System

Abstract

An object of a system according to an embodiment is to appropriately propose an action of a warrior on the basis of a user's advice.SOLUTION: A system includes a warrior setting unit, an advice analysis unit, and an action suggestion unit. The warrior setting unit sets an initial state of the warrior. The advice analyzer analyzes the user's advice prompt. The action suggestion unit suggests an action of the warrior based on the advice prompt analyzed by the advice analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In conventional technology, in games in which a user gives advice to a Sengoku warlord, there is a problem in that it is difficult to appropriately suggest actions for the warlord.

[0005] The system according to the embodiment aims to appropriately suggest actions for a Sengoku warlord based on advice from a user. [Means for solving the problem]

[0006] The system according to the embodiment includes a Sengoku warlord setting unit, an advice analysis unit, and an action suggestion unit. The Sengoku warlord setting unit sets the initial state of the Sengoku warlord. The advice analysis unit analyzes the user's advice prompt. The action suggestion unit suggests an action for the warlord based on the advice prompt analyzed by the advice analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can appropriately suggest actions for the Sengoku warlords based on the user's advice. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) In the online game system according to the embodiment of the present invention, a user becomes a military strategist and gives advice to a Sengoku warlord (an AI personality) to help the warlord grow. In this way, the online game system allows the user to give advice to the Sengoku warlord and help the warlord grow.

[0029] The online game system according to the embodiment includes a Sengoku warlord setting unit, an advice analysis unit, and an action suggestion unit. The Sengoku warlord setting unit sets the initial state of the Sengoku warlord. For example, the Sengoku warlord setting unit initially sets the warlord's skills, equipment, status, and the like. The Sengoku warlord setting unit can also set the warlord's background information and initial knowledge level. The advice analysis unit analyzes the user's advice prompts. For example, the advice analysis unit analyzes text prompts entered by the user and understands their content. The advice analysis unit can also analyze prompts from different interfaces, such as voice input and gesture input. The action suggestion unit suggests actions for the warlord based on the advice prompts analyzed by the advice analysis unit. For example, the action suggestion unit uses a generation AI (e.g., a text generation AI or a multimodal generation AI) to suggest specific actions for the warlord. The action suggestion unit can also refer to past successes and failures to suggest optimal actions. This allows the online game system according to the embodiment to suggest actions for the Sengoku warlord based on the user's advice, thereby enabling the warlord to grow.

[0030] The Sengoku warlord setting unit can customize the initial state of a Sengoku warlord based on the historical background and culture selected by the user. The Sengoku warlord setting unit sets the initial state of a Sengoku warlord based on, for example, the historical background selected by the user. For example, it reflects the background of a different era or region, such as Japan during the Sengoku period or China during the Three Kingdoms period. The Sengoku warlord setting unit also customizes the initial state of a warlord based on the culture selected by the user. For example, it reflects specific customs, habits, and values. This allows the initial state of a Sengoku warlord to be customized according to the user's selection.

[0031] The Sengoku warlord setting unit can dynamically change the initial knowledge of a warlord based on the user's past play history and selections. The Sengoku warlord setting unit, for example, analyzes the user's past play history and sets the warlord's initial knowledge based on that. For example, it generates a warlord whose initial knowledge is tactics or strategies that have been successful in the past. The Sengoku warlord setting unit also dynamically changes the warlord's initial knowledge based on the user's selections. For example, it adjusts the warlord's knowledge level based on the actions selected by the user and the results achieved by the user. This makes it possible to dynamically change the warlord's initial knowledge based on the user's past play history and selections.

[0032] The advice analysis unit can provide specific advice in response to a user's advice prompt by referring to past examples of success and failure. For example, the generation AI can provide specific advice in response to a user's advice prompt by referring to past examples of success. For example, advice can be given based on tactics and strategies that have been successful in the past. The advice analysis unit can also provide specific advice in response to a user's advice prompt by referring to past examples of failure. For example, advice can be given to avoid tactics and strategies that have failed in the past. In this way, specific advice can be provided by referring to past examples of success and failure.

[0033] The advice analysis unit can simulate multiple scenarios in response to the user's advice prompts and suggest the optimal action. For example, in response to the user's advice prompts, the generation AI simulates multiple scenarios and suggests the optimal action. For example, it simulates different tactics and strategies and selects the most effective action. The advice analysis unit also suggests the optimal action based on the simulation results in response to the user's advice prompts. For example, it suggests specific actions for the military commander based on the simulation results. This makes it possible to simulate multiple scenarios and suggest the optimal action.

[0034] The advice analysis unit can enable input of advice prompts using different interfaces, such as voice input or gesture input. The advice analysis unit, for example, builds a system that enables input of advice prompts using voice input. For example, a user uses a microphone to input advice by voice. The advice analysis unit also builds a system that enables input of advice prompts using gesture input. For example, a user uses a camera to input advice by gesture. This makes it possible to input advice prompts using different interfaces, such as voice input or gesture input.

[0035] The advice analysis unit can add a community function that allows the generation AI to suggest optimal advice by referring to advice prompts from other users. The advice analysis unit, for example, adds a community function that allows other users to share advice prompts. For example, successful advice prompts are shared with other users. The advice analysis unit also refers to other users' advice prompts by allowing the generation AI to suggest optimal advice. For example, advice is given based on the success stories of other users. This allows the generation AI to refer to other users' advice prompts by adding a community function that allows the generation AI to suggest optimal advice.

[0036] The action suggestion unit can simulate the battle situation in real time in response to battle advice and propose optimal tactics. For example, the action suggestion unit constructs a system in which a generation AI simulates the battle situation in real time in response to battle advice and proposes optimal tactics. For example, the tactics are adjusted according to changes in the battle situation. The action suggestion unit also simulates the battle situation in real time and proposes optimal tactics. For example, specific tactics are proposed to military commanders according to changes in the battle situation. This makes it possible to simulate the battle situation in real time and propose optimal tactics.

[0037] The action suggestion unit can refer to past tactical data based on the battle advice and suggest tactics with a high success rate. The action suggestion unit, for example, builds a system in which a generation AI refers to past tactical data based on the battle advice and suggests tactics with a high success rate. For example, it analyzes past battle data and selects the optimal tactic. The action suggestion unit also refers to past tactical data and suggests tactics with a high success rate. For example, it provides advice based on tactics that have been successful in the past. This makes it possible to refer to past tactical data and suggest tactics with a high success rate.

[0038] The action suggestion unit can apply the battle advice to different historical battle scenarios, allowing different tactics to be tried. The action suggestion unit, for example, builds a system that applies the battle advice to different historical battle scenarios and allows different tactics to be tried. For example, tactics are tried in different scenarios, such as Japan during the Warring States period or China during the Three Kingdoms period. The action suggestion unit also suggests specific tactics to military commanders based on different historical battle scenarios. For example, it recreates specific wars or battles and tries out the optimal tactics within those scenarios. This allows the battle advice to be applied to different historical battle scenarios and allows different tactics to be tried.

