WO2024171277A1

WO2024171277A1 - Information processing device and game play method

Info

Publication number: WO2024171277A1
Application number: PCT/JP2023/004907
Authority: WO
Inventors: 達紀網本; 宣之中村
Original assignee: 株式会社ソニー・インタラクティブエンタテインメント
Priority date: 2023-02-14
Filing date: 2023-02-14
Publication date: 2024-08-22

Abstract

A reception unit (110) receives user operation information, and a game execution unit (112) executes a game on the basis of the operation information. A notification unit (136) generates notification information for issuing notification of a play unit that an agent can play, and an output processing unit (120) displays the notification information so as to be superimposed over a game image. A game play controller (132) allows an agent generated for each play unit to play the game.

Description

Information processing device and game playing method

This disclosure relates to technology in which an agent plays a game on behalf of a user.

Patent document 1 discloses a system in which an AI (artificial intelligence) character progresses through a game on behalf of a user by handing over gameplay to a gameplay controller. Patent document 2 discloses a method of training a machine learning model to mimic the user's gameplay using gameplay data generated when a user plays a video game. The machine learning model is an artificial neural network that learns and mimics the user's gameplay style and tendencies. By training the machine learning model, the user's AI bot can perform gameplay that mimics the user.

Special table 2019-520154 publication Special Publication No. 2022-525413

AI agents in strategic games such as chess, shogi, and go have evolved significantly, and AI agents that outperform humans have appeared. However, in games with relatively complex rules, such as role-playing games and action games, it is still not easy to create AI agents with high playing accuracy.

　Generally, AI agents are often used as opponents for users, but if the playing accuracy of AI agents improves, users will be able to have the AI agents play on their behalf and progress through the game. Therefore, there is a need to build a system that allows users to effectively use AI agents with high playing accuracy.

An information processing device according to one embodiment of the present disclosure includes one or more processors having hardware, and the one or more processors receive operation information from a user, execute a game based on the operation information, notify the user of play units that an agent can play, and have the agent play the play units on behalf of the user.

Another aspect of the game playing method of the present disclosure is a method of playing a game in an information processing device, which accepts operation information from a user, executes a game based on the operation information, notifies the user of a play unit that an agent can play, and has the agent play that play unit on behalf of the user.

In addition, any combination of the above components, and conversions of the expressions of this disclosure between methods, devices, systems, recording media, computer programs, etc., are also valid aspects of this disclosure.

FIG. 1 is a diagram showing a game system according to an embodiment. FIG. 2 is a diagram illustrating a hardware configuration of an information processing device. FIG. 2 is a diagram illustrating functional blocks of the information processing device. FIG. 13 is a diagram showing an example of a game image. FIG. 1 is a diagram showing an example of a plurality of tasks that make up an activity. FIG. 2 is a diagram illustrating functional blocks of the server device. FIG. 13 is a diagram showing an example of a displayed notification area. FIG. 13 is a diagram showing an example of a displayed notification area. FIG. 13 is a diagram showing an example of a displayed notification area. FIG. 13 is a diagram showing an example of a displayed notification area. FIG. 13 is a diagram showing an example of a displayed notification area.

FIG. 1 shows a game system 1 according to an embodiment of the present disclosure. The game system 1 of the embodiment includes an information processing device 10 operated by a user and a server device 5. An access point (hereinafter referred to as "AP") 8 has the functions of a wireless access point and a router, and the information processing device 10 connects to the AP 8 wirelessly or via a wired connection to communicate with the server device 5 on a network 3 such as the Internet. Although FIG. 1 shows one user and one information processing device 10, in the game system 1, multiple information processing devices 10 operated by multiple users are connected to the server device 5 via the network 3.

The information processing device 10 is connected wirelessly or via a wire to an input device 6 operated by a user, and the input device 6 outputs information operated by the user to the information processing device 10. When the information processing device 10 receives operation information from the input device 6, it reflects the information in the processing of the system software and game software, and causes the output device 4 to output the processing results. In the game system 1, the information processing device 10 is a game device (game console) that executes a game, and the input device 6 is a device such as a game controller that supplies user operation information to the information processing device 10. The input device 6 may also be an input interface such as a keyboard or mouse.

