can improve the accuracy of the simulator based on the feedback verification results. For example, by improving the accuracy of the simulator based on the feedback verification results, the accuracy of the entire system is improved. The simulator accuracy improvement is carried out based on how the feedback is utilized and the evaluation criteria for accuracy improvement. As a result, by improving the accuracy of the simulator based on the feedback verification results, the accuracy of the entire system is improved.

[0043] The reception desk can analyze a user's past posting history and select the most suitable submission method. For example, it can analyze the trends in hypothesis testing tasks previously submitted by the user and prioritize accepting similar tasks. The reception desk can also analyze the time periods when users previously posted and accept submissions during those times. Furthermore, it can analyze the difficulty level of tasks previously submitted by the user and accept tasks of appropriate difficulty. In this way, by analyzing a user's past posting history, the reception desk can select the most suitable submission method.

[0044] The reception desk can filter hypothesis testing tasks based on the user's current research topic and areas of interest when receiving them. For example, the reception desk will prioritize receiving hypothesis testing tasks related to the user's current research topic. The reception desk can also filter and accept relevant hypothesis testing tasks based on the user's areas of interest. The reception desk can also suggest appropriate hypothesis testing tasks based on the user's research topic and areas of interest. In this way, by filtering based on the user's research topic and areas of interest, it is possible to accept tasks that are highly relevant.

[0045] The reception desk can prioritize accepting hypothesis testing tasks that are highly relevant, taking into account the user's geographical location. For example, the reception desk can prioritize accepting hypothesis testing tasks related to a specific region based on the user's geographical location. The reception desk can also accept tasks that involve collaboration with local research institutions, taking into account the user's geographical location. The reception desk can also prioritize accepting tasks related to solving local problems, taking into account the user's geographical location. In this way, by considering the user's geographical location, it is possible to prioritize accepting tasks that are highly relevant.

[0046] The reception desk can analyze users' social media activity when receiving hypothesis testing tasks and accept relevant tasks. For example, the reception desk can analyze users' social media activity and accept tasks related to areas of interest. The reception desk can also analyze the content of users' social media posts and propose relevant hypothesis testing tasks. The reception desk can also analyze users' social media followers and followed accounts and accept relevant tasks. In this way, relevant tasks can be accepted by analyzing users' social media activity.

[0047] The hypothesis generation unit can adjust the level of detail of a hypothesis based on the importance of the problem during the hypothesis generation process. For example, the hypothesis generation unit can generate detailed hypotheses for high-importance problems. It can also generate concise hypotheses for low-importance problems. It can also generate hypotheses with an appropriate level of detail for medium-importance problems. In this way, by adjusting the level of detail of a hypothesis based on the importance of the problem, it is possible to generate appropriate hypotheses.

[0048] The hypothesis generation unit can apply different hypothesis generation algorithms depending on the category of the problem during hypothesis generation. For example, the hypothesis generation unit can apply a specialized hypothesis generation algorithm to problems in the field of science and technology. It can also apply a hypothesis generation algorithm that takes social factors into account to problems in the field of social sciences. It can also apply a hypothesis generation algorithm based on medical data to problems in the field of medicine. In this way, appropriate hypotheses can be generated by applying different hypothesis generation algorithms depending on the category of the problem.

[0049] The hypothesis generation unit can prioritize hypotheses based on the assignment submission deadlines. For example, it can prioritize generating hypotheses for assignments with earlier submission deadlines. It can also postpone generating hypotheses for assignments with later submission deadlines. Furthermore, it can quickly generate hypotheses for assignments with approaching submission deadlines. By prioritizing hypotheses based on assignment submission deadlines, hypotheses can be generated in the appropriate order.

[0050] The hypothesis generation unit can adjust the order of hypotheses based on the relevance of the issues during hypothesis generation. For example, the hypothesis generation unit can prioritize generating hypotheses for highly relevant issues. It can also postpone generating hypotheses for less relevant issues. For issues of moderate relevance, the hypothesis generation unit can generate hypotheses in an appropriate order. In this way, by adjusting the order of hypotheses based on the relevance of the issues, highly relevant hypotheses can be generated preferentially.

[0051] The verification unit can improve the accuracy of verification by considering the interrelationships of hypotheses during the verification process. For example, the verification unit can analyze the interrelationships of multiple hypotheses and perform highly accurate verification. The verification unit can also determine the priority of verification by considering the interrelationships of hypotheses. The verification unit can also adjust the verification method based on the interrelationships of hypotheses. In this way, the accuracy of verification can be improved by considering the interrelationships of hypotheses.

[0052] The verification unit can perform verification while considering the attribute information of the hypothesis proposer. For example, the verification unit can select an appropriate verification method considering the hypothesis proposer's field of expertise. The verification unit can also adjust the difficulty of the verification considering the hypothesis proposer's years of experience. The verification unit can also determine the priority of verification considering the hypothesis proposer's past achievements. In this way, appropriate verification can be performed by considering the attribute information of the hypothesis proposer.

[0053] The verification unit can perform verification while considering the geographical distribution of the hypothesis. For example, the verification unit can analyze the geographical distribution of the hypothesis and perform verification while considering the characteristics of each region. The verification unit can also determine the priority of verification based on the geographical distribution. The verification unit can also select an appropriate verification method while considering the geographical distribution. In this way, by considering the geographical distribution of the hypothesis, verification can be performed while considering the characteristics of each region.

[0054] The verification unit can improve the accuracy of its verification by referring to relevant literature on the hypothesis during the verification process. For example, the verification unit can perform highly accurate verification by referring to relevant literature on the hypothesis. The verification unit can also adjust the verification method based on the relevant literature. The verification unit can also determine the priority of verification by referring to relevant literature. In this way, the accuracy of verification can be improved by referring to relevant literature on the hypothesis.

[0055] The feedback unit can select the optimal feedback method by referring to past feedback data during the feedback process. For example, the feedback unit can analyze past feedback data to select the most effective feedback method. Based on past feedback data, the feedback unit can also predict user reactions and adjust the feedback method accordingly. Furthermore, the feedback unit can customize the content of the feedback by referring to past feedback data. This allows the optimal feedback method to be selected by referring to past feedback data.

[0056] The feedback unit can apply different feedback methods depending on the hypothesis category during the feedback process. For example, the feedback unit can apply specialized feedback methods to hypotheses in the field of science and technology. It can also apply feedback methods that consider social factors to hypotheses in the field of social science. Furthermore, it can apply feedback methods based on medical data to hypotheses in the field of medicine. This allows for the provision of appropriate feedback by applying different feedback methods to each hypothesis category.

[0057] The feedback department can prioritize feedback based on when the hypotheses were submitted. For example, it can prioritize feedback on hypotheses submitted earlier, postpone feedback on hypotheses submitted later, or provide feedback quickly on hypotheses submitted sooner. By prioritizing feedback based on when the hypotheses were submitted, feedback can be provided in the appropriate order.

[0058] The feedback unit can provide feedback by referring to relevant market data for the hypothesis. For example, the feedback unit can provide highly accurate feedback by referring to relevant market data for the hypothesis. The feedback unit can also adjust the content of the feedback based on the relevant market data. The feedback unit can also determine the priority of feedback by referring to relevant market data. This allows for the provision of highly accurate feedback by referring to relevant market data for the hypothesis.

[0059] The reward setting unit can adjust the reward amount based on the difficulty of the hypothesis when setting rewards. For example, the reward setting unit can set a high reward for a high-difficulty hypothesis. The reward setting unit can also set a low reward for a low-difficulty hypothesis. The reward setting unit can also set a moderate reward for a hypothesis of medium difficulty. In this way, appropriate rewards can be provided by adjusting the reward amount based on the difficulty of the hypothesis.

[0060] The reward setting unit can apply different reward setting methods to each hypothesis category when setting rewards. For example, the reward setting unit can apply specialized reward setting methods to hypotheses in the field of science and technology. It can also apply reward setting methods that take social factors into account to hypotheses in the field of social science. It can also apply reward setting methods based on medical data to hypotheses in the field of medicine. By applying different reward setting methods to each hypothesis category, appropriate rewards can be provided.