[0039] The action suggestion unit can add a sharing function that allows the generation AI to propose optimal tactics by referring to the battle advice of other users. The action suggestion unit, for example, adds a function that allows sharing of battle advice from other users, and builds a system in which the generation AI proposes optimal tactics. For example, successful tactics are shared with other users. The action suggestion unit also refers to the battle advice of other users, and the generation AI proposes optimal tactics. For example, tactics are proposed based on successful examples of other users. This allows a sharing function to be added that allows the generation AI to propose optimal tactics by referring to the battle advice of other users.

[0040] The action suggestion unit can propose customized education plans for vassal education based on the characteristics and abilities of each vassal. The action suggestion unit, for example, analyzes the characteristics and abilities of each vassal and builds a system that proposes customized education plans based on the results. For example, it proposes education plans to strengthen specific skills. The action suggestion unit also proposes customized education plans based on the characteristics and abilities of each vassal. For example, it proposes education methods that suit the vassal's personality and skills. This makes it possible to propose customized education plans based on the characteristics and abilities of each vassal.

[0041] The action suggestion unit can refer to past educational data when giving advice on vassal education and suggest the most appropriate educational method. For example, the action suggestion unit constructs a system in which, when giving advice on vassal education, the generation AI refers to past educational data and suggests the most appropriate educational method. For example, advice is given based on educational methods that have been successful in the past. The action suggestion unit also refers to past educational data and suggests the most appropriate educational method. For example, advice is given based on past educational plans and educational results. This makes it possible to refer to past educational data and suggest the most appropriate educational method.

[0042] The action suggestion unit can expand the education of vassals to customized education plans according to different occupations and roles. The action suggestion unit, for example, builds a system that expands the education of vassals to customized education plans according to different occupations and roles. For example, it proposes education plans according to different occupations such as military commander, merchant, farmer, etc. The action suggestion unit also proposes education plans according to the role of the vassal. For example, it proposes an education plan to strengthen skills required for a specific role. This makes it possible to expand the education of vassals to customized education plans according to different occupations and roles.

[0043] The action suggestion unit can add a sharing function that allows the generation AI to refer to other users' vassal training advice and suggest the most appropriate training method. The action suggestion unit, for example, adds a function to share other users' vassal training advice and builds a system in which the generation AI suggests the most appropriate training method. For example, successful training methods are shared with other users. The action suggestion unit also refers to other users' vassal training advice and allows the generation AI to suggest the most appropriate training method. For example, a training method is suggested based on other users' successful examples. This allows the generation AI to refer to other users' vassal training advice and suggest the most appropriate training method.

[0044] The action suggestion unit can refer to regional population data and economic conditions when providing conscription advice and propose the optimal conscription method. For example, the action suggestion unit constructs a system in which, when providing conscription advice, the generation AI refers to regional population data and proposes the optimal conscription method. For example, conscript soldiers from areas with high population density. The action suggestion unit also refers to regional economic conditions and proposes the optimal conscription method. For example, conscript soldiers from areas where economic growth is expected. This makes it possible to refer to regional population data and economic conditions and propose the optimal conscription method.

[0045] The action suggestion unit can refer to past conscription data based on the conscription advice and suggest a conscription method with a high success rate. For example, the action suggestion unit builds a system in which, based on the conscription advice, the generation AI refers to past conscription data and suggests a conscription method with a high success rate. For example, advice is given based on conscription methods that have been successful in the past. The action suggestion unit also refers to past conscription data and suggests a conscription method with a high success rate. For example, advice is given based on past conscription records and success rates. This makes it possible to refer to past conscription data and suggest a conscription method with a high success rate.

[0046] The action suggestion unit can expand the conscription advice to customized conscription methods according to different regions and cultures. The action suggestion unit, for example, builds a system that expands the conscription advice to customized conscription methods according to different regions and cultures. For example, it proposes conscription methods that suit local customs and cultures. The action suggestion unit also proposes specific conscription methods to military commanders based on different regions and cultures. For example, it proposes conscription methods that are suitable for specific regions and cultures. This makes it possible to expand the conscription advice to customized conscription methods according to different regions and cultures.

[0047] The action suggestion unit can add a sharing function that enables the generation AI to propose the optimal conscription method by referring to the conscription advice of other users. The action suggestion unit, for example, adds a function to share the conscription advice of other users, and builds a system in which the generation AI proposes the optimal conscription method. For example, successful conscription methods are shared with other users. The action suggestion unit also refers to the conscription advice of other users, and enables the generation AI to propose the optimal conscription method. For example, a conscription method is proposed based on the success stories of other users. This allows the generation AI to refer to the conscription advice of other users and add a sharing function that enables the generation AI to propose the optimal conscription method.

[0048] The action suggestion unit can refer to regional economic data and demographics when providing advice on city development and propose the optimal city development method. For example, the action suggestion unit constructs a system in which the generation AI refers to regional economic data when providing advice on city development and proposes the optimal city development method. For example, it may set up a market in an area where economic growth is expected. The action suggestion unit also refers to regional demographics and proposes the optimal city development method. For example, it may build housing in an area where population growth is expected. This makes it possible to refer to regional economic data and demographics and propose the optimal city development method.

[0049] The action suggestion unit can refer to past city development data based on the city development advice and propose city development methods with a high success rate. For example, the action suggestion unit builds a system in which the generation AI refers to past city development data and proposes city development methods with a high success rate based on the city development advice. For example, advice is given based on city development methods that have been successful in the past. The action suggestion unit also refers to past city development data and proposes city development methods with a high success rate. For example, advice is given based on past city development plans and success rates. This makes it possible to refer to past city development data and propose city development methods with a high success rate.

[0050] The action suggestion unit can expand the city planning advice to a customized city planning method that suits different regions and cultures. The action suggestion unit, for example, builds a system that expands the city planning advice to a customized city planning method that suits different regions and cultures. For example, it proposes a city planning method that suits local customs and cultures. The action suggestion unit also proposes specific city planning methods based on different regions and cultures. For example, it proposes a city planning method that suits a specific region or culture. In this way, the city planning advice can be expanded to a customized city planning method that suits different regions and cultures.

[0051] The action suggestion unit can add a sharing function that enables the generation AI to propose the optimal city development method by referring to city development advice from other users. The action suggestion unit, for example, adds a function to share city development advice from other users, and builds a system in which the generation AI proposes the optimal city development method. For example, successful city development methods are shared with other users. The action suggestion unit also refers to city development advice from other users, and enables the generation AI to propose the optimal city development method. For example, a city development method is proposed based on successful examples from other users. This allows the generation AI to refer to city development advice from other users, and adds a sharing function that enables the generation AI to propose the optimal city development method.

