Programs and systems

Abstract

To promote the usage of the artificial intelligence in a game field.SOLUTION: The system generates a third object by synthesizing a first object and a second object different from the first object with each other, and generates a third artificial intelligence used to control actions of the third object by synthesizing a first artificial intelligence used to control actions of the first object and a second artificial intelligence used to control actions of the second object.SELECTED DRAWING: Figure 7

Description

[Technical Field]

[0001] The present invention relates to a program and a system. [Background technology]

[0002] In games that users can play online, an automatic response mode may be provided to, for example, reduce the effort and time required for the user to play the game (i.e., improve the convenience for users playing the game).

[0003] In the automatic response mode, for example, an object in the game (for example, a user's character) can be made to act automatically by performing an operation according to predetermined rules.

[0004] However, in the automatic response mode, the object may not behave as intended by the user, and the user's convenience may not be improved. For this reason, it is conceivable to apply artificial intelligence to the game field, where the automatic response mode and the like are available. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Publication No. 2019-095973 Summary of the Invention [Problem to be solved by the invention]

[0006] Therefore, an object of the present invention is to provide a program and system that can promote the use of artificial intelligence in the gaming field. [Means for solving the problem]

[0007] According to one aspect of the present invention, a computer is provided comprising: a first generating means for generating a third object by combining a first object with a second object different from the first object; a third artificial intelligence (AI) for controlling the behavior of the third object by combining a first AI for controlling the behavior of the first object with a second AI for controlling the behavior of the second object; When the third object is generated A program is provided that functions as second generating means for generating the image. The first artificial intelligence is generated by learning the behavior of the first object using first learning data related to the behavior of the first object, and the behavior of the first object is controlled by the first artificial intelligence. The second artificial intelligence is generated by learning the behavior of the second object using second learning data related to the behavior of the second object, and the behavior of the second object is controlled by the second artificial intelligence. When the first learning data and the second learning data are inconsistent and the operation period of the first artificial intelligence is longer than the operation period of the second artificial intelligence, the second generation means generates the third artificial intelligence by learning using the first learning data. The behavior of the third object is controlled by the third artificial intelligence. [Effects of the Invention]

[0008] The present invention makes it possible to promote the use of artificial intelligence in the gaming field. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of a game system according to a first embodiment. [Figure 2] FIG. 2 is a diagram showing an example of the hardware configuration of a user terminal. [Figure 3] FIG. 2 is a diagram illustrating an example of a hardware configuration of a server device. [Figure 4] FIG. 2 is a diagram showing an example of the functional configuration of a user terminal. [Figure 5] FIG. 2 is a diagram illustrating an example of the functional configuration of a server device. [Figure 6] 10 is a flowchart showing an example of a processing procedure of the game system when a user playing a location information game participates in an event. [Figure 7] 10 is a flowchart showing an example of a processing sequence of the game system when artificial intelligence is handed over from the first position information game to the second position information game. [Figure 8] FIG. 10 is a diagram showing an example of a takeover setting screen. [Figure 9] FIG. 10 is a diagram showing another example of the takeover setting screen. [Figure 10] FIG. 10 is a diagram showing yet another example of the takeover setting screen. [Figure 11]FIG. 2 is a diagram for explaining an outline of a learning model in the present embodiment. [Figure 12] FIG. 2 is a diagram for explaining an outline of a learning model in the present embodiment. [Figure 13] FIG. 10 is a diagram showing an example of a processing procedure of the game system according to the second embodiment. [Figure 14] FIG. 2 is a diagram showing an outline of the operation of the game system according to the present embodiment. [Figure 15] 3A and 3B are diagrams for explaining characters and artificial intelligence in the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. (First embodiment) Fig. 1 shows an example of the configuration of a game system according to the first embodiment. The game system 1 shown in Fig. 1 is configured to enable users to play games online, for example, and includes a user terminal 10 and a server device 20.

[0011] The user terminal 10 is, for example, an electronic device used by a user. In this embodiment, it is assumed that the user terminal 10 is, for example, a smartphone, but the user terminal 10 may also be, for example, another electronic device such as a tablet terminal.

[0012] The server device 20 is communicably connected to a user terminal 10 via a network 30 such as the Internet.

[0013] Although only one user terminal 10 is shown in FIG. 1, the game system 1 includes a plurality of user terminals used by a plurality of users who can play the game.

[0014] Fig. 2 shows an example of the hardware configuration of the user terminal 10 shown in Fig. 1. Here, with reference to Fig. 2, the hardware configuration when the user terminal 10 is a smartphone will be described.

[0015] As shown in FIG. 2, the user terminal 10 includes a nonvolatile memory 11, a CPU 12, a main memory 13, a wireless communication device 14, a display 15, a touch panel 16, and the like.

[0016] The nonvolatile memory 11 stores various programs. The various programs stored in the nonvolatile memory 11 include, for example, an operating system (OS) and various application programs that run on the user terminal 10.

[0017] The CPU 12 is a processor for controlling the operation of various components within the user terminal 10, and executes various programs stored in the non-volatile memory 11, for example. The CPU 12 may be a single processor or may be composed of multiple processors. The various programs stored in the non-volatile memory 11 are loaded from the non-volatile memory 11 to the main memory 13 and executed by the CPU 12, and the programs (application programs) executed by the CPU 12 include a game program 13A for operating as a user terminal in the game system 1.

[0018] The wireless communication device 14 is a device for performing wireless communication with an external device (for example, a server device 20, etc.).

[0019] The display 15 is a display device for displaying, for example, various screens relating to the game played by the user.

[0020] The touch panel 16 is an input device that detects the position where the user's fingertip or the like touches, and is disposed, for example, on top of the front surface of the display 15.

[0021] The display 15 and the touch panel 16 constitute a touch screen display, and the touch screen display can detect (accept) various operations performed by the user on the screen.

[0022] Fig. 3 shows an example of the hardware configuration of the server device 20 shown in Fig. 1. As shown in Fig. 3, the server device 20 includes a nonvolatile memory 21, a CPU 22, a main memory 23, a wireless communication device 24, and the like.

[0023] The nonvolatile memory 21 stores various programs, including, for example, an operating system (OS) and various application programs that run on the server device 20.

[0024] The CPU 22 is a processor for controlling the operation of various components in the server device 20, and executes various programs stored in the nonvolatile memory 21, for example. The CPU 22 may be a single processor or may be composed of multiple processors. The various programs stored in the nonvolatile memory 21 are loaded from the nonvolatile memory 21 to the main memory 23 and executed by the CPU 22, and the programs (application programs) executed by the CPU 22 include a game program 23A for operating as a server device in the game system 1.