The auxiliary storage device 2 is a large-capacity storage device such as an HDD (hard disk drive) or SSD (solid state drive), and may be an internal storage device, or an external storage device connected to the information processing device 10 via a USB (Universal Serial Bus) or the like. The output device 4 may be a television having a display for outputting images and a speaker for outputting sound. The output device 4 may be connected to the information processing device 10 via a wired cable, or may be connected wirelessly.

Camera 7, which is an imaging device, is provided near output device 4 and captures an image of the space around output device 4. While FIG. 1 shows an example in which camera 7 is attached to the top of output device 4, it may be disposed on the side or bottom of output device 4, and in either case, it is disposed in a position where it can capture an image of a user positioned in front of output device 4. Camera 7 may be a stereo camera.

The server device 5 provides network services to users of the game system 1. The server device 5 manages user accounts that identify each user, and each user signs in to the network service provided by the server device 5 using their user account. By signing in to the network service from the information processing device 10, users can register game save data and trophies, which are virtual rewards acquired during game play, in the server device 5. By registering the save data and trophies in the server device 5, the save data and trophies can be synchronized even if the user uses an information processing device other than the information processing device 10.

The server device 5 in the embodiment has a function of generating an AI agent that plays a game and providing it to the information processing device 10. To generate the AI agent, the server device 5 collects play data indicating the game play situation from multiple information processing devices 10. In the embodiment, the play data may be operation information of a player (user) operating the input device 6, or may be game footage (play footage) drawn based on the player's operation information. The server device 5 uses play data from one or more players to machine-learn a game operation model, and generates an AI agent (hereinafter sometimes simply referred to as an "agent") that can play the game autonomously.

In the game system 1 of the embodiment, the user can have an agent play the game on his/her behalf. While the agent is playing the game, the user does not perform any game operations related to the game, and the agent plays the game autonomously or automatically. For example, if the user is unable to operate the game because he/she has a meal, the user can have the agent play the game on his/her behalf, and the game can progress. The user can also take over operation of the game that the agent is playing midway.

The agent of the embodiment is generated by learning past play data from one or more players. The agent is a learned game operation model, and autonomously or automatically generates operation information for the input device 6 according to the progress of the game. The agent may generate game commands that the game can understand. Before the game starts, the learned game operation model is provided from the server device 5 to the information processing device 10 to assist the user in playing the game.

FIG. 2 shows the hardware configuration of the information processing device 10. The information processing device 10 is configured to include a main power button 20, a power ON LED 21, a standby LED 22, a system controller 24, a clock 26, a device controller 30, a media drive 32, a USB module 34, a flash memory 36, a wireless communication module 38, a wired communication module 40, a subsystem 50, and a main system 60.

The main system 60 comprises a main CPU (Central Processing Unit), a memory and memory controller serving as the main storage device, a GPU (Graphics Processing Unit), etc. The GPU is primarily used for the calculation and processing of game programs. The main CPU has the function of starting up the system software and executing the game program installed in the auxiliary storage device 2 in the environment provided by the system software. The subsystem 50 comprises a sub-CPU, a memory and memory controller serving as the main storage device, etc., but does not comprise a GPU.

While the main CPU has the function of executing game programs installed in the auxiliary storage device 2, the sub-CPU does not have such a function. However, the sub-CPU has the function of accessing the auxiliary storage device 2 and the function of sending and receiving data with the server device 5. The sub-CPU is configured with only these limited processing functions, and therefore can operate with less power consumption compared to the main CPU. These functions of the sub-CPU are executed when the main CPU is in standby mode.

The main power button 20 is an input unit through which the user inputs operations, is provided on the front of the housing of the information processing device 10, and is operated to turn on or off the power supply to the main system 60 of the information processing device 10. The power ON LED 21 lights up when the main power button 20 is turned on, and the standby LED 22 lights up when the main power button 20 is turned off. The system controller 24 detects when the main power button 20 is pressed by the user.