[0052] The action suggestion unit can refer to regional climate data and soil data when providing cultivation advice and suggest the optimal cultivation method. For example, the action suggestion unit constructs a system in which, when providing cultivation advice, the generation AI refers to regional climate data and suggests the optimal cultivation method. For example, it selects crops that are suitable for the climatic conditions. The action suggestion unit also refers to regional soil data and suggests the optimal cultivation method. For example, it selects crops based on the soil components and fertility. This makes it possible to refer to regional climate data and soil data and suggest the optimal cultivation method.

[0053] The action suggestion unit can refer to past cultivation data based on the cultivation advice and suggest cultivation methods with a high success rate. For example, the action suggestion unit constructs a system in which, based on the cultivation advice, the generation AI refers to past cultivation data and suggests cultivation methods with a high success rate. For example, advice is given based on cultivation methods that have been successful in the past. The action suggestion unit also refers to past cultivation data and suggests cultivation methods with a high success rate. For example, advice is given based on past cultivation records and success rates. This makes it possible to refer to past cultivation data and suggest cultivation methods with a high success rate.

[0054] The action suggestion unit can expand the cultivation advice to customized cultivation methods according to different regions and climates. For example, the action suggestion unit builds a system that expands the cultivation advice to customized cultivation methods according to different regions and climates. For example, it proposes cultivation methods that suit the climatic conditions of the region. The action suggestion unit also proposes specific cultivation methods based on different regions and climates. For example, it proposes cultivation methods that are suitable for specific regions and climates. This allows the cultivation advice to be expanded to customized cultivation methods according to different regions and climates.

[0055] The action suggestion unit can add a sharing function that enables the generation AI to suggest the optimal cultivation method by referring to the cultivation advice of other users. The action suggestion unit, for example, adds a function to share the cultivation advice of other users, and builds a system in which the generation AI suggests the optimal cultivation method. For example, successful cultivation methods are shared with other users. The action suggestion unit also refers to the cultivation advice of other users, and the generation AI suggests the optimal cultivation method. For example, a cultivation method is suggested based on the success stories of other users. This allows the generation AI to refer to the cultivation advice of other users and add a sharing function that enables the generation AI to suggest the optimal cultivation method.

[0056] The action suggestion unit allows the generation AI to refer to the user's past play data and make a fairer evaluation in an evaluation system for online battles. The action suggestion unit, for example, builds a system in an evaluation system for online battles in which the generation AI refers to the user's past play data and makes a fairer evaluation. For example, the evaluation is made based on past battle results and behavior patterns. The action suggestion unit also analyzes the user's past play data and makes an evaluation based on that. For example, the evaluation is made based on play time, selected actions, and achieved results. This allows the generation AI to refer to the user's past play data and make a fairer evaluation in an evaluation system for online battles.

[0057] The action suggestion unit enables the generation AI to analyze the user's actions in real time and provide instant feedback in an evaluation system for online battles. The action suggestion unit, for example, builds a system in an evaluation system for online battles in which the generation AI analyzes the user's actions in real time and provides instant feedback. For example, it evaluates the selection of tactics and the timing of actions. The action suggestion unit also analyzes the user's actions in real time and provides instant feedback based on that. For example, it evaluates the user's actions in real time and provides feedback. This enables the generation AI to analyze the user's actions in real time and provide instant feedback in an evaluation system for online battles.

[0058] The action suggestion unit can apply the rating system for online battles to different game modes and scenarios to provide a variety of battle formats. The action suggestion unit, for example, applies the rating system for online battles to different game modes and scenarios to build a system that provides a variety of battle formats. For example, different battle formats such as team battles and individual battles are provided. The action suggestion unit also adjusts the rating system based on different game modes and scenarios. For example, it sets evaluation criteria according to the progress method of a specific storyline or mission. This allows the rating system for online battles to be applied to different game modes and scenarios to provide a variety of battle formats.

[0059] The action suggestion unit can add a sharing function that allows the generation AI to propose optimal evaluation criteria by referring to the evaluation data of other users. The action suggestion unit, for example, adds a function to share the evaluation data of other users, and builds a system in which the generation AI proposes optimal evaluation criteria. For example, successful evaluation criteria are shared with other users. The action suggestion unit also refers to the evaluation data of other users, and the generation AI proposes optimal evaluation criteria. For example, evaluation criteria are set based on the success stories of other users. This allows the generation AI to refer to the evaluation data of other users and add a sharing function that allows the generation AI to propose optimal evaluation criteria.

[0060] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0061] The online game system may further include a health management unit that monitors the user's health condition. For example, the health management unit may monitor the user's heart rate and stress level in real time and encourage the user to take a break at an appropriate time. The health management unit may also adjust in-game activities based on the user's health data. For example, if the user is tired, the in-game difficulty may be temporarily lowered. This allows gameplay that takes the user's health condition into consideration.

[0062] The online game system may further include a learning analysis unit that analyzes the user's learning history. For example, the learning analysis unit may analyze the tactics and strategies the user has learned in the past and suggest new learning content based on the results. The learning analysis unit may also prompt the user to review the tactics at an appropriate time according to the user's learning pace. For example, if the user is starting to forget a particular tactic, the system may provide a quiz or mini-game related to that tactic. This may improve the user's learning effectiveness.

[0063] The online game system may further include a play style analysis unit that analyzes a user's play style. For example, the play style analysis unit may analyze the user's preferred tactics and behavioral patterns and provide a customized game experience based on the analysis. The play style analysis unit may also provide appropriate advice and hints depending on the user's play style. For example, if the user prefers an offensive play style, the play style analysis unit may suggest tactics specialized for attacking. This allows for a game experience tailored to the user's play style.

[0064] The online game system may further include an avatar customization unit that analyzes a user's play data and provides an avatar customized according to the user's play style. For example, the avatar customization unit may analyze the user's preferred equipment and appearance and automatically customize the avatar based on that information. The avatar's skills and abilities may also be adjusted according to the user's play style. This allows the system to provide an avatar tailored to the user's play style, resulting in a more personalized gaming experience.

[0065] The online game system may further include a quest customization unit that analyzes a user's play data and provides quests customized according to the user's play style. For example, the quest customization unit may analyze the type and difficulty of quests the user prefers and generate new quests based on that analysis. The quest customization unit may also adjust the rewards and goals of quests according to the user's play style. This allows the system to provide quests tailored to the user's play style, resulting in a more engaging game experience.

[0066] The processing flow of the first embodiment will be briefly explained below.