[0025] The wireless communication device 24 is a device for performing wireless communication with an external device (for example, the user terminal 10, etc.).

[0026] The following describes the functional configuration of the game system 1 according to this embodiment. The game system 1 according to this embodiment has a function that enables users to play games by, for example, operating in cooperation with the user terminal 10 and the server device 20.

[0027] Here, an overview of a game that a user can play in this embodiment will be described. The game system 1 (server device 20) according to this embodiment provides a gameplay environment in which a location-based game can be played, for example, using location information indicating the user's location. In a location-based game, a user can participate in events occurring in various locations by, for example, moving through real space and then moving through a virtual space associated with information about the movement in real space. Note that, as an event in this embodiment, for example, an event in which the user controls a character to battle an enemy character (hereinafter referred to as a battle event) is assumed, but other types of events (including quests, item acquisition, etc.) may also be used.

[0028] 4 shows an example of the functional configuration of the user terminal 10. As shown in FIG. 4, the user terminal 10 includes a display processing unit 101, a control unit 102, an operation receiving unit 103, and a storage unit 104.

[0029] 4 are functional units realized by, for example, the CPU 12 (computer of the user terminal 10) of the user terminal 10 executing the above-mentioned game program 13A (i.e., software). This game program 13A may be downloaded to the user terminal 10 via the network 30, or may be distributed by being stored in advance in a computer-readable storage medium.

[0030] 4 is realized by the nonvolatile memory 11 shown in FIG. 2 or another storage device (not shown).

[0031] The display processing unit 101 displays on the display 15, for example, a screen (hereinafter referred to as a map screen) including a map of the real space in which the user using the user terminal 10 moves. Note that on the map screen displayed by the display processing unit 101, for example, the user's character (the character used by the user in the game) is placed at the user's position, and an object indicating the occurrence of an event in which the user can participate is placed at a position where the event occurs (hereinafter referred to as the event occurrence position). Note that the event occurrence position may have a time limit for occurrence, or may move and displace. Examples of displacing the occurrence position include one that moves and displaces in real time, and one that moves and displaces at regular time intervals.

[0032] In this embodiment, the user's position (or the position information indicating the position) is obtained using, for example, a GPS (Global Positioning System) installed in the user terminal 10, and the display processing unit 101 updates the position (location) of the user's character placed on the map screen based on the user's position, which changes according to the user's movement.

[0033] Here, in the location-based game of this embodiment, when a user moves to the location where an event occurs (i.e., the user's character placed on the map screen displayed by the display processing unit 101 moves to the location of the object), the user can participate in the event.

[0034] The control unit 102 executes control to have the user participate in the event and progress the event in which the user has participated, based on the above-mentioned location of the user and the location where the event has occurred.

[0035] The operation accepting unit 103 accepts user operations (instructions) for playing the location-based game. When the user terminal 10 is a smartphone as described above, the operations accepted by the operation accepting unit 103 include operations of touching a fingertip to the touch panel 16 (touch screen display) of the user terminal 10 (for example, tapping, dragging, flicking, swiping, etc.).

[0036] The storage unit 104 stores, for example, game data and user data. In the game system 1, an account is issued for each user who can play the location-based game. The game data is data (information) common to the accounts and is referenced when the above-described game program 13A is executed. Specifically, the game data includes, for example, data for defining the game play environment and setting data related to the location-based game. Meanwhile, the user data is data related to the user that is managed for each user account. Specifically, the user data stored in the storage unit 104 included in the user terminal 10 (i.e., user data related to the user who uses the user terminal 10) includes, for example, data indicating the user's game progress in the location-based game and various points and items acquired by the user in the location-based game.

[0037] 5 shows an example of the functional configuration of the server device 20. As shown in FIG. 5, the server device 20 includes a storage unit 201, a data management unit 202, and a control unit 203.

[0038] The storage unit 201 shown in FIG. 5 is realized by the nonvolatile memory 21 shown in FIG. 3 or another storage device (not shown).

[0039] 5 are functional units realized by, for example, a CPU 22 (a computer of the server device 20) provided in the server device 20 executing the above-described game program 23A (i.e., software). This game program 23A may be downloaded to the server device 20 via the network 30, or may be distributed by being stored in advance in a computer-readable storage medium.

[0040] The storage unit 201 stores game data similar to the game data stored in the storage unit 104 included in the above-described user terminal 10. The storage unit 201 also stores user data for each user (i.e., a user to whom an account has been issued) who has been pre-registered in the game system 1 (server device 20).

[0041] The data management unit 202 manages the game data and user data stored in the storage unit 201. Specifically, the data management unit 202 executes processes such as adding, updating, and deleting game data and user data.

[0042] The game data and user data managed by the data management unit 202 are transmitted from the data management unit 202 (server device 20) to the user terminal 10 and stored in the storage unit 104 included in the user terminal 10.

[0043] Here, the data management unit 202 has been described as managing game data and user data, but the data management unit 202 also manages (location information indicating) the locations of users playing location-based games. The data management unit 202 also manages the locations where the above-mentioned events occur.

[0044] The control unit 203 executes various processes to provide a gameplay environment for playing the location information game (i.e., to enable users to play the location information game). Furthermore, if a multiplay can be performed in an event that occurs in the location information game, the control unit 203 executes processes to enable the multiplay. Multiplay refers to, for example, multiple matched users cooperating to play a game.

[0045] It should be noted that "provision of a game play environment" in this embodiment is realized by a game program that operates in the game system 1 (i.e., the game program 13A executed in the user terminal 10 and the game program 23A executed in the server device 20). However, the game program according to this embodiment may be a part of the game programs 13A and 23A.

[0046] Furthermore, in the game system 1 according to this embodiment, for example, the server device 20 may have at least some of the functions of the user terminal 10, or the user terminal 10 may have at least some of the functions of the server device 20. Furthermore, the game system 1 may include devices other than the user terminal 10 and the server device 20. That is, the game program according to this embodiment (game programs 13A and 23A) may be executed by the user terminal 10, the server device 20, or another device.

[0047] An example of the processing procedure of the game system 1 when a user playing a location information game participates in an event will be described below with reference to the flowchart of FIG.

[0048] When a user using the user terminal 10 plays a location-based game, the game program 13A is started in the user terminal 10, and a map screen including a map of real space is displayed on the user terminal 10 (on the display 15 provided therein). On the map screen displayed on the user terminal 10 in this manner, the user's character is placed at the user's position as described above, and an object indicating an event in which the user can participate is placed at the location where the event occurs.

[0049] When a user playing a location-based game participates in an event in this way, the user moves through real space while checking the location of the user's character and the locations of objects on the map screen.