The clock 26 is a real-time clock that generates current date and time information and supplies it to the system controller 24, the subsystem 50, and the main system 60.

The device controller 30 is configured as an LSI (Large-Scale Integrated Circuit) that transfers information between devices like a south bridge. As shown in the figure, devices such as the system controller 24, media drive 32, USB module 34, flash memory 36, wireless communication module 38, wired communication module 40, subsystem 50, and main system 60 are connected to the device controller 30. The device controller 30 absorbs differences in the electrical characteristics and data transfer speeds of each device and controls the timing of data transfer.

The media drive 32 is a drive device that operates by mounting a ROM medium 44 on which application software such as games and license information are recorded, and reads programs, data, and the like from the ROM medium 44. The ROM medium 44 is a read-only recording medium such as an optical disk, magneto-optical disk, or Blu-ray disk.

The USB module 34 is a module that connects to an external device via a USB cable. The USB module 34 may also be connected to the auxiliary storage device 2 and the camera 7 via a USB cable. The flash memory 36 is an auxiliary storage device that constitutes the internal storage. The wireless communication module 38 wirelessly communicates with the input device 6 using a communication protocol such as the Bluetooth (registered trademark) protocol or the IEEE802.11 protocol. The wired communication module 40 communicates with an external device via a wired connection and connects to the network 3 via the AP 8.

FIG. 3 shows functional blocks of the information processing device 10. The information processing device 10 has a processing unit 100 and a communication unit 102, and executes game software. The processing unit 100 has a reception unit 110, a game execution unit 112, a game image and sound generation unit 114, an output processing unit 120, a play data acquisition unit 122, an agent acquisition unit 130, a game play controller 132, an event information acquisition unit 134, a notification unit 136, and a transmission processing unit 140. The game image and sound generation unit 114 has a game image generation unit 116 and a game sound generation unit 118.

The information processing device 10 includes a computer, which executes a program to realize the various functions shown in FIG. 3. The computer includes hardware such as a memory into which the program is loaded, one or more processors that execute the loaded program, an auxiliary storage device, and other LSIs. The processor is composed of multiple electronic circuits including semiconductor integrated circuits and LSIs, and the multiple electronic circuits may be mounted on a single chip or on multiple chips. The functional blocks shown in FIG. 3 are realized by cooperation between hardware and software, and therefore, it will be understood by those skilled in the art that these functional blocks can be realized in various forms using only hardware, only software, or a combination thereof.

The communication unit 102 receives information (operation information) of the user operating the input device 6 to play the game, and provides it to the reception unit 110. The reception unit 110 receives the user's operation information, and provides it to the game execution unit 112 as well as to the play data acquisition unit 122. The communication unit 102 communicates with the server device 5 to send and receive various information or data. The communication unit 102 may have the functions of both the wireless communication module 38 and the wired communication module 40.

The game execution unit 112 executes game software based on the user's operation information. The game software includes at least a game program, image data, and sound data. While the user is playing a game, the reception unit 110 receives the user's operation information, and the game execution unit 112 performs calculation processing to move a player character in a virtual space based on the user's operation information. The game image generation unit 116 includes a GPU, and receives the results of the calculation processing in the virtual space, and generates a game image from a viewpoint position (virtual camera) in the virtual space. The game sound generation unit 118 also generates game sound from a viewpoint position in the virtual space. The output processing unit 120 outputs the game images and game sounds from the output device 4.

FIG. 4 shows an example of a game image displayed on the output device 4.
When an event occurs in the game, the game program of the embodiment outputs event information including information for identifying the occurred event (event ID) to the event information acquisition unit 134 .

A game includes multiple activities, each of which has a start condition and an end condition. An activity is one of the play units made up of stages, quests, missions, tournaments, sessions, etc. incorporated into the game, and the game progress from when the start condition is met to when the end condition is met constitutes one activity. Activities are set appropriately by the game maker, and for example, one quest that appears in the game progress may constitute one activity, or multiple quests may constitute one activity. When multiple quests constitute one activity, the end condition for that activity is to complete all of the multiple quests.

