Program, system, and method

Abstract

To provide a program, a system and a method that enable improvement of amusement.SOLUTION: A program allows a processor to function as: information acquisition means for acquiring action history information of a user in a game; population generation means for inputting the action history information to a learned model that has been learned in advance, and generating a population in a game medium subject to lottery; and lottery execution means for executing a lottery that discharges the game medium from the population generated by the population generation means.SELECTED DRAWING: Figure 8

Description

[Technical field]

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

[0002] Conventionally, online games including content (so-called gacha) that allows users to obtain characters or items (game media) selected by lottery have been known (see, for example, Patent Document 1). In this type of online game, users repeat gacha in hopes of obtaining desired characters or items, so if an attractive gacha can be implemented, the interest of the online game will increase. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Application No. 2019-026124 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in a typical gacha, the selectable characters (or items) and the selection probability of the characters are fixed in advance. Therefore, the character that the user wants is not necessarily selected. Therefore, there is room for improvement in terms of increasing the interest.

[0005] The present invention has been made in consideration of the above circumstances, and an object of the present invention is to provide a program, a system, and a method that can increase interest. [Means for solving the problem]

[0006] In order to solve the above problems, the program according to the present invention comprises: The processor, An information acquisition means for acquiring user action history information in a game; a population generation means for inputting the behavioral history information into a trained model that has been trained in advance to generate a population of game media to be selected by lottery; The means functions as a lottery execution means for executing a lottery to dispense the game medium from the population generated by the population generation means. Effect of the Invention

[0007] According to the present invention, interest can be improved. [Brief description of the drawings]

[0008] [Figure 1] 1 is a diagram showing an overview of a system according to an embodiment of the present invention; [Diagram 2] This is a conceptual diagram of the AI ​​learning process (A) and generation process (B). [Diagram 3] FIG. 1 is a diagram showing a neural network that realizes AI. [Figure 4] FIG. 2 is a hardware configuration diagram of a game server. [Diagram 5] FIG. 2 is a hardware configuration diagram of a user terminal. [Figure 6] FIG. 2 is a functional block diagram of a game server. [Figure 7] (a) is the home screen of a monster battle game, and (b) is the gacha announcement screen. [Figure 8] 13 is a flowchart showing the control executed between a user terminal, a game server, and an AI server when executing an AI gacha. [Figure 9] (a) is the AI ​​gacha waiting screen, and (b) is the AI ​​gacha screen (first time). [Figure 10] This is the initial AI gacha screen. [Figure 11] This is the AI ​​gacha lottery results screen (1st time). [Figure 12] This is the home screen after equipping the flaming sword obtained from the AI ​​gacha. [Figure 13]13 is a flowchart showing the control executed between the user terminal, the game server, and the AI ​​server when executing the AI ​​gacha (second time). [Figure 14] (a) is the AI ​​gacha screen (second time), and (b) is the AI ​​gacha lottery result screen (second time). [Figure 15] (a) is the initial AI gacha screen, and (b) is the AI ​​gacha screen (first time) related to variant example 1. [Figure 16] (a) is the event information screen, and (b) is the quest screen for the AI ​​gacha event. [Figure 17] 13A is an AI gacha screen according to the first modified example, and FIG. 13B is a reward granting screen. [Figure 18] (a) is a gacha notification screen for variant example 2, and (b) is an AI learning function setting screen. [Figure 19] This is the quest screen after the AI ​​learning function has been set to ON. [Figure 20] (a) is the learning function setting screen, and (b) is the quest screen after the AI ​​learning function has been set to ON and certain plays have been set as excluded. [Figure 21] (a) shows gameplay videos stored in memory and information related to the number of views and “likes” for those gameplay videos, and (b) shows the screen for setting input data for the trained model. [Figure 22] (a) is a gacha announcement screen for variant example 5, and (b) is a confirmation screen. [Figure 23] (a) is the registered friend screen, and (b) is the report screen. [Figure 24] FIG. 11 is a functional block diagram of a game server according to another embodiment. [Diagram 25] 13 is a flowchart showing control executed between a user terminal, a game server, and an AI server when an automatic lottery process is executed. [Figure 26] 13A is a home screen according to another embodiment, and FIG. 13B is a gacha setting screen according to another embodiment. [Figure 27] 13 is a priority setting screen. [Figure 28]13A is a gacha notification screen according to another embodiment, and FIG. 13B is a gacha lottery result screen according to another embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Note that the embodiment of the present invention described below is an example of how the present invention is embodied, and the scope of the present invention is not limited to the scope of the embodiment. Therefore, the present invention can be implemented by adding various modifications to the embodiment. In addition, the following embodiments and modifications can be combined in any combination without departing from the spirit of the present invention.

[0010] [System 1 Overview] FIG. 1 is a diagram showing an overview of a system 1 according to this embodiment. As shown in FIG. 1, the system 1 mainly includes a game server 10, an AI server 16, and a plurality of user terminals 20. Although three user terminals 20 are shown in FIG. 1, the number of user terminals 20 included in the system 1 is not limited to this. The game server 10, the AI ​​server 16, and the user terminals 20 are connected to each other so as to be able to communicate with each other via a communication network 2. A specific example of the communication network 2 is not particularly limited, and may be, for example, the Internet, a mobile communication system (e.g., 4G, 5G, etc.), a wireless network such as Wi-Fi (registered trademark), or a combination of these.

[0011] As one example, the system 1 realizes a cooperative online game in which users (players) of multiple user terminals 20A, 20B, and 20C cooperate to play. As another example, the system 1 realizes a competitive online game in which users (players) of multiple user terminals 20A, 20B, and 20C compete against each other. As yet another example, the system 1 realizes a virtual space in which users of multiple user terminals 20A, 20B, and 20C communicate with each other via avatars. These systems 1 are already well known, so detailed explanations will be omitted.

[0012] [AI Server 16 Configuration] The AI ​​server 16 is realized by, for example, a general-purpose computer such as a workstation or a personal computer. The AI ​​server 16 realizes AI (Artificial Intelligence) 16 including a trained model. As an example, the AI ​​server 16 may be equipped with a dedicated AI optimized for the online space provided by the game server 10. In this case, the game server 10 and the AI ​​server 16 may be realized by a single piece of hardware. As another example, the AI ​​server 16 may be equipped with a general-purpose AI that can be used for various purposes. The configuration of the AI ​​16 is already well known, so a detailed description will be omitted, but for example, it is configured as follows.

