system

Abstract

The system according to this embodiment aims to provide new missions and storylines in real time based on the player's actions. [Solution] The system according to the embodiment comprises a collection unit, a provision unit, and an information provision unit. The collection unit collects player action data. The provision unit proposes at least one new mission or a new story based on the data collected by the collection unit. The information provision unit provides information to the player based on the mission or new story proposed by the provision unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, real-time missions and stories corresponding to the actions of players are not sufficiently provided, and there is room for improvement.

[0005] The system according to the embodiment aims to provide new missions and stories in real time based on the actions of players.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, a provision unit, and an information provision unit. The collection unit collects player action data. The provision unit proposes at least one new mission or a new story based on the data collected by the collection unit. The information provision unit provides information to the player based on the mission or new story proposed by the provision unit. [Effects of the Invention]

[0007] The system according to this embodiment can provide new missions and storylines in real time based on the player's actions. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) An AI assistant system for an NPC in an online game, according to an embodiment of the present invention, is a system that responds in real time to the player's actions and the progress of the game, and plays a role in advancing the game's story, providing missions, and providing information. The AI ​​assistant system for an NPC in an online game collects player action data, proposes new missions or new stories based on the collected data, and provides the player with necessary information. For example, the AI ​​assistant system for an NPC in an online game collects data such as what actions the player has taken, which missions have been completed, and which characters the player has interacted with. This data is input into the AI ​​assistant. Next, based on the collected data, it proposes new missions or new stories. The AI ​​assistant analyzes the player's action data and proposes missions and stories that match the player's preferences and progress. For example, if the player has spent a lot of time with a particular character, it can propose a new mission related to that character. Furthermore, it provides the player with necessary information based on the proposed mission or new story. For example, it provides information on how to proceed with the mission and background information on the story. This allows the player to progress through the game smoothly. It can also collect and analyze the player's emotional data. For example, it can analyze what emotions the player is feeling during the game and propose missions or stories based on the results. This allows for the provision of an experience tailored to the player's emotions. Furthermore, it can suggest missions and stories that match the player's preferences based on their past behavior history. For example, it can suggest content similar to missions or stories that the player has enjoyed playing in the past. It can also dynamically change the dialogue and behavior of in-game characters based on the player's behavior data. For example, if the player takes a friendly action towards a particular character, that character's dialogue can be changed to reflect that friendliness.Furthermore, the game's characters can change their attitude towards players based on their actions, becoming either friendly or hostile. For example, if a player takes hostile actions towards a particular character, that character can change to a hostile attitude. Also, certain characters can offer new missions or storylines based on the player's progress. For instance, if a player completes a mission related to a character's background story, that character can offer a new mission. Additionally, data on how players interact with specific characters can be collected, and this data can be used to adjust the character's future actions and dialogue. This allows for a more personalized experience tailored to the player's play style. Finally, the results of missions players complete with specific characters can be collected, and their loyalty and trust levels can be dynamically adjusted based on those results. For example, if a player successfully completes a mission with a character, that character's loyalty can be increased. This allows the online game's NPC AI assistant system to react in real-time based on player behavior data, supporting game progression.

[0029] The AI ​​assistant system for an NPC in an online game according to this embodiment comprises a collection unit, a provision unit, and an information provision unit. The collection unit collects player behavior data. Player behavior data includes, but is not limited to, movement data, choice history, and play time. The collection unit collects data such as what actions the player has taken, which missions have been completed, and which characters the player has interacted with. The provision unit proposes new missions or new stories based on the data collected by the collection unit. The provision unit, for example, analyzes the player's behavior data and proposes missions or stories tailored to the player's preferences and progress. For example, if the player has spent a lot of time with a particular character, the provision unit can propose a new mission related to that character. The provision unit can also analyze the player's behavior data and emotional data using machine learning algorithms and propose new missions or new stories based on the results of the analysis. For example, the provision unit can analyze the player's behavior data using a neural network and propose missions tailored to the player's preferences. The information provision unit provides the player with the necessary information based on the missions or new stories proposed by the provision unit. The information provision unit provides, for example, information on how to proceed with a mission and background information on the story. For example, the information provision unit displays text messages to the player explaining how to proceed with a mission. The information provision unit can also display visual content that provides the player with background information on the story. As a result, the AI ​​assistant system for NPCs in the online game according to this embodiment can respond in real time based on the player's behavior data and support the progress of the game.

[0030] The data collection unit collects player behavior data. This data includes, but is not limited to, movement data, choice history, and play time. Specifically, the data collection unit collects detailed data such as what actions players take in the game, which missions they complete, and which characters they interact with. This also includes information such as which areas players explore, which items they acquire, and which enemies they fight. Furthermore, the data collection unit records the player's choice history and tracks the decisions players make. For example, it collects information such as which options players choose in conversations with specific characters, which quests they accept, and which rewards they choose. Data on play time is also collected to understand when players play and how much time they spend on the game. This allows the data collection unit to gain a detailed understanding of player behavior patterns and play styles, and to collect foundational data to provide to other departments. The collected data is transmitted in real time to a central database and used for analysis and recommendations. Furthermore, the data collection unit can adjust the frequency and accuracy of data collection, enabling flexible responses to specific situations and conditions. This allows the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0031] The content provision team proposes new missions or stories based on data collected by the data collection team. Specifically, the content provision team analyzes player behavior data and proposes missions and stories tailored to the player's preferences and progress. For example, if a player spends a lot of time with a particular character, the team can propose a new mission related to that character. The content provision team can also use machine learning algorithms to analyze player behavior and emotional data and propose new missions or stories based on the analysis results. For example, the content provision team can use neural networks to analyze player behavior data and propose missions tailored to the player's preferences. Furthermore, the content provision team predicts what types of missions and stories the player prefers based on the player's past behavior data and makes suggestions accordingly. For example, if a player prefers action-packed missions, the content provision team will propose a new mission with a high action element. The content provision team can also consider the player's progress and propose missions of appropriate difficulty. This allows the content provision team to always provide players with fresh and interesting content and support their continued enjoyment of the game. In addition, the content provision team can collect player feedback and continuously improve the accuracy and effectiveness of its suggestions. This allows the service provider to respond flexibly to players' needs, thereby enhancing the game's appeal.

[0032] The Information Department provides players with necessary information based on missions or new stories proposed by the department. Specifically, the Information Department provides information such as how to progress through missions and background information on the story. For example, the Information Department displays text messages explaining how to progress through missions to players. The Information Department can also display visual content that provides players with background information on the story. This makes it easier for players to understand the purpose and method of completing missions, and allows for smoother game progression. Furthermore, the Information Department can update information in real time according to the player's actions, providing players with the information they need in a timely manner. For example, when a player reaches a specific area, information related to that area is immediately displayed. The Information Department can also provide different information depending on the player's choices. For example, when a player selects a particular option, information related to that option is displayed. This allows the Information Department to quickly provide players with appropriate information and support their game progression. In addition, the Information Department can collect player feedback and continuously improve the accuracy and effectiveness of the information it provides. This allows the Information Department to respond flexibly to players' needs and enhance the appeal of the game.