[0050] The game system 1 acquires the position of the user moving in the real space as described above (step S1).

[0051] The user's position (or the position information indicating the position) can be acquired using, for example, a GPS installed in the user terminal 10, but may also be acquired by other methods.

[0052] The position of the user's character placed on the map screen displayed on the user terminal 10 is updated based on the user's position acquired in step S1.

[0053] When the process of step S1 is executed, the game system 1 acquires the occurrence position of an event managed, for example, in the server device 20 (data management unit 202) (step S2). Note that, if multiple events have occurred in the location-based game, for example, the occurrence positions of events near the user's location acquired in step S1 are acquired in step S2.

[0054] Here, the game system 1 determines whether or not the user has reached the event occurrence position based on the user position acquired in step S1 and the event occurrence position acquired in step S2 (step S3). Note that in step S3, for example, if the difference between the user position and the event occurrence position is equal to or less than a predetermined value, it is determined that the user has reached the event occurrence position.

[0055] If it is determined that the user has not reached the location where the event occurred (NO in step S3), the process returns to step S1 and is repeated.

[0056] On the other hand, if it is determined that the user has reached the event occurrence position (YES in step S3), the game system 1 permits the user to participate in the event and controls the progress of the event (step S4).

[0057] Now, assuming that a user participates in the above-mentioned battle event, the user can operate the user terminal 10 to instruct the actions of the user's character and engage in a battle with an enemy character.

[0058] That is, in the above-mentioned step S4, the actions of the user's character are controlled based on the user's operation on the user terminal 10, thereby controlling the progress of the event (battle event).

[0059] However, in location-based games, players may travel to various locations in real space to participate in multiple events, and if each of the multiple events requires user operation, it may not be possible to play the location-based game smoothly.

[0060] For this reason, the location-based game is provided with a mode (hereinafter referred to as an automatic response mode) for automatically playing the location-based game (automatically progressing through an event). This automatic response mode is set, for example, according to a user's operation, and when the automatic response mode is set, operations in the above-mentioned events are performed automatically, and the user can control the behavior of the user's character (i.e., progress through the event) without any operation. Although the automatic response mode has been described here, the location-based game also provides a mode (hereinafter referred to as a manual response mode) for manually playing the location-based game (i.e., progressing through an event based on a user's operation).

[0061] However, in general automatic response modes, predetermined operations are often performed, and it is difficult to automatically perform operations that are similar to those actually performed by a user (i.e., to control the character's behavior as intended by the user).

[0062] Therefore, in this embodiment, for example, when the above-mentioned manual response mode is set, we consider using artificial intelligence (learning model) that has learned the actions (behavior) of the user's character in a specific situation when the user is playing a location-based game, to control the actions of the user's character when the automatic response mode is set.

[0063] In this case, the AI ​​is updated (generated) by learning, as learning data, situation data indicating the situation of a battle held in a battle event (for example, whether the hit points of the user's character are above or below 50%) and operation data indicating the operation performed by the user to cause the character to act in that situation. With such an AI, for example, when a predetermined situation occurs while the automatic response mode is set, situation data indicating that situation is input to the AI, and the AI ​​outputs (operation data indicating) the operation that the user is expected to perform in that situation, so that the user's character can be automatically controlled based on that operation.

[0064] In other words, by using the above-described artificial intelligence, it is possible to realize (reproduce) the character's behavior as intended by the user, even when the character is automatically operated in the automatic response mode.

[0065] Generally, in games that users can play online, such as the location-based games described above, new games related to the games may be developed (released). Specifically, for example, in the case of a first location-based game featuring a first character, the first location-based game can be said to be related to a second location-based game that was developed after the first location-based game and features a second character that is the same type as or related to the first character. In other words, if the first location-based game is a previous version of the second location-based game, the second location-based game is a game related to the first location-based game.

[0066] A user who has played the above-mentioned first location information game may play a second location information game related to the first location information game, but when playing the second location information game, the user cannot use the above-mentioned artificial intelligence. Therefore, in order to use the artificial intelligence when, for example, automatic response mode is set in the second location information game, the user must repeatedly play the second location information game in manual response mode to accumulate the above-mentioned learning data (situation data and operation data), and then recreate the artificial intelligence (i.e., re-learn the character's other actions), which is time-consuming.

[0067] Therefore, in this embodiment, we propose a game system 1 that can take over (apply) artificial intelligence that has learned the behavior of a first character in a specific situation when the user is playing a first location information game to a second location information game that is different from the first location information game (related to the first location information game).

[0068] Hereinafter, an example of the processing procedure of the game system 1 when the artificial intelligence is taken over from the first position information game to the second position information game will be described with reference to the flowchart of FIG.

[0069] Although only one server device 20 is shown in the above-mentioned Figure 1, the game system 1 according to this embodiment is assumed to include, for example, a server device 20 (hereinafter referred to as the first server device 20) that provides a game play environment for playing a first location information game, and a server device 20 (hereinafter referred to as the second server device 20) that provides a game play environment for playing a second location information game.

[0070] First, when a user using the user terminal 10 plays the first position information game in manual response mode, the game system 1 accumulates learning data in response to the user's play of the first position information game (step S11). Note that the learning data accumulated in step S11 includes situation data indicating a predetermined situation when playing the first position information game, as described above, and operation data (a set of operation data) indicating an operation performed by the user to cause the first character to act in that situation.

[0071] Next, the game system 1 updates the artificial intelligence (hereinafter referred to as the artificial intelligence of the first position information game) by learning the learning data (group) accumulated in step S11 (step S12).

[0072] The AI ​​of the first position-based game updated in step S12 can output operation data indicating an operation that the user is expected to perform in a given situation when situation data indicating that situation is input, and by accumulating situation data indicating various situations and operation data indicating operations performed by the user in those situations as learning data in step S11 described above, it is possible to obtain AI capable of predicting appropriate operations in various situations in step S12. The AI ​​in this embodiment can be updated based on, for example, any machine learning algorithm.

[0073] The artificial intelligence of the first location information game updated in step S12 is stored, for example, in the user terminal 10 or the first server device 20 as part of the user data of the first location information game, and can be used to control the behavior of the user's first character when the above-mentioned automatic response mode is set.

[0074] Here, it is assumed that the user plays a second location information game, which is a game related to the first location information game as described above.

[0075] In this case, the game system 1 determines whether or not the user has started playing the second position information game (step S13). Note that in step S13, it is determined that the user has started playing the second position information game, for example, when the game program 13A for playing the second position information game is first started.