An activity is a single unit of play, but may be made up of multiple tasks. When a game maker sets up an activity, they can divide it and set multiple tasks. In this case, one activity is made up of multiple tasks.

Figure 5 shows an example of multiple tasks that make up an activity. In this example, activity A is made up of task a, task b, and task c, and the user completes activity A by completing tasks a, b, and c in that order. For example, if activity A is made up of three quests, task a may be assigned to the first quest, task b to the second quest, and task c to the third quest. Also, if one quest is set as activity A, task a may be assigned to the first game scene, task b to the middle game scene, and task c to the last game scene. Each task makes up one play unit. Game makers have the authority to freely set the play units, which are activities and tasks.

If we call an activity the "first play unit" and a task the "second play unit," then between the two,
The relationship is: first play unit>second play unit. Note that one task may be composed of multiple subtasks, in which case the subtasks may be called "third play unit."

When an activity is started, the game program outputs event information including information identifying the start event of the activity (event ID) to the event information acquisition unit 134. When an activity is ended, the game program outputs event information including information identifying the end event of the activity (event ID) to the event information acquisition unit 134. In addition to the event ID, the event information may include information identifying the activity (activity ID), and may also include information indicating the result of the activity (for example, success or failure). The event ID is set to be different for each activity.

Similarly, when a game program starts a task, it outputs event information including information identifying the start event of the task (event ID) to the event information acquisition unit 134. Furthermore, when a game program ends a task, it outputs event information including information identifying the end event of the task (event ID) to the event information acquisition unit 134. In addition to the event ID, the event information may include information identifying the task (task ID), and may also include information indicating the result of the task (for example, success or failure). The event ID is set to be different for each task.

When the event information acquisition unit 134 acquires the event information, it generates event data by adding a user identifier (user account) that identifies the user, a game identifier (game ID) that identifies the game, and time information (timestamp) that indicates the time when the event occurred to the event information, and provides the event data to the transmission processing unit 140. The game program may output the event information including the game ID and/or the timestamp to the event information acquisition unit 134. The transmission processing unit 140 transmits the event data provided from the event information acquisition unit 134 to the server device 5 via the communication unit 102.

As described above, when the reception unit 110 receives operation information from a user, it provides the information to the game execution unit 112 and also to the play data acquisition unit 122. The play data acquisition unit 122 generates play data by adding the user account, game ID, and time information (timestamp) indicating the time of the information provided to the operation information, and provides the play data to the transmission processing unit 140. The transmission processing unit 140 transmits the play data provided by the play data acquisition unit 122 to the server device 5 via the communication unit 102.

The play data acquisition unit 122 may provide the transmission processing unit 140 with game images (play footage) generated by the game image generation unit 116 as play data, in addition to the user's operation information. At this time, the transmission processing unit 140 transmits the user's operation information and play footage as play data to the server device 5 via the communication unit 102.

In the game system 1, the process of transmitting event data and play data is performed by all information processing devices 10 connected to the server device 5, and the server device 5 collects event data and play data for various games from the multiple information processing devices 10.

FIG. 6 shows functional blocks of the server device 5. The server device 5 of the embodiment includes a processing unit 200, a communication unit 202, and a recording device 230. The processing unit 200 includes a play data acquisition unit 210, an event data acquisition unit 212, an agent generation unit 214, and an agent providing unit 216. When the play data acquisition unit 210 acquires play data transmitted from the information processing device 10, it records the play data in the play data recording unit 232. When the event data acquisition unit 212 acquires event data transmitted from the information processing device 10, it records the event data in the event data recording unit 234. When the agent generation unit 214 generates an agent that plays the game, it records the agent in the game operation model recording unit 236.