[0061] The reward setting unit can adjust the reward amount based on the timing of hypothesis submission when setting rewards. For example, the reward setting unit can set a higher reward for hypotheses submitted earlier. It can also set a lower reward for hypotheses submitted later. It can also set a moderate reward for hypotheses submitted sooner. In this way, appropriate rewards can be provided by adjusting the reward amount based on the timing of hypothesis submission.

[0062] The reward setting unit can set reward amounts by referring to relevant market data for the hypothesis when setting rewards. For example, the reward setting unit can perform highly accurate reward setting by referring to relevant market data for the hypothesis. The reward setting unit can also adjust reward amounts based on relevant market data. The reward setting unit can also determine reward priorities by referring to relevant market data. This allows for highly accurate reward setting by referring to relevant market data for the hypothesis.

[0063] The subscription usage unit can select the optimal usage method by referring to past usage data when a subscription is used. For example, the subscription usage unit can analyze past usage data and select the most effective subscription usage method. The subscription usage unit can also predict user responses based on past usage data and adjust the usage method accordingly. The subscription usage unit can also customize the usage method by referring to past usage data. This allows for the selection of the optimal subscription usage method by referring to past usage data.

[0064] The subscription utilization unit can apply different utilization methods depending on the industry of the company when it uses a subscription. For example, the subscription utilization unit can apply a specialized subscription utilization method to companies in the science and technology sector. It can also apply a subscription utilization method that takes social factors into account to companies in the social sciences sector. It can also apply a subscription utilization method based on medical data to companies in the medical sector. In this way, by applying different utilization methods to each company's industry, it can provide an appropriate subscription utilization method.

[0065] The subscription utilization unit can select the optimal usage method when a company uses a subscription, taking into account the company's geographical location information. For example, the subscription utilization unit can provide region-related subscription utilization methods based on the company's geographical location information. The subscription utilization unit can also provide subscription utilization methods in collaboration with local research institutions, taking into account the company's geographical location information. The subscription utilization unit can also provide subscription utilization methods related to solving local problems, taking into account the company's geographical location information. In this way, the optimal subscription utilization method can be provided by taking into account the company's geographical location information.

[0066] The subscription utilization unit can adjust its usage methods by referring to relevant market data of the company when a subscription is used. For example, the subscription utilization unit can refer to relevant market data of the company and provide the optimal subscription utilization method. The subscription utilization unit can also adjust the subscription utilization method based on relevant market data. The subscription utilization unit can also refer to relevant market data to determine the priority of subscription utilization. In this way, by referring to relevant market data of the company, it can provide the optimal subscription utilization method.

[0067] The community site management department can select the optimal management method by referring to past operational data when managing the site. For example, the community site management department can analyze past operational data and select the most effective management method. The community site management department can also predict user reactions based on past operational data and adjust the management method accordingly. The community site management department can also customize the management method by referring to past operational data. In this way, the optimal management method can be selected by referring to past operational data.

[0068] The community site management department can customize its operational methods by considering user attribute information when managing the site. For example, the community site management department can provide appropriate operational methods according to the user's age group. The community site management department can also prioritize providing relevant content according to the user's field of expertise. The community site management department can also provide customized operational methods based on the user's interests. In this way, appropriate operational methods can be provided by considering user attribute information.

[0069] The community site management department can select the optimal management method when operating the site, taking into account the user's geographical location information. For example, the community site management department can prioritize providing content relevant to a user's region based on their geographical location information. The community site management department can also provide management methods that collaborate with local research institutions, taking into account the user's geographical location information. The community site management department can also provide management methods related to solving local problems, taking into account the user's geographical location information. In this way, the optimal management method can be provided by considering the user's geographical location information.

[0070] The community site management team can analyze users' social media activity and adjust their management methods accordingly. For example, they can analyze users' social media activity and provide content related to their areas of interest. They can also analyze users' social media posts and suggest relevant management methods. Furthermore, they can analyze users' social media followers and followed accounts and provide relevant management methods. In this way, by analyzing users' social media activity, they can provide appropriate management methods.

[0071] The simulator accuracy improvement unit can select the optimal accuracy improvement method by referring to past accuracy improvement data when improving accuracy. For example, the simulator accuracy improvement unit can analyze past accuracy improvement data and select the most effective accuracy improvement method. The simulator accuracy improvement unit can also predict user reactions based on past accuracy improvement data and adjust the accuracy improvement method accordingly. The simulator accuracy improvement unit can also customize the accuracy improvement method by referring to past accuracy improvement data. This allows for the selection of the optimal accuracy improvement method by referring to past accuracy improvement data.

[0072] The simulator accuracy improvement unit can apply different accuracy improvement methods to each simulator category during the accuracy improvement process. For example, it can apply specialized accuracy improvement methods to simulators in the scientific and technological fields. It can also apply accuracy improvement methods that take social factors into account to simulators in the social sciences. It can also apply accuracy improvement methods based on medical data to simulators in the medical field. By applying different accuracy improvement methods to each simulator category, it can provide an appropriate accuracy improvement method.

[0073] The simulator accuracy improvement unit can determine the priority of accuracy improvements based on the simulator's usage period. For example, it can prioritize accuracy improvements for simulators that have been used earlier. It can also postpone accuracy improvements for simulators that have been used later. It can also quickly improve the accuracy of simulators that have been used recently. By determining the priority of accuracy improvements based on the simulator's usage period, accuracy improvements can be carried out in an appropriate order.

[0074] The simulator accuracy improvement unit can adjust the accuracy improvement method by referring to relevant market data for the simulator when improving accuracy. For example, the simulator accuracy improvement unit can refer to relevant market data for the simulator and provide the optimal accuracy improvement method. The simulator accuracy improvement unit can also adjust the accuracy improvement method based on relevant market data. The simulator accuracy improvement unit can also refer to relevant market data to determine the priority of accuracy improvement. In this way, by referring to relevant market data for the simulator, it can provide the optimal accuracy improvement method.

[0075] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0076] The reception desk can analyze a user's past posting history and select the most suitable reception method. For example, it can analyze the trends in hypothesis testing tasks previously posted by a user and prioritize accepting similar tasks. It can also analyze the time periods when users previously posted and accept submissions during those times. Furthermore, it can analyze the difficulty level of tasks previously posted by users and accept tasks of appropriate difficulty. In this way, by analyzing a user's past posting history, the most suitable reception method can be selected.

[0077] The hypothesis generation unit can adjust the level of detail of a hypothesis based on the importance of the problem. For example, it can generate detailed hypotheses for high-importance problems, concise hypotheses for low-importance problems, and hypotheses with appropriate detail for medium-importance problems. By adjusting the level of detail of a hypothesis based on the importance of the problem, it is possible to generate appropriate hypotheses.

[0078] The verification unit can improve the accuracy of verification by considering the interrelationships of hypotheses during the verification process. For example, it can analyze the interrelationships of multiple hypotheses and perform highly accurate verification. It can also determine the priority of verification by considering the interrelationships of hypotheses. It can also adjust the verification method based on the interrelationships of hypotheses. In this way, the accuracy of verification can be improved by considering the interrelationships of hypotheses.

[0079] The feedback unit can select the optimal feedback method by referring to past feedback data during the feedback process. For example, it can analyze past feedback data to select the most effective feedback method. It can also predict user reactions based on past feedback data and adjust the feedback method accordingly. It can also customize the content of the feedback by referring to past feedback data. In this way, the optimal feedback method can be selected by referring to past feedback data.

[0080] The reward setting unit can adjust the reward amount based on the difficulty of the hypothesis when setting rewards. For example, a high reward can be set for a high-difficulty hypothesis. A low reward can be set for an easy hypothesis. A moderate reward can be set for a hypothesis of medium difficulty. In this way, appropriate rewards can be provided by adjusting the reward amount based on the difficulty of the hypothesis.

[0081] The following briefly describes the processing flow for example form 1.

