System

Abstract

To convert an abstract instruction by voice or text into a concrete motion, and generate an original character.SOLUTION: A system according to an embodiment includes a reception unit, a motion generation unit, a character generation unit, and an application unit. The reception unit receives an instruction by a voice of a user or a text. The motion generation unit analyzes the instruction received by the reception unit and generates a concrete motion. The character generation unit generates an original character on the basis of features input by the user. The application unit applies the motion generated by the motion generation unit to the character generated by the character generation 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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult to convert abstract voice or text instructions into concrete actions, and it was also difficult to create original characters for users to control.

[0005] The system according to the embodiment aims to convert abstract voice or text instructions into concrete actions and generate original characters. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a motion generation unit, a character generation unit, and an application unit. The reception unit receives voice or text instructions from a user. The motion generation unit analyzes the instructions received by the reception unit and generates specific motions. The character generation unit generates an original character based on features input by the user. The application unit applies the motions generated by the motion generation unit to the character generated by the character generation unit. Effect of the Invention

[0007] The system according to the embodiment can convert abstract voice or text instructions into concrete actions and generate original characters. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the 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 specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

[0028] (Example 1) The game operation system according to the embodiment of the present invention is a system that utilizes a generation AI to convert abstract instructions by voice or text into specific game operations. In this system, when a user inputs an abstract instruction such as "punch" or "kick," the generation AI analyzes the instruction and converts it into a specific action in the game. For example, when the user instructs "punch," the generation AI generates a specific action such as "right straight punch" or "left hook punch" depending on the situation. Furthermore, the character operated by the user can also be created as an original character using the generation AI. When a user inputs the characteristics and appearance of a character in text, the generation AI generates a character based on that information. For example, when "a character with blue hair and red eyes" is input, the generation AI generates a character with that characteristic. This mechanism allows the user to operate the game even with abstract instructions and to create an original character. As a result, the game operation system can convert the user's voice or text instructions into specific game operations and generate an original character.

[0029] The game operation system according to the embodiment includes a reception unit, a motion generation unit, a character generation unit, and an application unit. The reception unit receives a user's voice or text instruction. The user's voice or text instruction includes, but is not limited to, abstract instructions such as "punch" and "kick". The reception unit converts the voice instruction into text using, for example, a voice recognition technology. The reception unit also provides a text input interface, and the user can directly input text instructions. The motion generation unit uses a generation AI to analyze the instruction received by the reception unit and generate a specific motion. The motion generation unit uses, for example, a natural language processing technology to analyze the meaning of the instruction and generate a specific motion according to the situation. For example, when "punch" is instructed, the motion generation unit uses the generation AI to generate a specific motion such as "right straight punch" or "left hook punch". The character generation unit uses the generation AI to generate an original character based on the characteristics input by the user. For example, when the user inputs "a character with blue hair and red eyes", the character generation unit uses the generation AI to generate a character with the characteristics. The character generation unit uses a generation AI to generate a character based on characteristics such as the character's appearance and personality. The application unit applies the generated motion to the generated character. For example, the application unit applies the generated motion of "right straight punch" to the generated character and executes it in the game. The application unit can also use the generation AI to adjust the application method of the motion. For example, the application unit adjusts the timing and speed of the generated motion and applies it to the character. In this way, the game operation system according to the embodiment can convert the user's voice or text instructions into specific game operations and generate an original character.

[0030] The reception unit receives a voice or text instruction from the user. The user's voice or text instruction includes, but is not limited to, abstract instructions such as "punch" and "kick". The reception unit converts the voice instruction into text, for example, using a voice recognition technology. Specifically, the voice recognition technology includes a process of converting the user's voice into a digital signal, analyzing the signal, and converting it into text data. The voice recognition technology achieves accurate text conversion using advanced algorithms such as noise removal, voice feature extraction, and phoneme identification. The reception unit also provides a text input interface, allowing the user to directly input text instructions. The text input interface is designed to support input methods using a keyboard or a touch screen, allowing the user to easily input instructions. Furthermore, the reception unit has a feedback function for eliminating ambiguity in instructions when receiving a user's instruction. For example, if the user instructs "attack", the reception unit displays a confirmation message such as "Is it a punch? Is it a kick?" to clarify the user's intention. This allows the reception unit to accurately receive the user's voice or text instruction and pass it on to the next process.

[0031] The motion generation unit uses the generation AI to analyze the instruction received by the reception unit and generate a specific motion. The motion generation unit, for example, uses natural language processing technology to analyze the meaning of the instruction and generate a specific motion according to the situation. Natural language processing technology is a technology for analyzing text data and understanding its meaning, and performs analysis taking into account the context and meaning of the words. For example, when the instruction is "punch," the motion generation unit uses the generation AI to generate a specific motion such as "right straight punch" or "left hook punch." The generation AI has the ability to learn a large amount of data and generate motions according to various situations. For example, the generation AI learns past game play data and actual martial arts motion data, and generates optimal motions based on the user's instructions. Furthermore, the motion generation unit makes adjustments taking into account the continuity and smoothness of the motion so that the generated motion looks natural in the game. For example, the start position and end position of the motion are adjusted so that the transition from the previous motion to the next motion is smooth. As a result, the motion generation unit can generate specific and natural motions based on the user's instructions and realize operations in the game.

[0032] The character generation unit uses the generation AI to generate an original character based on the characteristics input by the user. For example, when the user inputs "a character with blue hair and red eyes," the character generation unit uses the generation AI to generate a character with those characteristics. The generation AI utilizes image generation technology and a character design database to generate the character's appearance and personality based on the user's instructions. For example, the generation AI designs the character's appearance taking into account the characteristics such as hair color, eye color, and clothing specified by the user. The generation AI can also generate the character's personality and behavior patterns. For example, if the user instructs "a brave and friendly character," the generation AI generates the character's behavior patterns and lines based on that personality. Furthermore, the character generation unit adjusts the character's actions and facial expressions so that the generated character looks natural in the game. For example, when the character expresses emotions, the character makes adjustments to make the facial expressions and body movements look natural. This allows the character generation unit to generate an original character based on the user's instructions, improving the play experience in the game.

[0033] The application unit applies the generated motion to the generated character. For example, the application unit applies the generated "right straight punch" motion to the generated character and executes it in the game. The application unit can also adjust the application method of the motion using the generation AI. For example, the application unit adjusts the timing and speed of the generated motion and applies it to the character. Specifically, the application unit applies the generated motion to the character using the character's skeletal model and animation data. The skeletal model defines the position and movement of each part of the character's body, and the animation data is data that expresses continuous changes in motion. The application unit uses these data to make adjustments so that the generated motion is naturally applied to the character. For example, the arm movement and body balance are adjusted so that the punch motion appears smooth. In addition, the application unit also takes into account the character's surrounding environment and interactions with other characters when applying the motion. For example, when a punch motion hits another character, the effect is calculated in real time and an appropriate reaction is generated. This allows the application unit to naturally apply the generated motion to the character and realize realistic motion in the game.

[0034] The motion generation unit can analyze the user's voice or text instructions and generate specific motions according to the situation. The motion generation unit, for example, uses natural language processing technology to analyze the user's voice or text instructions. For example, when the motion generation unit receives an instruction to "punch," it uses a generation AI to analyze the meaning of the instruction and generates specific motions according to the situation. For example, the motion generation unit generates specific motions such as "right straight punch" and "left hook punch" in consideration of the situation in the game. The motion generation unit can also generate optimal motions based on the user's past actions and in-game scenarios. For example, the motion generation unit refers to the motion history when the user previously instructed "punch" and generates optimal motions in a similar situation. This allows the motion generation unit to convert the user's abstract instructions into specific motions.