[0033] The data collection unit can collect player emotion data. For example, the data collection unit can collect the player's facial expression data with a camera and estimate the emotion using an emotion estimation algorithm. The data collection unit can also collect the player's voice data with a microphone and estimate the emotion using voice analysis technology. Furthermore, the data collection unit can collect the player's biometric data (heart rate and skin electrical activity) with sensors and estimate the emotion using an emotion estimation algorithm. By collecting the player's emotion data, a more personalized experience can be provided. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the player's facial expression data acquired by the camera into a generating AI and have the generating AI perform emotion estimation.

[0034] The service provider can analyze player behavior and emotional data using machine learning algorithms and propose new missions or stories based on the analysis results. For example, the service provider can use a neural network to analyze player behavior data and propose missions tailored to the player's preferences. It can also use a support vector machine to analyze player emotional data and propose stories tailored to the player's emotions. Furthermore, it can use a decision tree to analyze player behavior and emotional data and propose missions and stories based on the player's preferences and emotions. This allows for more accurate suggestions by using machine learning algorithms. Some or all of the above processing in the service provider may be performed using a generative AI, or it may be performed without a generative AI. For example, the service provider inputs player behavior and emotional data into a generative AI, which then outputs the analysis results.

[0035] The provisioning unit can suggest missions or stories tailored to the player's preferences based on data collected by the collection unit and the player's past behavior history. For example, the provisioning unit can analyze the player's past mission completion history and suggest content similar to missions the player enjoyed playing. It can also analyze the player's choice history and suggest stories tailored to the player's preferences. Furthermore, the provisioning unit can analyze the player's play time and make new suggestions based on missions or stories the player has played for extended periods. This allows the provisioning unit to provide an experience tailored to the player's preferences through suggestions based on past behavior history. Some or all of the above processing in the provisioning unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the provisioning unit inputs the player's past behavior history into a generative AI, and the generative AI outputs the analysis results.

[0036] The service provider can dynamically change the dialogue or behavior of in-game characters based on player action data. For example, if the player takes a friendly action towards a particular character, the service provider can change that character to speak friendly dialogue. The service provider can also change a character to speak hostile dialogue if the player takes a hostile action towards that character. Furthermore, the service provider can dynamically change the character's movements and reactions based on player action data. For example, if the player takes an aggressive action towards a particular character, the service provider can change that character to act defensively. This allows for a more realistic game experience through character reactions that correspond to the player's actions. Some or all of the above processing in the service provider may be performed using a generative AI, or it may be performed without a generative AI. For example, the service provider inputs player action data into a generative AI, and the generative AI dynamically changes the character's dialogue and behavior.

[0037] The service provider can change the attitude of in-game characters to be friendly or hostile depending on the player's actions. For example, if the player takes a friendly action towards a particular character, the service provider can change that character to be friendly. The service provider can also change a character to be hostile if the player takes a hostile action towards that character. This allows for a more dynamic game experience by changing the characters' attitudes in response to the player's actions. Some or all of the above processing in the service provider may be performed using a generative AI, or it may be performed without a generative AI. For example, the service provider can input player action data into a generative AI, and the generative AI can dynamically change the character's attitude.

[0038] The provisioning unit may, depending on the player's progress, have a specific character in the game offer a new mission or a new story, and such new mission or story may be related to the background story of that specific character. For example, if the player completes a mission related to a specific character's background story, the provisioning unit will have that character offer a new mission. The provisioning unit may also have a specific character offer a new story depending on the player's progress. This increases the depth of the game by providing new missions and stories that are tailored to the player's progress. Some or all of the above processing in the provisioning unit may be performed using a generation AI, or not. For example, the provisioning unit may input the player's progress data into a generation AI, and the generation AI may suggest new missions or stories.

[0039] The collection unit collects data on interactions between the player and a specific character in the game as behavioral data, and the provision unit adjusts the future actions and dialogues of the specific character based on the data, providing an experience tailored to the player's play style. The collection unit, for example, collects the content of conversations and the history of choices the player made with a specific character. The provision unit adjusts the future actions and dialogues of the specific character based on the collected data. For example, if the player chooses a friendly option with a specific character, the provision unit adjusts the character to take friendly actions in the future. Also, if the player chooses a hostile option with a specific character, the provision unit can adjust the character to take hostile actions in the future. This allows for a more personalized experience by adjusting the character's actions and dialogues based on the player's interaction data. Some or all of the above processing in the collection unit and provision unit may be performed using a generative AI, or not. For example, the collection unit inputs the player's interaction data into a generative AI, and the generative AI adjusts the character's future actions and dialogues.

[0040] The collection unit collects the results of missions performed by the player with a specific character in the game, and the provision unit can dynamically change the loyalty and trust level of the specific character based on the results. For example, the collection unit collects the success / failure and completion rate of missions performed by the player with a specific character. The provision unit dynamically changes the loyalty and trust level of the specific character based on the collected mission results. For example, if the player successfully completes a mission with a specific character, the character's loyalty level may be increased. Conversely, if the player fails a mission with a specific character, the character's trust level may be decreased. This enhances the realism of the game by changing the character's loyalty and trust level based on mission results. Some or all of the above-described processes in the collection and provision units may be performed using a generation AI, or they may not be performed using a generation AI. For example, the collection unit inputs the player's mission result data into a generation AI, and the generation AI dynamically changes the character's loyalty and trust level.

[0041] The data collection unit can analyze the player's past behavior history and select an appropriate data collection method. For example, the data collection unit can prioritize collecting actions that the player has frequently performed in the past. The data collection unit can also analyze the player's past behavior patterns and concentrate data collection during specific time periods. Furthermore, the data collection unit can adjust the frequency of data collection based on actions that the player has preferred to perform in the past. This enables efficient data collection by selecting a data collection method based on past behavior history. Some or all of the above processing in the data collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the data collection unit inputs the player's past behavior history into a generative AI, and the generative AI selects the optimal data collection method.

[0042] The data collection unit can filter the collected behavioral data based on the player's current game progress and areas of interest. For example, if the player is in the middle of a specific mission, the data collection unit will prioritize collecting behavioral data related to that mission. The data collection unit can also collect behavioral data related to a specific character if the player has shown interest in that character. Furthermore, if the player is in a specific game area, the data collection unit can collect behavioral data related to that area. This allows for the collection of more relevant data through data filtering based on game progress and areas of interest. Some or all of the above processing in the data collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the data collection unit inputs the player's game progress data into a generative AI, which then performs the filtering.

[0043] The data collection unit can prioritize the collection of highly relevant data based on the player's geographical location when collecting behavioral data. For example, if the player is in a specific region, the data collection unit can collect event data related to that region. It can also collect item data related to a specific building if the player is inside that building. Furthermore, if the player is in a specific terrain, the data collection unit can collect enemy data related to that terrain. This allows for the collection of more relevant data through data collection based on geographical location information. Some or all of the above processing in the data collection unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the data collection unit inputs the player's geographical location information into a generation AI, which then prioritizes the collection of highly relevant data.