[0076] If it is determined that the user has started playing the second location information game (YES in step S13), the game system 1 executes a process of transferring the artificial intelligence of the first location information game from the first location information game to the second location information game (step S14). Note that in step S14, a process is executed in which the artificial intelligence of the first location information game, which is held in the user terminal 10 or the second server device 20 as part of the user data of the first location information game as described above, is held in the user terminal 10 or the second server device 20 as part of the user data of the second location information game, for example, by transmitting the artificial intelligence of the first location information game from the first server device 20 to the second server device 20.

[0077] By executing the process of step S14, the artificial intelligence of the first location information game carried over from the first location information game to the second location information game becomes applicable to the second location information game (step S15). When the process of step S15 is executed, an automatic response mode is set in the second location information game, making it possible to automatically control the behavior of the user's second character (a character appearing in the second location information game that is the same type as or related to the first character appearing in the first location information game) in a predetermined situation using the artificial intelligence carried over from the first location information game.

[0078] The processing of steps S11 to S15 shown in FIG. 7 may be executed at least by the entire game system 1, and at least a part of the processing may be executed on the user terminal 10 side or on the server device 20 (first and second server devices 20) side.

[0079] As described above, in this embodiment, artificial intelligence (including functions executed by the artificial intelligence, functions possessed by the artificial intelligence, learning models used by the artificial intelligence, etc.) that has learned the behavior of a first character in a specific situation (first situation) when a user is playing a first location information game (first game) is applied to a second location information game (second game), thereby controlling the behavior of a second character in a specific situation (second situation) of the second location information game.This configuration eliminates the need to generate new artificial intelligence for a second character appearing in the second location information game (i.e., to relearn the behavior of the second character), thereby promoting the utilization of artificial intelligence in the gaming field and reducing the burden on users playing the second location information game.

[0080] The artificial intelligence in this embodiment is updated by learning, for example, situation data indicating a predetermined situation and operation data indicating operations performed by a user to cause a character to act in that situation as learning data, and when a predetermined situation occurs in the second position information game, the artificial intelligence outputs operation data indicating operations to cause the second character to act in that situation by inputting situation data indicating that situation. In this embodiment, such a configuration makes it possible to reproduce an operation intended by a user (i.e., an operation previously performed by the user in a similar situation) based on operation data according to the situation output from the artificial intelligence, thereby making it possible to realize the action of the second character intended by the user.

[0081] In addition, in this embodiment, the control of the second character's behavior using artificial intelligence is performed when an automatic response mode is set, and the automatic response mode is set according to a user's operation. In this embodiment, this configuration makes it possible to perform control using artificial intelligence at the user's desired timing (time period, etc.).

[0082] Furthermore, in this embodiment, the artificial intelligence is carried over from the first location information game to the second location information game, for example, when play of the second location information game is started. With this configuration, the user can use the artificial intelligence from the moment play of the second location information game is started. Note that although it has been described here that the artificial intelligence is carried over when play of the second location information game is started, the artificial intelligence may be carried over at any timing (for example, at a timing instructed by the user) after play of the second location information game is started.

[0083] In the present embodiment, the case where the artificial intelligence generated by playing the first location information game (i.e., the artificial intelligence updated in step S12 shown in FIG. 7) is automatically applied to the second location information game has been described. However, whether or not the artificial intelligence is to be applied to the second location information game (i.e., whether or not the artificial intelligence is to be used to control the behavior of a second character appearing in the second location information game) may be specified (instructed) by the user. Furthermore, if the user is able to control multiple first characters in the first location information game, the above-mentioned artificial intelligence is generated for each of the first characters. In this case, the present embodiment may be configured to inherit only a portion of the multiple artificial intelligences generated for each first character.

[0084] Here, if it is determined in step S13 shown in Figure 7 above that the user has started playing the second location information game, the game system 1 will display, for example, a screen 10a shown in Figure 8 (hereinafter referred to as the takeover setting screen) on the user terminal 10.

[0085] In this case, the user can specify whether or not to use the artificial intelligence (learning model) of the first location information game (i.e., a previous version of the second location information game) on the handover setting screen 10a displayed on the user terminal 10 (i.e., select either "use" or "do not use").

[0086] When "Do not use" is selected on the takeover setting screen 10a and the "OK" button is pressed, the processes of steps S14 and S15 shown in Fig. 7 are not executed. On the other hand, when "Use" is selected on the takeover setting screen 10a and the "OK" button is pressed, the takeover setting screen 10a transitions to the takeover setting screen 10b.

[0087] The user can specify on the handover setting screen 10b whether to use all of the multiple artificial intelligences generated for each first character or to use only some of the multiple artificial intelligences (i.e., select either "use all" or "use some").

[0088] When "Use all" is selected on the takeover setting screen 10b and the "Confirm" button is pressed, a process is executed in step S14 shown in Fig. 7 to take over all of the multiple AIs generated for each first character from the first location information game to the second location information game. On the other hand, when "Use some" is selected on the takeover setting screen 10b, the takeover setting screen 10b transitions to a takeover setting screen 10c.

[0089] The user can select (designate) a first character whose artificial intelligence will be inherited on the takeover setting screen 10c. When a predetermined first character is selected on the takeover setting screen 10c and the "OK" button is pressed, in step S14 shown in Fig. 7, a process is executed to inherit the artificial intelligence generated for the selected first character (i.e., the artificial intelligence that has learned the behavior of the first character).

[0090] For example, the artificial intelligence generated for a specific first character among a plurality of first characters is used to control the behavior of a second character of the same type or related to the first character among a plurality of second characters appearing in the second location-based game. In this case, a second character of the same type as the first character may be a character that is completely identical to the first character, or may be a character that at least shares the same name, etc. Furthermore, a second character related to a first character may be a character that is an evolved version of the first character, or a character that has a parent-child relationship with the first character.

[0091] Furthermore, although the above-mentioned takeover setting screen 10c has been described as selecting a first character, a second character of the same type as or related to the first character (i.e., a second character appearing in a second location-based game to which artificial intelligence is applied) may also be selected.

[0092] According to the above-described configuration, for example, it is possible to take over only a portion of the multiple artificial intelligences that have learned the behaviors of each of the multiple first characters, as specified by the user (i.e., the artificial intelligence of the character desired by the user).

[0093] Although the case where an artificial intelligence is generated for each first character (i.e., one artificial intelligence is generated for one character) has been described above, multiple artificial intelligences may be generated for one first character. Specifically, an artificial intelligence may be generated for each function of the first character (a situation in which the first character acts) for one first character. Examples of the functions of the first character include a battle function and an equipment function.

[0094] In this case, all of the multiple artificial intelligences generated for each function of the first character selected on the takeover setting screen 10c described above may be taken over, or only some of the multiple artificial intelligences may be taken over.