The server device 5 is an information processing device equipped with a computer, which executes a program to realize the various functions shown in FIG. 6. The computer includes hardware such as a memory into which the programs are loaded, one or more processors that execute the loaded programs, an auxiliary storage device, and other LSIs. The processor is composed of multiple electronic circuits including semiconductor integrated circuits and LSIs, and the multiple electronic circuits may be mounted on a single chip or on multiple chips. The functional blocks shown in FIG. 6 are realized by the cooperation of hardware and software, and therefore, it will be understood by those skilled in the art that these functional blocks can be realized in various forms by hardware alone, software alone, or a combination of both.

In an embodiment, the play data is used as learning data for training a game operation model, which is a machine learning model (or an artificial intelligence model). The play data may be used as teacher data in supervised learning. As described above, the play data includes operation information of the input device 6 operated by the player (user) to play the game, a user account, a game ID, and a timestamp. The agent generation unit 214 may use the play data of multiple players as teacher data to train a game operation model.

When considering the game operation by the user, during game play, the user recognizes the game situation by watching the game video (play video), and operates the input device 6 according to the game situation to progress through the game. Therefore, when the play data includes play video drawn by operation information of the input device 6, the game operation model may be trained to output operation information (or game commands) of the input device 6 when the game video (play video) that is the teacher data is input. When the game video is used as the input for the game operation model, the game operation model (machine learning model) may be a CNN (Convolutional Neural Network) that is equivalent to a multi-layer neural network including an input layer, one or more convolutional layers, and an output layer, and the agent generation unit 214 may learn each coupling coefficient (weight) in the CNN using a learning method such as deep learning.

The agent generation unit 214 may further enhance the play accuracy of the game operation model by subjecting the game operation model generated by supervised learning to reinforcement learning. Play accuracy can be evaluated based on the play time of the game operation model, the remaining HP of the player character, and other status values.

In games with relatively complicated rules, such as role-playing games, the play content often changes for each game scene, and it is not easy to improve the play accuracy of an AI agent (game operation model) that achieves an all-clear from the start of the game. In this embodiment, the agent generation unit 214 generates an AI agent for each play unit of the game, thereby improving the play accuracy of the AI agent dedicated to each play unit. As described above, the game software includes an "activity," which is a first play unit, and a "task," which is a second play unit that is even finer than that. It may also include a "subtask," which is a third play unit that is even finer than a task. The agent generation unit 214 generates an AI agent (game operation model) for each such play unit, thereby improving the play accuracy of the AI agent.

The agent generation unit 214 refers to the timestamps included in the play data and the timestamps included in the event data to identify the play data (operation information and play video) used in each unit of play (for example, an activity or task). For example, the agent generation unit 214 refers to the event data of player A and recognizes that the start event of task a occurs at 10:00 on January 1st, and the end event of task a occurs at 10:05 on January 1st, and identifies that player A's play data between 10:00 and 10:05 on January 1st is play data related to task a. In this way, the agent generation unit 214 can generate an AI agent for each unit of play by identifying the play data related to each unit of play.

For example, activity A shown in FIG. 5 is composed of task a, task b, and task c. If the agent generation unit 214 generates an AI agent specialized in the activity and an AI agent specialized in the task, it is expected that the playing accuracy of the AI agent specialized in the task, which is a small unit of play, will be higher. Therefore, it is preferable for the agent generation unit 214 to generate an AI agent specialized in a task, which is a small unit of play. Therefore, with regard to activity A, the agent generation unit 214 generates AI agents specialized in each of task A, task B, and task C.

The agent generation unit 214 evaluates the playing accuracy of each AI agent using an evaluation index such as playing time. For example, if the playing time of an AI agent is longer than a target playing time, the agent generation unit 214 determines that the playing accuracy of the AI agent is low. If the playing accuracy does not meet a predetermined standard, the agent generation unit 214 continues to perform supervised learning and/or reinforcement learning of the AI agent in order to improve the playing accuracy.

The agent generation unit 214 records an AI agent (game operation model) whose playing accuracy meets a predetermined standard in the game operation model recording unit 236. The AI agent recorded in the game operation model recording unit 236 is provided to the user before the start of the game and is used to support the user's game play, etc.