[0067] Step 1: The Sengoku warlord setting unit sets the initial state of the Sengoku warlord. For example, the Sengoku warlord setting unit sets the initial state of the warlord, such as the warlord's skills, equipment, and status. It can also set the warlord's background information and initial knowledge level. Step 2: The advice analyzer analyzes the user's advice prompt. For example, the advice analyzer analyzes and understands the text prompt entered by the user. It can also analyze prompts from different interfaces, such as voice input and gesture input. Step 3: The action suggestion unit suggests actions for the general based on the advice prompts analyzed by the advice analysis unit. For example, the action suggestion unit uses a generation AI (e.g., a text generation AI or a multimodal generation AI) to suggest specific actions for the general. It can also refer to past examples of success and failure to suggest optimal actions.

[0068] (Example 2) In the online game system according to the embodiment of the present invention, a user becomes a military strategist and gives advice to a Sengoku warlord (an AI personality) to help the warlord grow. In this way, the online game system allows the user to give advice to the Sengoku warlord and help the warlord grow.

[0069] The online game system according to the embodiment includes a Sengoku warlord setting unit, an advice analysis unit, and an action suggestion unit. The Sengoku warlord setting unit sets the initial state of the Sengoku warlord. For example, the Sengoku warlord setting unit initially sets the warlord's skills, equipment, status, and the like. The Sengoku warlord setting unit can also set the warlord's background information and initial knowledge level. The advice analysis unit analyzes the user's advice prompts. For example, the advice analysis unit analyzes text prompts entered by the user and understands their content. The advice analysis unit can also analyze prompts from different interfaces, such as voice input and gesture input. The action suggestion unit suggests actions for the warlord based on the advice prompts analyzed by the advice analysis unit. For example, the action suggestion unit uses a generation AI (e.g., a text generation AI or a multimodal generation AI) to suggest specific actions for the warlord. The action suggestion unit can also refer to past successes and failures to suggest optimal actions. This allows the online game system according to the embodiment to suggest actions for the Sengoku warlord based on the user's advice, thereby enabling the warlord to grow.

[0070] The Sengoku warlord setting unit can customize the initial state of a Sengoku warlord based on the historical background and culture selected by the user. The Sengoku warlord setting unit sets the initial state of a Sengoku warlord based on, for example, the historical background selected by the user. For example, it reflects the background of a different era or region, such as Japan during the Sengoku period or China during the Three Kingdoms period. The Sengoku warlord setting unit also customizes the initial state of a warlord based on the culture selected by the user. For example, it reflects specific customs, habits, and values. This allows the initial state of a Sengoku warlord to be customized according to the user's selection.

[0071] The Sengoku warlord setting unit can dynamically change the initial knowledge of a warlord based on the user's past play history and selections. The Sengoku warlord setting unit, for example, analyzes the user's past play history and sets the warlord's initial knowledge based on that. For example, it generates a warlord whose initial knowledge is tactics or strategies that have been successful in the past. The Sengoku warlord setting unit also dynamically changes the warlord's initial knowledge based on the user's selections. For example, it adjusts the warlord's knowledge level based on the actions selected by the user and the results achieved by the user. This makes it possible to dynamically change the warlord's initial knowledge based on the user's past play history and selections.

[0072] The Sengoku warlord setting unit can use the emotion estimation function to adjust the initial state of the warlord in accordance with the user's emotions. The Sengoku warlord setting unit, for example, analyzes the user's emotions in real time and adjusts the initial state of the warlord based on the results. For example, if the user has positive emotions, the initial state of the warlord is strengthened. The Sengoku warlord setting unit also uses the emotion estimation function to adjust the initial state of the warlord in accordance with the user's emotions. For example, if the user is feeling stressed, the initial state of the warlord is relaxed. This makes it possible to adjust the initial state of the warlord in accordance with the user's emotions.

[0073] The advice analysis unit can provide specific advice in response to a user's advice prompt by referring to past examples of success and failure. For example, the generation AI can provide specific advice in response to a user's advice prompt by referring to past examples of success. For example, advice can be given based on tactics and strategies that have been successful in the past. The advice analysis unit can also provide specific advice in response to a user's advice prompt by referring to past examples of failure. For example, advice can be given to avoid tactics and strategies that have failed in the past. In this way, specific advice can be provided by referring to past examples of success and failure.

[0074] The advice analysis unit can simulate multiple scenarios in response to the user's advice prompts and suggest the optimal action. For example, in response to the user's advice prompts, the generation AI simulates multiple scenarios and suggests the optimal action. For example, it simulates different tactics and strategies and selects the most effective action. The advice analysis unit also suggests the optimal action based on the simulation results in response to the user's advice prompts. For example, it suggests specific actions for the military commander based on the simulation results. This makes it possible to simulate multiple scenarios and suggest the optimal action.

[0075] The advice analysis unit uses the emotion estimation function to generate advice based on the user's emotions and reflect it in the actions of the warlord. The advice analysis unit, for example, uses the emotion estimation function to generate advice based on the user's emotions. For example, if the user is excited, it suggests aggressive tactics. The advice analysis unit also uses the emotion estimation function to generate advice based on the user's emotions and reflect it in the actions of the warlord. For example, if the user is relaxed, it suggests defensive tactics. In this way, advice based on the user's emotions can be generated and reflected in the actions of the warlord.

[0076] The advice analysis unit can enable input of advice prompts using different interfaces, such as voice input or gesture input. The advice analysis unit, for example, builds a system that enables input of advice prompts using voice input. For example, a user uses a microphone to input advice by voice. The advice analysis unit also builds a system that enables input of advice prompts using gesture input. For example, a user uses a camera to input advice by gesture. This makes it possible to input advice prompts using different interfaces, such as voice input or gesture input.

[0077] The advice analysis unit can add a community function that allows the generation AI to suggest optimal advice by referring to advice prompts from other users. The advice analysis unit, for example, adds a community function that allows other users to share advice prompts. For example, successful advice prompts are shared with other users. The advice analysis unit also refers to other users' advice prompts by allowing the generation AI to suggest optimal advice. For example, advice is given based on the success stories of other users. This allows the generation AI to refer to other users' advice prompts by adding a community function that allows the generation AI to suggest optimal advice.

[0078] The advice analysis unit uses the emotion estimation function to analyze the user's emotional response to the advice prompt and can propose optimal advice to other users. The advice analysis unit, for example, uses the emotion estimation function to analyze the user's emotional response to the advice prompt. For example, it proposes advice prompts with a high number of positive emotional responses to other users. The advice analysis unit also uses the emotion estimation function to analyze the user's emotional response to the advice prompt and proposes optimal advice to other users. For example, it provides specific advice to other users based on the emotional response. In this way, it is possible to use the emotion estimation function to analyze the user's emotional response to the advice prompt and propose optimal advice to other users.