[0013] FIG. 2 is a conceptual diagram of the learning process (A) and the generation process (B) by the AI ​​16. FIG. 3 is a diagram showing a neural network 17 that realizes the AI ​​16. The AI ​​16 mounted on the AI ​​server 16 is a so-called "generation AI" that processes input data and generates output data. The AI ​​16 executes the learning process shown in FIG. 2(A) and the generation process shown in FIG. 2(B). The AI ​​16 also generates output data from the input data using, for example, a neural network 17 shown in FIG. 3.

[0014] As shown in FIG. 2(A), the AI ​​16 includes a learning model 16a. The learning model 16a refers to the neural network 17 before the learning process is performed. The learning model 16a becomes a trained model 16b by learning data including input data and correct answer data. The input data refers to data input to the AI ​​16. The correct answer data refers to data that should be output when the input data is input. By inputting a plurality of learning data to the learning model 16a, the neural network 17 is optimized as described below, and becomes the trained model 16b.

[0015] As shown in FIG. 2(B), the trained model 16b generates and outputs output data by inputting input data to the neural network 17. The input data and output data may be in any format, such as text, image, or audio. The input data and output data may also be in different formats. On the other hand, the format of the correct answer data is the same as the format of the output data.

[0016] 2A may be executed not only for the learning model 16a but also for the trained model 16b. Also, the AI ​​16 does not need to learn using the input data and correct answer data actually used in the present invention, and may learn using general-purpose learning data. Furthermore, the learning process executed by the AI ​​16 is not limited to "supervised learning" in which input data and correct answer data are input, but may be "unsupervised learning" in which correct answer data is not input, or may execute reinforcement learning, transfer learning, or the like.

[0017] As shown in FIG. 3, the neural network 17 of the learning model 16a or the trained model 16b is composed of an input layer L1 composed of a plurality of nodes I1, I2, and I3, an intermediate layer L2 composed of a plurality of nodes H1, H2, H3, H4, and H5, and an output layer L3 composed of a plurality of nodes O1, O2, and O3. In the example of FIG. 3, the number of nodes in the input layer L1 and the output layer L3 is the same, but the number of nodes in the input layer L1 and the output layer L3 may be different. The neural network 17 may also have a plurality of intermediate layers L2. Furthermore, FIG. 3 shows a fully connected neural network 17 in which a plurality of nodes constituting each layer L1, L2, and L3 are connected to all nodes in the adjacent layer, but the structure of the neural network 17 is not limited to this.

[0018] The learning process is a process of adjusting the weighting coefficients and biases of each node so that correct data is output from the output layer L3 when input data is input to the input layer L1. The generation process is a process of generating output data by processing the input data input to the input layer L1 using weighting coefficients and biases previously adjusted for each node, and outputting the output data from the output layer L3.

[0019] However, the specific example of the processing by the AI ​​16 described above is merely an example, and the AI ​​server 16 can employ various well-known methods. As another example, the AI ​​16 may have a network structure such as a Convolutional Neural Network (CNN). As yet another example, the network structure may have a configuration such as a Large Language Model (LLM), a Recurrent Neural Network (RNN), or a Long Short-Term Memory (LSTM). In other words, the AI ​​16 may have a network structure other than deep learning.

[0020] In this embodiment, an AI gacha is described in which the objects to be drawn are generated by the trained model 16b (AI server 16) according to the behavioral history of the user. As will be described in detail later, in the AI ​​gacha, the behavioral history information of the user is input to the trained model 16b to generate a population to be drawn.

[0021] [Game Server 10 Configuration] Fig. 2 is a hardware configuration diagram of the game server 10. The game server 10 is realized by, for example, a general-purpose computer such as a workstation or a personal computer. As shown in Fig. 2, the game server 10 mainly includes a processor 11, a memory 12, a storage 13, an input / output interface 14, and a communication interface 15. Each component of the game server 10 is connected to a communication bus 19.

[0022] The processor 11 realizes processes described below by executing a series of instructions included in a server program 13P stored in the memory 12 or the storage 13. The processor 11 is realized as, for example, a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor unit (MPU), a field-programmable gate array (FPGA), or other device.

[0023] The memory 12 temporarily holds a server program 13P and data. The server program 13P is loaded from, for example, the storage 13. The data includes data input to the game server 10 and data generated by the processor 11. For example, the memory 12 is realized as a RAM (Random Access Memory) or other volatile memory.

[0024] The storage 13 permanently holds the server program 13P and data. The storage 13 is realized, for example, as a ROM (Read-Only Memory), a hard disk drive, a flash memory, or other non-volatile storage device. The storage 13 may also be realized as a removable storage device such as a memory card. As yet another example, the storage 13 may be connected to the game server 10 as an external storage device instead of being built into the game server 10. With this configuration, for example, in a scene where a plurality of user terminals 20 are used, such as an amusement facility, it becomes possible to collectively update the server program 13P and data.

[0025] The input / output interface 14 is an interface for connecting external devices such as a monitor, an input device (e.g., a keyboard, a pointing device), an external storage device, a speaker, a camera, a microphone, a sensor, etc. to the game server 10. The processor 11 communicates with the external devices through the input / output interface 14. The input / output interface 14 is realized using, for example, a Universal Serial Bus (USB), a Digital Visual Interface (DVI), a High-Definition Multimedia Interface (HDMI, registered trademark), or other terminals.

[0026] The communication interface 15 communicates with other devices (e.g., user terminal 20) connected to the communication network 2. The communication interface 15 is realized as, for example, a wired communication interface such as a Local Area Network (LAN) or a wireless communication interface such as Wireless Fidelity (Wi-Fi), Bluetooth (registered trademark), or Near Field Communication (NFC).

[0027] [Configuration of user terminal 20] The user terminal 20 is realized, for example, as an HMD set, a tablet terminal, a smartphone, a feature phone, a laptop computer, a desktop computer, etc. In this embodiment, an example of the user terminal 20 as a tablet terminal will be described as shown in FIG.

[0028] Fig. 4 is a hardware configuration diagram of the user terminal 20. As shown in Fig. 4, the user terminal 20 mainly includes a processor 21, a memory 22, a storage 23, a communication interface 25, a monitor 31, cameras 33 and 34, a microphone 35, a speaker 36, a motion sensor 41, and an operation device 42 (operation unit). Each component of the user terminal 20 is connected to a communication bus 29.

[0029] The processor 21 realizes the processes described below by executing a series of instructions included in a terminal program 23P stored in the memory 22 or the storage 23. The processor 21 is realized as, for example, a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor unit (MPU), a field-programmable gate array (FPGA), or other devices.

[0030] The memory 22 temporarily holds the terminal program 23P and data. The terminal program 23P is loaded, for example, from the storage 23. The data includes data input to the user terminal 20 and data generated by the processor 21. For example, the memory 22 is realized as a RAM (Random Access Memory) or other volatile memory.