[0044] The data collection unit can analyze a player's online activity and collect relevant data when collecting behavioral data. For example, the data collection unit can collect relevant behavioral data based on screenshots of the game shared by the player on social media. The data collection unit can also collect data related to characters mentioned by the player on social media. Furthermore, the data collection unit can collect data related to game events participated in by the player on social media. This allows for the collection of more diverse data through data collection based on social media activity. Some or all of the above processing in the data collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the data collection unit inputs the player's social media activity data into a generative AI, and the generative AI collects the relevant data.

[0045] The service provider can adjust the level of detail in a proposal based on the importance of the mission and story. For example, for an important mission, the service provider will provide a detailed explanation and background information. For a simple mission, the service provider may provide only a brief explanation. Furthermore, for important turning points in the story, the service provider may provide a detailed story development. This allows for more appropriate information to be provided by adjusting the level of detail in the proposal based on the importance of the mission and story. Some or all of the above processing in the service provider may be performed using a generative AI, or not. For example, the service provider inputs mission and story importance data into a generative AI, and the generative AI adjusts the level of detail in the proposal.

[0046] The provisioning unit can apply different suggestion algorithms depending on the mission and story categories when making suggestions. For example, in the case of combat missions, the provisioning unit can apply a strategic suggestion algorithm. In the case of exploration missions, the provisioning unit can also apply a suggestion algorithm specialized for exploration. Furthermore, in the case of story missions, the provisioning unit can apply a suggestion algorithm that matches the progression of the story. This allows for more appropriate suggestions by applying suggestion algorithms according to the mission and story categories. Some or all of the above processing in the provisioning unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the provisioning unit inputs mission and story category data into a generative AI, and the generative AI applies a suggestion algorithm.

[0047] The provisioning department can prioritize proposals based on the submission timing of missions and stories. For example, in the case of urgent missions, the provisioning department will propose them with the highest priority. For regular event missions, the provisioning department can also propose them according to the submission timing. Furthermore, the provisioning department can propose them at appropriate times in line with the progression of the story. This allows for more timely proposals by prioritizing them based on submission timing. Some or all of the above processes in the provisioning department may be performed using a generation AI, or not. For example, the provisioning department inputs mission and story submission timing data into a generation AI, which then determines the proposal priority.

[0048] The provisioning unit can adjust the order of suggestions based on the relevance of missions and stories when making suggestions. For example, the provisioning unit will prioritize suggesting missions with high relevance. It can also suggest related missions in a sequence that matches the progression of the story. Furthermore, the provisioning unit can suggest missions with high relevance based on the player's past actions. This allows for more effective suggestions by adjusting the order of suggestions based on relevance. Some or all of the above processing in the provisioning unit may be performed using a generative AI, or not. For example, the provisioning unit inputs mission and story relevance data into a generative AI, and the generative AI adjusts the order of suggestions.

[0049] The information provision unit can analyze the player's past behavior history to select an appropriate method of information provision. For example, the information provision unit can prioritize providing information in formats that the player has previously preferred to receive. It can also analyze the player's past behavior patterns and provide information at specific time periods. Furthermore, it can provide relevant information based on information the player has shown interest in in the past. This allows for more effective information provision by selecting a method of information provision based on past behavior history. Some or all of the above processing in the information provision unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the information provision unit inputs the player's past behavior history into a generative AI, which then selects the optimal method of information provision.

[0050] The information provision unit can customize the means of providing information based on the player's current game progress. For example, if the player is in the middle of a particular mission, the information provision unit can provide information related to that mission. It can also provide information related to a particular character if the player has shown interest in that character. Furthermore, if the player is in a particular game area, the information provision unit can provide information related to that area. This allows for more appropriate information provision by customizing the means of information provision based on game progress. Some or all of the above processing in the information provision unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the information provision unit inputs the player's game progress data into a generative AI, which then customizes the means of information provision.

[0051] The information provision unit can select an appropriate method of providing information based on the player's geographical location. For example, if the player is in a specific region, the information provision unit can provide event information related to that region. It can also provide item information related to a specific building if the player is inside that building. Furthermore, if the player is in a specific terrain, the information provision unit can provide enemy information related to that terrain. This allows for more relevant information to be provided by selecting an information provision method based on geographical location. Some or all of the above processing in the information provision unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the information provision unit inputs the player's geographical location information into a generation AI, which then selects an appropriate method of providing information.

[0052] The information provision unit can analyze the player's online activity and propose means of providing information when providing information. For example, the information provision unit can provide relevant information based on screenshots of the game shared by the player on social media. It can also provide information related to characters mentioned by the player on social media. Furthermore, the information provision unit can provide information related to game events that the player participated in on social media. This enables more diverse information provision by proposing means of providing information based on social media activity. Some or all of the above processing in the information provision unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the information provision unit inputs the player's social media activity data into a generative AI, and the generative AI proposes means of providing information.

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

[0054] The AI ​​assistant system for NPCs in online games can estimate a player's skill level based on their behavior data and suggest missions and storylines appropriate to that level. For example, if a player is estimated to be a beginner, it can suggest easy missions and tutorials. Conversely, if a player is estimated to be an advanced player, it can suggest more difficult missions and challenges. Furthermore, the system can adjust the dialogue and behavior of in-game characters according to the player's skill level. For instance, characters can be made to offer helpful advice to beginner players. This allows for a more personalized experience tailored to the player's skill level.

[0055] The AI ​​assistant system for NPCs in online games can estimate a player's play style based on their behavior data and suggest missions and storylines tailored to that style. For example, if a player prefers exploration, it can suggest exploration-related missions. Similarly, if a player prefers combat, it can suggest combat-related missions. Furthermore, it can adjust the dialogue and behavior of in-game characters according to the player's play style. For instance, for players who prefer exploration, characters can be modified to provide exploration hints. This allows for a more personalized experience for each player.

[0056] The AI ​​assistant system for NPCs in online games can estimate a player's interests based on their behavioral data and suggest missions and storylines tailored to those interests. For example, if a player is interested in a particular character, the system can suggest missions related to that character. Similarly, if a player is interested in a particular item, the system can suggest missions related to that item. Furthermore, the system can adjust the dialogue and behavior of in-game characters according to the player's interests. For instance, if a player is interested in a particular character, that character can be made to provide more information. This allows the system to offer an experience that is tailored to the player's interests.

[0057] The AI ​​assistant system for NPCs in online games can estimate a player's preferred playtime based on their behavior data and suggest missions and stories appropriate to that time. For example, if a player often plays at night, the system can suggest missions and stories suitable for nighttime play. Similarly, if a player often plays during the day, the system can suggest missions and stories suitable for daytime play. Furthermore, the system can adjust the dialogue and behavior of in-game characters according to the player's playtime. For instance, for players who play at night, characters can be modified to provide information related to nighttime. This allows the system to provide an experience tailored to the player's playtime.

[0058] The AI ​​assistant system for NPCs in online games can estimate a player's preferred game genre based on their behavior data and suggest missions and stories tailored to that genre. For example, if a player prefers RPGs, it can suggest RPG-related missions and stories. Similarly, if a player prefers action games, it can suggest action-related missions and stories. Furthermore, it can adjust the dialogue and behavior of in-game characters according to the player's preferred game genre. For instance, for a player who prefers RPGs, the character's dialogue can be modified to provide RPG-related information. This allows for a more personalized gaming experience tailored to the player's preferences.