[0079] The action suggestion unit can simulate the battle situation in real time in response to battle advice and propose optimal tactics. For example, the action suggestion unit constructs a system in which a generation AI simulates the battle situation in real time in response to battle advice and proposes optimal tactics. For example, the tactics are adjusted according to changes in the battle situation. The action suggestion unit also simulates the battle situation in real time and proposes optimal tactics. For example, specific tactics are proposed to military commanders according to changes in the battle situation. This makes it possible to simulate the battle situation in real time and propose optimal tactics.

[0080] The action suggestion unit can refer to past tactical data based on the battle advice and suggest tactics with a high success rate. The action suggestion unit, for example, builds a system in which a generation AI refers to past tactical data based on the battle advice and suggests tactics with a high success rate. For example, it analyzes past battle data and selects the optimal tactic. The action suggestion unit also refers to past tactical data and suggests tactics with a high success rate. For example, it provides advice based on tactics that have been successful in the past. This makes it possible to refer to past tactical data and suggest tactics with a high success rate.

[0081] The action suggestion unit uses the emotion estimation function to suggest tactics based on the user's emotions, thereby increasing the morale of the general. The action suggestion unit, for example, uses the emotion estimation function to suggest tactics based on the user's emotions. For example, if the user is excited, it suggests aggressive tactics. The action suggestion unit also uses the emotion estimation function to suggest tactics based on the user's emotions, thereby increasing the morale of the general. For example, if the user is relaxed, it suggests defensive tactics. In this way, it is possible to suggest tactics based on the user's emotions and increase the morale of the general.

[0082] The action suggestion unit can apply the battle advice to different historical battle scenarios, allowing different tactics to be tried. The action suggestion unit, for example, builds a system that applies the battle advice to different historical battle scenarios and allows different tactics to be tried. For example, tactics are tried in different scenarios, such as Japan during the Warring States period or China during the Three Kingdoms period. The action suggestion unit also suggests specific tactics to military commanders based on different historical battle scenarios. For example, it recreates specific wars or battles and tries out the optimal tactics within those scenarios. This allows the battle advice to be applied to different historical battle scenarios and allows different tactics to be tried.

[0083] The action suggestion unit can add a sharing function that allows the generation AI to propose optimal tactics by referring to the battle advice of other users. The action suggestion unit, for example, adds a function that allows sharing of battle advice from other users, and builds a system in which the generation AI proposes optimal tactics. For example, successful tactics are shared with other users. The action suggestion unit also refers to the battle advice of other users, and the generation AI proposes optimal tactics. For example, tactics are proposed based on successful examples of other users. This allows a sharing function to be added that allows the generation AI to propose optimal tactics by referring to the battle advice of other users.

[0084] The action suggestion unit uses the emotion estimation function to analyze the user's emotional response to the battle advice and can suggest optimal tactics to other users. The action suggestion unit, for example, uses the emotion estimation function to analyze the user's emotional response to the battle advice. For example, the action suggestion unit suggests advice that has a high percentage of positive emotional responses to other users. The action suggestion unit also uses the emotion estimation function to analyze the user's emotional response to the battle advice and suggests optimal tactics to other users. For example, the action suggestion unit suggests specific tactics to other users based on the emotional response. In this way, the emotion estimation function can be used to analyze the user's emotional response to the battle advice and suggest optimal tactics to other users.

[0085] The action suggestion unit can propose customized education plans for vassal education based on the characteristics and abilities of each vassal. The action suggestion unit, for example, analyzes the characteristics and abilities of each vassal and builds a system that proposes customized education plans based on the results. For example, it proposes education plans to strengthen specific skills. The action suggestion unit also proposes customized education plans based on the characteristics and abilities of each vassal. For example, it proposes education methods that suit the vassal's personality and skills. This makes it possible to propose customized education plans based on the characteristics and abilities of each vassal.

[0086] The action suggestion unit can refer to past educational data when giving advice on vassal education and suggest the most appropriate educational method. For example, the action suggestion unit constructs a system in which, when giving advice on vassal education, the generation AI refers to past educational data and suggests the most appropriate educational method. For example, advice is given based on educational methods that have been successful in the past. The action suggestion unit also refers to past educational data and suggests the most appropriate educational method. For example, advice is given based on past educational plans and educational results. This makes it possible to refer to past educational data and suggest the most appropriate educational method.

[0087] The action suggestion unit uses the emotion estimation function to suggest a training method based on the user's emotions, thereby increasing the motivation of the vassals. The action suggestion unit, for example, uses the emotion estimation function to suggest a training method based on the user's emotions. For example, if the user is excited, it suggests an active training method. The action suggestion unit also uses the emotion estimation function to suggest a training method based on the user's emotions, thereby increasing the motivation of the vassals. For example, if the user is relaxed, it suggests a relaxed training method. In this way, it is possible to suggest a training method based on the user's emotions and increase the motivation of the vassals.

[0088] The action suggestion unit can expand the education of vassals to customized education plans according to different occupations and roles. The action suggestion unit, for example, builds a system that expands the education of vassals to customized education plans according to different occupations and roles. For example, it proposes education plans according to different occupations such as military commander, merchant, farmer, etc. The action suggestion unit also proposes education plans according to the role of the vassal. For example, it proposes an education plan to strengthen skills required for a specific role. This makes it possible to expand the education of vassals to customized education plans according to different occupations and roles.

[0089] The action suggestion unit can add a sharing function that allows the generation AI to refer to other users' vassal training advice and suggest the most appropriate training method. The action suggestion unit, for example, adds a function to share other users' vassal training advice and builds a system in which the generation AI suggests the most appropriate training method. For example, successful training methods are shared with other users. The action suggestion unit also refers to other users' vassal training advice and allows the generation AI to suggest the most appropriate training method. For example, a training method is suggested based on other users' successful examples. This allows the generation AI to refer to other users' vassal training advice and suggest the most appropriate training method.

[0090] The action suggestion unit uses the emotion estimation function to analyze the user's emotional response to vassal training advice and can suggest optimal training methods to other users. The action suggestion unit, for example, uses the emotion estimation function to analyze the user's emotional response to vassal training advice. For example, it suggests advice that has a high percentage of positive emotional responses to other users. The action suggestion unit also uses the emotion estimation function to analyze the user's emotional response to vassal training advice and suggests optimal training methods to other users. For example, it suggests specific training methods to other users based on the emotional responses. In this way, it is possible to use the emotion estimation function to analyze the user's emotional response to vassal training advice and suggest optimal training methods to other users.