[0031] The storage 23 permanently holds the terminal program 23P and data. The storage 23 is realized, for example, as a ROM (Read-Only Memory), a hard disk drive, a flash memory, or other non-volatile storage device. The storage 23 may also be realized as a removable storage device such as a memory card. As yet another example, the storage 23 may be connected to the user terminal 20 as an external storage device instead of being built into the user terminal 20. With this configuration, for example, in a scene where a plurality of user terminals 20 are used, such as an amusement facility, it becomes possible to collectively update the terminal program 23P and data.

[0032] The communication interface 25 communicates with other devices (e.g., the game server 10, the AI ​​server 16) connected to the communication network 2. The communication interface 25 is realized as, for example, a wired communication interface such as a Local Area Network (LAN), or a wireless communication interface such as Wi-Fi (Wireless Fidelity), Bluetooth (registered trademark), or NFC (Near Field Communication).

[0033] The monitor 31 is provided on the surface of a flat housing, as shown in Fig. 1 for example. The monitor 31 is a display device (display unit) that displays images or videos. The camera 33 is a so-called in-camera that is attached to the surface of the flat housing and captures an image of the face of a user viewing the monitor 31. The camera 34 is a so-called out-camera that is attached to the back surface of the flat housing (the surface opposite to the monitor 31) and captures an image of the surroundings.

[0034] The microphone 35 converts the user's speech into an audio signal (electrical signal) and outputs it to the computer 26. The speaker 36 converts the audio signal output from the computer 26 into voice and outputs it to the user. Note that the user terminal 20 may include an earphone instead of the speaker 36.

[0035] The motion sensor 41 detects the motion of the housing (for example, rotation around three mutually orthogonal axes). The motion sensor 41 may be realized by, for example, an angular velocity sensor, a geomagnetic sensor, or an acceleration sensor.

[0036] The operation device 42 accepts input (operation) of commands by the user to the user terminal 20. The operation device 42 is, for example, a touch panel that is superimposed on the monitor 31 and accepts various touch operations by the user. That is, the monitor 31 according to this embodiment is a touch panel type display unit. However, the specific hardware configuration of the user terminal 20 is not limited to the above example.

[0037] [Game Server 10 Functional Block Diagram] Fig. 6 is a functional block diagram of the game server 10. As shown in Fig. 6, the server program 13P loaded into the memory 12 causes the game server 10 (processor 11) to function as an information acquisition means 110, a population generation means 120, a change display means 130, a lottery execution means 140, an awarding means 150, and a management means 160.

[0038] The information acquisition means 110 acquires action history information of the user in the game from the user terminal 20. Then, the information acquisition means 110 transmits the acquired action history information to the population generation means 120. Here, the action history information is information related to the weapon or armor equipped by the user, the attributes of the weapon or armor, the weapon, armor, and items (e.g., recovery items, etc.) used by the user in quests in the game. In addition, the action history information acquired by the information acquisition means 110 reflects the action history of the user during the period from when the AI ​​gacha is implemented in the game to when the user executes the AI ​​gacha.

[0039] The population generation means 120 inputs the behavioral history information received from the information acquisition means 110 to the trained model 16b that has been trained in advance. Then, the population generation means 120 causes the trained model 16b to generate a population of game media (weapons, armor, recovery items, etc.) that are the subject of AI gacha (lottery) according to the user's behavioral history. Here, the population is a list (see, for example, FIG. 9(b)) that associates multiple game media that can be dispensed in the lottery with the dispense probability of each of the multiple game media.

[0040] Moreover, the trained model 16b is a dedicated AI configured exclusively for the game. The trained model 16b may be tuned in advance, for example, with the frequency of use of an item set as a hyperparameter. As an example, the trained model 16b increases the probability of an item having a frequency of use equal to or greater than an upper threshold (first threshold), or adds the item to the population. As another example, the trained model 16b decreases the probability of an item having a frequency of use less than a lower threshold (second threshold), or excludes the item from the population. Alternatively, the trained model 16b may be pre-trained in advance using teacher data having the above-mentioned tendency. Note that the AI ​​is not limited to being a dedicated AI, and may be a general-purpose AI.

[0041] Furthermore, the population generation means 120 generates a new population by changing the game contents or the release probability of the game contents contained in the initial population. The population generation means 120 then obtains data relating to the new population (hereinafter referred to as "population data") from the AI ​​server 16 and stores it in the memory 12 of the game server 10.

[0042] The change display means 130 acquires the population data stored in the memory 12, and displays a new population on the monitor 31 of the user terminal 20. In addition, the change display means 130 transmits the acquired population data to the lottery executing means 140.

[0043] The lottery execution means 140 executes a lottery to dispense game media from the new population generated by the population generation means 120 based on the population data received from the change display means 130.

[0044] The granting means 150 grants the game medium obtained by lottery to the user.

[0045] The management means 160 manages the progress of the game. For example, when the user terminal 20 accepts a user operation, the management means 160 identifies the game account used by the user, obtains game progress information of the identified account, and transitions the monitor 31 to a predetermined game progress screen.

[0046] Furthermore, the management means 160 stores the save data in the memory 12 for each user account. When a game is started on the user terminal 20, the management means 160 identifies the save data corresponding to the user's account and starts the game by reading the identified save data. Furthermore, when updating the save data, the management means 160 acquires information to be updated (e.g., information indicating that the game has progressed, information indicating that the user has acquired an item, etc.) from the user terminal 20 and stores it in the corresponding memory 12, thereby updating the save data. Note that the configuration is not limited to the management means 160 storing the save data in the memory 12 for each user account, and the user terminal 20 itself may have a memory for storing and updating the save data of the game.

[0047] Next, a game according to this embodiment will be described with reference to Fig. 7 to Fig. 13. In the following, a monster battle game in which a user defeats monsters will be described as an example of the game. Also, items (weapons, etc.) will be described as an example of the game medium.

[0048] 7(a) shows a home screen of the monster battle game. Based on a command from the game server 10 (e.g., the management means 160, etc.), the game account used by the user is identified, the processor 21 of the user terminal 20 displays a predetermined screen on the monitor 31, and the user terminal 20 notifies the game server 10 of the content of the operation accepted from the user.

[0049] 7(a), the management means 160 displays a home screen on the monitor 31 of the user terminal 20. The home screen includes an owned coins, etc. display area A1, a main area A2, and an event information, etc. display area A3.

[0050] The coins and jewels display area A1 is an area for displaying the amount of coins and jewels owned by the user, as well as the user's rank. Coins and jewels are items that the user can acquire by playing battles (playing against other players in the monster battle game). However, jewels are an item that the user can also acquire by paying a fee. The rank indicates the user's rank in the monster battle game, and can be increased by the user's playing battles.