The agent generation unit 214 may generate an AI agent specialized in activity A. When evaluating play accuracy by play time, if the time that an AI agent specialized in activity A takes to play activity A (i.e., task A, task B, task C) is shorter than the total time that an AI agent specialized in task A takes to play task A, the time that an AI agent specialized in task B takes to play task B, and the time that an AI agent specialized in task C takes to play task C, the play accuracy of the AI agent specialized in activity A may be evaluated as being high. In this case, the agent generation unit 214 may record the AI agent specialized in activity A in the game operation model recording unit 236.

As shown in FIG. 5, when an activity is made up of multiple tasks, the agent generation unit 214 generates an AI agent dedicated to the activity and an AI agent dedicated to the task, and by comparing the play accuracy of both, the user can use the AI agent with the superior quality. In this way, the server device 5 generates a dedicated AI agent specialized for each play unit from the play data of multiple players.

Returning to FIG. 3, the game execution unit 112 executes the game based on information obtained by the user operating the input device 6. Before the game execution unit 112 starts the game, the agent acquisition unit 130 acquires an agent generated for the game from the server device 5. This allows the user to have the agent play the game on their behalf during the game. The agent acquisition unit 130 records the acquired agent (game operation model) in the auxiliary storage device 2.

As described above, the server device 5 records agents whose playing accuracy meets a predetermined standard in the game operation model recording unit 236, but does not record agents whose playing accuracy does not meet the predetermined standard in the game operation model recording unit 236. Therefore, within a single game, there are play units in which agents are generated and play units in which agents are not generated. Therefore, the agent acquisition unit 130 cannot acquire agents for all play units in a game, and there are play units in which agents cannot be acquired.

Therefore, the notification section 136 may notify the user of play units (activities or tasks) that the agent can play.
7 shows an example of a notification area 150 displayed on the output device 4. When a user performs a predetermined operation during gameplay, the notification unit 136 generates information for notifying a list of recommended activities and whether or not AI play is possible. When the notification information generated by the notification unit 136 is provided to the output processing unit 120, the output processing unit 120 displays the notification area 150 including such information superimposed on a game image. Note that the output processing unit 120 may display the notification area 150 on the output device 4 not only during gameplay. The notification area 150 shown in FIG. 7 displays a plurality of activities recommended to be played, and here activity A, activity B, and activity C are displayed.

The display area 150a for activity A shows that it is possible to play using an agent in part of activity A. This means that, for example, if activity A is made up of three tasks, it is not possible to use an agent in all three tasks, but it is possible to use an agent in at least one task.

The display area 150b for Activity B indicates that it is not possible to play Activity B using an agent. Therefore, the user must play Activity B on his or her own, without relying on an agent.

Display area 150c for activity C shows that all activities in activity C can be played using the activity. This means that, for example, if activity C is made up of four tasks, an agent can be used in all four tasks.

Each

display area

150a, 150b, 150c is configured as a GUI (Graphical User Interface), and when the user selects one of the display areas, the output processing unit 120 displays a notification area including a group of tasks that make up the activity of that display area. Here, it is assumed that the user has selected display area 150a.

FIG. 8 shows an example of a notification area 152 displayed on the output device 4. When the notification unit 136 generates a list of tasks included in activity A and information for notifying whether AI play is possible and provides this to the output processing unit 120, the output processing unit 120 displays the notification area 152 including such information superimposed on the game image. Task a, task b, and task c included in activity A are displayed in the notification area 152 shown in FIG. 8.

The display area 152a for task a shows that it is possible to play task a using an agent. The display area 152b for task b shows that it is not possible to play task b using an agent. The display area 152c for task c shows that it is possible to play task c using an agent.

When the user selects the user play button 152d, which is a button GUI, in the notification area 152, the reception unit 110 provides information on the user's operation of the input device 6 to the game execution unit 112, and the game execution unit 112 executes the game based on the user's operation information. At this time, the agent is not started, and the user plays the game by himself/herself.