[0091] The action suggestion unit can refer to regional population data and economic conditions when providing conscription advice and propose the optimal conscription method. For example, the action suggestion unit constructs a system in which, when providing conscription advice, the generation AI refers to regional population data and proposes the optimal conscription method. For example, conscript soldiers from areas with high population density. The action suggestion unit also refers to regional economic conditions and proposes the optimal conscription method. For example, conscript soldiers from areas where economic growth is expected. This makes it possible to refer to regional population data and economic conditions and propose the optimal conscription method.

[0092] The action suggestion unit can refer to past conscription data based on the conscription advice and suggest a conscription method with a high success rate. For example, the action suggestion unit builds a system in which, based on the conscription advice, the generation AI refers to past conscription data and suggests a conscription method with a high success rate. For example, advice is given based on conscription methods that have been successful in the past. The action suggestion unit also refers to past conscription data and suggests a conscription method with a high success rate. For example, advice is given based on past conscription records and success rates. This makes it possible to refer to past conscription data and suggest a conscription method with a high success rate.

[0093] The action suggestion unit uses the emotion estimation function to suggest a conscription method based on the user's emotions, thereby increasing the morale of the soldiers. The action suggestion unit, for example, uses the emotion estimation function to suggest a conscription method based on the user's emotions. For example, if the user is excited, the action suggestion unit suggests an aggressive conscription method. The action suggestion unit also uses the emotion estimation function to suggest a conscription method based on the user's emotions, thereby increasing the morale of the soldiers. For example, if the user is relaxed, the action suggestion unit suggests a relaxed conscription method. In this way, the action suggestion unit suggests a conscription method based on the user's emotions, thereby increasing the morale of the soldiers.

[0094] The action suggestion unit can expand the conscription advice to customized conscription methods according to different regions and cultures. The action suggestion unit, for example, builds a system that expands the conscription advice to customized conscription methods according to different regions and cultures. For example, it proposes conscription methods that suit local customs and cultures. The action suggestion unit also proposes specific conscription methods to military commanders based on different regions and cultures. For example, it proposes conscription methods that are suitable for specific regions and cultures. This makes it possible to expand the conscription advice to customized conscription methods according to different regions and cultures.

[0095] The action suggestion unit can add a sharing function that enables the generation AI to propose the optimal conscription method by referring to the conscription advice of other users. The action suggestion unit, for example, adds a function to share the conscription advice of other users, and builds a system in which the generation AI proposes the optimal conscription method. For example, successful conscription methods are shared with other users. The action suggestion unit also refers to the conscription advice of other users, and enables the generation AI to propose the optimal conscription method. For example, a conscription method is proposed based on the success stories of other users. This allows the generation AI to refer to the conscription advice of other users and add a sharing function that enables the generation AI to propose the optimal conscription method.

[0096] The action suggestion unit uses the emotion estimation function to analyze the user's emotional response to the conscription advice and can suggest the optimal conscription method to other users. The action suggestion unit, for example, uses the emotion estimation function to analyze the user's emotional response to the conscription advice. For example, it suggests advice that has a high percentage of positive emotional responses to other users. The action suggestion unit also uses the emotion estimation function to analyze the user's emotional response to the conscription advice and suggests the optimal conscription method to other users. For example, it suggests a specific conscription method to other users based on the emotional response. In this way, it is possible to use the emotion estimation function to analyze the user's emotional response to the conscription advice and suggest the optimal conscription method to other users.

[0097] The action suggestion unit can refer to regional economic data and demographics when providing advice on city development and propose the optimal city development method. For example, the action suggestion unit constructs a system in which the generation AI refers to regional economic data when providing advice on city development and proposes the optimal city development method. For example, it may set up a market in an area where economic growth is expected. The action suggestion unit also refers to regional demographics and proposes the optimal city development method. For example, it may build housing in an area where population growth is expected. This makes it possible to refer to regional economic data and demographics and propose the optimal city development method.

[0098] The action suggestion unit can refer to past city development data based on the city development advice and propose city development methods with a high success rate. For example, the action suggestion unit builds a system in which the generation AI refers to past city development data and proposes city development methods with a high success rate based on the city development advice. For example, advice is given based on city development methods that have been successful in the past. The action suggestion unit also refers to past city development data and proposes city development methods with a high success rate. For example, advice is given based on past city development plans and success rates. This makes it possible to refer to past city development data and propose city development methods with a high success rate.

[0099] The action suggestion unit uses the emotion estimation function to suggest a city development method based on the user's emotions, thereby increasing resident satisfaction. The action suggestion unit, for example, uses the emotion estimation function to suggest a city development method based on the user's emotions. For example, if the user is excited, the action suggestion unit suggests an aggressive city development method. The action suggestion unit also uses the emotion estimation function to suggest a city development method based on the user's emotions, thereby increasing resident satisfaction. For example, if the user is relaxed, the action suggestion unit suggests a relaxed city development method. In this way, a city development method based on the user's emotions can be suggested, thereby increasing resident satisfaction.

[0100] The action suggestion unit can expand the city planning advice to a customized city planning method that suits different regions and cultures. The action suggestion unit, for example, builds a system that expands the city planning advice to a customized city planning method that suits different regions and cultures. For example, it proposes a city planning method that suits local customs and cultures. The action suggestion unit also proposes specific city planning methods based on different regions and cultures. For example, it proposes a city planning method that suits a specific region or culture. In this way, the city planning advice can be expanded to a customized city planning method that suits different regions and cultures.

[0101] The action suggestion unit can add a sharing function that enables the generation AI to propose the optimal city development method by referring to city development advice from other users. The action suggestion unit, for example, adds a function to share city development advice from other users, and builds a system in which the generation AI proposes the optimal city development method. For example, successful city development methods are shared with other users. The action suggestion unit also refers to city development advice from other users, and enables the generation AI to propose the optimal city development method. For example, a city development method is proposed based on successful examples from other users. This allows the generation AI to refer to city development advice from other users, and adds a sharing function that enables the generation AI to propose the optimal city development method.

[0102] The action suggestion unit uses the emotion estimation function to analyze the user's emotional response to the city development advice and can suggest the most suitable city development method to other users. The action suggestion unit, for example, uses the emotion estimation function to analyze the user's emotional response to the city development advice. For example, it suggests advice that has a high percentage of positive emotional responses to other users. The action suggestion unit also uses the emotion estimation function to analyze the user's emotional response to the city development advice and suggests the most suitable city development method to other users. For example, it suggests a specific city development method to other users based on the emotional response. In this way, it is possible to use the emotion estimation function to analyze the user's emotional response to the city development advice and suggest the most suitable city development method to other users.