[0082] Step 1: The reception desk accepts hypothesis testing tasks. For example, it provides a community site where users can post hypothesis testing tasks. Step 2: The hypothesis generation unit generates hypotheses for the problem received by the reception unit. For example, an AI agent generates multiple hypotheses. Step 3: The verification unit verifies the hypotheses generated by the hypothesis generation unit. For example, researchers or students might verify the hypotheses. Step 4: The feedback unit feeds back the verification results obtained by the verification unit to the system. For example, the verification results are fed back to the system and used to improve the accuracy of the simulator. Step 5: The reward setting unit sets rewards based on the feedback received by the feedback unit. For example, it sets rewards according to the difficulty of the hypothesis and automatically increases the reward amount over time for untested hypotheses.

[0083] (Example of form 2) An advanced scientific and technological simulation system according to an embodiment of the present invention is a mechanism that provides a community site for hypothesis testing challenges and rewards. In this system, users post hypothesis testing challenges to the community site, and an AI agent generates multiple hypotheses for those challenges. The generated hypotheses are published on the community site, and rewards are set. Companies use the simulation AI on a subscription basis, and the usage fees become the source of rewards. The results of hypothesis testing are fed back into the system and used to improve the accuracy of the simulator. This realizes the creation of a sustainable ecosystem, where companies can utilize cutting-edge simulation technology, and researchers and students can participate in hypothesis testing and earn rewards, thereby accelerating scientific discovery. Through this initiative, we aim to make a significant contribution to the development of human knowledge and technology. For example, a user posts a hypothesis testing challenge to the community site. Next, an AI agent generates multiple hypotheses for that challenge. The generated hypotheses are published on the community site, and rewards are set. Companies use the simulation AI on a subscription basis, and the usage fees become the source of rewards. The results of hypothesis testing are fed back into the system and used to improve the accuracy of the simulator. This will enable the creation of a sustainable ecosystem, accelerating scientific discovery by allowing companies to leverage cutting-edge simulation technology and enabling researchers and students to participate in hypothesis testing and receive rewards. Through this initiative, we aim to make a significant contribution to the advancement of human knowledge and technology. This will allow advanced scientific and technological simulation systems to efficiently handle the entire process, from receiving hypothesis testing challenges to setting rewards.

[0084] The advanced scientific and technological simulation system according to this embodiment comprises a reception unit, a hypothesis generation unit, a verification unit, a feedback unit, and a reward setting unit. The reception unit receives hypothesis testing tasks. The reception unit provides, for example, a community site for users to post hypothesis testing tasks. The hypothesis generation unit generates hypotheses for the hypothesis testing tasks. The hypothesis generation unit generates multiple hypotheses, for example, using an AI agent. The verification unit verifies the hypotheses generated by the hypothesis generation unit. The verification unit verifies the hypotheses, for example, researchers or students. The feedback unit feeds back the verification results obtained by the verification unit to the system. The feedback unit feeds back the verification results to the system and uses them to improve the accuracy of the simulator. The reward setting unit sets rewards based on the results fed back by the feedback unit. The reward setting unit sets rewards according to the difficulty level of the hypotheses and automatically increases the reward amount over time for unverified hypotheses. As a result, the advanced scientific and technological simulation system according to this embodiment can efficiently perform a series of processes from receiving hypothesis testing tasks to setting rewards.

[0085] The reception department accepts hypothesis testing tasks. Specifically, it provides a community site for users to post hypothesis testing tasks. The community site has an easy-to-access interface and provides functions such as posting, viewing, and commenting on hypothesis testing tasks. When posting a hypothesis testing task, users can enter detailed descriptions of the task, background information, and expected results. The community site also organizes the posted hypothesis testing tasks by category, making it easy for other users to find tasks of interest. Furthermore, the reception department has a function to automatically analyze the content of the posted hypothesis testing tasks and classify them into the appropriate category. This allows users to efficiently post hypothesis testing tasks and share information with other users.

[0086] The hypothesis generation unit generates hypotheses for a hypothesis testing task. Specifically, it generates multiple hypotheses using an AI agent. The AI ​​agent analyzes the content of the hypothesis testing task using natural language processing technology and generates hypotheses based on relevant information. For example, the AI ​​agent refers to past research data and literature information to generate multiple appropriate hypotheses for the hypothesis testing task. The generated hypotheses are scored to evaluate their reliability and validity and presented to the user. The user can select the most appropriate hypothesis from those presented and send it to the testing unit. In this way, the hypothesis generation unit can efficiently generate hypotheses and support the user's hypothesis testing process.

[0087] The verification unit verifies the hypotheses generated by the hypothesis generation unit. Specifically, researchers and students verify the hypotheses. The verification unit provides the tools and resources necessary for conducting experiments and simulations to verify the hypotheses. For example, the verification unit is equipped with advanced simulation software and experimental equipment, allowing users to collect and analyze the data necessary to verify the hypotheses. The verification unit also has a function to automatically record the hypothesis verification results and send them to the feedback unit. In this way, the verification unit can efficiently verify hypotheses and support the user's research activities.

[0088] The feedback unit feeds the verification results obtained by the verification unit back into the system. Specifically, it feeds the verification results back into the system and uses them to improve the accuracy of the simulator. The feedback unit improves the accuracy of the simulator by analyzing the verification results and adjusting the simulator's parameters. The feedback unit also has a function to save the verification results to a database, making them accessible to other users. In this way, the feedback unit can contribute to improving the accuracy of the entire system and support the user's research activities.

[0089] The reward setting unit sets rewards based on the feedback received by the feedback unit. Specifically, it sets rewards according to the difficulty of the hypothesis and automatically increases the reward amount over time for untested hypotheses. The reward setting unit has an algorithm for evaluating the difficulty of hypotheses and determines the reward amount based on the complexity of the hypothesis and the resources required for verification. In addition, the reward setting unit has a function to evaluate the user's contribution and the quality of the verification results and adjust the reward amount accordingly. This allows the reward setting unit to increase user motivation and efficiently advance hypothesis testing tasks.

[0090] The reception desk can provide a community site for users to post hypothesis testing tasks. For example, the reception desk can make it easy for users to post hypothesis testing tasks. The reception desk can include posting functions, commenting functions, and rating functions. This allows users to easily post hypothesis testing tasks.

[0091] The hypothesis generation unit can generate multiple hypotheses using an AI agent. For example, the hypothesis generation unit efficiently generates multiple hypotheses using an AI agent. The AI ​​agent can generate hypotheses using machine learning algorithms and natural language processing techniques. This allows the AI ​​agent to efficiently generate multiple hypotheses.

[0092] The verification section allows researchers and students to test hypotheses. For example, the verification section accelerates scientific discovery by enabling researchers and students to test hypotheses. Researchers and students can test hypotheses according to their field of expertise, academic year, and major. This accelerates scientific discovery by enabling researchers and students to test hypotheses.

[0093] The feedback unit can feed back verification results to the system and use them to improve the simulator's accuracy. For example, the feedback unit can feed back verification results to the system and use them to improve the simulator's accuracy. The simulator can improve its accuracy depending on the simulation target and the method of accuracy improvement. This allows for improved simulator accuracy through feedback of verification results.

[0094] The reward setting unit sets rewards according to the difficulty of the hypothesis and can automatically increase the reward amount for untested hypotheses over time. For example, the reward setting unit enhances motivation for hypothesis testing by setting rewards according to the difficulty of the hypothesis and by automatically increasing the reward amount for untested hypotheses. The difficulty of a hypothesis is evaluated based on the complexity and feasibility of the hypothesis. The automatic increase in the reward amount is based on the rate of increase over time and the upper limit of the increase. This enhances motivation for hypothesis testing by setting rewards according to the difficulty of the hypothesis and by automatically increasing the reward amount for untested hypotheses.

[0095] The Subscription Service allows companies to use simulation AI on a subscription basis. For example, by enabling companies to use simulation AI on a subscription basis, the Subscription Service helps build a sustainable ecosystem. The subscription model operates based on usage fees, contract periods, and the services provided. This allows companies to use simulation AI on a subscription basis, thereby building a sustainable ecosystem.