[0035] The character generation unit can generate an original character based on the characteristics input by the user. For example, when the user inputs "a character with blue hair and red eyes," the character generation unit uses a generation AI to generate a character with the characteristics. The character generation unit uses the generation AI to generate a character based on characteristics such as the character's appearance and personality. For example, the character generation unit analyzes the characteristics input by the user and generates the character's appearance based on the characteristics. The character generation unit can also set the character's personality, skills, etc. based on the characteristics input by the user. For example, when the character generation unit inputs "a character with a brave personality and excellent swordsmanship," the character generation unit uses the generation AI to generate a character with the characteristics. This allows the character generation unit to generate an original character based on the characteristics input by the user.

[0036] The application unit can apply the generated motion to the generated character. For example, the application unit applies the generated motion of "right straight punch" to the generated character and executes it in the game. The application unit can also adjust the application method of the motion using the generation AI. For example, the application unit adjusts the timing and speed of the generated motion and applies it to the character. The application unit can also apply the generated motion according to the situation in the game. For example, the application unit applies an attack motion to a character in combat and applies a search motion to a character in search. In this way, the application unit can apply the generated motion to the generated character.

[0037] The reception unit can analyze the user's past instruction history and select an appropriate reception method. The reception unit, for example, stores the user's past instruction history in a database and analyzes it. For example, the reception unit preferentially suggests an instruction method (such as voice or text) that the user has used frequently in the past. The reception unit can also predict and suggest an instruction method to be used in a specific time period from the user's past instruction history. For example, if the user has used voice instructions a lot in a specific time period in the past, the reception unit preferentially suggests voice instructions in that time period. Furthermore, the reception unit can automatically complement related instructions based on the instruction contents input by the user in the past. For example, the reception unit refers to the operation history when the user has previously instructed "punch" and suggests related instructions such as "kick" in a similar situation. This allows the reception unit to select an optimal reception method based on the user's past instruction history.

[0038] The reception unit can perform filtering based on the user's current game progress when receiving an instruction. The reception unit, for example, stores the user's current game progress in a database and analyzes it. For example, when the user is in a specific stage, the reception unit only receives instructions related to that stage. In addition, when the user is in a boss battle, the reception unit can also preferentially receive instructions related to the battle. Furthermore, when the user is searching, the reception unit can also preferentially receive instructions related to the search. For example, when the user instructs "search for an item" during a search, the reception unit preferentially receives instructions related to the search. This allows the reception unit to filter instructions based on the user's current game progress.

[0039] When receiving an instruction, the reception unit can preferentially receive an instruction with high relevance in consideration of the geographical location information of the user. The reception unit, for example, acquires and analyzes the geographical location information of the user. For example, the reception unit identifies the user's current location using GPS data or an IP address. When the user is in a specific area, the reception unit preferentially receives an instruction related to the area. For example, when the user is traveling, the reception unit preferentially receives an instruction related to the travel. In addition, when the user is at home, the reception unit can also preferentially receive an instruction related to activities at home. Furthermore, the reception unit can also suggest an instruction with high relevance based on the geographical location information of the user. For example, when the user is in a specific area, the reception unit suggests an event or activity related to the area. This allows the reception unit to preferentially receive an instruction with high relevance based on the geographical location information of the user.

[0040] The reception unit can analyze the user's social media activity and receive related instructions when receiving the instruction. The reception unit, for example, stores the user's social media activity in a database and analyzes it. For example, the reception unit receives related instructions based on information shared by the user on social media. The reception unit can also receive related instructions based on the activity of an account the user follows on social media. Furthermore, the reception unit can receive instructions related to an event the user is participating in on social media. For example, the reception unit receives travel-related instructions based on travel photos shared by the user on social media. This allows the reception unit to receive related instructions based on the user's social media activity.

[0041] The motion generation unit can adjust the level of detail of the motion based on the situation in the game when generating the motion. The motion generation unit, for example, stores the situation in the game in a database and analyzes it. For example, when the user is in a boss battle, the motion generation unit generates detailed combat motions. Also, when the user is exploring, the motion generation unit can generate motions suitable for exploration. Furthermore, when the user is taking a break, the motion generation unit can generate a relaxed motion. For example, when the user instructs "relax" during a break, the motion generation unit generates a relaxed motion. This allows the motion generation unit to adjust the level of detail of the motion based on the situation in the game.

[0042] The motion generation unit can apply different motion generation algorithms depending on the attributes of the character when generating motion. The motion generation unit, for example, stores the attributes of the character in a database and analyzes them. For example, if the character is a warrior, the motion generation unit generates motions specialized for combat. Also, if the character is a magician, the motion generation unit can also generate motions related to magic. Furthermore, if the character is a thief, the motion generation unit can also generate motions suitable for stealth action. For example, if the character is a thief, the motion generation unit generates motions suitable for stealth action. This allows the motion generation unit to apply different motion generation algorithms depending on the attributes of the character.

[0043] The motion generation unit can generate motions taking into consideration geographical elements in the game when generating motions. The motion generation unit, for example, stores the geographical elements in the game in a database and analyzes them. For example, when the character is in a mountainous area, the motion generation unit generates motions suitable for mountain climbing. Also, when the character is near water, the motion generation unit can generate motions related to swimming or fishing. Furthermore, when the character is in an urban area, the motion generation unit can generate motions suitable for an urban environment. For example, when the character is in an urban area, the motion generation unit generates motions suitable for an urban environment. This allows the motion generation unit to generate motions based on the geographical elements in the game.

[0044] The motion generation unit can improve the accuracy of the motion by referring to related game data when generating the motion. The motion generation unit, for example, stores past player data in a database and analyzes it. For example, the motion generation unit generates optimal motions by referring to past player data. The motion generation unit can also generate effective motions based on statistical data within the game. Furthermore, the motion generation unit can analyze the motion data of other players and generate motions by referring to it. For example, the motion generation unit analyzes the motion data of other players and generates motions by referring to it. In this way, the motion generation unit can improve the accuracy of the motion by referring to related game data.

[0045] When generating a character, the character generation unit can select an optimal generation method by referring to the user's past character creation history. The character generation unit, for example, stores the user's past character creation history in a database and analyzes it. For example, the character generation unit generates a new character based on the characteristics of characters created by the user in the past. The character generation unit can also analyze the user's preference trends from the user's past character creation history and suggest an optimal character. Furthermore, the character generation unit can generate a similar character by referring to data of a character created by the user in the past. For example, the character generation unit generates a new character based on the characteristics of a character created by the user in the past. This allows the character generation unit to select an optimal generation method based on the user's past character creation history.

[0046] The character generation unit can customize the attributes of the character based on the user's current game progress at the time of character generation. The character generation unit, for example, saves the user's current game progress in a database and analyzes it. For example, when the user is in a specific stage, the character generation unit generates a character suitable for that stage. In addition, when the user is in a boss battle, the character generation unit can also generate a character specialized for combat. Furthermore, when the user is exploring, the character generation unit can also generate a character suitable for exploration. For example, when the user instructs "generate a character suitable for exploration" during exploration, the character generation unit generates a character suitable for exploration. This allows the character generation unit to customize the attributes of the character based on the user's current game progress.