[0059] The AI ​​assistant system for NPCs in online games can estimate a player's preferred in-game activities based on their behavioral data and suggest missions and storylines tailored to those activities. For example, if a player enjoys crafting, it can suggest crafting-related missions and storylines. Similarly, if a player prefers PvP, it can suggest PvP-related missions and storylines. Furthermore, it can adjust the dialogue and behavior of in-game characters according to the player's preferred activities. For instance, for players who enjoy crafting, characters can be modified to provide crafting hints. This allows for a more personalized experience tailored to the player's interests.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The data collection unit collects player behavior data. This data includes movement data, choice history, and play time. The data collection unit collects data such as what actions the player took, which missions they completed, and which characters they interacted with. Step 2: The provisioning department proposes new missions or new stories based on the data collected by the collection department. The provisioning department analyzes the player's behavioral data and proposes missions and stories tailored to the player's preferences and progress. For example, if a player spends a lot of time with a particular character, the provisioning department will propose a new mission related to that character. The provisioning department can also use machine learning algorithms to analyze the player's behavioral and emotional data and propose new missions or new stories based on the results of the analysis. For example, a neural network can be used to propose missions tailored to the player's preferences. Step 3: The Information Department provides players with the necessary information based on the mission or new story proposed by the Information Department. The Information Department provides information such as how to progress through the mission and background information on the story. For example, the Information Department displays text messages explaining how to progress through the mission to the player. It can also display visual content that provides players with background information on the story.

[0062] (Example of form 2) An AI assistant system for an NPC in an online game, according to an embodiment of the present invention, is a system that responds in real time to the player's actions and the progress of the game, and plays a role in advancing the game's story, providing missions, and providing information. The AI ​​assistant system for an NPC in an online game collects player action data, proposes new missions or new stories based on the collected data, and provides the player with necessary information. For example, the AI ​​assistant system for an NPC in an online game collects data such as what actions the player has taken, which missions have been completed, and which characters the player has interacted with. This data is input into the AI ​​assistant. Next, based on the collected data, it proposes new missions or new stories. The AI ​​assistant analyzes the player's action data and proposes missions and stories that match the player's preferences and progress. For example, if the player has spent a lot of time with a particular character, it can propose a new mission related to that character. Furthermore, it provides the player with necessary information based on the proposed mission or new story. For example, it provides information on how to proceed with the mission and background information on the story. This allows the player to progress through the game smoothly. It can also collect and analyze the player's emotional data. For example, it can analyze what emotions the player is feeling during the game and propose missions or stories based on the results. This allows for the provision of an experience tailored to the player's emotions. Furthermore, it can suggest missions and stories that match the player's preferences based on their past behavior history. For example, it can suggest content similar to missions or stories that the player has enjoyed playing in the past. It can also dynamically change the dialogue and behavior of in-game characters based on the player's behavior data. For example, if the player takes a friendly action towards a particular character, that character's dialogue can be changed to reflect that friendliness.Furthermore, the game's characters can change their attitude towards players based on their actions, becoming either friendly or hostile. For example, if a player takes hostile actions towards a particular character, that character can change to a hostile attitude. Also, certain characters can offer new missions or storylines based on the player's progress. For instance, if a player completes a mission related to a character's background story, that character can offer a new mission. Additionally, data on how players interact with specific characters can be collected, and this data can be used to adjust the character's future actions and dialogue. This allows for a more personalized experience tailored to the player's play style. Finally, the results of missions players complete with specific characters can be collected, and their loyalty and trust levels can be dynamically adjusted based on those results. For example, if a player successfully completes a mission with a character, that character's loyalty can be increased. This allows the online game's NPC AI assistant system to react in real-time based on player behavior data, supporting game progression.

[0063] The AI ​​assistant system for an NPC in an online game according to this embodiment comprises a collection unit, a provision unit, and an information provision unit. The collection unit collects player behavior data. Player behavior data includes, but is not limited to, movement data, choice history, and play time. The collection unit collects data such as what actions the player has taken, which missions have been completed, and which characters the player has interacted with. The provision unit proposes new missions or new stories based on the data collected by the collection unit. The provision unit, for example, analyzes the player's behavior data and proposes missions or stories tailored to the player's preferences and progress. For example, if the player has spent a lot of time with a particular character, the provision unit can propose a new mission related to that character. The provision unit can also analyze the player's behavior data and emotional data using machine learning algorithms and propose new missions or new stories based on the results of the analysis. For example, the provision unit can analyze the player's behavior data using a neural network and propose missions tailored to the player's preferences. The information provision unit provides the player with the necessary information based on the missions or new stories proposed by the provision unit. The information provision unit provides, for example, information on how to proceed with a mission and background information on the story. For example, the information provision unit displays text messages to the player explaining how to proceed with a mission. The information provision unit can also display visual content that provides the player with background information on the story. As a result, the AI ​​assistant system for NPCs in the online game according to this embodiment can respond in real time based on the player's behavior data and support the progress of the game.

[0064] The data collection unit collects player behavior data. This data includes, but is not limited to, movement data, choice history, and play time. Specifically, the data collection unit collects detailed data such as what actions players take in the game, which missions they complete, and which characters they interact with. This also includes information such as which areas players explore, which items they acquire, and which enemies they fight. Furthermore, the data collection unit records the player's choice history and tracks the decisions players make. For example, it collects information such as which options players choose in conversations with specific characters, which quests they accept, and which rewards they choose. Data on play time is also collected to understand when players play and how much time they spend on the game. This allows the data collection unit to gain a detailed understanding of player behavior patterns and play styles, and to collect foundational data to provide to other departments. The collected data is transmitted in real time to a central database and used for analysis and recommendations. Furthermore, the data collection unit can adjust the frequency and accuracy of data collection, enabling flexible responses to specific situations and conditions. This allows the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0065] The content provision team proposes new missions or stories based on data collected by the data collection team. Specifically, the content provision team analyzes player behavior data and proposes missions and stories tailored to the player's preferences and progress. For example, if a player spends a lot of time with a particular character, the team can propose a new mission related to that character. The content provision team can also use machine learning algorithms to analyze player behavior and emotional data and propose new missions or stories based on the analysis results. For example, the content provision team can use neural networks to analyze player behavior data and propose missions tailored to the player's preferences. Furthermore, the content provision team predicts what types of missions and stories the player prefers based on the player's past behavior data and makes suggestions accordingly. For example, if a player prefers action-packed missions, the content provision team will propose a new mission with a high action element. The content provision team can also consider the player's progress and propose missions of appropriate difficulty. This allows the content provision team to always provide players with fresh and interesting content and support their continued enjoyment of the game. In addition, the content provision team can collect player feedback and continuously improve the accuracy and effectiveness of its suggestions. This allows the service provider to respond flexibly to players' needs, thereby enhancing the game's appeal.