[0096] The Community Site Management Department can publish hypothesis testing tasks and set rewards. For example, the Community Site Management Department can encourage user participation by publishing hypothesis testing tasks and setting rewards. The publication of hypothesis testing tasks is determined based on the timing and scope of publication. This process, including publishing hypothesis testing tasks and setting rewards, encourages user participation.

[0097] The simulator accuracy improvement unit can improve the accuracy of the simulator based on the feedback verification results. For example, by improving the accuracy of the simulator based on the feedback verification results, the accuracy of the entire system is improved. The simulator accuracy improvement is carried out based on how the feedback is utilized and the evaluation criteria for accuracy improvement. As a result, by improving the accuracy of the simulator based on the feedback verification results, the accuracy of the entire system is improved.

[0098] The reception desk can estimate the user's emotions and adjust the timing of hypothesis testing task submissions based on the estimated emotions. For example, if the user is feeling stressed, the reception desk will submit the hypothesis testing task during a time when the user can relax. If the user is concentrating, the reception desk can also submit the hypothesis testing task at that time. If the user is tired, the reception desk can also submit the hypothesis testing task after the user has rested. In this way, the user's burden is reduced by adjusting the timing of hypothesis testing task submissions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0099] The reception desk can analyze a user's past posting history and select the most suitable submission method. For example, it can analyze the trends in hypothesis testing tasks previously submitted by the user and prioritize accepting similar tasks. The reception desk can also analyze the time periods when users previously posted and accept submissions during those times. Furthermore, it can analyze the difficulty level of tasks previously submitted by the user and accept tasks of appropriate difficulty. In this way, by analyzing a user's past posting history, the reception desk can select the most suitable submission method.

[0100] The reception desk can filter hypothesis testing tasks based on the user's current research topic and areas of interest when receiving them. For example, the reception desk will prioritize receiving hypothesis testing tasks related to the user's current research topic. The reception desk can also filter and accept relevant hypothesis testing tasks based on the user's areas of interest. The reception desk can also suggest appropriate hypothesis testing tasks based on the user's research topic and areas of interest. In this way, by filtering based on the user's research topic and areas of interest, it is possible to accept tasks that are highly relevant.

[0101] The reception desk can estimate the user's emotions and determine the priority of tasks to accept based on those emotions. For example, if the user is excited, the reception desk will prioritize tasks of higher difficulty. If the user is relaxed, the reception desk may also prioritize tasks of lower difficulty. If the user is focused, the reception desk may also prioritize tasks of moderate difficulty. This reduces the user's burden by prioritizing tasks according to their emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0102] The reception desk can prioritize accepting hypothesis testing tasks that are highly relevant, taking into account the user's geographical location. For example, the reception desk can prioritize accepting hypothesis testing tasks related to a specific region based on the user's geographical location. The reception desk can also accept tasks that involve collaboration with local research institutions, taking into account the user's geographical location. The reception desk can also prioritize accepting tasks related to solving local problems, taking into account the user's geographical location. In this way, by considering the user's geographical location, it is possible to prioritize accepting tasks that are highly relevant.

[0103] The reception desk can analyze users' social media activity when receiving hypothesis testing tasks and accept relevant tasks. For example, the reception desk can analyze users' social media activity and accept tasks related to areas of interest. The reception desk can also analyze the content of users' social media posts and propose relevant hypothesis testing tasks. The reception desk can also analyze users' social media followers and followed accounts and accept relevant tasks. In this way, relevant tasks can be accepted by analyzing users' social media activity.

[0104] The hypothesis generation unit can estimate the user's emotions and adjust the hypothesis generation method based on the estimated user emotions. For example, if the user is relaxed, the hypothesis generation unit can generate a detailed hypothesis. If the user is in a hurry, the hypothesis generation unit can also generate a concise hypothesis. If the user is excited, the hypothesis generation unit can also generate multiple hypotheses. This allows for the generation of hypotheses appropriate to the user by adjusting the hypothesis generation method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. Generative AIs include, but are not limited to, text generation AIs (e.g., LLM) and multimodal generation AIs.

[0105] The hypothesis generation unit can adjust the level of detail of a hypothesis based on the importance of the problem during the hypothesis generation process. For example, the hypothesis generation unit can generate detailed hypotheses for high-importance problems. It can also generate concise hypotheses for low-importance problems. It can also generate hypotheses with an appropriate level of detail for medium-importance problems. In this way, by adjusting the level of detail of a hypothesis based on the importance of the problem, it is possible to generate appropriate hypotheses.

[0106] The hypothesis generation unit can apply different hypothesis generation algorithms depending on the category of the problem during hypothesis generation. For example, the hypothesis generation unit can apply a specialized hypothesis generation algorithm to problems in the field of science and technology. It can also apply a hypothesis generation algorithm that takes social factors into account to problems in the field of social sciences. It can also apply a hypothesis generation algorithm based on medical data to problems in the field of medicine. In this way, appropriate hypotheses can be generated by applying different hypothesis generation algorithms depending on the category of the problem.

[0107] The hypothesis generation unit can estimate the user's emotions and adjust the length of the hypothesis based on the estimated emotions. For example, if the user is in a hurry, the hypothesis generation unit will generate a short hypothesis. If the user is relaxed, the hypothesis generation unit can also generate a detailed hypothesis. If the user is excited, the hypothesis generation unit can also generate multiple hypotheses. This allows for the generation of hypotheses that are appropriate for the user by adjusting the length of the hypothesis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. Generative AIs include, but are not limited to, text generation AIs (e.g., LLM) and multimodal generation AIs.

[0108] The hypothesis generation unit can prioritize hypotheses based on the assignment submission deadlines. For example, it can prioritize generating hypotheses for assignments with earlier submission deadlines. It can also postpone generating hypotheses for assignments with later submission deadlines. Furthermore, it can quickly generate hypotheses for assignments with approaching submission deadlines. By prioritizing hypotheses based on assignment submission deadlines, hypotheses can be generated in the appropriate order.

[0109] The hypothesis generation unit can adjust the order of hypotheses based on the relevance of the issues during hypothesis generation. For example, the hypothesis generation unit can prioritize generating hypotheses for highly relevant issues. It can also postpone generating hypotheses for less relevant issues. For issues of moderate relevance, the hypothesis generation unit can generate hypotheses in an appropriate order. In this way, by adjusting the order of hypotheses based on the relevance of the issues, highly relevant hypotheses can be generated preferentially.

[0110] The verification unit can estimate the user's emotions and adjust the verification criteria based on the estimated emotions. For example, if the user is relaxed, the verification unit can apply detailed verification criteria. If the user is in a hurry, the verification unit can also apply concise verification criteria. If the user is excited, the verification unit can also apply multiple verification criteria. This allows for user-appropriate verification by adjusting the verification criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0111] The verification unit can improve the accuracy of verification by considering the interrelationships of hypotheses during the verification process. For example, the verification unit can analyze the interrelationships of multiple hypotheses and perform highly accurate verification. The verification unit can also determine the priority of verification by considering the interrelationships of hypotheses. The verification unit can also adjust the verification method based on the interrelationships of hypotheses. In this way, the accuracy of verification can be improved by considering the interrelationships of hypotheses.

[0112] The verification unit can perform verification while considering the attribute information of the hypothesis proposer. For example, the verification unit can select an appropriate verification method considering the hypothesis proposer's field of expertise. The verification unit can also adjust the difficulty of the verification considering the hypothesis proposer's years of experience. The verification unit can also determine the priority of verification considering the hypothesis proposer's past achievements. In this way, appropriate verification can be performed by considering the attribute information of the hypothesis proposer.