[0095] As described above, in the case where only some of the multiple AIs generated for each function of the first character are inherited, for example, after the first character is selected on the above-described takeover setting screen 10c, the takeover setting screen 10c transitions to the takeover setting screen 10d shown in FIG. 9, and the user can select (specify) the function of the first character to inherit the AI ​​on the takeover setting screen 10d. For example, when a "battle function" is selected on the takeover setting screen 10d and the "OK" button is pressed, the AI ​​can be inherited, which has learned the behavior of the first character selected on the takeover setting screen 10c during battle (i.e., the learning data accumulated during battle). Furthermore, when an "equipment function" is selected on the takeover setting screen 10d and the "OK" button is pressed, the AI ​​can be inherited, which has learned the behavior of the first character selected on the takeover setting screen 10c when setting (changing) the equipment (i.e., the learning data accumulated when setting the equipment).

[0096] According to the above-described configuration, for example, it is possible to inherit only a portion of the multiple artificial intelligences generated for each function of the first character that is specified by the user (i.e., the artificial intelligence for the function desired by the user).

[0097] Note that, although it has been described here that some of the multiple artificial intelligences specified by the user (multiple artificial intelligences generated for each first character or multiple artificial intelligences generated for each function of the first character) are carried over from the first location information game to the second location information game, the artificial intelligences to be carried over may also be determined automatically.

[0098] Specifically, if some of the multiple artificial intelligences generated for each first character (multiple artificial intelligences that have learned the behavior of each of the multiple first characters) are carried over, for example, an artificial intelligence generated for a first character that is the same type as or related to a second character that appears in the second location-based game may be determined to be the artificial intelligence to be carried over.

[0099] In addition, if some of the multiple artificial intelligences generated for each function of the first character (multiple artificial intelligences that have learned behaviors related to the multiple functions of the first character) are carried over, the artificial intelligence generated for functions common to or related to the first and second location-based games may be determined to be the artificial intelligence to be carried over.

[0100] In this embodiment, it has been described that the artificial intelligence is carried over from the first location information game to the second location information game, but when the artificial intelligence is carried over from the first location information game to the second location information game (i.e., the artificial intelligence that has learned the behavior of the first character is used to control the behavior of the second character), the parameter values ​​of the first character (e.g., attack power and magical power, etc.) may also be carried over from the first location information game to the second location information game, and the parameter values ​​may be used as the parameter values ​​of the second character.

[0101] Furthermore, in this embodiment, it is assumed that the first location information game is a previous version of the second location information game, but the second location information game may be any game related to the first location information game.

[0102] Furthermore, in the present embodiment, for example, an AI that has learned the behavior of a first character is described as being used to control the behavior of a second character that is the same type as or related to the first character. However, the characters in this embodiment may be any object (game content) that appears in a location-based game. That is, this embodiment may be configured such that an AI that has learned the behavior of a first object is used to control the behavior of a second object that is the same type as or related to the first object. In this case, if the object (first and second objects) is, for example, a weapon, it is conceivable that the AI ​​can be used to control the timing of an attack using the weapon. Furthermore, if the object is, for example, a skill (such as magic), it is conceivable that the AI ​​can be used to control the timing of using the skill.

[0103] Furthermore, in this embodiment, the AI ​​carried over from the first location information game can be applied to the second location information game to automatically control the behavior of a second character (a second character of the same type as or related to the first character) appearing in the second location information game, but it is also possible to play the first location information game again in manual response mode after the AI ​​has been carried over. In this way, learning data can be accumulated again by playing the first location information game in manual response mode, for example.

[0104] In this case, the user terminal 10 displays, for example, a takeover setting screen 10e shown in Fig. 10. On this takeover setting screen 10e, the user can specify whether or not to share the learning data or artificial intelligence that has been re-accumulated as described above (i.e., select either "share learning data" or "share artificial intelligence").

[0105] When "Share learning data" is selected on the takeover setting screen 10e and the "OK" button is pressed, the re-accumulated learning data is carried over from the first location information game to the second location information game as described above (i.e., the learning data is transmitted from the first server device 20 to the second server device 20), and the AI ​​held as part of the user data for the second location information game learns the learning data again. In other words, when "Share learning data" is selected as described above, the learning data is shared, and the AI ​​is updated on the second location information game (i.e., the second server device 20) side. Note that the AI ​​is also updated on the first location information game side.

[0106] On the other hand, when "Share AI" is selected on the takeover setting screen 10e and the "OK" button is pressed, the AI ​​held as part of the user data of the first position information game re-learns the accumulated learning data as described above, and the re-learned AI is taken over from the first position information game to the second position information game (i.e., the AI ​​is transmitted from the first server device 20 to the second server device 20). In other words, when "Share AI" is selected as described above, the AI ​​updated on the first position information game (i.e., the first server device 20) side is taken over to the second position information game in order to share the AI.

[0107] With this configuration, it is possible to update the artificial intelligence based on learning data acquired, for example, while the user is playing the first location-based game, thereby enabling the second character to continuously behave as intended by the user.

[0108] Here, we have described the artificial intelligence (learning model) as re-learning the learning data accumulated by playing the first location-based game in manual response mode, but the artificial intelligence (learning model) may also re-learn the learning data accumulated by playing the second location-based game in manual response mode (i.e., the learning data obtained while playing the second location-based game) after applying the artificial intelligence functions from the first location-based game to the second location-based game.

[0109] The learning model in this embodiment may be in the form of a learning model commonly used by the entire AI (FIG. 11), as described above, or in the form of a separate learning model for each of the multiple functions (elements) possessed by the AI ​​(FIG. 12). When separate learning models are provided for each of the multiple functions (elements), the data to be learned and the learning weighting parameters may be changed for each learning model. For example, Function 1 possessed by the AI ​​may generate a learning model consisting of game data 1 of Game 1 (first location-based game), and Function 2 may generate a learning model consisting of game data 1 of Game 1 (first location-based game) and game data 2 of Game 2 (second location-based game).

[0110] In this embodiment, the user is described as playing a location-based game (first and second location-based games), but the games played by the user in this embodiment are not limited to location-based games, and this embodiment is applicable to any game that has a function implemented to automatically control a specific object (or its behavior) (i.e., a mode equivalent to an automatic response mode is provided).

[0111] (Second embodiment) Next, a second embodiment will be described. Here, in the above-mentioned online games that users can play (for example, location information games, etc.), a function may be provided that allows a user to combine a first object and a second object owned by the user to generate a third object that is different from the first and second objects.