[0051] The main area A2 is an area for displaying the character used by the user and its name (Hanako in this example), an equipment button for setting the character's equipment, a button for transitioning to battle play, and a button for transitioning to the item exchange screen. When the user terminal 20 accepts the pressing of any button, the management means 160 transitions the monitor 31 to the screen corresponding to the pressed button.

[0052] The event information display area A3 is an area for displaying a button for transitioning to an event information screen and a button for transitioning to a gacha notification screen. When the user terminal 20 accepts the pressing of any button, the management means 160 transitions the monitor 31 to a screen corresponding to the pressed button.

[0053] Fig. 7(b) is a gacha notification screen. As shown in Fig. 7(b), the gacha notification screen is a screen for notifying the user of the gacha currently implemented in the monster battle game. In this example, the gacha notification screen displays AI gacha, summer vacation gacha, daily gacha, etc.

[0054] As described above, the AI ​​gacha is a gacha in which the object of the lottery is generated by the trained model 16b (AI server 16) according to the user's behavior history. The summer vacation gacha is a special gacha implemented during a specified period in the summer. The daily gacha is a gacha implemented every day. When the user terminal 20 accepts a press on an area that notifies any gacha, the management means 160 shifts the monitor 31 of the user terminal 20 to the corresponding gacha screen. In addition, a jewel purchase button for purchasing jewels and a home button for shifting to the home screen are displayed below the gacha notification screen. In the following, the control executed between the user terminal 20, the game server 10, and the AI ​​server 16 after the user terminal 20 accepts a press on the AI ​​gacha notification area will be described.

[0055] Fig. 8 is a flowchart showing the control executed between the user terminal 20, the game server 10, and the AI ​​server 16 when executing an AI gacha. When the user presses the AI ​​gacha notification area (see Fig. 7(b)) and the user terminal 20 accepts the selection of the AI ​​gacha as shown in Fig. 8 (step S10), the information acquisition means 110 acquires the user's action history information in the monster battle game from the user terminal 20 (step S20).

[0056] Next, the population generation means 120 inputs the behavior history information received from the information acquisition means 110 to the trained model 16b that has been trained in advance (step S30). Then, the population generation means 120 causes the trained model 16b to generate a population of game media that are the target of the AI ​​gacha according to the user's behavior history (step S40). At this time, the management means 160 transitions the monitor 31 to an AI gacha waiting screen.

[0057] FIG. 9(a) is an AI gacha standby screen. As shown in FIG. 9(a), the AI ​​gacha standby screen is a standby screen when the population generation means 120 generates a population that is the target of the AI ​​gacha. The AI ​​gacha standby screen displays a message saying, "We will generate a population that is optimal for you with the AI ​​gacha. Please wait a moment." Here, the population generation means 120 causes the AI ​​server 16 (trained model 16b) to generate a population so as to change the items that are the target of the AI ​​gacha to be dispensed or the probability of dispensing the items, based on the user's behavior history information.

[0058] When the AI ​​server 16 generates a population, the population generation means 120 acquires the population data from the AI ​​server 16 and stores it in the memory 12 (step S50).

[0059] Next, the change display means 130 acquires the population data stored in the memory 12, and displays the population on the monitor 31 of the user terminal 20 (step S60). At this time, the management means 160 transitions the monitor 31 to an AI gacha screen.

[0060] 9(b) is an AI gacha screen. The AI ​​gacha screen is a screen for displaying the population generated by the population generation means 120 as a lottery target. The change display means 130 displays a flaming sword, a flaming shield, flaming armor, a wooden staff, etc. as items to be selected in the AI ​​gacha screen. The change display means 130 also displays the probability of the flaming sword being 0.50000%, the probability of the flaming shield being 0.50000%, the probability of the flaming armor being 0.50000%, and the probability of the wooden staff being 0.23809%.

[0061] Here, the initial state of the AI ​​gacha screen will be explained. Fig. 10 shows the initial state of the AI ​​gacha screen. As shown in Fig. 10, the initial state of the AI ​​gacha screen displays the Water Sword, the Flame Shield, the Dark Armor, the Wooden Staff, etc. as items to be selected by lottery. The probability of the Water Sword being released is set to 0.50000%, the Flame Shield being released to 0.50000%, the Dark Armor being released to 0.50000%, and the Wooden Staff being 0.23809%.

[0062] Comparing Figure 9(b) with Figure 10, the items to be drawn in the AI ​​gacha in Figure 9(b) have been changed to include a fire sword instead of the water sword in Figure 10, and fire armor instead of the dark armor in Figure 10. The reason for the change in the items to be drawn in the AI ​​gacha in Figure 9(b) is that the user (Hanako in this example) frequently uses fire-attribute characters, weapons, or armor in the monster battle game.

[0063] A button for drawing an AI gacha is displayed at the bottom of the AI ​​gacha screen. When the user checks the AI ​​gacha lottery items and their drop rates, and the user terminal 20 accepts the pressing of the AI ​​gacha lottery button (step S70), the lottery execution means 140 executes the AI ​​gacha (step S80). Here, when executing the AI ​​gacha, the lottery execution means 140 draws an item from the population generated by the AI ​​server 16 according to the drop rate. In addition, the user is able to execute the AI ​​gacha in response to the AI ​​gacha lottery items and their drop rates being displayed on the user terminal 20. When the AI ​​gacha is executed, a predetermined number of gems owned by the user are consumed. After that, the management means 160 transitions the monitor 31 to the AI ​​gacha lottery result screen.

[0064] FIG. 11 is an AI gacha lottery result screen (first time). As shown in FIG. 11, the AI ​​gacha lottery result screen (first time) is a screen for showing the user the lottery result (first time) of the AI ​​gacha. In this example, it is shown that a flaming sword was drawn in the AI ​​gacha. Then, the granting means 150 grants the flaming sword to the user. In this way, a user who has been using a fire attribute character or the like will obtain a flaming sword that has affinity with the item used by the user through the AI ​​gacha, and will benefit from the AI ​​gacha.

[0065] After that, the user who has acquired the flaming sword moves to the home screen and presses the equipment button to set the flaming sword to be equipped. FIG. 12 shows the home screen after equipping the flaming sword obtained by the AI ​​gacha. As shown in FIG. 12, a character equipped with the flaming sword is displayed in the main area A2 of the home screen. After that, the user uses the flaming sword in multiple battle plays to defeat monsters.

[0066] Next, a case where the user executes the AI ​​gacha (second time) after using the flaming sword in multiple battle plays will be described with reference to Fig. 13. Fig. 13 is a flowchart showing the control executed between the user terminal 20, the game server 10, and the AI ​​server 16 when executing the AI ​​gacha (second time).