[0113] The verification unit can estimate the user's emotions and adjust the order in which verification results are displayed based on the estimated emotions. For example, if the user is relaxed, the verification unit may prioritize displaying detailed verification results. If the user is in a hurry, the verification unit may also prioritize displaying concise verification results. If the user is excited, the verification unit may also display multiple verification results. This allows the system to provide verification results that are appropriate to the user by adjusting the order in which the results are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0114] The verification unit can perform verification while considering the geographical distribution of the hypothesis. For example, the verification unit can analyze the geographical distribution of the hypothesis and perform verification while considering the characteristics of each region. The verification unit can also determine the priority of verification based on the geographical distribution. The verification unit can also select an appropriate verification method while considering the geographical distribution. In this way, by considering the geographical distribution of the hypothesis, verification can be performed while considering the characteristics of each region.

[0115] The verification unit can improve the accuracy of its verification by referring to relevant literature on the hypothesis during the verification process. For example, the verification unit can perform highly accurate verification by referring to relevant literature on the hypothesis. The verification unit can also adjust the verification method based on the relevant literature. The verification unit can also determine the priority of verification by referring to relevant literature. In this way, the accuracy of verification can be improved by referring to relevant literature on the hypothesis.

[0116] The feedback unit can estimate the user's emotions and adjust the feedback method based on the estimated emotions. For example, if the user is relaxed, the feedback unit can provide detailed feedback. If the user is in a hurry, the feedback unit can also provide concise feedback. If the user is excited, the feedback unit can also provide multiple pieces of feedback. This allows the system to provide user-appropriate feedback by adjusting the feedback method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0117] The feedback unit can select the optimal feedback method by referring to past feedback data during the feedback process. For example, the feedback unit can analyze past feedback data to select the most effective feedback method. Based on past feedback data, the feedback unit can also predict user reactions and adjust the feedback method accordingly. Furthermore, the feedback unit can customize the content of the feedback by referring to past feedback data. This allows the optimal feedback method to be selected by referring to past feedback data.

[0118] The feedback unit can apply different feedback methods depending on the hypothesis category during the feedback process. For example, the feedback unit can apply specialized feedback methods to hypotheses in the field of science and technology. It can also apply feedback methods that consider social factors to hypotheses in the field of social science. Furthermore, it can apply feedback methods based on medical data to hypotheses in the field of medicine. This allows for the provision of appropriate feedback by applying different feedback methods to each hypothesis category.

[0119] The feedback unit can estimate the user's emotions and adjust the importance of the feedback based on the estimated emotions. For example, if the user is relaxed, the feedback unit can provide detailed feedback. If the user is in a hurry, the feedback unit can also provide concise feedback. If the user is excited, the feedback unit can also provide multiple pieces of feedback. This allows the system to provide user-appropriate feedback by adjusting the importance of the feedback according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0120] The feedback department can prioritize feedback based on when the hypotheses were submitted. For example, it can prioritize feedback on hypotheses submitted earlier, postpone feedback on hypotheses submitted later, or provide feedback quickly on hypotheses submitted sooner. By prioritizing feedback based on when the hypotheses were submitted, feedback can be provided in the appropriate order.

[0121] The feedback unit can provide feedback by referring to relevant market data for the hypothesis. For example, the feedback unit can provide highly accurate feedback by referring to relevant market data for the hypothesis. The feedback unit can also adjust the content of the feedback based on the relevant market data. The feedback unit can also determine the priority of feedback by referring to relevant market data. This allows for the provision of highly accurate feedback by referring to relevant market data for the hypothesis.

[0122] The reward setting unit can estimate the user's emotions and adjust the reward setting method based on the estimated user emotions. For example, if the user is relaxed, the reward setting unit can set detailed rewards. If the user is in a hurry, the reward setting unit can also set simple rewards. If the user is excited, the reward setting unit can also set multiple rewards. In this way, by adjusting the reward setting method according to the user's emotions, it is possible to provide rewards that are appropriate for the user. Emotion estimation is achieved using an emotion estimation function using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0123] The reward setting unit can adjust the reward amount based on the difficulty of the hypothesis when setting rewards. For example, the reward setting unit can set a high reward for a high-difficulty hypothesis. The reward setting unit can also set a low reward for a low-difficulty hypothesis. The reward setting unit can also set a moderate reward for a hypothesis of medium difficulty. In this way, appropriate rewards can be provided by adjusting the reward amount based on the difficulty of the hypothesis.

[0124] The reward setting unit can apply different reward setting methods to each hypothesis category when setting rewards. For example, the reward setting unit can apply specialized reward setting methods to hypotheses in the field of science and technology. It can also apply reward setting methods that take social factors into account to hypotheses in the field of social science. It can also apply reward setting methods based on medical data to hypotheses in the field of medicine. By applying different reward setting methods to each hypothesis category, appropriate rewards can be provided.

[0125] The reward setting unit can estimate the user's emotions and determine the priority of rewards based on the estimated emotions. For example, if the user is relaxed, the reward setting unit can set detailed rewards. If the user is in a hurry, the reward setting unit can also set simple rewards. If the user is excited, the reward setting unit can also set multiple rewards. This allows the system to provide rewards appropriate to the user by determining the priority of rewards according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0126] The reward setting unit can adjust the reward amount based on the timing of hypothesis submission when setting rewards. For example, the reward setting unit can set a higher reward for hypotheses submitted earlier. It can also set a lower reward for hypotheses submitted later. It can also set a moderate reward for hypotheses submitted sooner. In this way, appropriate rewards can be provided by adjusting the reward amount based on the timing of hypothesis submission.

[0127] The reward setting unit can set reward amounts by referring to relevant market data for the hypothesis when setting rewards. For example, the reward setting unit can perform highly accurate reward setting by referring to relevant market data for the hypothesis. The reward setting unit can also adjust reward amounts based on relevant market data. The reward setting unit can also determine reward priorities by referring to relevant market data. This allows for highly accurate reward setting by referring to relevant market data for the hypothesis.

[0128] The subscription usage unit can estimate the user's emotions and adjust the subscription usage method based on the estimated emotions. For example, if the user is relaxed, the subscription usage unit can provide a detailed subscription usage method. If the user is in a hurry, the subscription usage unit can also provide a concise subscription usage method. If the user is excited, the subscription usage unit can also provide multiple subscription usage methods. This allows the system to provide a usage method that is suitable for the user by adjusting the subscription usage method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0129] The subscription usage unit can select the optimal usage method by referring to past usage data when a subscription is used. For example, the subscription usage unit can analyze past usage data and select the most effective subscription usage method. The subscription usage unit can also predict user responses based on past usage data and adjust the usage method accordingly. The subscription usage unit can also customize the usage method by referring to past usage data. This allows for the selection of the optimal subscription usage method by referring to past usage data.

[0130] The subscription utilization unit can apply different utilization methods depending on the industry of the company when it uses a subscription. For example, the subscription utilization unit can apply a specialized subscription utilization method to companies in the science and technology sector. It can also apply a subscription utilization method that takes social factors into account to companies in the social sciences sector. It can also apply a subscription utilization method based on medical data to companies in the medical sector. In this way, by applying different utilization methods to each company's industry, it can provide an appropriate subscription utilization method.

[0131] The subscription application can estimate the user's emotions and prioritize subscriptions based on those emotions. For example, if the user is relaxed, the subscription application can provide detailed subscription usage instructions. If the user is in a hurry, it can also provide concise subscription usage instructions. If the user is excited, it can also provide multiple subscription usage instructions. This allows the application to provide a usage method that is appropriate for the user by prioritizing subscriptions according to their emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0132] The subscription utilization unit can select the optimal usage method when a company uses a subscription, taking into account the company's geographical location information. For example, the subscription utilization unit can provide region-related subscription utilization methods based on the company's geographical location information. The subscription utilization unit can also provide subscription utilization methods in collaboration with local research institutions, taking into account the company's geographical location information. The subscription utilization unit can also provide subscription utilization methods related to solving local problems, taking into account the company's geographical location information. In this way, the optimal subscription utilization method can be provided by taking into account the company's geographical location information.