[0066] The Information Department provides players with necessary information based on missions or new stories proposed by the department. Specifically, the Information Department provides information such as how to progress through missions and background information on the story. For example, the Information Department displays text messages explaining how to progress through missions to players. The Information Department can also display visual content that provides players with background information on the story. This makes it easier for players to understand the purpose and method of completing missions, and allows for smoother game progression. Furthermore, the Information Department can update information in real time according to the player's actions, providing players with the information they need in a timely manner. For example, when a player reaches a specific area, information related to that area is immediately displayed. The Information Department can also provide different information depending on the player's choices. For example, when a player selects a particular option, information related to that option is displayed. This allows the Information Department to quickly provide players with appropriate information and support their game progression. In addition, the Information Department can collect player feedback and continuously improve the accuracy and effectiveness of the information it provides. This allows the Information Department to respond flexibly to players' needs and enhance the appeal of the game.

[0067] The data collection unit can collect player emotion data. For example, the data collection unit can collect the player's facial expression data with a camera and estimate the emotion using an emotion estimation algorithm. The data collection unit can also collect the player's voice data with a microphone and estimate the emotion using voice analysis technology. Furthermore, the data collection unit can collect the player's biometric data (heart rate and skin electrical activity) with sensors and estimate the emotion using an emotion estimation algorithm. By collecting the player's emotion data, a more personalized experience can be provided. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the player's facial expression data acquired by the camera into a generating AI and have the generating AI perform emotion estimation.

[0068] The service provider can analyze player behavior and emotional data using machine learning algorithms and propose new missions or stories based on the analysis results. For example, the service provider can use a neural network to analyze player behavior data and propose missions tailored to the player's preferences. It can also use a support vector machine to analyze player emotional data and propose stories tailored to the player's emotions. Furthermore, it can use a decision tree to analyze player behavior and emotional data and propose missions and stories based on the player's preferences and emotions. This allows for more accurate suggestions by using machine learning algorithms. Some or all of the above processing in the service provider may be performed using a generative AI, or it may be performed without a generative AI. For example, the service provider inputs player behavior and emotional data into a generative AI, which then outputs the analysis results.

[0069] The provisioning unit can suggest missions or stories tailored to the player's preferences based on data collected by the collection unit and the player's past behavior history. For example, the provisioning unit can analyze the player's past mission completion history and suggest content similar to missions the player enjoyed playing. It can also analyze the player's choice history and suggest stories tailored to the player's preferences. Furthermore, the provisioning unit can analyze the player's play time and make new suggestions based on missions or stories the player has played for extended periods. This allows the provisioning unit to provide an experience tailored to the player's preferences through suggestions based on past behavior history. Some or all of the above processing in the provisioning unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the provisioning unit inputs the player's past behavior history into a generative AI, and the generative AI outputs the analysis results.

[0070] The service provider can dynamically change the dialogue or behavior of in-game characters based on player action data. For example, if the player takes a friendly action towards a particular character, the service provider can change that character to speak friendly dialogue. The service provider can also change a character to speak hostile dialogue if the player takes a hostile action towards that character. Furthermore, the service provider can dynamically change the character's movements and reactions based on player action data. For example, if the player takes an aggressive action towards a particular character, the service provider can change that character to act defensively. This allows for a more realistic game experience through character reactions that correspond to the player's actions. Some or all of the above processing in the service provider may be performed using a generative AI, or it may be performed without a generative AI. For example, the service provider inputs player action data into a generative AI, and the generative AI dynamically changes the character's dialogue and behavior.

[0071] The service provider can change the attitude of in-game characters to be friendly or hostile depending on the player's actions. For example, if the player takes a friendly action towards a particular character, the service provider can change that character to be friendly. The service provider can also change a character to be hostile if the player takes a hostile action towards that character. This allows for a more dynamic game experience by changing the characters' attitudes in response to the player's actions. Some or all of the above processing in the service provider may be performed using a generative AI, or it may be performed without a generative AI. For example, the service provider can input player action data into a generative AI, and the generative AI can dynamically change the character's attitude.

[0072] The provisioning unit may, depending on the player's progress, have a specific character in the game offer a new mission or a new story, and such new mission or story may be related to the background story of that specific character. For example, if the player completes a mission related to a specific character's background story, the provisioning unit will have that character offer a new mission. The provisioning unit may also have a specific character offer a new story depending on the player's progress. This increases the depth of the game by providing new missions and stories that are tailored to the player's progress. Some or all of the above processing in the provisioning unit may be performed using a generation AI, or not. For example, the provisioning unit may input the player's progress data into a generation AI, and the generation AI may suggest new missions or stories.

[0073] The collection unit collects data on interactions between the player and a specific character in the game as behavioral data, and the provision unit adjusts the future actions and dialogues of the specific character based on the data, providing an experience tailored to the player's play style. The collection unit, for example, collects the content of conversations and the history of choices the player made with a specific character. The provision unit adjusts the future actions and dialogues of the specific character based on the collected data. For example, if the player chooses a friendly option with a specific character, the provision unit adjusts the character to take friendly actions in the future. Also, if the player chooses a hostile option with a specific character, the provision unit can adjust the character to take hostile actions in the future. This allows for a more personalized experience by adjusting the character's actions and dialogues based on the player's interaction data. Some or all of the above processing in the collection unit and provision unit may be performed using a generative AI, or not. For example, the collection unit inputs the player's interaction data into a generative AI, and the generative AI adjusts the character's future actions and dialogues.

[0074] The collection unit collects the results of missions performed by the player with a specific character in the game, and the provision unit can dynamically change the loyalty and trust level of the specific character based on the results. For example, the collection unit collects the success / failure and completion rate of missions performed by the player with a specific character. The provision unit dynamically changes the loyalty and trust level of the specific character based on the collected mission results. For example, if the player successfully completes a mission with a specific character, the character's loyalty level may be increased. Conversely, if the player fails a mission with a specific character, the character's trust level may be decreased. This enhances the realism of the game by changing the character's loyalty and trust level based on mission results. Some or all of the above-described processes in the collection and provision units may be performed using a generation AI, or they may not be performed using a generation AI. For example, the collection unit inputs the player's mission result data into a generation AI, and the generation AI dynamically changes the character's loyalty and trust level.

[0075] The data collection unit can estimate the player's state and adjust the timing of behavioral data collection based on the estimated player state. For example, if the player is excited, the data collection unit can collect behavioral data more frequently to enhance real-time responses. Conversely, if the player is relaxed, the data collection unit can collect behavioral data at regular intervals to avoid excessive data collection. Furthermore, if the player is stressed, the data collection unit can temporarily stop data collection until the stress subsides. This allows for more appropriate data collection by adjusting the collection timing according to the player's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the data collection unit may be performed using or without a generative AI. For example, the data collection unit inputs the player's emotion data into a generative AI, which then adjusts the collection timing.

[0076] The data collection unit can analyze the player's past behavior history and select an appropriate data collection method. For example, the data collection unit can prioritize collecting actions that the player has frequently performed in the past. The data collection unit can also analyze the player's past behavior patterns and concentrate data collection during specific time periods. Furthermore, the data collection unit can adjust the frequency of data collection based on actions that the player has preferred to perform in the past. This enables efficient data collection by selecting a data collection method based on past behavior history. Some or all of the above processing in the data collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the data collection unit inputs the player's past behavior history into a generative AI, and the generative AI selects the optimal data collection method.