[0112] This embodiment differs from the first embodiment described above in that, when a first object and a second object are combined to generate a third object in such a game, a third artificial intelligence for controlling the behavior of the third object is generated from a first artificial intelligence (including some of the functions executed by the artificial intelligence, some of the functions possessed by the artificial intelligence, some of the learning model used by the artificial intelligence, etc.) used to control the behavior of the first object and a second artificial intelligence (including some of the functions executed by the artificial intelligence, some of the functions possessed by the artificial intelligence, some of the learning model used by the artificial intelligence, etc.) used to control the behavior of the second object.

[0113] In this embodiment, detailed description of the same parts as in the first embodiment will be omitted, and the description will focus mainly on the parts that are different from the first embodiment. Also, since the configuration of the game system according to this embodiment is the same as in the first embodiment, the description will be made using Figures 1 to 5 as appropriate.

[0114] An example of the processing procedure of the game system 1 according to this embodiment will be described below with reference to the flowchart in Fig. 13. Here, it is assumed that the game played by the user is a location information game, and that the user owns a first and a second object in the location information game. Here, the processing when the first object and the second object are combined will be described.

[0115] This position information game may be the first position information game described in the first embodiment, or may be the second position information game. Here, the first and second objects are described as first and second characters. In the first embodiment, the first character is a character appearing in the first position information game, and the second character is a character appearing in the second position information game. However, in this embodiment, the first and second characters (i.e., multiple characters to be combined) are characters appearing in, for example, the same type of position information game.

[0116] In this case, the user can perform an operation (hereinafter referred to as a "combining operation") to instruct the user terminal 10 to combine the first and second characters owned by the user. Such a combining operation is accepted by the operation accepting unit 103 included in the user terminal 10 (step S1). Note that the combining operation accepted in step S1 includes an operation to specify the first and second characters to be combined, etc.

[0117] When the process of step S1 is executed, the game system 1 executes a process of combining the first and second characters (hereinafter referred to as a first combining process) in accordance with the combining operation accepted in step S1 (step S2).

[0118] When the first synthesis process is executed in step S2, a third character is generated based on the first and second characters, and the user can own (use) the third character.

[0119] Here, the game system 1 holds, as part of the user data, a first artificial intelligence (AI) used to control the actions of the first character (i.e., the AI ​​generated for the first character) and a second artificial intelligence (AI) used to control the actions of the second character (i.e., the AI ​​generated for the second character). In this case, the game system 1 executes a process of combining the first and second AIs (hereinafter referred to as a second combining process) (step S3).

[0120] When the second synthesis process is executed in step S3, a third AI is generated based on the first and second AIs. The third AI generated in this manner is stored as part of the user data and can be used to control the behavior of the third character.

[0121] 14 shows an overview of the operation of the game system 1 in this embodiment. Here, it is assumed that the user owns a character A corresponding to a first character and a character B corresponding to a second character. Furthermore, the artificial intelligence A is an artificial intelligence (first artificial intelligence) used to control the behavior of the character A, and the artificial intelligence B is an artificial intelligence (second artificial intelligence) used to control the behavior of the character B.

[0122] In this case, in this embodiment, as shown in Figure 14, character C (third character) can be generated by combining characters A and B, and artificial intelligence C (third artificial intelligence) can be generated by combining artificial intelligence A and B.

[0123] In this embodiment, the artificial intelligence C is generated at the same time as the character C is generated, for example.

[0124] Hereinafter, with reference to FIG. 15, specific examples of the above-mentioned characters A to C (first to third characters) and artificial intelligences A to C (first to third artificial intelligences) will be described.

[0125] In Figure 15, for example, characters A and B have attack power and magic power parameters, and the attack power and magic power parameter values ​​of character A are "1000" and "200", respectively, and the attack power and magic power parameter values ​​of character B are "300" and "800", respectively.

[0126] In this case, the example shown in Figure 15 shows that by combining characters A and B, character C is generated with attack power and magic power parameter values ​​of "800" and "450", respectively. In this way, when characters A and B are combined, for example, character C may be generated with parameter values ​​determined based on the parameter values ​​of characters A and B. However, the combination (generation) of characters in this embodiment may be performed by other methods.

[0127] 15 shows that the AI ​​A used to control the actions of character A is an AI that prioritizes attack. According to this AI A, character A is controlled to prioritize actions such as attacking enemy characters over actions that would help character A recover.

[0128] 15 shows that the AI ​​B used to control the actions of character B is an AI that prioritizes recovery. According to this AI B, character B is controlled to prioritize actions that will recover character B over actions such as attacking enemy characters.

[0129] In this case, the example shown in Figure 15 shows that by combining artificial intelligences A and B, artificial intelligence C is generated, which emphasizes attack when hit points (HP) are 50% or more and recovery when hit points are less than 50%.

[0130] Here, an example of a process for generating an artificial intelligence C by combining the artificial intelligences A and B will be described.

[0131] Generally, artificial intelligence includes rule-based AI (Artificial Intelligence) and machine learning AI. Rule-based AI corresponds to a scenario type with clear correspondences, and is generated by registering predetermined rules (patterns). On the other hand, machine learning AI is generated by implementing machine learning such as unsupervised learning, supervised learning, and reinforcement learning. Note that deep learning, for example, may be applied as machine learning. The difference between rule-based AI and machine learning AI is that rule-based AI operates based on pre-registered rules, while machine learning AI operates based on appropriate rules discovered by analyzing learning data.

[0132] In this embodiment, it is assumed that the artificial intelligences A and B are rule-based AIs. In this case, the artificial intelligence C is generated by registering, for example, the rules registered in the artificial intelligence A (rules related to the behavior of character A) and the rules registered in the artificial intelligence B (rules related to the behavior of character B).

[0133] Specifically, for example, if multiple rules are registered in artificial intelligence A and multiple rules are registered in artificial intelligence B, artificial intelligence C is generated by registering a rule that is common to the multiple rules registered in artificial intelligence A and the multiple rules registered in artificial intelligence B.

[0134] For example, if there is a contradiction between a rule registered in artificial intelligence A and a rule registered in artificial intelligence B, one of the rules may be preferentially adopted (i.e., registered in artificial intelligence C).

[0135] Specifically, for example, if the operational period of artificial intelligence A is longer than the operational period of artificial intelligence B, the rules registered in artificial intelligence A may be adopted in preference to the rules registered in artificial intelligence B (i.e., artificial intelligence C may be generated so as to reflect artificial intelligence A in preference to artificial intelligence B).