[0067] Fig. 13 differs from Fig. 8 in that the usage status of the flaming sword obtained by the AI ​​gacha is taken into consideration. The following will begin with the description of the process in step S90 in Fig. 7.

[0068] The user acquires the item (the flaming sword) dispensed by the lottery execution means 140 (step S90) and uses the item in multiple battle plays (step S100). After that, when the user presses the AI ​​gacha notification area (see FIG. 7(b)) and the user terminal 20 accepts the selection of the AI ​​gacha as shown in FIG. 13 (step S110), the information acquisition means 110 acquires the user's action history information in the game from the user terminal 20 (step S120). At this time, the information acquisition means 110 acquires the frequency of use of the flaming sword as the action history information.

[0069] Next, the population generation means 120 inputs the behavior history information received from the information acquisition means 110 to the trained model 16b that has been trained in advance (step S130). Here, the behavior history information includes information that the user has used the flaming sword.

[0070] Then, the population generation means 120 causes the trained model 16b to generate a population of game media to be the target of the AI ​​gacha, according to the user's behavioral history (step S140). In this example, it is assumed that the trained model 16b determines that the frequency of use of the flaming sword is equal to or greater than the upper threshold. Thereafter, the management means 160 transitions the monitor 31 to an AI gacha waiting screen. Here, the management means 160 causes the monitor 31 to display an AI gacha waiting screen similar to that shown in FIG. 9.

[0071] When the AI ​​server 16 generates the population, the population generation means 120 acquires the population data from the AI ​​server 16 and stores it in the memory 12 (step S150).

[0072] Next, the change display means 130 acquires the population data stored in the memory 12 and displays the population on the monitor 31 of the user terminal 20 (step S160). At this time, the management means 160 transitions the monitor 31 to the AI ​​gacha screen (second time).

[0073] 14(a) is an AI gacha screen (second time). The change display means 130 displays a flaming sword, a flaming shield, flaming armor, a wooden staff, etc. as items to be selected on the AI ​​gacha screen (second time). The change display means 130 also displays the probability of the flaming sword being 0.60000%, the probability of the flaming shield being 0.60000%, the probability of the flaming armor being 0.60000%, and the probability of the wooden staff being 0.23809%.

[0074] Here, before the AI ​​gacha (second time) population is generated, the AI ​​gacha (first time) population (see FIG. 9(b)) is set. Comparing FIG. 14(b) with FIG. 9(b), the probability of obtaining the flaming sword, flaming shield, and flaming armor in FIG. 9(b) for the AI ​​gacha lottery items in FIG. 14(b) has increased. The reason why the probability of obtaining the AI ​​gacha lottery items has changed in this way is because the user used the flaming sword obtained in the AI ​​gacha (first time) multiple times in battle mode.

[0075] When the user confirms the AI ​​gacha lottery items and their probability of winning, and the user terminal 20 accepts the pressing of the button to draw the AI ​​gacha (step S170), the lottery execution means 140 executes the AI ​​gacha (step S180). At this time, the management means 160 transitions the monitor 31 to the AI ​​gacha lottery result screen (second time).

[0076] FIG. 14(b) is an AI gacha lottery result screen (second time). As shown in FIG. 14(b), the AI ​​gacha lottery result screen (second time) shows that a flaming sword has been drawn in the AI ​​gacha. The granting means 150 then grants the flaming sword to the user. In this way, the user who has used the flaming sword multiple times in the battle mode can obtain the flaming sword again through the AI ​​gacha, and will once again enjoy the benefits of the AI ​​gacha.

[0077] [Effects of the embodiment] According to the above embodiment, the behavioral history information of the user in the monster battle game (game) is acquired, and the acquired behavioral history information is input to the trained model 16b that has been trained in advance to generate a population of items (game media) that are the subject of the AI ​​gacha (lottery). Then, an AI gacha is executed to dispense items from the generated population, and the items dispensed by the AI ​​gacha are given to the user. Therefore, since the items dispensed by the AI ​​gacha change according to the user's behavioral history, it becomes easier for the user to dispense the items that he or she desires. Therefore, it is possible to improve the interest.

[0078] In addition, according to the above embodiment, a new population is generated by changing the items (game contents) included in the population from the initial state population, and the items included in the new population are displayed. Therefore, the user can check the AI ​​gacha population, which can attract the user's interest in the AI ​​gacha population.

[0079] Furthermore, according to the above embodiment, the behavioral history information of the user during the period (within a specified period) from when the AI ​​gacha is implemented in the monster battle game to when the AI ​​gacha (lottery) is executed is obtained to generate the AI ​​gacha population, so that the user can concentrate on the game in order to make the AI ​​gacha population advantageous.

[0080] In the above embodiment, the frequency of use of the flaming sword (game medium) dispensed by the AI ​​gacha (lottery) is acquired as behavior history information, and when the frequency of use is equal to or greater than an upper threshold, a population is generated so that the probability of dispensing the flaming sword increases. Therefore, it becomes easier to strengthen the flaming sword by synthesizing the flaming sword with the same flaming sword.

[0081] In addition, in the above embodiment, since the lottery can be executed in response to displaying information related to items included in the population on the user terminal 20, the user can execute the lottery after accurately recognizing the population. Therefore, a fair lottery based on the user's consent can be realized.

[0082] In the above embodiment, the user used the flaming sword discharged in the AI ​​gacha (first time) multiple times in the battle mode, so the discharge probability of the flaming sword, flaming shield, and flaming armor in FIG. 9(b) was increased, but this is not limited to this. For example, even if the user used the flaming sword multiple times in the battle mode, if an item (e.g., a sword) with another attribute (water attribute, wood attribute, light attribute, dark attribute, etc.) stronger than the flaming sword (i.e., with a higher parameter such as the basic value of the attack power) is discharged in the AI ​​gacha (second time), the user may use the item with the other attribute. Therefore, even if the user used the flaming sword multiple times in the battle mode, an item with another attribute stronger than the flaming sword may be added to the AI ​​gacha population, or the discharge probability of the item with the other attribute may be increased. In this way, the same effect as in the above embodiment can be achieved.

[0083] In the above embodiment, the population is generated so that the probability of the flaming sword being released increases when the frequency of use of the flaming sword is equal to or greater than the upper threshold, but the present invention is not limited to this. For example, the population may be generated so that the probability of the flaming sword being released decreases when the frequency of use of the flaming sword is less than the lower threshold. This makes it more difficult for the user to obtain an item whose frequency of use is less than the threshold, which is convenient for the user.