[0077] The data collection unit can filter the collected behavioral data based on the player's current game progress and areas of interest. For example, if the player is in the middle of a specific mission, the data collection unit will prioritize collecting behavioral data related to that mission. The data collection unit can also collect behavioral data related to a specific character if the player has shown interest in that character. Furthermore, if the player is in a specific game area, the data collection unit can collect behavioral data related to that area. This allows for the collection of more relevant data through data filtering based on game progress and areas of interest. Some or all of the above processing in the data collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the data collection unit inputs the player's game progress data into a generative AI, which then performs the filtering.

[0078] The data collection unit can estimate the player's state and determine the priority of data to collect based on the estimated player state. For example, if the player is excited, the data collection unit may prioritize collecting combat-related data. It may also prioritize collecting exploration-related data if the player is relaxed. Furthermore, if the player is stressed, the data collection unit may prioritize collecting data related to stress reduction. This allows for the collection of more important data by prioritizing data according to the player's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the processing described above in the data collection unit may be performed using or without a generative AI. For example, the data collection unit inputs the player's emotion data into a generative AI, which then determines the data priority.

[0079] The data collection unit can prioritize the collection of highly relevant data based on the player's geographical location when collecting behavioral data. For example, if the player is in a specific region, the data collection unit can collect event data related to that region. It can also collect item data related to a specific building if the player is inside that building. Furthermore, if the player is in a specific terrain, the data collection unit can collect enemy data related to that terrain. This allows for the collection of more relevant data through data collection based on geographical location information. Some or all of the above processing in the data collection unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the data collection unit inputs the player's geographical location information into a generation AI, which then prioritizes the collection of highly relevant data.

[0080] The data collection unit can analyze a player's online activity and collect relevant data when collecting behavioral data. For example, the data collection unit can collect relevant behavioral data based on screenshots of the game shared by the player on social media. The data collection unit can also collect data related to characters mentioned by the player on social media. Furthermore, the data collection unit can collect data related to game events participated in by the player on social media. This allows for the collection of more diverse data through data collection based on social media activity. Some or all of the above processing in the data collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the data collection unit inputs the player's social media activity data into a generative AI, and the generative AI collects the relevant data.

[0081] The offering unit can estimate the player's state and adjust the way suggestions are presented based on that estimate. For example, if the player is excited, the offering unit can propose a mission using energetic language. If the player is relaxed, the offering unit can propose a story using calm language. Furthermore, if the player is stressed, the offering unit can provide information using gentle language. This allows for more appropriate suggestions by adjusting the presentation of suggestions according to the player's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the offering unit may be performed using a generative AI or not. For example, the offering unit inputs the player's emotion data into a generative AI, and the generative AI adjusts the way suggestions are presented.

[0082] The service provider can adjust the level of detail in a proposal based on the importance of the mission and story. For example, for an important mission, the service provider will provide a detailed explanation and background information. For a simple mission, the service provider may provide only a brief explanation. Furthermore, for important turning points in the story, the service provider may provide a detailed story development. This allows for more appropriate information to be provided by adjusting the level of detail in the proposal based on the importance of the mission and story. Some or all of the above processing in the service provider may be performed using a generative AI, or not. For example, the service provider inputs mission and story importance data into a generative AI, and the generative AI adjusts the level of detail in the proposal.

[0083] The provisioning unit can apply different suggestion algorithms depending on the mission and story categories when making suggestions. For example, in the case of combat missions, the provisioning unit can apply a strategic suggestion algorithm. In the case of exploration missions, the provisioning unit can also apply a suggestion algorithm specialized for exploration. Furthermore, in the case of story missions, the provisioning unit can apply a suggestion algorithm that matches the progression of the story. This allows for more appropriate suggestions by applying suggestion algorithms according to the mission and story categories. Some or all of the above processing in the provisioning unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the provisioning unit inputs mission and story category data into a generative AI, and the generative AI applies a suggestion algorithm.

[0084] The offering unit can estimate the player's state and adjust the length of suggestions based on the estimated state. For example, if the player is in a hurry, the offering unit will provide short, concise suggestions. If the player is relaxed, the offering unit can provide longer suggestions with detailed explanations. Furthermore, if the player is excited, the offering unit can provide suggestions with visually stimulating effects. This allows for more appropriate suggestions by adjusting the length of suggestions according to the player's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the offering unit may be performed using or without a generative AI. For example, the offering unit inputs the player's emotion data into a generative AI, which then adjusts the length of the suggestions.

[0085] The provisioning department can prioritize proposals based on the submission timing of missions and stories. For example, in the case of urgent missions, the provisioning department will propose them with the highest priority. For regular event missions, the provisioning department can also propose them according to the submission timing. Furthermore, the provisioning department can propose them at appropriate times in line with the progression of the story. This allows for more timely proposals by prioritizing them based on submission timing. Some or all of the above processes in the provisioning department may be performed using a generation AI, or not. For example, the provisioning department inputs mission and story submission timing data into a generation AI, which then determines the proposal priority.

[0086] The provisioning unit can adjust the order of suggestions based on the relevance of missions and stories when making suggestions. For example, the provisioning unit will prioritize suggesting missions with high relevance. It can also suggest related missions in a sequence that matches the progression of the story. Furthermore, the provisioning unit can suggest missions with high relevance based on the player's past actions. This allows for more effective suggestions by adjusting the order of suggestions based on relevance. Some or all of the above processing in the provisioning unit may be performed using a generative AI, or not. For example, the provisioning unit inputs mission and story relevance data into a generative AI, and the generative AI adjusts the order of suggestions.

[0087] The information provider can estimate the player's state and adjust the method of information provision based on the estimated player state. For example, if the player is excited, the information provider can provide information in an energetic manner. If the player is relaxed, the information provider can also provide information in a calm manner. Furthermore, if the player is stressed, the information provider can provide information in a gentle manner. This allows for more appropriate information provision by adjusting the method of information provision according to the player's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the information provider may be performed using the generative AI or not. For example, the information provider inputs the player's emotion data into the generative AI, and the generative AI adjusts the method of information provision.

[0088] The information provision unit can analyze the player's past behavior history to select an appropriate method of information provision. For example, the information provision unit can prioritize providing information in formats that the player has previously preferred to receive. It can also analyze the player's past behavior patterns and provide information at specific time periods. Furthermore, it can provide relevant information based on information the player has shown interest in in the past. This allows for more effective information provision by selecting a method of information provision based on past behavior history. Some or all of the above processing in the information provision unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the information provision unit inputs the player's past behavior history into a generative AI, which then selects the optimal method of information provision.

[0089] The information provision unit can customize the means of providing information based on the player's current game progress. For example, if the player is in the middle of a particular mission, the information provision unit can provide information related to that mission. It can also provide information related to a particular character if the player has shown interest in that character. Furthermore, if the player is in a particular game area, the information provision unit can provide information related to that area. This allows for more appropriate information provision by customizing the means of information provision based on game progress. Some or all of the above processing in the information provision unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the information provision unit inputs the player's game progress data into a generative AI, which then customizes the means of information provision.