[0103] The action suggestion unit can refer to regional climate data and soil data when providing cultivation advice and suggest the optimal cultivation method. For example, the action suggestion unit constructs a system in which, when providing cultivation advice, the generation AI refers to regional climate data and suggests the optimal cultivation method. For example, it selects crops that are suitable for the climatic conditions. The action suggestion unit also refers to regional soil data and suggests the optimal cultivation method. For example, it selects crops based on the soil components and fertility. This makes it possible to refer to regional climate data and soil data and suggest the optimal cultivation method.

[0104] The action suggestion unit can refer to past cultivation data based on the cultivation advice and suggest cultivation methods with a high success rate. For example, the action suggestion unit constructs a system in which, based on the cultivation advice, the generation AI refers to past cultivation data and suggests cultivation methods with a high success rate. For example, advice is given based on cultivation methods that have been successful in the past. The action suggestion unit also refers to past cultivation data and suggests cultivation methods with a high success rate. For example, advice is given based on past cultivation records and success rates. This makes it possible to refer to past cultivation data and suggest cultivation methods with a high success rate.

[0105] The action suggestion unit uses the emotion estimation function to suggest a cultivation method based on the user's emotions, thereby increasing the motivation of the farmer. The action suggestion unit, for example, uses the emotion estimation function to suggest a cultivation method based on the user's emotions. For example, if the user is excited, it suggests an aggressive cultivation method. The action suggestion unit also uses the emotion estimation function to suggest a cultivation method based on the user's emotions, thereby increasing the motivation of the farmer. For example, if the user is relaxed, it suggests a relaxed cultivation method. In this way, it is possible to suggest a cultivation method based on the user's emotions and increase the motivation of the farmer.

[0106] The action suggestion unit can expand the cultivation advice to customized cultivation methods according to different regions and climates. For example, the action suggestion unit builds a system that expands the cultivation advice to customized cultivation methods according to different regions and climates. For example, it proposes cultivation methods that suit the climatic conditions of the region. The action suggestion unit also proposes specific cultivation methods based on different regions and climates. For example, it proposes cultivation methods that are suitable for specific regions and climates. This allows the cultivation advice to be expanded to customized cultivation methods according to different regions and climates.

[0107] The action suggestion unit can add a sharing function that enables the generation AI to suggest the optimal cultivation method by referring to the cultivation advice of other users. The action suggestion unit, for example, adds a function to share the cultivation advice of other users, and builds a system in which the generation AI suggests the optimal cultivation method. For example, successful cultivation methods are shared with other users. The action suggestion unit also refers to the cultivation advice of other users, and the generation AI suggests the optimal cultivation method. For example, a cultivation method is suggested based on the success stories of other users. This allows the generation AI to refer to the cultivation advice of other users and add a sharing function that enables the generation AI to suggest the optimal cultivation method.

[0108] The action suggestion unit uses the emotion estimation function to analyze the user's emotional response to the farming advice and can suggest optimal farming methods to other users. The action suggestion unit, for example, uses the emotion estimation function to analyze the user's emotional response to the farming advice. For example, it suggests advice that has a high number of positive emotional responses to other users. The action suggestion unit also uses the emotion estimation function to analyze the user's emotional response to the farming advice and suggests optimal farming methods to other users. For example, it suggests specific farming methods to other users based on the emotional responses. In this way, it is possible to use the emotion estimation function to analyze the user's emotional response to the farming advice and suggest optimal farming methods to other users.

[0109] The action suggestion unit allows the generation AI to refer to the user's past play data and make a fairer evaluation in an evaluation system for online battles. The action suggestion unit, for example, builds a system in an evaluation system for online battles in which the generation AI refers to the user's past play data and makes a fairer evaluation. For example, the evaluation is made based on past battle results and behavior patterns. The action suggestion unit also analyzes the user's past play data and makes an evaluation based on that. For example, the evaluation is made based on play time, selected actions, and achieved results. This allows the generation AI to refer to the user's past play data and make a fairer evaluation in an evaluation system for online battles.

[0110] The action suggestion unit enables the generation AI to analyze the user's actions in real time and provide instant feedback in an evaluation system for online battles. The action suggestion unit, for example, builds a system in an evaluation system for online battles in which the generation AI analyzes the user's actions in real time and provides instant feedback. For example, it evaluates the selection of tactics and the timing of actions. The action suggestion unit also analyzes the user's actions in real time and provides instant feedback based on that. For example, it evaluates the user's actions in real time and provides feedback. This enables the generation AI to analyze the user's actions in real time and provide instant feedback in an evaluation system for online battles.

[0111] The action suggestion unit uses the emotion estimation function to make an evaluation based on the user's emotions, thereby realizing a more emotionally satisfying match. The action suggestion unit, for example, uses the emotion estimation function to build a system that makes an evaluation based on the user's emotions. For example, if the user is excited, it evaluates proactive behavior. The action suggestion unit also uses the emotion estimation function to make an evaluation based on the user's emotions, thereby realizing a more emotionally satisfying match. For example, it adjusts the evaluation criteria for the match depending on the user's emotions. In this way, the emotion estimation function can be used to make an evaluation based on the user's emotions, thereby realizing a more emotionally satisfying match.

[0112] The action suggestion unit can apply the rating system for online battles to different game modes and scenarios to provide a variety of battle formats. The action suggestion unit, for example, applies the rating system for online battles to different game modes and scenarios to build a system that provides a variety of battle formats. For example, different battle formats such as team battles and individual battles are provided. The action suggestion unit also adjusts the rating system based on different game modes and scenarios. For example, it sets evaluation criteria according to the progress method of a specific storyline or mission. This allows the rating system for online battles to be applied to different game modes and scenarios to provide a variety of battle formats.

[0113] The action suggestion unit can add a sharing function that allows the generation AI to propose optimal evaluation criteria by referring to the evaluation data of other users. The action suggestion unit, for example, adds a function to share the evaluation data of other users, and builds a system in which the generation AI proposes optimal evaluation criteria. For example, successful evaluation criteria are shared with other users. The action suggestion unit also refers to the evaluation data of other users, and the generation AI proposes optimal evaluation criteria. For example, evaluation criteria are set based on the success stories of other users. This allows the generation AI to refer to the evaluation data of other users and add a sharing function that allows the generation AI to propose optimal evaluation criteria.

[0114] The action suggestion unit uses the emotion estimation function to analyze the user's emotional response to the match evaluation and can propose optimal evaluation criteria to other users. The action suggestion unit, for example, uses the emotion estimation function to analyze the user's emotional response to the match evaluation. For example, it proposes to other users evaluation criteria with a high proportion of positive emotional responses. The action suggestion unit also uses the emotion estimation function to analyze the user's emotional response to the match evaluation and proposes optimal evaluation criteria to other users. For example, it proposes specific evaluation criteria to other users based on the emotional response. In this way, it is possible to use the emotion estimation function to analyze the user's emotional response to the match evaluation and propose optimal evaluation criteria to other users.