[0133] The subscription utilization unit can adjust its usage methods by referring to relevant market data of the company when a subscription is used. For example, the subscription utilization unit can refer to relevant market data of the company and provide the optimal subscription utilization method. The subscription utilization unit can also adjust the subscription utilization method based on relevant market data. The subscription utilization unit can also refer to relevant market data to determine the priority of subscription utilization. In this way, by referring to relevant market data of the company, it can provide the optimal subscription utilization method.

[0134] The community site management team can estimate users' emotions and adjust the site's operation based on those estimated emotions. For example, if a user is relaxed, the community site management team can provide detailed site operation instructions. If a user is in a hurry, the community site management team can also provide concise site operation instructions. If a user is excited, the community site management team can also provide multiple site operation instructions. This allows the site management team to provide an appropriate operation method for users by adjusting the site's operation according to their emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0135] The community site management department can select the optimal management method by referring to past operational data when managing the site. For example, the community site management department can analyze past operational data and select the most effective management method. The community site management department can also predict user reactions based on past operational data and adjust the management method accordingly. The community site management department can also customize the management method by referring to past operational data. In this way, the optimal management method can be selected by referring to past operational data.

[0136] The community site management department can customize its operational methods by considering user attribute information when managing the site. For example, the community site management department can provide appropriate operational methods according to the user's age group. The community site management department can also prioritize providing relevant content according to the user's field of expertise. The community site management department can also provide customized operational methods based on the user's interests. In this way, appropriate operational methods can be provided by considering user attribute information.

[0137] The community site management team can estimate user emotions and determine site management priorities based on those estimated emotions. For example, if a user is relaxed, the community site management team can provide detailed management instructions. If a user is in a hurry, the community site management team can also provide concise instructions. If a user is excited, the community site management team can also provide multiple management instructions. This allows the site management team to provide users with appropriate management methods by determining site management priorities according to their emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0138] The community site management department can select the optimal management method when operating the site, taking into account the user's geographical location information. For example, the community site management department can prioritize providing content relevant to a user's region based on their geographical location information. The community site management department can also provide management methods that collaborate with local research institutions, taking into account the user's geographical location information. The community site management department can also provide management methods related to solving local problems, taking into account the user's geographical location information. In this way, the optimal management method can be provided by considering the user's geographical location information.

[0139] The community site management team can analyze users' social media activity and adjust their management methods accordingly. For example, they can analyze users' social media activity and provide content related to their areas of interest. They can also analyze users' social media posts and suggest relevant management methods. Furthermore, they can analyze users' social media followers and followed accounts and provide relevant management methods. In this way, by analyzing users' social media activity, they can provide appropriate management methods.

[0140] The simulator accuracy improvement unit can estimate the user's emotions and adjust the accuracy improvement method based on the estimated user emotions. For example, if the user is relaxed, the simulator accuracy improvement unit can provide a detailed accuracy improvement method. If the user is in a hurry, the simulator accuracy improvement unit can also provide a concise accuracy improvement method. If the user is excited, the simulator accuracy improvement unit can also provide multiple accuracy improvement methods. This allows for the provision of an accuracy improvement method suitable for the user by adjusting the accuracy improvement method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0141] The simulator accuracy improvement unit can select the optimal accuracy improvement method by referring to past accuracy improvement data when improving accuracy. For example, the simulator accuracy improvement unit can analyze past accuracy improvement data and select the most effective accuracy improvement method. The simulator accuracy improvement unit can also predict user reactions based on past accuracy improvement data and adjust the accuracy improvement method accordingly. The simulator accuracy improvement unit can also customize the accuracy improvement method by referring to past accuracy improvement data. This allows for the selection of the optimal accuracy improvement method by referring to past accuracy improvement data.

[0142] The simulator accuracy improvement unit can apply different accuracy improvement methods to each simulator category during the accuracy improvement process. For example, it can apply specialized accuracy improvement methods to simulators in the scientific and technological fields. It can also apply accuracy improvement methods that take social factors into account to simulators in the social sciences. It can also apply accuracy improvement methods based on medical data to simulators in the medical field. By applying different accuracy improvement methods to each simulator category, it can provide an appropriate accuracy improvement method.

[0143] The simulator accuracy improvement unit can estimate the user's emotions and determine the priority of accuracy improvements based on the estimated emotions. For example, if the user is relaxed, the simulator accuracy improvement unit can provide detailed accuracy improvement methods. If the user is in a hurry, the simulator accuracy improvement unit can also provide concise accuracy improvement methods. If the user is excited, the simulator accuracy improvement unit can also provide multiple accuracy improvement methods. This allows for the provision of accuracy improvement methods tailored to the user by determining the priority of accuracy improvements according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0144] The simulator accuracy improvement unit can determine the priority of accuracy improvements based on the simulator's usage period. For example, it can prioritize accuracy improvements for simulators that have been used earlier. It can also postpone accuracy improvements for simulators that have been used later. It can also quickly improve the accuracy of simulators that have been used recently. By determining the priority of accuracy improvements based on the simulator's usage period, accuracy improvements can be carried out in an appropriate order.

[0145] The simulator accuracy improvement unit can adjust the accuracy improvement method by referring to relevant market data for the simulator when improving accuracy. For example, the simulator accuracy improvement unit can refer to relevant market data for the simulator and provide the optimal accuracy improvement method. The simulator accuracy improvement unit can also adjust the accuracy improvement method based on relevant market data. The simulator accuracy improvement unit can also refer to relevant market data to determine the priority of accuracy improvement. In this way, by referring to relevant market data for the simulator, it can provide the optimal accuracy improvement method.

[0146] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0147] The reception desk can estimate the user's emotions and adjust the timing of hypothesis testing task submission based on those estimates. For example, if a user is feeling stressed, the hypothesis testing task can be submitted during a time when they can relax. If a user is concentrating, the task can be submitted at that time. If a user is tired, the task can be submitted after they have rested. By adjusting the timing of hypothesis testing task submission according to the user's emotions, the burden on the user can be reduced.

[0148] 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, it can generate a detailed hypothesis. If the user is in a hurry, it can generate a concise hypothesis. If the user is excited, it can generate multiple hypotheses. In this way, by adjusting the hypothesis generation method according to the user's emotions, it is possible to generate hypotheses that are appropriate for the user.

[0149] The verification unit can estimate the user's emotions and adjust the verification criteria based on those emotions. For example, if the user is relaxed, detailed verification criteria can be applied. If the user is in a hurry, concise verification criteria can be applied. If the user is excited, multiple verification criteria can be applied. This allows for verification tailored to the user by adjusting the verification criteria according to their emotions.

[0150] The feedback unit can estimate the user's emotions and adjust the feedback method based on those emotions. For example, if the user is relaxed, it can provide detailed feedback. If the user is in a hurry, it can provide concise feedback. If the user is excited, it can provide multiple pieces of feedback. This allows the system to provide feedback that is appropriate for the user by adjusting the feedback method according to their emotions.

[0151] The reward setting unit can estimate the user's emotions and adjust the reward setting method based on the estimated user emotions. For example, if the user is relaxed, detailed reward settings can be made. If the user is in a hurry, simple reward settings can be made. If the user is excited, multiple reward settings can be made. In this way, by adjusting the reward setting method according to the user's emotions, it is possible to provide rewards that are appropriate for the user.

[0152] The reception desk can analyze a user's past posting history and select the most suitable reception method. For example, it can analyze the trends in hypothesis testing tasks previously posted by a user and prioritize accepting similar tasks. It can also analyze the time periods when users previously posted and accept submissions during those times. Furthermore, it can analyze the difficulty level of tasks previously posted by users and accept tasks of appropriate difficulty. In this way, by analyzing a user's past posting history, the most suitable reception method can be selected.

[0153] The hypothesis generation unit can adjust the level of detail of a hypothesis based on the importance of the problem. For example, it can generate detailed hypotheses for high-importance problems, concise hypotheses for low-importance problems, and hypotheses with appropriate detail for medium-importance problems. By adjusting the level of detail of a hypothesis based on the importance of the problem, it is possible to generate appropriate hypotheses.