[0090] The information provision unit can estimate the player's state and determine the priority of information provision based on the estimated player state. For example, if the player is excited, the information provision unit may prioritize providing combat-related information. It may also prioritize providing exploration-related information if the player is relaxed. Furthermore, if the player is stressed, the information provision unit may prioritize providing stress-reducing information. This allows for the prioritization of more important information based on the player's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the information provision unit may be performed using or without a generative AI. For example, the information provision unit inputs the player's emotion data into a generative AI, which then determines the priority of information provision.

[0091] The information provision unit can select an appropriate method of providing information based on the player's geographical location. For example, if the player is in a specific region, the information provision unit can provide event information related to that region. It can also provide item information related to a specific building if the player is inside that building. Furthermore, if the player is in a specific terrain, the information provision unit can provide enemy information related to that terrain. This allows for more relevant information to be provided by selecting an information provision method based on geographical location. Some or all of the above processing in the information provision unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the information provision unit inputs the player's geographical location information into a generation AI, which then selects an appropriate method of providing information.

[0092] The information provision unit can analyze the player's online activity and propose means of providing information when providing information. For example, the information provision unit can provide relevant information based on screenshots of the game shared by the player on social media. It can also provide information related to characters mentioned by the player on social media. Furthermore, the information provision unit can provide information related to game events that the player participated in on social media. This enables more diverse information provision by proposing means of providing information based on social media activity. Some or all of the above processing in the information provision unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the information provision unit inputs the player's social media activity data into a generative AI, and the generative AI proposes means of providing information.

[0093] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0094] The AI ​​assistant system for NPCs in online games can estimate a player's skill level based on their behavior data and suggest missions and storylines appropriate to that level. For example, if a player is estimated to be a beginner, it can suggest easy missions and tutorials. Conversely, if a player is estimated to be an advanced player, it can suggest more difficult missions and challenges. Furthermore, the system can adjust the dialogue and behavior of in-game characters according to the player's skill level. For instance, characters can be made to offer helpful advice to beginner players. This allows for a more personalized experience tailored to the player's skill level.

[0095] The AI ​​assistant system for NPCs in online games can estimate a player's play style based on their behavior data and suggest missions and storylines tailored to that style. For example, if a player prefers exploration, it can suggest exploration-related missions. Similarly, if a player prefers combat, it can suggest combat-related missions. Furthermore, it can adjust the dialogue and behavior of in-game characters according to the player's play style. For instance, for players who prefer exploration, characters can be modified to provide exploration hints. This allows for a more personalized experience for each player.

[0096] The AI ​​assistant system for NPCs in online games can estimate a player's interests based on their behavioral data and suggest missions and storylines tailored to those interests. For example, if a player is interested in a particular character, the system can suggest missions related to that character. Similarly, if a player is interested in a particular item, the system can suggest missions related to that item. Furthermore, the system can adjust the dialogue and behavior of in-game characters according to the player's interests. For instance, if a player is interested in a particular character, that character can be made to provide more information. This allows the system to offer an experience that is tailored to the player's interests.

[0097] The AI ​​assistant system for NPCs in online games can estimate a player's stress level based on their behavior data and suggest missions and stories tailored to that level. For example, if a player is experiencing high stress, it can suggest relaxing missions and stories. Conversely, if a player is experiencing low stress, it can suggest challenging missions and stories. Furthermore, it can adjust the dialogue and behavior of in-game characters according to the player's stress level. For instance, a character might offer words of encouragement to a player experiencing high stress. This allows for a more personalized experience for each player based on their stress level.

[0098] The AI ​​assistant system for NPCs in online games can estimate a player's motivation based on their behavioral data and suggest missions and stories that match that motivation. For example, if a player has high motivation, it can suggest more difficult missions and stories. Conversely, if a player has low motivation, it can suggest easier missions and stories. Furthermore, it can adjust the dialogue and behavior of in-game characters according to the player's motivation. For instance, for players with low motivation, characters can be changed to offer words of encouragement. This allows for a more responsive experience for each player.

[0099] The AI ​​assistant system for NPCs in online games can estimate a player's concentration level based on their behavioral data and suggest missions and storylines tailored to that level. For example, if a player has a high level of concentration, it can suggest complex missions and storylines. Conversely, if a player has a low level of concentration, it can suggest simpler missions and storylines. Furthermore, it can adjust the dialogue and behavior of in-game characters according to the player's concentration level. For instance, for players with low concentration levels, characters can be modified to provide concise instructions. This allows for a more immersive experience tailored to the player's level of concentration.

[0100] The AI ​​assistant system for NPCs in online games can estimate the player's fatigue level based on their behavior data and suggest missions and stories appropriate to that level. For example, if a player is highly fatigued, it can suggest relaxing missions and stories. Conversely, if a player is less fatigued, it can suggest challenging missions and stories. Furthermore, it can adjust the dialogue and behavior of in-game characters according to the player's fatigue level. For instance, a character can offer words of encouragement to a highly fatigued player. This allows for a more personalized experience tailored to the player's fatigue level.

[0101] The AI ​​assistant system for NPCs in online games can estimate a player's preferred playtime based on their behavior data and suggest missions and stories appropriate to that time. For example, if a player often plays at night, the system can suggest missions and stories suitable for nighttime play. Similarly, if a player often plays during the day, the system can suggest missions and stories suitable for daytime play. Furthermore, the system can adjust the dialogue and behavior of in-game characters according to the player's playtime. For instance, for players who play at night, characters can be modified to provide information related to nighttime. This allows the system to provide an experience tailored to the player's playtime.

[0102] The AI ​​assistant system for NPCs in online games can estimate a player's preferred game genre based on their behavior data and suggest missions and stories tailored to that genre. For example, if a player prefers RPGs, it can suggest RPG-related missions and stories. Similarly, if a player prefers action games, it can suggest action-related missions and stories. Furthermore, it can adjust the dialogue and behavior of in-game characters according to the player's preferred game genre. For instance, for a player who prefers RPGs, the character's dialogue can be modified to provide RPG-related information. This allows for a more personalized gaming experience tailored to the player's preferences.

[0103] The AI ​​assistant system for NPCs in online games can estimate a player's preferred in-game activities based on their behavioral data and suggest missions and storylines tailored to those activities. For example, if a player enjoys crafting, it can suggest crafting-related missions and storylines. Similarly, if a player prefers PvP, it can suggest PvP-related missions and storylines. Furthermore, it can adjust the dialogue and behavior of in-game characters according to the player's preferred activities. For instance, for players who enjoy crafting, characters can be modified to provide crafting hints. This allows for a more personalized experience tailored to the player's interests.

[0104] The following briefly describes the processing flow for example form 2.

[0105] Step 1: The data collection unit collects player behavior data. This data includes movement data, choice history, and play time. The data collection unit collects data such as what actions the player took, which missions they completed, and which characters they interacted with. Step 2: The provisioning department proposes new missions or new stories based on the data collected by the collection department. The provisioning department analyzes the player's behavioral data and proposes missions and stories tailored to the player's preferences and progress. For example, if a player spends a lot of time with a particular character, the provisioning department will propose a new mission related to that character. The provisioning department can also use machine learning algorithms to analyze the player's behavioral and emotional data and propose new missions or new stories based on the results of the analysis. For example, a neural network can be used to propose missions tailored to the player's preferences. Step 3: The Information Department provides players with the necessary information based on the mission or new story proposed by the Information Department. The Information Department provides information such as how to progress through the mission and background information on the story. For example, the Information Department displays text messages explaining how to progress through the mission to the player. It can also display visual content that provides players with background information on the story.