[0047] The character generation unit can generate an optimal character by taking into consideration the geographical location information of the user when generating a character. The character generation unit, for example, acquires and analyzes the geographical location information of the user. For example, the character generation unit identifies the user's current location using GPS data or an IP address. When the user is in a specific area, the character generation unit generates a character related to the area. For example, when the user is traveling, the character generation unit generates a character related to the travel destination. In addition, when the user is at home, the character generation unit can also generate a character related to activities at home. Furthermore, the character generation unit can also suggest an optimal character based on the geographical location information of the user. For example, when the user is in a specific area, the character generation unit suggests a character related to the area. This allows the character generation unit to generate an optimal character based on the geographical location information of the user.

[0048] The character generation unit may determine the characteristics of the character by analyzing the social media activities of the user when generating the character. For example, the character generation unit stores and analyzes the social media activities of the user in a database. For example, the character generation unit may generate a related character based on information shared by the user on social media. The character generation unit may also generate a related character based on the activities of an account that the user follows on social media. Furthermore, the character generation unit may generate a character related to an event that the user participates in on social media. For example, the character generation unit may generate a travel-related character based on travel photos shared by the user on social media. In this way, the character generation unit may determine the characteristics of the character based on the social media activities of the user.

[0049] The application unit can adjust the level of detail of application based on the situation in the game when applying the action. The application unit, for example, stores and analyzes the situation in the game in a database. For example, the application unit applies detailed combat actions when the user is in a boss battle. Also, the application unit can apply actions suitable for exploration when the user is exploring. Furthermore, the application unit can apply a relaxing action when the user is taking a break. For example, the application unit applies a relaxing action when the user instructs "relax" during a break. This allows the application unit to adjust the level of detail of application of the action based on the situation in the game.

[0050] The application unit can apply different application algorithms according to the attributes of the character when applying an action. The application unit, for example, stores and analyzes the attributes of the character in a database. For example, if the character is a warrior, the application unit applies an action specialized for combat. Also, if the character is a magician, the application unit can apply an action related to magic. Furthermore, if the character is a thief, the application unit can apply an action suitable for stealth action. For example, if the character is a thief, the application unit applies an action suitable for stealth action. This allows the application unit to apply different application algorithms according to the attributes of the character.

[0051] The application unit can apply an action by taking into consideration geographical elements in the game when applying the action. The application unit, for example, stores and analyzes the geographical elements in the game in a database. For example, when the character is in a mountainous area, the application unit applies an action suitable for mountain climbing. Also, when the character is near water, the application unit can apply an action related to swimming or fishing. Furthermore, when the character is in an urban area, the application unit can apply an action suitable for an urban environment. For example, when the character is in an urban area, the application unit applies an action suitable for an urban environment. This allows the application unit to apply an action based on the geographical elements in the game.

[0052] The application unit can improve the accuracy of application when applying an action by referring to related game data. The application unit, for example, stores past player data in a database and analyzes it. For example, the application unit applies an optimal action by referring to the past player data. The application unit can also apply an effective action based on statistical data within the game. Furthermore, the application unit can analyze the action data of other players and apply the action by referring to it. For example, the application unit analyzes the action data of other players and applies the action by referring to it. In this way, the application unit can improve the accuracy of application of the action by referring to related game data.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] The game operation system may further include a health management unit that monitors the user's health condition. The health management unit acquires biometric information such as the user's heart rate and body temperature, and adjusts the in-game movements and character behavior based on this. For example, if the user's heart rate is high, the movement generation unit generates a relaxing movement, and the application unit applies this to the character. Also, if the user's body temperature is high, the character generation unit may generate a character with a cool appearance. This makes it possible to provide a game experience that is tailored to the user's health condition.

[0055] The motion generation unit can analyze the user's past game play data and generate motions according to the play style. For example, if the user has preferred an aggressive play style in the past, the motion generation unit generates aggressive motions preferentially. Also, if the user has preferred a defensive play style, the motion generation unit can generate defensive motions. Furthermore, if the user has a play style that emphasizes exploration, the motion generation unit can generate motions suitable for exploration. This makes it possible to provide motions according to the user's play style.

[0056] The character generation unit can analyze the user's social media activity and generate a character based on the characters and trends the user follows. For example, if the user follows a specific anime character, a character with an appearance and characteristics similar to that character is generated. Popular characters can also be generated based on trends in the community in which the user participates. Furthermore, related characters can also be generated based on images and posted content shared by the user. This makes it possible to generate characters based on the user's social media activity.

[0057] The application unit can apply an action taking into account the geographical location information of the user. For example, when the user is in a particular area, an action based on the culture and customs of the area can be applied. When the user is traveling, an action related to tourist attractions and activities at the travel destination can be applied. Furthermore, when the user is at home, an action related to activities at home can be applied. This makes it possible to apply an action based on the geographical location information of the user.

[0058] The reception unit can analyze the user's past instruction history and customize the instruction reception method based on the user's preferred game genre and play style. For example, if the user likes action games, action-related instructions can be preferentially received. Also, if the user likes puzzle games, puzzle-related instructions can be preferentially received. Furthermore, the reception unit can suggest the optimal reception method based on instruction methods (voice, text, etc.) that the user has frequently used in the past. This makes it possible to receive instructions according to the user's preferences.

[0059] The reception unit can provide appropriate advice and hints based on the user's current game progress. For example, if the user is stuck on a particular stage, the reception unit can provide hints for clearing that stage. If the user is in a boss battle, the reception unit can provide advice on the boss's weaknesses and how to beat it. Furthermore, if the user is exploring, the reception unit can provide information useful for the exploration and the locations of items. This makes it possible to provide support according to the user's game progress.

[0060] The reception unit can suggest events and activities related to the region, taking into account the geographical location information of the user. For example, when the user is in a particular region, events and tourist attractions held in the region can be suggested. When the user is traveling, recommended spots and activities at the travel destination can be suggested. Furthermore, when the user is at home, online events and activities that can be enjoyed at home can be suggested. This makes it possible to make suggestions based on the geographical location information of the user.

[0061] The reception unit can analyze the user's social media activity and customize the method of receiving instructions based on topics and trends that the user is interested in. For example, if the user posts a lot about a specific game genre, instructions related to that genre can be preferentially received. In addition, related instructions can be suggested based on the activity of accounts the user follows. Furthermore, instructions related to events and communities in which the user participates can be received. This makes it possible to receive instructions based on the user's social media activity.

[0062] The process flow of the first embodiment will be briefly described below.

[0063] Step 1: The reception unit receives a voice or text instruction from a user. The voice instruction from the user is converted into text using a voice recognition technology, and the text instruction is directly input through a text input interface. Step 2: The action generation unit analyzes the instructions received by the reception unit and generates specific actions. Using generation AI and natural language processing technology, it analyzes the meaning of the instructions and generates specific actions according to the situation. For example, if the instruction is "punch," it generates specific actions such as "right straight punch" or "left hook punch." Step 3: The character generation unit generates an original character based on the characteristics entered by the user. Using a generation AI, a character with characteristics such as "a character with blue hair and red eyes" is generated. A character is generated based on the character's appearance, personality, and other characteristics. Step 4: The application unit applies the motion generated by the motion generation unit to the character generated by the character generation unit. For example, the generated motion of "right straight punch" is applied to the generated character and executed in the game. The application unit adjusts the timing and speed of the motion using the generation AI and applies it to the character.