[0084] According to the above embodiment, a new population is generated by changing the probability of release of items included in the initial population, and the items included in the new population are displayed, but this is not limiting. For example, a new population may be generated by changing the items included in the initial population, and the items included in the new population may be displayed.

[0085] FIG. 15(a) shows the initial AI gacha screen, and (b) shows the AI ​​gacha screen (first time). As shown in FIG. 15(a), the initial AI gacha screen displays items to be drawn, such as a flaming sword, a flaming shield, flaming armor, and a wooden staff. The probability of obtaining a flaming sword is set to 0.40000%, a flaming shield to 0.40000%, a flaming armor to 0.40000%, and a wooden staff to 0.23809%.

[0086] On the other hand, as shown in Fig. 15(b), the AI ​​gacha screen displaying the newly generated population displays items different from the initial state. Comparing Fig. 15(a) and Fig. 15(b), in Fig. 15(b), the Extreme Flame Sword has been added instead of the Flame Sword, the Extreme Flame Shield has been added instead of the Flame Shield, and the Extreme Flame Armor has been added instead of the Flame Armor. Even in this way, the same effect as the above embodiment can be achieved.

[0087] Furthermore, according to the above embodiment, the user's behavior history information during the period (predetermined period) from when the AI ​​gacha is implemented in the monster battle game until the AI ​​gacha (lottery) is executed is acquired, but this is not limited to this. For example, a specific event may be implemented, and the user's behavior history information during the specific event may be acquired. Here, an event refers to content that is periodically held in the game. This content includes various quests. In this example, the quest is a mission imposed on the user to defeat a monster.

[0088] Fig. 16(a) is an event information screen. As shown in Fig. 16(a), the event information screen displays that an AI gacha event is being held as a specific event. In this AI gacha event, user behavior history information is stored in the user terminal 20. Then, when the AI ​​gacha is executed, the information acquisition means 110 acquires the behavior history information.

[0089] In this way, the user's behavior history information during the AI ​​gacha event (specific event) held within the monster battle game is acquired, so the user can clearly understand the acquisition period of the behavior history information when performing the AI ​​gacha. Therefore, the user can concentrate on enjoying the monster battle game during that acquisition period.

[0090] [Variation 1] Normally, a user would acquire gems by paying a fee or clearing quests, and then be able to draw an AI gacha by spending a certain number of the acquired gems. However, in variant 1, if a user draws a 10-series gacha 10 times, they are given the right to draw that AI gacha for free.

[0091] In the monster battle game of variant example 1, the server program 13P loaded into the memory 12 causes the game server 10 (processor 21) to function as a reward granting means that grants a reward to the user when the AI ​​gacha (lottery) is executed 10 times (a predetermined number of times or more) at one time by the lottery execution means 140, and the reward granting means differs from the above embodiment in that it can grant, as a reward, the right to execute a lottery free of charge to obtain game media from a new population generated by the population generation means 120.

[0092] Fig. 17(a) is an AI gacha screen according to the modified example 1. As shown in Fig. 17(a), at the bottom of the AI ​​gacha screen, a button for drawing the AI ​​gacha once (a button for performing a single consecutive gacha) and a button for drawing the AI ​​gacha ten times (a button for performing a 10-consecutive gacha) are displayed. In this modified example, a predetermined item or the like is given to the user as a reward every time a 10-consecutive gacha is performed.

[0093] FIG. 17(b) is a reward granting screen. As shown in FIG. 17(b), the reward granting screen displays "10 times AI gacha reward", and below that, rewards 1 to 10 are displayed. The user can obtain rewards starting from reward 1 every time they perform a 10-series gacha. In this modified example, when the user performs a 10-series gacha 10 times, the reward granting means grants the user an AI gacha ticket. The AI ​​gacha ticket is a ticket that grants the right to draw the AI ​​gacha once for free.

[0094] According to the first modification, when a user performs 10 consecutive AI gacha (lottery), the user is given a reward, and when the user performs the 10 consecutive AI gacha 10 times, the user is given an AI gacha ticket. Therefore, the user can be interested in the AI ​​gacha and can be motivated to perform as many 10 consecutive AI gacha as possible.

[0095] In the above-mentioned modified example 1, when the 10-series gacha is performed 10 times, the reward granting means grants the AI ​​gacha ticket to the user, but it is not limited to 10 times and can be set appropriately. Even in this case, the same effect as the above-mentioned modified example 1 can be achieved.

[0096] [Variation 2] The monster battle game according to the second modification differs from the above embodiment in that an AI learning function (hereinafter, referred to as an "AI learning function") can be turned ON or OFF.

[0097] 18(a) is a gacha notification screen according to the modified example 2. The gacha notification screen displays an AI gacha, and below it, an AI learning function setting button is displayed. When the user terminal 20 accepts a user pressing the AI ​​learning function setting button, the management means 160 transitions the monitor 31 to the AI ​​learning function setting screen.

[0098] FIG. 18(b) is an AI learning function setting screen. The AI ​​learning function setting screen is a screen for setting the AI ​​learning function to ON or OFF. The AI ​​learning function setting screen displays a message saying "Please set the AI ​​learning function." And below the message, there are provided radio buttons for selecting ON or OFF of the AI ​​learning function. When the user terminal 20 accepts a user pressing one of the radio buttons, the AI ​​learning function is set to ON or OFF. In this example, the AI ​​learning function is set to ON.

[0099] Fig. 19 shows the quest screen after the AI ​​learning function is set to ON. As shown in Fig. 19, the quest screen displays messages such as "AI learning" and "The user's actions here will be reflected in the AI ​​Gacha." Based on the action history information in this quest, the population generation means 120 will generate a new population (see Fig. 10(b), for example).

[0100] According to the above-mentioned modification 2, the user can set the AI ​​learning function to ON or OFF, which improves the freedom of playing AI gacha. In addition, when the user wants to improve the AI ​​gacha population, the user can simply set the AI ​​learning function to ON, so that the items included in the AI ​​gacha population or the probability of releasing the items can be efficiently customized according to the user's preferences.

[0101] [Variation 3] The monster battle game according to the third modification is different from the second modification in that it is possible to exclude certain plays from being subject to AI learning on the AI ​​learning function setting screen.

[0102] FIG. 20(a) is an AI learning function setting screen according to the third modification. On the AI ​​learning function setting screen, below the setting display of the AI ​​learning function ON or OFF, a message "Please select not to be included in the AI ​​learning function" is displayed. In addition, below this message, a number of items that are not included in the AI ​​learning function are displayed, and a check button is provided to the left of each item, allowing the user to select one of the items. The multiple items include "Plays that lost," "Plays in automatic response mode," "Plays that were difficult," "Plays against a weak enemy," "Plays against a strong enemy," and "Plays against a boss." In this example, "Plays that lost" and "Plays against a boss" are selected.