[0154] The verification unit can improve the accuracy of verification by considering the interrelationships of hypotheses during the verification process. For example, it can analyze the interrelationships of multiple hypotheses and perform highly accurate verification. It can also determine the priority of verification by considering the interrelationships of hypotheses. It can also adjust the verification method based on the interrelationships of hypotheses. In this way, the accuracy of verification can be improved by considering the interrelationships of hypotheses.

[0155] The feedback unit can select the optimal feedback method by referring to past feedback data during the feedback process. For example, it can analyze past feedback data to select the most effective feedback method. It can also predict user reactions based on past feedback data and adjust the feedback method accordingly. It can also customize the content of the feedback by referring to past feedback data. In this way, the optimal feedback method can be selected by referring to past feedback data.

[0156] The reward setting unit can adjust the reward amount based on the difficulty of the hypothesis when setting rewards. For example, a high reward can be set for a high-difficulty hypothesis. A low reward can be set for an easy hypothesis. A moderate reward can be set for a hypothesis of medium difficulty. In this way, appropriate rewards can be provided by adjusting the reward amount based on the difficulty of the hypothesis.

[0157] The following briefly describes the processing flow for example form 2.

[0158] Step 1: The reception desk accepts hypothesis testing tasks. For example, it provides a community site where users can post hypothesis testing tasks. Step 2: The hypothesis generation unit generates hypotheses for the problem received by the reception unit. For example, an AI agent generates multiple hypotheses. Step 3: The verification unit verifies the hypotheses generated by the hypothesis generation unit. For example, researchers or students might verify the hypotheses. Step 4: The feedback unit feeds back the verification results obtained by the verification unit to the system. For example, the verification results are fed back to the system and used to improve the accuracy of the simulator. Step 5: The reward setting unit sets rewards based on the feedback received by the feedback unit. For example, it sets rewards according to the difficulty of the hypothesis and automatically increases the reward amount over time for untested hypotheses.

[0159] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0160] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0161] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0162] Each of the multiple elements described above, including the reception unit, hypothesis generation unit, verification unit, feedback unit, reward setting unit, subscription usage unit, community site operation unit, and simulator accuracy improvement unit, is implemented, for example, by at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and provides a community site for users to post hypothesis testing tasks. The hypothesis generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and generates multiple hypotheses using an AI agent. The verification unit is implemented, for example, by the control unit 46A of the smart device 14 and allows researchers and students to verify hypotheses. The feedback unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and feeds the verification results back to the system to improve the accuracy of the simulator. The reward setting unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and sets rewards according to the difficulty of the hypotheses and automatically increases the reward amount over time for unverified hypotheses. The subscription usage unit is implemented, for example, by the control unit 46A of the smart device 14, allowing companies to use the simulation AI on a subscription basis. The community site operation unit is implemented, for example, by the control unit 46A of the smart device 14, and handles the publication of hypothesis testing tasks and the setting of rewards. The simulator accuracy improvement unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and improves the accuracy of the simulator based on the feedbacked verification results. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various changes are possible.

[0163] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0164] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0165] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0166] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0167] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0168] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0169] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0170] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0171] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0172] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0173] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0174] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0175] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0176] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0177] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0178] Each of the multiple elements described above, including the reception unit, hypothesis generation unit, verification unit, feedback unit, reward setting unit, subscription usage unit, community site operation unit, and simulator accuracy improvement unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and provides a community site for users to post hypothesis testing tasks. The hypothesis generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and generates multiple hypotheses using an AI agent. The verification unit is implemented, for example, by the control unit 46A of the smart glasses 214 and allows researchers and students to verify hypotheses. The feedback unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and feeds the verification results back to the system to improve the accuracy of the simulator. The reward setting unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and sets rewards according to the difficulty of the hypotheses and automatically increases the reward amount over time for unverified hypotheses. The subscription usage unit is implemented, for example, by the control unit 46A of the smart glasses 214, allowing companies to use the simulation AI on a subscription basis. The community site operation unit is implemented, for example, by the control unit 46A of the smart glasses 214, and handles the publication of hypothesis testing tasks and the setting of rewards. The simulator accuracy improvement unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and improves the accuracy of the simulator based on the feedbacked verification results. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various changes are possible.

[0179] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0180] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0181] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0182] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0183] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0184] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0185] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0186] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0187] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0188] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0189] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0190] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0191] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0192] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0193] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0194] Each of the multiple elements described above, including the reception unit, hypothesis generation unit, verification unit, feedback unit, reward setting unit, subscription usage unit, community site operation unit, and simulator accuracy improvement unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and provides a community site for users to post hypothesis testing tasks. The hypothesis generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and generates multiple hypotheses using an AI agent. The verification unit is implemented by, for example, the control unit 46A of the headset terminal 314 and allows researchers and students to verify hypotheses. The feedback unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and feeds the verification results back to the system to improve the accuracy of the simulator. The reward setting unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and sets rewards according to the difficulty of the hypotheses and automatically increases the reward amount over time for unverified hypotheses. The subscription usage unit is implemented, for example, by the control unit 46A of the headset terminal 314, allowing companies to use the simulation AI on a subscription basis. The community site operation unit is implemented, for example, by the control unit 46A of the headset terminal 314, and handles the publication of hypothesis testing tasks and the setting of rewards. The simulator accuracy improvement unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and improves the accuracy of the simulator based on the feedbacked verification results. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various changes are possible.

[0195] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0196] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0197] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0198] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0199] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0200] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0201] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0202] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0203] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0204] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0205] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0206] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0207] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0208] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0209] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0210] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0211] Each of the multiple elements described above, including the reception unit, hypothesis generation unit, verification unit, feedback unit, reward setting unit, subscription usage unit, community site operation unit, and simulator accuracy improvement unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and provides a community site for users to post hypothesis testing tasks. The hypothesis generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and generates multiple hypotheses using an AI agent. The verification unit is implemented by, for example, the control unit 46A of the robot 414 and allows researchers and students to verify hypotheses. The feedback unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and feeds the verification results back to the system to improve the accuracy of the simulator. The reward setting unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and sets rewards according to the difficulty of the hypotheses and automatically increases the reward amount over time for unverified hypotheses. The subscription usage unit is implemented, for example, by the control unit 46A of robot 414, allowing companies to use the simulation AI on a subscription basis. The community site operation unit is implemented, for example, by the control unit 46A of robot 414, and handles the publication of hypothesis testing tasks and the setting of rewards. The simulator accuracy improvement unit is implemented, for example, by the specific processing unit 290 of data processing device 12, and improves the accuracy of the simulator based on the feedbacked verification results. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various changes are possible.

[0212] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0213] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0214] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0215] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0216] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0217] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0218] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0219] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0220] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0221] 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.