[0064] (Example 2) The game operation system according to the embodiment of the present invention is a system that utilizes a generation AI to convert abstract instructions by voice or text into specific game operations. In this system, when a user inputs an abstract instruction such as "punch" or "kick," the generation AI analyzes the instruction and converts it into a specific action in the game. For example, when the user instructs "punch," the generation AI generates a specific action such as "right straight punch" or "left hook punch" depending on the situation. Furthermore, the character operated by the user can also be created as an original character using the generation AI. When a user inputs the characteristics and appearance of a character in text, the generation AI generates a character based on that information. For example, when "a character with blue hair and red eyes" is input, the generation AI generates a character with that characteristic. This mechanism allows the user to operate the game even with abstract instructions and to create an original character. As a result, the game operation system can convert the user's voice or text instructions into specific game operations and generate an original character.

[0065] The game operation system according to the embodiment includes a reception unit, a motion generation unit, a character generation unit, and an application unit. The reception unit receives a user's voice or text instruction. The user's voice or text instruction includes, but is not limited to, abstract instructions such as "punch" and "kick". The reception unit converts the voice instruction into text using, for example, a voice recognition technology. The reception unit also provides a text input interface, and the user can directly input text instructions. The motion generation unit uses a generation AI to analyze the instruction received by the reception unit and generate a specific motion. The motion generation unit uses, for example, a natural language processing technology to analyze the meaning of the instruction and generate a specific motion according to the situation. For example, when "punch" is instructed, the motion generation unit uses the generation AI to generate a specific motion such as "right straight punch" or "left hook punch". The character generation unit uses the generation AI to generate an original character based on the characteristics input by the user. For example, when the user inputs "a character with blue hair and red eyes", the character generation unit uses the generation AI to generate a character with the characteristics. The character generation unit uses a generation AI to generate a character based on characteristics such as the character's appearance and personality. The application unit applies the generated motion to the generated character. For example, the application unit applies the generated motion of "right straight punch" to the generated character and executes it in the game. The application unit can also use the generation AI to adjust the application method of the motion. For example, the application unit adjusts the timing and speed of the generated motion and applies it to the character. In this way, the game operation system according to the embodiment can convert the user's voice or text instructions into specific game operations and generate an original character.

[0066] The reception unit receives a voice or text instruction from the user. The user's voice or text instruction includes, but is not limited to, abstract instructions such as "punch" and "kick". The reception unit converts the voice instruction into text, for example, using a voice recognition technology. Specifically, the voice recognition technology includes a process of converting the user's voice into a digital signal, analyzing the signal, and converting it into text data. The voice recognition technology achieves accurate text conversion using advanced algorithms such as noise removal, voice feature extraction, and phoneme identification. The reception unit also provides a text input interface, allowing the user to directly input text instructions. The text input interface is designed to support input methods using a keyboard or a touch screen, allowing the user to easily input instructions. Furthermore, the reception unit has a feedback function for eliminating ambiguity in instructions when receiving a user's instruction. For example, if the user instructs "attack", the reception unit displays a confirmation message such as "Is it a punch? Is it a kick?" to clarify the user's intention. This allows the reception unit to accurately receive the user's voice or text instruction and pass it on to the next process.

[0067] The motion generation unit uses the generation AI to analyze the instruction received by the reception unit and generate a specific motion. The motion generation unit, for example, uses natural language processing technology to analyze the meaning of the instruction and generate a specific motion according to the situation. Natural language processing technology is a technology for analyzing text data and understanding its meaning, and performs analysis taking into account the context and meaning of the words. For example, when the instruction is "punch," the motion generation unit uses the generation AI to generate a specific motion such as "right straight punch" or "left hook punch." The generation AI has the ability to learn a large amount of data and generate motions according to various situations. For example, the generation AI learns past game play data and actual martial arts motion data, and generates optimal motions based on the user's instructions. Furthermore, the motion generation unit makes adjustments taking into account the continuity and smoothness of the motion so that the generated motion looks natural in the game. For example, the start position and end position of the motion are adjusted so that the transition from the previous motion to the next motion is smooth. As a result, the motion generation unit can generate specific and natural motions based on the user's instructions and realize operations in the game.

[0068] The character generation unit uses the generation AI to generate an original character based on the characteristics input by the user. For example, when the user inputs "a character with blue hair and red eyes," the character generation unit uses the generation AI to generate a character with those characteristics. The generation AI utilizes image generation technology and a character design database to generate the character's appearance and personality based on the user's instructions. For example, the generation AI designs the character's appearance taking into account the characteristics such as hair color, eye color, and clothing specified by the user. The generation AI can also generate the character's personality and behavior patterns. For example, if the user instructs "a brave and friendly character," the generation AI generates the character's behavior patterns and lines based on that personality. Furthermore, the character generation unit adjusts the character's actions and facial expressions so that the generated character looks natural in the game. For example, when the character expresses emotions, the character makes adjustments to make the facial expressions and body movements look natural. This allows the character generation unit to generate an original character based on the user's instructions, improving the play experience in the game.

[0069] The application unit applies the generated motion to the generated character. For example, the application unit applies the generated "right straight punch" motion to the generated character and executes it in the game. The application unit can also adjust the application method of the motion using the generation AI. For example, the application unit adjusts the timing and speed of the generated motion and applies it to the character. Specifically, the application unit applies the generated motion to the character using the character's skeletal model and animation data. The skeletal model defines the position and movement of each part of the character's body, and the animation data is data that expresses continuous changes in motion. The application unit uses these data to make adjustments so that the generated motion is naturally applied to the character. For example, the arm movement and body balance are adjusted so that the punch motion appears smooth. In addition, the application unit also takes into account the character's surrounding environment and interactions with other characters when applying the motion. For example, when a punch motion hits another character, the effect is calculated in real time and an appropriate reaction is generated. This allows the application unit to naturally apply the generated motion to the character and realize realistic motion in the game.

[0070] The motion generation unit can analyze the user's voice or text instructions and generate specific motions according to the situation. The motion generation unit, for example, uses natural language processing technology to analyze the user's voice or text instructions. For example, when the motion generation unit receives an instruction to "punch," it uses a generation AI to analyze the meaning of the instruction and generates specific motions according to the situation. For example, the motion generation unit generates specific motions such as "right straight punch" and "left hook punch" in consideration of the situation in the game. The motion generation unit can also generate optimal motions based on the user's past actions and in-game scenarios. For example, the motion generation unit refers to the motion history when the user previously instructed "punch" and generates optimal motions in a similar situation. This allows the motion generation unit to convert the user's abstract instructions into specific motions.

[0071] The character generation unit can generate an original character based on the characteristics input by the user. For example, when the user inputs "a character with blue hair and red eyes," the character generation unit uses a generation AI to generate a character with the characteristics. The character generation unit uses the generation AI to generate a character based on characteristics such as the character's appearance and personality. For example, the character generation unit analyzes the characteristics input by the user and generates the character's appearance based on the characteristics. The character generation unit can also set the character's personality, skills, etc. based on the characteristics input by the user. For example, when the character generation unit inputs "a character with a brave personality and excellent swordsmanship," the character generation unit uses the generation AI to generate a character with the characteristics. This allows the character generation unit to generate an original character based on the characteristics input by the user.

[0072] The application unit can apply the generated motion to the generated character. For example, the application unit applies the generated motion of "right straight punch" to the generated character and executes it in the game. The application unit can also adjust the application method of the motion using the generation AI. For example, the application unit adjusts the timing and speed of the generated motion and applies it to the character. The application unit can also apply the generated motion according to the situation in the game. For example, the application unit applies an attack motion to a character in combat and applies a search motion to a character in search. In this way, the application unit can apply the generated motion to the generated character.