[0103] FIG. 20(b) shows the quest screen after the AI ​​learning function has been set to ON and certain plays have been set as excluded. As shown in FIG. 20(b), the quest screen displays the message "However, the following cases are excluded: (i) plays that result in a loss (ii) plays against a boss" below the messages "AI learning" and "The user's actions here will be reflected in the AI ​​Gacha" mentioned above. This message reflects the items selected by the user in FIG. 19(a).

[0104] According to the third modification, it is possible to exclude certain plays from the AI ​​learning function setting screen from the AI ​​learning function, so that the user can prevent plays that are disadvantageous to the user from being included in the action history information, thereby providing a user-friendly monster battle game.

[0105] [Variation 4] In the monster battle game of variant example 4, the population generation means 120 differs from the above embodiment in that it inputs information related to users' gameplay videos published on social media, video distribution sites, etc. into the trained model 16b to generate a new population.

[0106] In this modified example, when a user posts a gameplay video of a monster battle game to other users on a social networking site, a video distribution site, or the like, the game server 10 is configured to store information related to the gameplay video in the memory 12 and acquire the number of views and the number of likes from other users for the gameplay video. The information acquisition means 110 acquires information related to the number of views and the number of likes for the gameplay video and stores it in the memory 12, and the population generation means 120 inputs the information into the trained model to generate a new population.

[0107] FIG. 21(a) shows information related to play data stored in memory 12, the number of views of the play data, and the number of likes. As shown in FIG. 21(a), play video 1 to play video 3 are stored in memory 12. Play video 1 has been viewed 10,000 times and has been liked 500 times. Play video 2 has been viewed 30,000 times and has been liked 1,000 times. Play video 3 has been viewed 5,000 times and has been liked 3,000 times. The population generation means 120 inputs these data into the trained model 16b.

[0108] FIG. 21(b) is an input data setting screen for the trained model. As shown in FIG. 21(b), the input data setting screen is a screen for setting data to be input to the trained model from among the play videos 1 to 3. The AI ​​learning function setting screen shown in FIG. 20(a) above is provided with an input data setting screen button (not shown). When the user terminal 20 accepts the user pressing the input data setting screen button, the management means 160 shifts the monitor 31 to the input data setting screen. The input data setting screen displays a message saying "Please select the data to be input." And, below the message, the display order of the play videos 1 to 3 can be selected. Specifically, the order of the most viewed videos and the order of the most liked videos are displayed, and radio buttons are provided to the left of these displays, allowing the user to select. In this example, the order of the most viewed videos is selected. Therefore, on the input data setting screen, "1st place, gameplay video 2, 30,000 views" is displayed at the top, "2nd place, gameplay video 1, 10,000 views" is displayed below that, and "3rd place, gameplay video 3, 5,000 views" is displayed below that. When the user terminal 20 accepts the user's pressing of "1st place, gameplay video 1, 30,000 views", the population generation means 120 inputs the gameplay video 2 into the trained model to generate a new population.

[0109] According to the above-mentioned modification 4, the AI ​​Gacha population can be generated according to the preferences of users who have viewed content published on SNS, video distribution sites, etc., so that, for example, by inputting a play video of a skilled user, the possibility of acquiring an item owned by that user increases. Therefore, the interest can be further improved.

[0110] In the above-mentioned modified example 4, three play videos are stored, but the present invention is not limited to this, and one, two, or more than three play videos can be stored. Even in this case, the same effect as that of the above-mentioned modified example 4 can be achieved.

[0111] In addition, in the above-mentioned modified example 4, the example of inputting the play video 2 with the most views to the trained model 16b has been described, but this is not limiting. For example, the play video 3 with the most likes may be adopted, or both the play video with the most likes and the play video with the most views may be adopted. Even in this case, the same effect as that of the above-mentioned modified example 4 can be achieved.

[0112] In the fourth modification, the game server 10 is configured to store information related to a gameplay video of a monster battle game in the memory 12 and to obtain the number of views of the gameplay video by other users, based on the user publishing the gameplay video of the monster battle game. The information acquisition means 110 is configured to obtain the number of views of the gameplay video and store it in the memory 12, and the population generation means 120 is configured to input the information into the trained model to generate a new population, but is not limited to this.

[0113] Based on a user publishing a play video of a monster battle game, the game server 10 may be configured to store information on a specific scene in the play video in which a predetermined character battles in the memory 12, and to acquire the number of times the specific scene has been viewed by other users. The information acquisition means 110 may acquire the number of times the specific scene in the play video has been viewed and store it in the memory 12, and the population generation means 120 may input the information into the trained model to generate a new population. For example, if the number of times the specific scene has been viewed is equal to or greater than a predetermined number, the population generation means 120 may add a predetermined character to the population or increase the probability of the predetermined character being released. On the other hand, if the number of times the specific scene has been viewed is less than a predetermined number, the population generation means 120 may exclude a predetermined character from the population or decrease the probability of the predetermined character being released. This can also produce the same effect as the above-mentioned modification 4.

[0114] In addition, in the above-mentioned modification example 4, the number of views and the number of likes for the play video are described as examples, but the present invention is not limited to these. For example, the viewing time of the play video can be adopted. Here, since the viewing time varies depending on the content of the play video, for example, rather than a user viewing a short one-minute play video ten times, the game server 10 may obtain the setting information of the character appearing in the play video when the user is viewing a one-hour play video full time and store the information in the memory 12.

[0115] In addition, for long play videos, it is preferable that the game server 10 extracts information about which time period the user viewed. In this way, it is possible to reflect information about the characters appearing in the part of the play video that the user really pays attention to in the AI ​​gacha, and the accuracy of the AI ​​gacha can be improved. Here, when watching a live broadcast or a recorded video from the beginning, the game server 10 only needs to store information about the play video within the viewing time in the memory 12. However, in reality, the viewing target in the play video actually changes depending on where the user started watching the live broadcast or where the user started playing the recorded video. Therefore, it is preferable that the game server 10 measures the start time and end time of the playback time (playback position) and stores them in the memory 12.

[0116] In the above-mentioned fourth modification, the game server 10 stores information related to a gameplay video in the memory 12 based on the user posting the gameplay video of the monster battle game to other users on a social networking site, a video distribution site, or the like, but is not limited to this. For example, the game server 10 may acquire information on the user's gaze via smart glasses or a smartphone (camera 33) capable of acquiring the user's gaze information, and acquire information on which part of the gameplay video the user is paying attention to when watching. In this way, the part the user is gazing at in the gameplay video can be reflected as learning data, and the accuracy of the AI ​​gacha can be further improved.