[0136] Furthermore, for example, if the achievements achieved in the location-based game by character A, whose actions are controlled using artificial intelligence A, are greater than the achievements achieved in the location-based game by character B, whose actions are controlled using artificial intelligence B, the rules registered in artificial intelligence A may be adopted with priority over the rules registered in artificial intelligence B (i.e., artificial intelligence C may be generated so as to reflect artificial intelligence A with priority over artificial intelligence B). Note that the achievements achieved by a character in the location-based game include, for example, the number of battles fought in the location-based game and the number of events cleared, and these achievements are managed, for example, in user data, etc.

[0137] Furthermore, rules registered in the artificial intelligence designated by the user may be preferentially adopted.

[0138] Although the artificial intelligence in this embodiment has been described as a rule-based AI, the artificial intelligence may also be a machine learning AI. In this case, it is sufficient to generate an artificial intelligence C by integrating artificial intelligences A and B. For example, the learning data learned by artificial intelligences A and B may be stored, and the artificial intelligence C may be generated by re-learning the stored learning data learned by artificial intelligences A and B. Note that the artificial intelligence C may preferentially learn either the learning data learned by artificial intelligence A or the learning data learned by artificial intelligence B, depending on the above-mentioned operation period (learning period), results, user specifications, etc.

[0139] Furthermore, when an artificial intelligence to which situation data has been input outputs operation data as described in the first embodiment, artificial intelligences A and B may be retained as artificial intelligence C, and the operation data output from artificial intelligence A and the operation data output from artificial intelligence B may be used as the operation data output from artificial intelligence C. In this case, when the operation data output from artificial intelligence A and the operation data output from artificial intelligence B are not contradictory (i.e., match), the operation data can be used as the operation data output from artificial intelligence C. On the other hand, when the operation data output from artificial intelligence A and the operation data output from artificial intelligence B are contradictory (i.e., do not match), one of the operation data may be preferentially adopted. The operation data to be preferentially adopted may be determined according to the above-mentioned operation period (learning period), results, user specifications, etc.

[0140] As described above, in this embodiment, when generating a third object by combining a first object (e.g., a first character) with a second object (e.g., a second character) different from the first object, a third artificial intelligence used to control the behavior of the third object is generated by combining a first artificial intelligence used to control the behavior of the first object with a second artificial intelligence used to control the behavior of the second object.

[0141] In this embodiment, with this configuration, when combining multiple objects (e.g., characters, etc.), it is possible to generate and use a new artificial intelligence that reflects the artificial intelligence for controlling the behavior of each of the multiple objects as a behavioral model for the new object generated by the combination.

[0142] The present invention is not limited to the above-described embodiments, and the components can be modified and embodied in practice without departing from the spirit of the invention. Furthermore, various inventions can be created by appropriately combining multiple components disclosed in the above-described embodiments. For example, some components may be omitted from all the components shown in the embodiments. Furthermore, components from different embodiments may be appropriately combined.

[0143] The contents of this disclosure are as follows: <1> Computer, A control means for controlling the behavior of a second object in a second situation of a second game by applying a function of an artificial intelligence that has learned the behavior of a first object in a first situation when a user is playing a first game to a second game different from the first game. A program that functions as a <2> the function of the artificial intelligence is updated by learning, as learning data, situation data indicating the first situation and operation data indicating an operation performed by the user to cause the first object to act in the first situation, and when a second situation occurs in the second game, the function of the artificial intelligence outputs operation data indicating an operation to cause the second object to act in the second situation by inputting situation data indicating the second situation. <1> Program described. <3> the behavior of the second object is controlled using a function of the artificial intelligence when an automatic response mode for automatically playing the second game is set; <1> Program described. <4> the automatic response mode is set in accordance with an operation of a user playing the second game. <3> Program described. <5> The function of the artificial intelligence is carried over from the first game to the second game when play of the second game begins. <1> Program described. <6> The function of an artificial intelligence designated by a user playing the second game is taken over from among the functions of a plurality of artificial intelligences that have learned the behaviors of each of the plurality of first objects. <5> Program described. <7> Among the functions of a plurality of artificial intelligences that have learned the behavior of each of a plurality of first objects, the function of the artificial intelligence that has learned the behavior of a first object that is the same as or related to a second object that appears in the second game is taken over. <5> Program described. <8> Among the functions of the plurality of artificial intelligences that have learned behaviors related to the plurality of functions of the first object, a function of an artificial intelligence that has learned behaviors related to functions common to or related to the first game and the second game is taken over. <5> Program described. <9> When the function of the artificial intelligence is carried over from the first game to the second game, the parameter value of the first object is carried over from the first game to the second game as the parameter value of the second object. <5> Program described. <10> The second game is a game related to the first game. <1> Program described. <11> The second object is an object of the same type as or related to the first object. <1> Program described. <12> the artificial intelligence is updated based on the learning data acquired while the user is playing the second game after applying the function of the artificial intelligence from the first game to the second game; <2> Program described. <13> A system comprising a control means for controlling the behavior of a second object in a second situation of a second game by applying the functions of an artificial intelligence that has learned the behavior of a first object in a first situation when a user is playing a first game to a second game that is different from the first game. <14> A method comprising controlling the behavior of a second object in a second situation of a second game by applying to a second game different from the first game the functions of an artificial intelligence that has learned the behavior of a first object in a first situation when a user is playing a first game. <15> Computer, a first generating means for generating a third object by combining a first object with a second object different from the first object; a second generation means for generating a third artificial intelligence used to control the behavior of the third object by combining a first artificial intelligence used to control the behavior of the first object and a second artificial intelligence used to control the behavior of the second object; A program that functions as a <16> The third artificial intelligence is generated at the same time as the third object is generated. <15> Program described. <17> the first artificial intelligence is generated by registering a plurality of first rules related to the behavior of the first object; the second artificial intelligence is generated by registering a plurality of second rules related to the behavior of the second object; The second generation means generates a third artificial intelligence in which a rule common to the plurality of first rules and the plurality of second rules is registered. <15> Program described. <18> When the operation period of the first artificial intelligence is longer than the operation period of the second artificial intelligence, the second generation means generates the third artificial intelligence so as to preferentially reflect the first artificial intelligence over the second artificial intelligence. <15> Program described. <19> the second generation means generates the third artificial intelligence so as to preferentially reflect the first artificial intelligence over the second artificial intelligence when the achievements achieved by the first object in the game are greater than the achievements achieved by the second object in the game; <15> Program described. <20> the second generation means generates the third AI so as to preferentially reflect the first AI designated by a user playing the game over the second AI. <15> Program described. [Explanation of symbols]

[0144] 1...game system, 10...user terminal, 11...non-volatile memory, 12...CPU, 13...main memory, 13A...game program, 14...wireless communication device, 15...display, 16...touch panel, 20...server device, 21...non-volatile memory, 22...CPU, 23...main memory, 23A...game program, 24...wireless communication device, 101...display processing unit, 102...control unit, 103...operation reception unit, 104...storage unit, 201...storage unit, 202...data management unit, 203...control unit.