[0073] The reception unit can analyze the user's emotions and adjust the method of receiving instructions based on the analyzed user's emotions. The reception unit, for example, analyzes the user's voice tone and facial expression to estimate the user's emotions. For example, the reception unit uses a voice recognition technology to analyze the user's voice tone and estimate whether the user is excited or relaxed. The reception unit can also use a camera to analyze the user's facial expression and estimate the user's emotions. For example, the reception unit uses a facial expression recognition technology to analyze the user's facial expression and estimate whether the user is stressed or relaxed. The reception unit adjusts the method of receiving instructions based on the estimated user's emotions. For example, when the user is excited, the sensitivity of the voice input is increased to quickly accept instructions. Also, when the user is relaxed, an interface for accepting detailed instructions is provided. Furthermore, when the user is stressed, a simple interface is provided to minimize input procedures. This allows the reception unit to adjust the method of receiving instructions according to the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. Examples of the generation AI include, but are not limited to, a text generation AI (eg, LLM) and a multimodal generation AI.

[0074] The reception unit can analyze the user's past instruction history and select an appropriate reception method. The reception unit, for example, stores the user's past instruction history in a database and analyzes it. For example, the reception unit preferentially suggests an instruction method (such as voice or text) that the user has used frequently in the past. The reception unit can also predict and suggest an instruction method to be used in a specific time period from the user's past instruction history. For example, if the user has used voice instructions a lot in a specific time period in the past, the reception unit preferentially suggests voice instructions in that time period. Furthermore, the reception unit can automatically complement related instructions based on the instruction contents input by the user in the past. For example, the reception unit refers to the operation history when the user has previously instructed "punch" and suggests related instructions such as "kick" in a similar situation. This allows the reception unit to select an optimal reception method based on the user's past instruction history.

[0075] The reception unit can perform filtering based on the user's current game progress when receiving an instruction. The reception unit, for example, stores the user's current game progress in a database and analyzes it. For example, when the user is in a specific stage, the reception unit only receives instructions related to that stage. In addition, when the user is in a boss battle, the reception unit can also preferentially receive instructions related to the battle. Furthermore, when the user is searching, the reception unit can also preferentially receive instructions related to the search. For example, when the user instructs "search for an item" during a search, the reception unit preferentially receives instructions related to the search. This allows the reception unit to filter instructions based on the user's current game progress.

[0076] The reception unit can estimate the user's emotion and determine the priority of the instructions to be received based on the estimated user's emotion. The reception unit, for example, analyzes the user's voice tone and facial expression to estimate the user's emotion. For example, the reception unit uses a voice recognition technology to analyze the user's voice tone and estimate whether the user is excited or relaxed. The reception unit can also use a camera to analyze the user's facial expression and estimate the user's emotion. For example, the reception unit uses a facial expression recognition technology to analyze the user's facial expression and estimate whether the user is stressed or relaxed. The reception unit determines the priority of the instructions to be received based on the estimated user's emotion. For example, when the user is excited, instructions with high urgency are preferentially received. Also, when the user is relaxed, detailed instructions are preferentially received. Furthermore, when the user is stressed, simple instructions are preferentially received. This allows the reception unit to determine the priority of the instructions according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. Examples of the generation AI include, but are not limited to, a text generation AI (eg, LLM) and a multimodal generation AI.

[0077] When receiving an instruction, the reception unit can preferentially receive an instruction with high relevance in consideration of the geographical location information of the user. The reception unit, for example, acquires and analyzes the geographical location information of the user. For example, the reception unit identifies the user's current location using GPS data or an IP address. When the user is in a specific area, the reception unit preferentially receives an instruction related to the area. For example, when the user is traveling, the reception unit preferentially receives an instruction related to the travel. In addition, when the user is at home, the reception unit can also preferentially receive an instruction related to activities at home. Furthermore, the reception unit can also suggest an instruction with high relevance based on the geographical location information of the user. For example, when the user is in a specific area, the reception unit suggests an event or activity related to the area. This allows the reception unit to preferentially receive an instruction with high relevance based on the geographical location information of the user.

[0078] The reception unit can analyze the user's social media activity and receive related instructions when receiving the instruction. The reception unit, for example, stores the user's social media activity in a database and analyzes it. For example, the reception unit receives related instructions based on information shared by the user on social media. The reception unit can also receive related instructions based on the activity of an account the user follows on social media. Furthermore, the reception unit can receive instructions related to an event the user is participating in on social media. For example, the reception unit receives travel-related instructions based on travel photos shared by the user on social media. This allows the reception unit to receive related instructions based on the user's social media activity.

[0079] The motion generation unit can estimate the user's emotion and adjust the motion generation method based on the estimated user's emotion. The motion generation unit, for example, analyzes the user's voice tone and facial expression to estimate the user's emotion. For example, the motion generation unit uses a voice recognition technology to analyze the user's voice tone and estimate whether the user is excited or relaxed. The motion generation unit can also use a camera to analyze the user's facial expression and estimate the user's emotion. For example, the motion generation unit uses a facial expression recognition technology to analyze the user's facial expression and estimate whether the user is stressed or relaxed. The motion generation unit adjusts the motion generation method based on the estimated user's emotion. For example, if the user is excited, an aggressive motion is generated. Also, if the user is relaxed, a gentle motion is generated. Furthermore, if the user is stressed, a motion that helps relieve stress is generated. This allows the motion generation unit to adjust the motion generation method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. Examples of the generation AI include, but are not limited to, a text generation AI (eg, LLM) and a multimodal generation AI.

[0080] The motion generation unit can adjust the level of detail of the motion based on the situation in the game when generating the motion. The motion generation unit, for example, stores the situation in the game in a database and analyzes it. For example, when the user is in a boss battle, the motion generation unit generates detailed combat motions. Also, when the user is exploring, the motion generation unit can generate motions suitable for exploration. Furthermore, when the user is taking a break, the motion generation unit can generate a relaxed motion. For example, when the user instructs "relax" during a break, the motion generation unit generates a relaxed motion. This allows the motion generation unit to adjust the level of detail of the motion based on the situation in the game.

[0081] The motion generation unit can apply different motion generation algorithms depending on the attributes of the character when generating motion. The motion generation unit, for example, stores the attributes of the character in a database and analyzes them. For example, if the character is a warrior, the motion generation unit generates motions specialized for combat. Also, if the character is a magician, the motion generation unit can also generate motions related to magic. Furthermore, if the character is a thief, the motion generation unit can also generate motions suitable for stealth action. For example, if the character is a thief, the motion generation unit generates motions suitable for stealth action. This allows the motion generation unit to apply different motion generation algorithms depending on the attributes of the character.

[0082] The motion generation unit can estimate the user's emotion and determine the priority of the motion to be generated based on the estimated user's emotion. The motion generation unit, for example, analyzes the user's voice tone and facial expression to estimate the user's emotion. For example, the motion generation unit uses a voice recognition technology to analyze the user's voice tone and estimate whether the user is excited or relaxed. The motion generation unit can also analyze the user's facial expression using a camera to estimate the user's emotion. For example, the motion generation unit uses a facial expression recognition technology to analyze the user's facial expression and estimate whether the user is stressed or relaxed. The motion generation unit determines the priority of the motion to be generated based on the estimated user's emotion. For example, if the user is excited, aggressive motions are preferentially generated. Also, if the user is relaxed, motions related to exploration and collection are preferentially generated. Furthermore, if the user is stressed, motions that are useful for stress relief are preferentially generated. This allows the motion generation unit to determine the priority of the motions according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. Examples of the generation AI include, but are not limited to, a text generation AI (eg, LLM) and a multimodal generation AI.