If the user wishes to play a task with an agent, the user may select the task for which agent play is desired. For example, if the user wishes to play tasks a and c as an agent, the user presses display area 152a and display area 152c once to select them, and then selects AI play button 152e, which is a button GUI. When AI play button 152e is selected, game play controller 132 starts the agent, and game execution unit 112 executes the game based on the operation information of the agent. Note that in a play unit (task b) in which no agent exists, an agent cannot be started, so game execution unit 112 executes the game based on the operation information of the user.

If the user wishes to play with an agent for task a only, he or she presses display area 152a once to select it, and then selects AI play button 152e. If the user wishes to play with an agent for task c only, he or she presses display area 152c once to select it, and then selects AI play button 152e. The operation to select a play unit in this way is accepted by acceptance unit 110, and game play controller 132 activates an agent corresponding to the play unit selected by the user, and causes the game to be played.

Below is a description of the behavior when the user selects the AI play button 152e while tasks a and c are selected. At this time, the game play controller 132 starts up an agent (game operation model) for task a. The agent, as a player, generates operation information (or game commands) for the game, and the game execution unit 112 executes the game program for task a based on the agent's operation information. In this way, when the user requests the agent to play, the game play controller 132 starts up the agent and has the agent play the game on behalf of the user.

FIG. 9 shows an example of a notification area 154 that is displayed while an agent is playing task a. While the agent is playing the game, the notification unit 136 generates information to notify the user that the agent is playing and provides this information to the output processing unit 120, and the output processing unit 120 displays the notification area 154 containing this notification information superimposed on the game image. This allows the user to confirm that the agent is playing.

Referring to Figure 8, in activity A, a dedicated agent for task a exists, but a dedicated agent for task b does not exist. Therefore, when the agent finishes playing task a, the user must play the following task b by himself/herself.

FIG. 10 shows an example of a notification area 156 that is displayed when the agent finishes playing task a. The notification unit 136 generates information for notifying the end of the agent's play and provides it to the output processing unit 120, and the output processing unit 120 displays the notification area 156 including the notification information superimposed on the game image. This allows the user to recognize that they need to play and to begin operating the input device 6.

When the user finishes playing task b, the game play controller 132 starts an agent (game operation model) for task c. The agent generates operation information for the game, and the game execution unit 112 executes the game program for task c based on the operation information of the agent. At this time, the output processing unit 120 displays the notification area 154 shown in FIG. 9 superimposed on the game image.

In the above example, the user selects an activity from the notification area 150 and requests an agent to play a game, but the output processing unit 120 may also present the user with notification information indicating that the agent is available.

FIG. 11 shows an example of a notification area 158 that is displayed when agent play is available. When a play-by-play scene in which an agent has been generated is displayed, the notification unit 136 generates notification information indicating that the agent is available to play and provides it to the output processing unit 120, and the output processing unit 120 displays the notification area 158 containing such notification information superimposed on the game image. This allows the user to recognize that an agent is available. For example, when the user selects the notification area 158, the game play controller 132 may launch the agent and begin playing with the agent.

Note that while playing with an agent, the user can return control rights for the game to the user by performing a specified operation. For example, the user may return control rights for the game to the user by displaying the notification area 152 and selecting the user play button 152d. Also, while playing with an agent, if the user operates the input device 6, control rights for the game may be returned to the user.

Furthermore, when the user has the operation authority, if the user leaves the input device 6 without operating it for a predetermined time, the operation authority of the game may be controlled to be transferred to the agent. Furthermore, if the user is unable to complete a task successfully, the notification unit 136 may generate notification information indicating that an agent is available, and the output processing unit 120 may display such notification information superimposed on the game image. When the user's progress in the game is stalled, it is possible to support the user's play by suggesting the use of an agent.