Claims

1. Computer, a first generating means for generating a third object by combining a first object with a second object different from the first object; a second generation means for generating a third artificial intelligence used to control the behavior of the third object at the timing when the third object is generated by combining a first artificial intelligence used to control the behavior of the first object and a second artificial intelligence used to control the behavior of the second object; It functions as the first artificial intelligence is generated by learning a behavior of the first object using first learning data related to the behavior of the first object, and the behavior of the first object is controlled by the first artificial intelligence; the second artificial intelligence is generated by learning a behavior of the second object using second learning data related to the behavior of the second object, and the behavior of the second object is controlled by the second artificial intelligence; the second generation means generates the third AI by learning using the first learning data when the first learning data and the second learning data are inconsistent and the operation period of the first AI is longer than the operation period of the second AI; The behavior of the third object is controlled by the third artificial intelligence program.

2. A computer, a first generating means for generating a third object by combining a first object with a second object different from the first object; a second generation means for generating a third artificial intelligence used to control the behavior of the third object at the timing when the third object is generated by combining a first artificial intelligence used to control the behavior of the first object and a second artificial intelligence used to control the behavior of the second object; It functions as the first artificial intelligence is generated by learning a behavior of the first object using first learning data related to the behavior of the first object, and the behavior of the first object is controlled by the first artificial intelligence; the second artificial intelligence is generated by learning a behavior of the second object using second learning data related to the behavior of the second object, and the behavior of the second object is controlled by the second artificial intelligence; the second generation means, when the first learning data and the second learning data are contradictory and the achievement of the first object in the game is greater than the achievement of the second object in the game, generates the third artificial intelligence by learning using the first learning data; The behavior of the third object is controlled by the third artificial intelligence program.

3. A computer, a first generating means for generating a third object by combining a first object with a second object different from the first object; a second generation means for generating a third artificial intelligence used to control the behavior of the third object at the timing when the third object is generated by combining a first artificial intelligence used to control the behavior of the first object and a second artificial intelligence used to control the behavior of the second object; It functions as the first artificial intelligence is generated by registering a first rule regarding the behavior of the first object, and the behavior of the first object is controlled based on the first rule; the second artificial intelligence is generated by registering a second rule regarding the behavior of the second object, and the behavior of the second object is controlled based on the second rule; the second generation means generates the third AI in which the first rule is registered when the first rule and the second rule are contradictory and the operation period of the first AI is longer than the operation period of the second AI; A program in which the behavior of the third object is controlled based on the first rule.

4. A computer, a first generating means for generating a third object by combining a first object with a second object different from the first object; a second generation means for generating a third artificial intelligence used to control the behavior of the third object at the timing when the third object is generated by combining a first artificial intelligence used to control the behavior of the first object and a second artificial intelligence used to control the behavior of the second object; It functions as the first artificial intelligence is generated by registering a first rule regarding the behavior of the first object, and the behavior of the first object is controlled based on the first rule; the second artificial intelligence is generated by registering a second rule regarding the behavior of the second object, and the behavior of the second object is controlled based on the second rule; the second generation means, when the first rule and the second rule are in contradiction and the achievement achieved by the first object in the game is greater than the achievement achieved by the second object in the game, generates the third artificial intelligence in which the first rule is registered; A program in which the behavior of the third object is controlled based on the first rule.

5. a first generating means for generating a third object by combining a first object with a second object different from the first object; a second generation means for generating a third artificial intelligence (AI) used to control the behavior of the third object at the timing when the third object is generated by combining a first AI used to control the behavior of the first object and a second AI used to control the behavior of the second object; Equipped with the first artificial intelligence is generated by learning a behavior of the first object using first learning data related to the behavior of the first object, and the behavior of the first object is controlled by the first artificial intelligence; the second artificial intelligence is generated by learning a behavior of the second object using second learning data related to the behavior of the second object, and the behavior of the second object is controlled by the second artificial intelligence; the second generation means generates the third AI by learning using the first learning data when the first learning data and the second learning data are inconsistent and the operation period of the first AI is longer than the operation period of the second AI; The system wherein the behavior of the third object is controlled by the third artificial intelligence.

6. A first generating means for generating a third object by combining a first object with a second object different from the first object; a second generation means for generating a third artificial intelligence (AI) used to control the behavior of the third object at the timing when the third object is generated by combining a first AI used to control the behavior of the first object and a second AI used to control the behavior of the second object; Equipped with the first artificial intelligence is generated by learning a behavior of the first object using first learning data related to the behavior of the first object, and the behavior of the first object is controlled by the first artificial intelligence; the second artificial intelligence is generated by learning a behavior of the second object using second learning data related to the behavior of the second object, and the behavior of the second object is controlled by the second artificial intelligence; the second generation means, when the first learning data and the second learning data are contradictory and the achievement of the first object in the game is greater than the achievement of the second object in the game, generates the third artificial intelligence by learning using the first learning data; The system wherein the behavior of the third object is controlled by the third artificial intelligence.

7. A first generating means for generating a third object by combining a first object with a second object different from the first object; a second generation means for generating a third artificial intelligence (AI) used to control the behavior of the third object at the timing when the third object is generated by combining a first AI used to control the behavior of the first object and a second AI used to control the behavior of the second object; Equipped with the first artificial intelligence is generated by registering a first rule regarding the behavior of the first object, and the behavior of the first object is controlled based on the first rule; the second artificial intelligence is generated by registering a second rule regarding the behavior of the second object, and the behavior of the second object is controlled based on the second rule; the second generation means generates the third AI in which the first rule is registered when the first rule and the second rule are contradictory and the operation period of the first AI is longer than the operation period of the second AI; The system controls the behavior of the third object based on the first rule.

8. A first generating means for generating a third object by combining a first object with a second object different from the first object; a second generation means for generating a third artificial intelligence (AI) used to control the behavior of the third object at the timing when the third object is generated by combining a first AI used to control the behavior of the first object and a second AI used to control the behavior of the second object; Equipped with the first artificial intelligence is generated by registering a first rule regarding the behavior of the first object, and the behavior of the first object is controlled based on the first rule; the second artificial intelligence is generated by registering a second rule regarding the behavior of the second object, and the behavior of the second object is controlled based on the second rule; the second generation means, when the first rule and the second rule are in contradiction and the achievement achieved by the first object in the game is greater than the achievement achieved by the second object in the game, generates the third artificial intelligence in which the first rule is registered; The system controls the behavior of the third object based on the first rule.

Images