[0083] The motion generation unit can generate motions taking into consideration geographical elements in the game when generating motions. The motion generation unit, for example, stores the geographical elements in the game in a database and analyzes them. For example, when the character is in a mountainous area, the motion generation unit generates motions suitable for mountain climbing. Also, when the character is near water, the motion generation unit can generate motions related to swimming or fishing. Furthermore, when the character is in an urban area, the motion generation unit can generate motions suitable for an urban environment. For example, when the character is in an urban area, the motion generation unit generates motions suitable for an urban environment. This allows the motion generation unit to generate motions based on the geographical elements in the game.

[0084] The motion generation unit can improve the accuracy of the motion by referring to related game data when generating the motion. The motion generation unit, for example, stores past player data in a database and analyzes it. For example, the motion generation unit generates optimal motions by referring to past player data. The motion generation unit can also generate effective motions based on statistical data within the game. Furthermore, the motion generation unit can analyze the motion data of other players and generate motions by referring to it. For example, the motion generation unit analyzes the motion data of other players and generates motions by referring to it. In this way, the motion generation unit can improve the accuracy of the motion by referring to related game data.

[0085] The character generation unit can estimate the user's emotion and adjust the character generation method based on the estimated user's emotion. The character generation unit, for example, analyzes the user's voice tone and facial expression to estimate the user's emotion. For example, the character generation unit uses a voice recognition technology to analyze the user's voice tone and estimate whether the user is excited or relaxed. The character generation unit can also use a camera to analyze the user's facial expression and estimate the user's emotion. For example, the character generation unit uses a facial expression recognition technology to analyze the user's facial expression and estimate whether the user is stressed or relaxed. The character generation unit adjusts the character generation method based on the estimated user's emotion. For example, when the user is excited, a flashy and conspicuous character is generated. Also, when the user is relaxed, a character with a calm atmosphere is generated. Furthermore, when the user is stressed, a soothing character is generated. This allows the character generation unit to adjust the character generation method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. Examples of the generation AI include, but are not limited to, a text generation AI (eg, LLM) and a multimodal generation AI.

[0086] When generating a character, the character generation unit can select an optimal generation method by referring to the user's past character creation history. The character generation unit, for example, stores the user's past character creation history in a database and analyzes it. For example, the character generation unit generates a new character based on the characteristics of characters created by the user in the past. The character generation unit can also analyze the user's preference trends from the user's past character creation history and suggest an optimal character. Furthermore, the character generation unit can generate a similar character by referring to data of a character created by the user in the past. For example, the character generation unit generates a new character based on the characteristics of a character created by the user in the past. This allows the character generation unit to select an optimal generation method based on the user's past character creation history.

[0087] The character generation unit can customize the attributes of the character based on the user's current game progress at the time of character generation. The character generation unit, for example, saves the user's current game progress in a database and analyzes it. For example, when the user is in a specific stage, the character generation unit generates a character suitable for that stage. In addition, when the user is in a boss battle, the character generation unit can also generate a character specialized for combat. Furthermore, when the user is exploring, the character generation unit can also generate a character suitable for exploration. For example, when the user instructs "generate a character suitable for exploration" during exploration, the character generation unit generates a character suitable for exploration. This allows the character generation unit to customize the attributes of the character based on the user's current game progress.

[0088] The character generation unit can estimate the user's emotion and determine the priority of the characters to be generated based on the estimated user's emotion. The character generation unit, for example, analyzes the user's voice tone and facial expression to estimate the user's emotion. For example, the character generation unit uses a voice recognition technology to analyze the user's voice tone and estimate whether the user is excited or relaxed. The character generation unit can also use a camera to analyze the user's facial expression and estimate the user's emotion. For example, the character generation unit uses a facial expression recognition technology to analyze the user's facial expression and estimate whether the user is stressed or relaxed. The character generation unit determines the priority of the characters to be generated based on the estimated user's emotion. For example, if the user is excited, a flashy and conspicuous character is generated preferentially. Also, if the user is relaxed, a character with a calm atmosphere is generated preferentially. Furthermore, if the user is stressed, a healing character is generated preferentially. This allows the character generation unit to determine the priority of the characters according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. Examples of the generation AI include, but are not limited to, a text generation AI (eg, LLM) and a multimodal generation AI.

[0089] The character generation unit can generate an optimal character by taking into consideration the geographical location information of the user when generating a character. The character generation unit, for example, acquires and analyzes the geographical location information of the user. For example, the character generation unit identifies the user's current location using GPS data or an IP address. When the user is in a specific area, the character generation unit generates a character related to the area. For example, when the user is traveling, the character generation unit generates a character related to the travel destination. In addition, when the user is at home, the character generation unit can also generate a character related to activities at home. Furthermore, the character generation unit can also suggest an optimal character based on the geographical location information of the user. For example, when the user is in a specific area, the character generation unit suggests a character related to the area. This allows the character generation unit to generate an optimal character based on the geographical location information of the user.

[0090] The character generation unit may determine the characteristics of the character by analyzing the social media activities of the user when generating the character. For example, the character generation unit stores and analyzes the social media activities of the user in a database. For example, the character generation unit may generate a related character based on information shared by the user on social media. The character generation unit may also generate a related character based on the activities of an account that the user follows on social media. Furthermore, the character generation unit may generate a character related to an event that the user participates in on social media. For example, the character generation unit may generate a travel-related character based on travel photos shared by the user on social media. In this way, the character generation unit may determine the characteristics of the character based on the social media activities of the user.

[0091] The application unit can estimate the user's emotion and adjust the application method of the action based on the estimated user's emotion. The application unit, for example, analyzes the user's voice tone and facial expression to estimate the user's emotion. For example, the application unit uses a voice recognition technology to analyze the user's voice tone and estimate whether the user is excited or relaxed. The application unit can also use a camera to analyze the user's facial expression and estimate the user's emotion. For example, the application unit uses a facial expression recognition technology to analyze the user's facial expression and estimate whether the user is stressed or relaxed. The application unit adjusts the application method of the action based on the estimated user's emotion. For example, if the user is excited, the action is applied at a faster speed. Also, if the user is relaxed, the action is applied at a slower speed. Furthermore, if the user is stressed, the action is applied with emphasis on the smoothness of the action. This allows the application unit to adjust the application method of the action according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. Examples of the generation AI include, but are not limited to, a text generation AI (eg, LLM) and a multimodal generation AI.

[0092] The application unit can adjust the level of detail of application based on the situation in the game when applying the action. The application unit, for example, stores and analyzes the situation in the game in a database. For example, the application unit applies detailed combat actions when the user is in a boss battle. Also, the application unit can apply actions suitable for exploration when the user is exploring. Furthermore, the application unit can apply a relaxing action when the user is taking a break. For example, the application unit applies a relaxing action when the user instructs "relax" during a break. This allows the application unit to adjust the level of detail of application of the action based on the situation in the game.