[0222] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0223] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0224] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0225] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0226] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0227] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0228] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0229] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0230] (Note 1) The reception desk accepts hypothesis testing assignments, A hypothesis generation unit that generates hypotheses for the issues received by the reception unit, A verification unit that verifies the hypothesis generated by the hypothesis generation unit, A feedback unit that feeds back the verification results obtained by the verification unit to the system, A reward setting unit sets a reward based on the results of the feedback received by the aforementioned feedback unit, Equipped with A system characterized by the following features. (Note 2) The aforementioned reception unit is We provide a community site where users can post hypothesis testing challenges. The system described in Appendix 1, characterized by the features described herein. (Note 3) The hypothesis generation unit, AI agent generates multiple hypotheses The system described in Appendix 1, characterized by the features described herein. (Note 4) The verification unit, Researchers and students test hypotheses. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned feedback unit is The verification results are fed back into the system and used to improve the accuracy of the simulator. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reward setting unit, The system sets rewards according to the difficulty of the hypothesis, and automatically increases the reward amount over time for untested hypotheses. The system described in Appendix 1, characterized by the features described herein. (Note 7) It has a subscription service section, The aforementioned subscription usage unit allows companies to use simulation AI on a subscription basis. The system described in Appendix 1, characterized by the features described herein. (Note 8) It has a community site management department, The aforementioned community site management department will publish hypothesis testing tasks and set rewards. The system described in Appendix 1, characterized by the features described herein. (Note 9) Equipped with a simulator accuracy improvement unit, The simulator accuracy improvement unit improves the simulator's accuracy based on the feedback verification results. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is We estimate the user's emotions and adjust the timing of accepting hypothesis testing tasks based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is Analyze the user's past posting history and select the most suitable submission method. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When receiving hypothesis testing assignments, filtering is performed based on the user's current research topic and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned reception unit is It estimates the user's emotions and determines the priority of the tasks to be accepted based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned reception unit is When accepting hypothesis testing tasks, the system prioritizes accepting tasks that are highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned reception unit is When receiving hypothesis testing tasks, we analyze users' social media activity and accept related tasks. The system described in Appendix 1, characterized by the features described herein. (Note 16) The hypothesis generation unit, We estimate the user's emotions and adjust the hypothesis generation method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The hypothesis generation unit, When generating hypotheses, adjust the level of detail of the hypotheses based on the importance of the problem. The system described in Appendix 1, characterized by the features described herein. (Note 18) The hypothesis generation unit, When generating hypotheses, different hypothesis generation algorithms are applied depending on the category of the problem. The system described in Appendix 1, characterized by the features described herein. (Note 19) The hypothesis generation unit, We estimate the user's emotions and adjust the length of the hypothesis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The hypothesis generation unit, When generating hypotheses, prioritize them based on the deadline for submitting the assignment. The system described in Appendix 1, characterized by the features described herein. (Note 21) The hypothesis generation unit, When generating hypotheses, adjust the order of hypotheses based on their relevance to the problem. The system described in Appendix 1, characterized by the features described herein. (Note 22) The verification unit, We estimate the user's emotions and adjust the validation criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The verification unit, During verification, consider the interrelationships between hypotheses to improve the accuracy of the verification. The system described in Appendix 1, characterized by the features described herein. (Note 24) The verification unit, During verification, the attribute information of the hypothesis proposer will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 25) The verification unit, It estimates the user's sentiment and adjusts the order in which the verification results are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The verification unit, During verification, the geographical distribution of the hypothesis should be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 27) The verification unit, During verification, refer to relevant literature related to the hypothesis to improve the accuracy of the verification. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned feedback unit is It estimates the user's emotions and adjusts the feedback method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned feedback unit is When providing feedback, refer to past feedback data to select the most suitable feedback method. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned feedback unit is When providing feedback, apply different feedback methods to each hypothesis category. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned feedback unit is It estimates the user's emotions and adjusts the importance of feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned feedback unit is When providing feedback, determine the priority of the feedback based on the timing of hypothesis submission The system according to appended claim 1, characterized in that (Appended claim 33) The feedback unit When providing feedback, refer to the related market data of the hypothesis to provide feedback The system according to appended claim 1, characterized in that (Appended claim 34) The reward setting unit Estimate the user's sentiment and adjust the reward setting method based on the estimated user sentiment The system according to appended claim 1, characterized in that (Appended claim 35) The reward setting unit When setting the reward, adjust the reward amount based on the difficulty level of the hypothesis The system according to appended claim 1, characterized in that (Appended claim 36) The reward setting unit When setting the reward, apply different reward setting methods for each category of hypothesis The system according to appended claim 1, characterized in that (Appended claim 37) The reward setting unit Estimate the user's sentiment and determine the priority of the reward based on the estimated user sentiment The system according to appended claim 1, characterized in that (Appended claim 38) The reward setting unit When setting the reward, adjust the reward amount based on the timing of hypothesis submission The system according to appended claim 1, characterized in that (Appended claim 39) The reward setting unit When setting the reward, refer to the related market data of the hypothesis to set the reward amount The system according to appended claim 1, characterized in that (Appended claim 40) The subscription usage unit It estimates user sentiment and adjusts subscription usage based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned subscription usage unit is: When using a subscription, past usage data is referenced to select the optimal usage method. The system described in Appendix 1, characterized by the features described herein. (Note 42) The aforementioned subscription usage unit is: When using a subscription service, different usage methods will be applied depending on the company's industry. The system described in Appendix 1, characterized by the features described herein. (Note 43) The aforementioned subscription usage unit is: It estimates user sentiment and prioritizes subscriptions based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 44) The aforementioned subscription usage unit is: When using a subscription service, the optimal usage method is selected considering the company's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 45) The aforementioned subscription usage unit is: When using a subscription, adjust usage methods by referring to relevant market data from the company. The system described in Appendix 1, characterized by the features described herein. (Note 46) The aforementioned community site management department, We estimate user sentiment and adjust how the site is operated based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 47) The aforementioned community site management department, When operating a website, refer to past operational data to select the optimal operating method. The system described in Appendix 1, characterized by the features described herein. (Note 48) The aforementioned community site management department, When operating a website, customize the operating methods by taking user attribute information into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 49) The aforementioned community site management department, It estimates user sentiment and determines site operational priorities based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 50) The aforementioned community site management department, When operating a website, the optimal operating method is selected by considering the user's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 51) The aforementioned community site management department, When managing a website, we analyze users' social media activity and adjust our management methods accordingly. The system described in Appendix 1, characterized by the features described herein. (Note 52) The aforementioned simulator accuracy improvement unit is: We estimate the user's emotions and adjust the method of improving accuracy based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 53) The aforementioned simulator accuracy improvement unit is: When improving accuracy, the optimal method for improving accuracy is selected by referring to past accuracy improvement data. The system described in Appendix 1, characterized by the features described herein. (Note 54) The aforementioned simulator accuracy improvement unit is: When improving accuracy, different accuracy improvement methods are applied to each category of simulator. The system described in Appendix 1, characterized by the features described herein. (Note 55) The aforementioned simulator accuracy improvement unit is: Estimate the user's emotions and determine the priority of accuracy improvement based on the estimated user emotions The system according to Appendix 1, characterized in that it does the above. (Appendix 56) The simulator accuracy improvement unit When improving accuracy, determine the priority of accuracy improvement based on the usage time of the simulator The system according to Appendix 1, characterized in that it does the above. (Appendix 57) The simulator accuracy improvement unit When improving accuracy, adjust the accuracy improvement method by referring to the related market data of the simulator The system according to Appendix 1, characterized in that it does the above.

Description of signs

[0231] 10, 210, 310, 410 Data processing system 12 Data processing device 14 Smart device 214 Smart glasses 314 Headset-type terminal 414 Robot

Claims

1. The reception desk accepts hypothesis testing assignments, A hypothesis generation unit that generates hypotheses for the issues received by the reception unit, A verification unit that verifies the hypothesis generated by the hypothesis generation unit, A feedback unit that feeds back the verification results obtained by the verification unit to the system, A reward setting unit sets a reward based on the results of the feedback received by the aforementioned feedback unit, Equipped with A system characterized by the following features.

2. The aforementioned reception unit is We provide a community site where users can post hypothesis testing challenges. The system according to feature 1.

3. The hypothesis generation unit, An AI agent generates multiple hypotheses. The system according to feature 1.

4. The verification unit, Researchers and students test hypotheses. The system according to feature 1.

5. The aforementioned feedback unit is The verification results are fed back into the system and used to improve the accuracy of the simulator. The system according to feature 1.

6. The aforementioned reward setting unit, The system sets rewards according to the difficulty of the hypothesis, and automatically increases the reward amount over time for untested hypotheses. The system according to feature 1.

7. It has a subscription service section, The aforementioned subscription usage unit allows companies to use simulation AI on a subscription basis. The system according to feature 1.

8. It has a community site management department, The aforementioned community site management department will publish hypothesis testing tasks and set rewards. The system according to feature 1.

9. Equipped with a simulator accuracy improvement unit, The simulator accuracy improvement unit improves the simulator's accuracy based on the feedback verification results. The system according to feature 1.

10. The aforementioned reception unit is We estimate the user's emotions and adjust the timing of accepting hypothesis testing tasks based on the estimated user emotions. The system according to feature 1.

Images