[0106] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0107] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0108] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0109] For example, the data collection unit can collect player behavior data and emotional data using the camera 42 and microphone 38B of the smart device 14. The data provision unit is implemented by the specific processing unit 290 of the data processing device 12 and proposes new missions and stories based on the collected data. The information provision unit is implemented by the control unit 46A of the smart device 14 and provides the player with necessary information. For example, it displays information on how to proceed with the mission and background information of the story on the display 40A. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0110] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0111] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0112] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0113] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0114] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0115] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0116] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0117] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0118] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0119] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0120] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0121] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0122] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0123] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0124] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0125] For example, the data collection unit can collect player behavior data and emotional data using the camera 42 and microphone 238 of the smart glasses 214. The data provision unit is implemented by the specific processing unit 290 of the data processing device 12 and proposes new missions and stories based on the collected data. The information provision unit is implemented by the control unit 46A of the smart glasses 214 and provides the player with necessary information. For example, it provides information on how to proceed with the mission and background information on the story via voice through the speaker 240. The correspondence between each unit and the device and control unit is not limited to the example described above and can be changed in various ways.

[0126] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0127] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0128] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0129] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0130] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0132] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0133] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0134] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0135] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0136] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0137] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0138] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0140] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0141] For example, the data collection unit can collect player behavior data and emotional data using the camera 42 and microphone 238 of the headset terminal 314. The data provision unit is implemented by the specific processing unit 290 of the data processing device 12 and proposes new missions and stories based on the collected data. The information provision unit is implemented by the control unit 46A of the headset terminal 314 and provides the player with necessary information. For example, it displays information on how to proceed with the mission and background information of the story on the display 343. The correspondence between each unit and the devices and control units is not limited to the examples described above and can be modified in various ways.

[0142] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0143] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0144] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0145] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0146] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0148] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0149] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0150] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] For example, the data collection unit can collect player behavior data and emotional data using the camera 42 and microphone 238 of the robot 414. The data provision unit is implemented by the specific processing unit 290 of the data processing device 12 and proposes new missions and stories based on the collected data. The information provision unit is implemented by the control unit 46A of the robot 414 and provides the player with necessary information. For example, it provides information on how to proceed with the mission and background information on the story via voice through the speaker 240. The correspondence between each unit and the devices and control units is not limited to the examples described above and can be changed in various ways.

[0159] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0160] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0161] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0162] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0163] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0164] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0165] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0166] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0167] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0168] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0169] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0170] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0171] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0172] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0173] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0174] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0175] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0176] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0177] (Note 1) A data collection unit that collects player behavior data, Based on the data collected by the aforementioned collection unit, the provision unit proposes at least one of the new missions or a new story, The system comprises: an information provision unit that provides information to the player based on a mission or new story proposed by the aforementioned provision unit; A system characterized by the following features. (Note 2) The aforementioned collection unit is Collect player data The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned supply unit is, Using machine learning algorithms, we analyze player behavior data and other data, and based on the analysis results, we propose new missions or new storylines. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned supply unit is, Based on the data collected by the aforementioned collection unit and the player's past behavior history, the system proposes at least one mission or story tailored to the player's preferences. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned supply unit is, Based on player action data, dynamically change at least one of the in-game character's lines of dialogue or behavior. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned supply unit is, Depending on the player's actions, the in-game characters will change to adopt at least one friendly or hostile attitude. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned supply unit is, Depending on the player's progress, a specific character in the game will provide at least one new mission or a new story, and the new mission or story will be related to the background story of that specific character. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is The data collected from the player's interactions with a specific character in the game is referred to as the aforementioned behavioral data. The aforementioned supply unit is, Based on the aforementioned data, the future actions and dialogue of the specific character are adjusted to provide an experience tailored to the player's play style. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is The game collects the results of missions that players complete with specific characters within the game. The aforementioned supply unit is, Based on the results described above, the loyalty and trust levels of the specific character are dynamically changed. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is The system estimates the player's state and adjusts the timing of behavioral data collection based on the estimated player state. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is Analyze the player's past behavior history and select the appropriate data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is When collecting behavioral data, filtering is performed based on the player's current game progress and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned collection unit is The system estimates the player's state and determines the priority of data to collect based on the estimated player state. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned collection unit is When collecting behavioral data, the system prioritizes collecting data that is highly relevant based on the player's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned collection unit is When collecting behavioral data, analyze the player's online activity and collect relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned supply unit is, The system estimates the player's state and adjusts the proposed representation based on the estimated player state. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned supply unit is, When making a proposal, adjust the level of detail based on the importance of the mission and story. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned supply unit is, When submitting a proposal, different proposal algorithms are applied depending on the mission and story categories. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned supply unit is, The system estimates the player's state and adjusts the length of the suggestion based on the estimated player's state. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned supply unit is, When submitting proposals, prioritize them based on the submission timing of the mission and story. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned supply unit is, When making proposals, adjust the order of proposals based on their relevance to the mission and story. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned information provision unit, The system estimates the player's state and adjusts the information provided based on that estimate. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned information provision unit, When providing information, the system analyzes the player's past behavior history to select the appropriate method of information provision. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned information provision unit, When providing information, the method of providing information will be adjusted based on the player's current game progress. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned information provision unit, The system estimates the player's state and determines the priority of information provision based on the estimated player state. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned information provision unit, When providing information, the appropriate method of providing information will be selected based on the player's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned information provision unit, When providing information, we analyze the player's online activity and propose methods for providing that information. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0178] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A data collection unit that collects player behavior data, Based on the data collected by the aforementioned collection unit, the provision unit proposes at least one of the new missions or a new story, The system comprises: an information providing unit that provides information to the player based on a mission or new story proposed by the providing unit; A system characterized by the following features.

2. The aforementioned collection unit is Collect the data of the aforementioned player. The system according to feature 1.

3. The aforementioned supply unit is, Using machine learning algorithms, the system analyzes the player's behavioral and emotional data, and proposes a new mission or story based on the analysis results. The system according to feature 1.

4. The aforementioned supply unit is, Based on the data collected by the collection unit and the player's past behavior history, the unit proposes at least one mission or story tailored to the player's preferences. The system according to feature 1.

5. The aforementioned supply unit is, Based on the aforementioned player action data, at least one of the in-game character's lines of dialogue or behavior is dynamically changed. The system according to feature 1.

6. The aforementioned supply unit is, Depending on the player's actions, the in-game character changes to adopt at least one friendly or hostile attitude. The system according to feature 1.

7. The aforementioned supply unit is, Depending on the player's progress, a specific character in the game will provide at least one new mission or a new story, and the new mission or story will be related to the background story of that specific character. The system according to feature 1.

8. The aforementioned collection unit is The data obtained from the player's interactions with a specific character in the game is collected as the behavioral data. The aforementioned supply unit is, Based on the aforementioned data, the future actions and dialogue of the specific character are adjusted to provide an experience tailored to the player's play style. The system according to feature 1.

Images