[0093] The application unit can apply different application algorithms according to the attributes of the character when applying an action. The application unit, for example, stores and analyzes the attributes of the character in a database. For example, if the character is a warrior, the application unit applies an action specialized for combat. Also, if the character is a magician, the application unit can apply an action related to magic. Furthermore, if the character is a thief, the application unit can apply an action suitable for stealth action. For example, if the character is a thief, the application unit applies an action suitable for stealth action. This allows the application unit to apply different application algorithms according to the attributes of the character.

[0094] The application unit can estimate the user's emotion and determine the priority of the operations to be applied based on the estimated user's emotion. The application unit, for example, analyzes the user's voice tone and facial expression to estimate the user's emotion. For example, the application unit uses a voice recognition technology to analyze the user's voice tone and estimate whether the user is excited or relaxed. The application unit can also use a camera to analyze the user's facial expression and estimate the user's emotion. For example, the application unit uses a facial expression recognition technology to analyze the user's facial expression and estimate whether the user is stressed or relaxed. The application unit determines the priority of the operations to be applied based on the estimated user's emotion. For example, if the user is excited, aggressive operations are applied preferentially. Also, if the user is relaxed, operations related to exploration and collection are applied preferentially. Furthermore, if the user is stressed, operations that are useful for relieving stress are applied preferentially. This allows the application unit to determine the priority of the operations according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. Examples of the generation AI include, but are not limited to, a text generation AI (eg, LLM) and a multimodal generation AI.

[0095] The application unit can apply an action by taking into consideration geographical elements in the game when applying the action. The application unit, for example, stores and analyzes the geographical elements in the game in a database. For example, when the character is in a mountainous area, the application unit applies an action suitable for mountain climbing. Also, when the character is near water, the application unit can apply an action related to swimming or fishing. Furthermore, when the character is in an urban area, the application unit can apply an action suitable for an urban environment. For example, when the character is in an urban area, the application unit applies an action suitable for an urban environment. This allows the application unit to apply an action based on the geographical elements in the game.

[0096] The application unit can improve the accuracy of application when applying an action by referring to related game data. The application unit, for example, stores past player data in a database and analyzes it. For example, the application unit applies an optimal action by referring to the past player data. The application unit can also apply an effective action based on statistical data within the game. Furthermore, the application unit can analyze the action data of other players and apply the action by referring to it. For example, the application unit analyzes the action data of other players and applies the action by referring to it. In this way, the application unit can improve the accuracy of application of the action by referring to related game data.

[0097] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0098] The game operation system may further include a health management unit that monitors the user's health condition. The health management unit acquires biometric information such as the user's heart rate and body temperature, and adjusts the in-game movements and character behavior based on this. For example, if the user's heart rate is high, the movement generation unit generates a relaxing movement, and the application unit applies this to the character. Also, if the user's body temperature is high, the character generation unit may generate a character with a cool appearance. This makes it possible to provide a game experience that is tailored to the user's health condition.

[0099] The motion generation unit can analyze the user's past game play data and generate motions according to the play style. For example, if the user has preferred an aggressive play style in the past, the motion generation unit generates aggressive motions preferentially. Also, if the user has preferred a defensive play style, the motion generation unit can generate defensive motions. Furthermore, if the user has a play style that emphasizes exploration, the motion generation unit can generate motions suitable for exploration. This makes it possible to provide motions according to the user's play style.

[0100] The character generation unit can analyze the user's social media activity and generate a character based on the characters and trends the user follows. For example, if the user follows a specific anime character, a character with an appearance and characteristics similar to that character is generated. Popular characters can also be generated based on trends in the community in which the user participates. Furthermore, related characters can also be generated based on images and posted content shared by the user. This makes it possible to generate characters based on the user's social media activity.

[0101] The application unit can apply an action taking into account the geographical location information of the user. For example, when the user is in a particular area, an action based on the culture and customs of the area can be applied. When the user is traveling, an action related to tourist attractions and activities at the travel destination can be applied. Furthermore, when the user is at home, an action related to activities at home can be applied. This makes it possible to apply an action based on the geographical location information of the user.

[0102] The reception unit can estimate the user's emotions and adjust the music and sound effects in the game based on the estimated user's emotions. For example, if the user is excited, fast-paced music is played, and if the user is relaxed, calm music is played. Also, if the user is feeling stressed, music with a relaxing effect can be played. Furthermore, the volume and type of sound effects can be adjusted according to the user's emotions. This makes it possible to provide an acoustic environment that corresponds to the user's emotions.

[0103] The reception unit can analyze the user's past instruction history and customize the instruction reception method based on the user's preferred game genre and play style. For example, if the user likes action games, action-related instructions can be preferentially received. Also, if the user likes puzzle games, puzzle-related instructions can be preferentially received. Furthermore, the reception unit can suggest the optimal reception method based on instruction methods (voice, text, etc.) that the user has frequently used in the past. This makes it possible to receive instructions according to the user's preferences.

[0104] The reception unit can provide appropriate advice and hints based on the user's current game progress. For example, if the user is stuck on a particular stage, the reception unit can provide hints for clearing that stage. If the user is in a boss battle, the reception unit can provide advice on the boss's weaknesses and how to beat it. Furthermore, if the user is exploring, the reception unit can provide information useful for the exploration and the locations of items. This makes it possible to provide support according to the user's game progress.

[0105] The reception unit can estimate the user's emotions and adjust the words and actions of the in-game character based on the estimated user's emotions. For example, if the user is excited, the character can say encouraging words. If the user is relaxed, the character can say calming words. Furthermore, if the user is stressed, the character can say soothing words. This makes it possible to provide the character's words and actions according to the user's emotions.

[0106] The reception unit can suggest events and activities related to the region, taking into account the geographical location information of the user. For example, when the user is in a particular region, events and tourist attractions held in the region can be suggested. When the user is traveling, recommended spots and activities at the travel destination can be suggested. Furthermore, when the user is at home, online events and activities that can be enjoyed at home can be suggested. This makes it possible to make suggestions based on the geographical location information of the user.

[0107] The reception unit can analyze the user's social media activity and customize the method of receiving instructions based on topics and trends that the user is interested in. For example, if the user posts a lot about a specific game genre, instructions related to that genre can be preferentially received. In addition, related instructions can be suggested based on the activity of accounts the user follows. Furthermore, instructions related to events and communities in which the user participates can be received. This makes it possible to receive instructions based on the user's social media activity.

[0108] The process flow of the second embodiment will be briefly described below.

[0109] Step 1: The reception unit receives a voice or text instruction from a user. The voice instruction from the user is converted into text using a voice recognition technology, and the text instruction is directly input through a text input interface. Step 2: The action generation unit analyzes the instructions received by the reception unit and generates specific actions. Using generation AI and natural language processing technology, it analyzes the meaning of the instructions and generates specific actions according to the situation. For example, if the instruction is "punch," it generates specific actions such as "right straight punch" or "left hook punch." Step 3: The character generation unit generates an original character based on the characteristics entered by the user. Using a generation AI, a character with characteristics such as "a character with blue hair and red eyes" is generated. A character is generated based on the character's appearance, personality, and other characteristics. Step 4: The application unit applies the motion generated by the motion generation unit to the character generated by the character generation unit. For example, the generated motion of "right straight punch" is applied to the generated character and executed in the game. The application unit adjusts the timing and speed of the motion using the generation AI and applies it to the character.

[0110] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0111] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0112] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0113] Each of the multiple elements including the above-mentioned reception unit, action generation unit, character generation unit, and application unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit receives voice or text instructions from the user using the microphone 38B or touch panel 38A of the smart device 14. The action generation unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the instructions using a generation AI to generate specific actions. The character generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates an original character based on the characteristics input by the user. The application unit is realized by the control unit 46A of the smart device 14, and applies the generated action to the generated character and executes it in the game. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0114] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0115] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0116] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0117] 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.