[0115] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0116] The online game system may further include a health management unit that monitors the user's health condition. For example, the health management unit may monitor the user's heart rate and stress level in real time and encourage the user to take a break at an appropriate time. The health management unit may also adjust in-game activities based on the user's health data. For example, if the user is tired, the in-game difficulty may be temporarily lowered. This allows gameplay that takes the user's health condition into consideration.

[0117] The online game system may further include a learning analysis unit that analyzes the user's learning history. For example, the learning analysis unit may analyze the tactics and strategies the user has learned in the past and suggest new learning content based on the results. The learning analysis unit may also prompt the user to review the tactics at an appropriate time according to the user's learning pace. For example, if the user is starting to forget a particular tactic, the system may provide a quiz or mini-game related to that tactic. This may improve the user's learning effectiveness.

[0118] The online game system may further include a play style analysis unit that analyzes a user's play style. For example, the play style analysis unit may analyze the user's preferred tactics and behavioral patterns and provide a customized game experience based on the analysis. The play style analysis unit may also provide appropriate advice and hints depending on the user's play style. For example, if the user prefers an offensive play style, the play style analysis unit may suggest tactics specialized for attacking. This allows for a game experience tailored to the user's play style.

[0119] The online game system may further include an audio adjustment unit that estimates the user's emotions and adjusts the in-game music and sound effects based on the estimated emotions. For example, the audio adjustment unit may play soft music when the user is relaxed, or fast-paced music when the user is excited. This provides an audio environment that corresponds to the user's emotions, resulting in a more immersive gaming experience.

[0120] The online game system may further include a character adjustment unit that estimates the user's emotions and adjusts the facial expressions and behavior of the in-game character based on the estimated emotions. For example, if the user is sad, the character may use a comforting facial expression or behavior. Alternatively, if the user is happy, the character may use a joyful facial expression or behavior. This allows the character to respond in accordance with the user's emotions, creating a stronger emotional connection.

[0121] The online game system may further include a scenario adjustment unit that estimates the user's emotions and adjusts in-game events and scenarios based on the estimated emotions. For example, the scenario adjustment unit may provide a relaxing event if the user is feeling stressed. Alternatively, the scenario adjustment unit may provide a high-action event if the user is excited. This allows the system to provide a scenario that matches the user's emotions, resulting in a more personalized game experience.

[0122] The online game system may further include a reward adjustment unit that estimates the user's emotions and adjusts in-game rewards and items based on the estimated emotions. For example, if the user is feeling down, the reward adjustment unit may provide a special item to increase the user's motivation. Alternatively, if the user is feeling happy, the reward adjustment unit may provide a reward that gives the user a greater sense of accomplishment. This allows the user to receive rewards according to their emotions and increase their enjoyment of the game.

[0123] The online game system may further include a difficulty adjustment unit that estimates a user's emotions and adjusts the in-game difficulty based on the estimated emotions. For example, the difficulty adjustment unit may lower the game difficulty if the user is feeling stressed. Alternatively, the difficulty adjustment unit may increase the game difficulty if the user is seeking a challenge. This allows the difficulty to be adjusted according to the user's emotions, providing a more appropriate game experience.

[0124] The online game system may further include an avatar customization unit that analyzes a user's play data and provides an avatar customized according to the user's play style. For example, the avatar customization unit may analyze the user's preferred equipment and appearance and automatically customize the avatar based on that information. The avatar's skills and abilities may also be adjusted according to the user's play style. This allows the system to provide an avatar tailored to the user's play style, resulting in a more personalized gaming experience.

[0125] The online game system may further include a quest customization unit that analyzes a user's play data and provides quests customized according to the user's play style. For example, the quest customization unit may analyze the type and difficulty of quests the user prefers and generate new quests based on that analysis. The quest customization unit may also adjust the rewards and goals of quests according to the user's play style. This allows the system to provide quests tailored to the user's play style, resulting in a more engaging game experience.

[0126] The processing flow of the second embodiment will be briefly explained below.

[0127] Step 1: The Sengoku warlord setting unit sets the initial state of the Sengoku warlord. For example, the Sengoku warlord setting unit sets the initial state of the warlord, such as the warlord's skills, equipment, and status. It can also set the warlord's background information and initial knowledge level. Step 2: The advice analyzer analyzes the user's advice prompt. For example, the advice analyzer analyzes and understands the text prompt entered by the user. It can also analyze prompts from different interfaces, such as voice input and gesture input. Step 3: The action suggestion unit suggests actions for the general based on the advice prompts analyzed by the advice analysis unit. For example, the action suggestion unit uses a generation AI (e.g., a text generation AI or a multimodal generation AI) to suggest specific actions for the general. It can also refer to past examples of success and failure to suggest optimal actions.

[0128] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0129] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0130] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0131] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0132] 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.

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

[0134] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

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

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

[0137] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0138] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

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

[0140] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0141] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0142] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0143] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0145] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0146] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0147] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0148] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0149] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0150] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0152] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0153] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0154] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0155] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0156] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0157] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0158] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0159] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0160] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0161] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0162] 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.

[0163] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0164] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0165] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0166] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0167] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0168] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0169] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0170] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0171] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0172] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0173] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0174] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0175] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0176] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0177] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0178] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0179] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0180] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0181] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0182] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0183] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0184] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0185] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0186] 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.

[0187] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0188] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0189] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0190] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0191] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0192] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0193] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0194] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a Sengoku warlord setting section for setting the initial state of the Sengoku warlord; an advice analyzer for analyzing a user's advice prompt; an action suggestion unit that suggests an action for the warlord based on the advice prompt analyzed by the advice analysis unit; A system characterized by:

2. The Sengoku warlord setting unit Dynamically changing the initial knowledge of the warlord based on the user's past play history and selections The system of claim 1 .

3. The advice analysis unit In response to the user's advice prompt, specific advice is provided by referring to past successes and failures. The system of claim 1 .

4. The action suggestion unit Simulates battle situations in real time based on battle advice and proposes optimal tactics The system of claim 1 .

5. The action suggestion unit Propose customized educational plans for each vassal based on their individual characteristics and abilities. The system of claim 1 .

6. The action suggestion unit When advising on conscription, the system refers to local population data and economic conditions to suggest the most appropriate method of conscription. The system of claim 1 .

7. The action suggestion unit We will propose the most suitable urban development method for the city planning advice by referring to regional economic data and demographics. The system of claim 1 .

8. The action suggestion unit Using emotion estimation function, the system proposes cultivation methods based on the user's emotions, thereby increasing farmers' motivation. The system of claim 1 .

Images