The present disclosure has been described above based on an embodiment. This embodiment is merely an example, and those skilled in the art will understand that various modifications are possible in the combination of each of the components and each processing process, and that such modifications are also within the scope of the present disclosure. In the embodiment, an agent is used as a player on behalf of a user, but it is also possible to use an agent to generate help videos (hint videos), for example, and it is also possible to use an agent as an NPC.

In the embodiment, the game execution unit 112 is provided in the information processing device 10, but in a modified example, the game execution unit 112 may be provided in the server device 5, and the game system 1 may provide a cloud gaming service. In this case, the server device 5 may also include a game play controller 132, and the server device 5 may function like the information processing device 10.

When the agent is learning in the server device 5, the playing accuracy required of the agent only needs to be moderately high, and does not need to be extremely high. For example, the playing accuracy required may be at the same level as a player with average skill. In other words, the playing accuracy may be at a level that a human can achieve, and there is no need to require high-speed play that is impossible for a human to achieve.

In the embodiment, an example was shown in which learning about task b did not go well, and the agent's playing accuracy for task b could not be improved. This is thought to be because task b was not appropriate as a unit of play for learning.

Therefore, when developing game software, it is preferable for game makers to use an analysis device that can suggest dividing play units into lengths that are easy to learn. For example, when a game developer test-plays a certain play unit (such as a task) in game software under development, the analysis device can determine the ease of learning from the operation information and gameplay footage from the test play.

Specifically, the analysis device analyzes the operation information and play footage of one play unit, and if the context (play content) has changed, proposes dividing the play unit.
When analyzing operation information in a chronological order, if there are long periods of no operation or menu display operations are frequently performed, the analysis device may determine that the play unit is long and unsuitable for learning, and may suggest dividing the play unit.
In addition, when analyzing gameplay footage in chronological order, if there is a major scene change, the analysis device may determine that the play unit contains multiple play contents and suggest dividing the play unit.
In this way, when the analysis device detects a change in the play content from the operation information and play footage in one provisionally set play unit, it may suggest to the game maker that the one play unit be divided.

This disclosure can be used in technology where an agent plays a game on behalf of a user.

1: Game system, 5: Server device, 6: Input device, 10: Information processing device, 100: Processing unit, 102: Communication unit, 110: Reception unit, 112: Game execution unit, 114: Game image and sound generation unit, 116: Game image generation unit, 118: Game sound generation unit, 120: Output processing unit, 122: Play data acquisition unit, 130: Agent acquisition unit, 132: Game play controller, 134: Event information acquisition unit, 136: Notification unit, 140: Transmission processing unit, 200: Processing unit, 202: Communication unit, 210: Play data acquisition unit, 212: Event data acquisition unit, 214: Agent generation unit, 216: Agent provision unit, 230: Recording device, 232: Play data recording unit, 234: Event data recording unit, 236: Game operation model recording unit.

Claims

An information processing device, comprising one or more processors having hardware,
The one or more processors:
Accepts user operation information,
Execute the game based on the operation information,
The agent notifies the user of available play units;
having an agent play the play unit on behalf of the user;
Information processing device.
The one or more processors:
Accepting an operation by an agent to select a playable unit of play,
Have the agent play the selected play unit;
The information processing device according to claim 1 .
The one or more processors:
While an agent is playing, display information indicating that the agent is playing;
The information processing device according to claim 1 .
The one or more processors:
When an agent becomes unable to play, display a message indicating that the agent will stop playing;
The information processing device according to claim 2 .
The one or more processors:
During play by the user, if the agent is playable, display information indicating that the agent is playable;
The information processing device according to claim 1 .
Agents are generated for each play unit.
The one or more processors:
Have a different agent play each play unit,
The information processing device according to claim 1 .
A method for playing a game in an information processing device, comprising:
Accepts user operation information,
Execute the game based on the operation information,
The agent notifies the user of available play units;
having an agent play the play unit on behalf of the user;
How to play the game.
On the computer,
A function for receiving user operation information;
A function for executing a game based on the operation information;
A function to inform the user of the play units that the agent can play;
a function of having an agent play the unit of play on behalf of the user;
A program to achieve this.