[0118] 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 the voice according to instructions from the processor 46.

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0120] 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 performed in a secure state.

[0121] Fig. 4 shows an example of 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.

[0122] 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.

[0123] 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0124] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 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 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0125] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0126] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0127] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0128] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0129] Each of the multiple elements including the above-mentioned reception unit, action generation unit, character generation unit, and application unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit receives a user's voice or text instruction using the microphone 238 or text input interface of the smart glasses 214. The action generation unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the instruction using a generation AI and generates a specific action. The character generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates an original character based on the characteristics input by the user. The application unit is realized by the control unit 46A of the smart glasses 214, and applies the generated action to the generated character and executes it in the game. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0130] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0131] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0132] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0133] 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.

[0134] 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 the voice according to instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0136] 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 performed in a secure state.

[0137] 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.

[0138] 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.

[0139] 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0140] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0141] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0142] 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 voice indicating a user input for 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.

[0143] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0144] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0145] Each of the multiple elements including the above-mentioned reception unit, action generation unit, character generation unit, and application unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit receives a user's voice or text instruction using the microphone 238 or text input interface of the headset type terminal 314. The action generation unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the instruction using a generation AI and generates a specific action. The character generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates an original character based on the characteristics input by the user. The application unit is realized by the control unit 46A of the headset type terminal 314, and applies the generated action to the generated character and executes it in the game. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0146] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0147] 7, a 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.

[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, the RAM 30, and the 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 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. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 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 the voice according to instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of 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 performed in a secure state.

[0153] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0154] 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.

[0155] 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.

[0156] 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0157] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0158] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0159] 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 a voice indicating a user input for 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.

[0160] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0161] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information 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.

[0162] Each of the multiple elements including the above-mentioned reception unit, action generation unit, character generation unit, and application unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit receives a user's voice or text instruction using the microphone 238 or text input interface of the robot 414. The action generation unit is realized by the specific processing unit 290 of the data processing device 12, analyzes the instruction using a generation AI, and generates a specific action. The character generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates an original character based on the characteristics input by the user. The application unit is realized by the control unit 46A of the robot 414, and applies the generated action to the generated character and executes it in the game. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0163] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0164] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0165] These emotions are distributed in the three o'clock direction of emotion map 400 and usually 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.

[0166] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0167] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0168] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0169] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0170] 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.

[0171] 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 Universal Serial Bus (USB) 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.

[0172] In addition, 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 upon request from the data processing device 12.

[0173] 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.

[0174] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0175] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0176] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0177] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0178] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0179] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0180] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0181] (Appendix 1) a reception unit for receiving voice or text instructions from a user; an action generating unit that analyzes the instruction received by the receiving unit and generates a specific action; a character generation unit that generates an original character based on characteristics input by a user; an application unit that applies the motion generated by the motion generation unit to the character generated by the character generation unit; A system characterized by: (Appendix 2) The action generation unit is Analyze the user's voice or text instructions and generate specific actions based on the situation 2. The system of claim 1, (Appendix 3) The character generation unit is Generate original characters based on user-entered features 2. The system of claim 1, (Appendix 4) The application unit includes: Applying the generated behavior to the generated character 2. The system of claim 1, (Appendix 5) The reception unit is Analyze the user's emotions and adjust the way instructions are accepted based on the analyzed user's emotions. 2. The system of claim 1, (Appendix 6) The reception unit is Analyze the user's past instruction history and select the appropriate reception method 2. The system of claim 1, (Appendix 7) The reception unit is When receiving instructions, filtering is performed based on the user's current game progress. 2. The system of claim 1, (Appendix 8) The reception unit is A user's emotion is estimated, and a priority order of instructions to be accepted is determined based on the estimated user's emotion. 2. The system of claim 1, (Appendix 9) The reception unit is When accepting instructions, the system takes into account the user's geographic location information and prioritizes accepting instructions that are more relevant to the user. 2. The system of claim 1, (Appendix 10) The reception unit is Upon receiving an instruction, analyze the user's social media activity and receive relevant instructions. 2. The system of claim 1, (Appendix 11) The action generation unit is Estimate the user's emotions and adjust the way the action is generated based on the estimated user's emotions. 2. The system of claim 1, (Appendix 12) The action generation unit is When generating movements, adjust the level of detail based on the in-game situation. 2. The system of claim 1, (Appendix 13) The action generation unit is When generating movements, different movement generation algorithms are applied depending on the character's attributes. 2. The system of claim 1, (Appendix 14) The action generation unit is Estimate the user's emotions and prioritize the actions to be generated based on the estimated user's emotions. 2. The system of claim 1, (Appendix 15) The action generation unit is When generating movements, the geographical elements in the game are taken into account. 2. The system of claim 1, (Appendix 16) The action generation unit is When generating movements, the accuracy of the movements is improved by referencing related game data. 2. The system of claim 1, (Appendix 17) The character generation unit is Estimate the user's emotions and adjust the character generation method based on the estimated user emotions. 2. The system of claim 1, (Appendix 18) The character generation unit is When generating a character, the system selects the optimal generation method by referring to the user's past character creation history. 2. The system of claim 1, (Appendix 19) The character generation unit is During character generation, customize the character's attributes based on the user's current game progress 2. The system of claim 1, (Appendix 20) The character generation unit is Estimate the user's emotions and determine the priority of the characters to be generated based on the estimated user's emotions. 2. The system of claim 1, (Appendix 21) The character generation unit is When generating a character, the optimal character is generated taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 22) The character generation unit is When generating a character, the user's social media activity is analyzed to determine the character's characteristics. 2. The system of claim 1, (Appendix 23) The application unit includes: Inferring a user's emotion and adjusting how an action is applied based on the inferred user emotion 2. The system of claim 1, (Appendix 24) The application unit includes: When applying actions, adjust the granularity of the application based on the in-game situation 2. The system of claim 1, (Appendix 25) The application unit includes: When applying actions, different application algorithms are applied depending on the character's attributes. 2. The system of claim 1, (Appendix 26) The application unit includes: To estimate a user's emotion and determine a priority of an action to be applied based on the estimated user's emotion. 2. The system of claim 1, (Appendix 27) The application unit includes: When applying actions, the action is applied taking into account the geographical elements in the game. 2. The system of claim 1, (Appendix 28) The application unit includes: When applying an action, the relevant game data is referenced to improve the accuracy of the application. 2. The system of claim 1, [Explanation of symbols]

[0182] 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 reception unit for receiving voice or text instructions from a user; an action generating unit that analyzes the instruction received by the receiving unit and generates a specific action; a character generation unit that generates an original character based on characteristics input by a user; an application unit that applies the motion generated by the motion generation unit to the character generated by the character generation unit; A system characterized by:

2. The reception unit is Analyze the user's emotions and adjust the way instructions are accepted based on the analyzed user's emotions.

2. The system of claim 1 .

3. The reception unit is Analyze the user's past instruction history and select the appropriate reception method 2. The system of claim 1 .

4. The reception unit is When receiving instructions, filtering is performed based on the user's current game progress.

2. The system of claim 1 .

5. The reception unit is A user's emotion is estimated, and a priority order of instructions to be accepted is determined based on the estimated user's emotion.

2. The system of claim 1 .

Images