[0117] [Variation 5] In the monster battle game of variant example 5, the server program 13P loaded into the memory 12 causes the game server 10 (processor 11) to further function as a storage means for storing, in association with each other, the population generated by the population generation means 120 and the result of the lottery performed by the lottery execution means 140 using that population, and as a confirmation means for allowing the user to confirm the population and the result of the lottery stored by the storage means.

[0118] In this case, the storage means first stores in the memory 12, for example, the population displayed on the AI ​​gacha screen (first time) of FIG. 9(b), such as the flaming sword, flaming shield, flaming armor, and wooden staff, as well as information related to their probability of being dispensed. Next, the storage means stores in the memory 12 information related to the flaming sword displayed on the AI ​​gacha lottery result screen of FIG. 11 (i.e., information that the flaming sword was dispensed in the AI ​​gacha (first time)). Finally, the storage means associates the population displayed on the AI ​​gacha screen (first time) of FIG. 9(b) with the flaming sword displayed on the AI ​​gacha lottery result screen of FIG. 11. The confirmation means displays on the user terminal 20 the population displayed on the AI ​​gacha screen (first time) of FIG. 9(b) stored in the memory 12 and the information that the flaming sword was dispensed in the AI ​​gacha (first time), and allows the user to confirm.

[0119] FIG. 22(a) is a gacha announcement screen relating to variant example 5. As shown in FIG. 22(a), a confirmation button is displayed in the AI ​​gacha announcement area. When the user terminal 20 accepts pressing of the confirmation button, it transitions to a confirmation screen. FIG. 22(b) is the confirmation screen. The confirmation screen is a screen for confirming the results of past AI gacha lottery draws. The confirmation screen displays an AI gacha (1st time) button, an AI gacha (2nd time) button, ..., and an AI gacha (Nth time) button. When the user presses any of the buttons, the confirmation means displays the results of the AI ​​gacha lottery corresponding to the user terminal 20 and the population at the time the lottery was performed, allowing the user to confirm them.

[0120] According to the above-mentioned variant example 5, the user can view the population at the time of executing the AI ​​gacha in association with the results of the lottery at that time, thereby preventing the user from getting bored even after executing the AI ​​gacha.

[0121] In addition, according to the above-mentioned variant example 5, you can enjoy analyzing the population and lottery results of past AI gachas and reflecting them in the AI ​​gachas you plan to run in the future.

[0122] [Variation 6] In the monster battle game of variant example 5, the server program 13P loaded into the memory 12 is configured so that the storage means further stores the behavior history information acquired by the information acquisition means 110 in association with the result of the lottery, and the confirmation means allows the user to further confirm the behavior history information and the result of the lottery.

[0123] In this case, the storage means first stores the user's behavior history information acquired by the information acquisition means 110 in the memory 12. Next, the storage means stores the flaming sword displayed on the AI ​​gacha lottery result screen of FIG. 11 (i.e., information that the flaming sword was dispensed in the AI ​​gacha (first time)) in the memory 12. And, finally, the storage means associates the user's behavior history information with the flaming sword displayed on the AI ​​gacha lottery result screen of FIG. 11. The confirmation means displays the user's behavior history information and the information that the flaming sword was dispensed in the AI ​​gacha (first time) on the user terminal 20 and allows the user to confirm it.

[0124] As in Figure 22(b) described above, when any of the AI ​​gacha (1st time) button, the AI ​​gacha (2nd time) button, ..., or the AI ​​gacha (Nth time) button is pressed on the confirmation screen, the confirmation means displays the behavioral history information obtained in the AI ​​gacha corresponding to the user terminal 20 and the results of the lottery in the corresponding AI gacha, and allows the user to confirm them.

[0125] In this modified example, as shown in Fig. 23(a), a registered friend screen is provided that displays a list of registered friends, and a report button is provided on the registered friend screen for each friend to report on the AI ​​gacha to the friend. When the user presses the report button and the user terminal 20 accepts the pressing of the report button, the screen transitions to the report screen.

[0126] Fig. 23(b) is the report screen. As shown in Fig. 23(b), the report screen displays a message saying "To Mr. A: Before you play the AI ​​gacha, it's better to use XX on XX!!", and a send button is displayed below the message. Note that "XX" is the name of the quest, and "XX" is the name of the item. When the user terminal 20 accepts the pressing of the send button, the above message is sent to Mr. A.

[0127] According to the above variant example 6, a user can send a report about the AI ​​gacha to a friend, and the friend who receives the report can set similar conditions as the user to generate a population of AI gacha similar to that of the user.

[0128] Furthermore, according to the above-mentioned variant example 6, the user can view the behavioral history information in association with the results of the lottery at that time, so that the user can enjoy analyzing the behavioral history information and reflecting it in the AI ​​gacha that is executed subsequently.

[0129] [Another embodiment] Next, a monster battle game according to another embodiment will be described with reference to FIG. 24 to FIG. 28. FIG. 24 is a functional block diagram of the game server 10 according to another embodiment. This embodiment aims to facilitate the execution of a lottery, and differs from the above embodiment in that one gacha is specified from among a plurality of gachas currently implemented based on information related to an item set by the user, and the one gacha is continued to be executed until the item is discharged, for example. Hereinafter, the process of executing a gacha in this way is called an automatic lottery process. This reduces the user's operation effort required to execute a lottery until the user obtains the item he or she desires to acquire. That is, when a predetermined automatic lottery is executed, the lottery can be automatically executed without the user's operation during the process.

[0130] As shown in FIG. 24, the server program 13P loaded into the memory 12 causes the game server 10 (processor 11) to function as a game medium setting means 210, a priority setting means 220, a gacha identification means 230, a lottery execution means 240, an awarding means 250, and a management means 260.

[0131] The game media setting means 210 allows a user playing a monster battle game to set items (game media) that the user wishes to acquire.

[0132] When there are multiple items that a user desires to acquire, the priority setting means 220 allows the user to set priorities among the multiple items.

[0133] The gacha specification means 230 inputs information related to the item set by the user by the game media setting means 210 into the trained model 16b that has been trained in advance, and specifies a gacha that will hold a lottery to dispense the item from among multiple types of gacha currently implemented in the game. At this time, the gacha specification means 230 follows the priority set by the user by the priority setting means 220.

[0134] The lottery execution means 240 executes the lottery for the gacha specified by the gacha specification means 230 until a predetermined condition is satisfied. Here, the predetermined condition may be, for example, that an item that the user desires to obtain is dispensed in the lottery.

[0135] The granting means 250 grants the item obtained by the lottery executed by the lottery executing means 240 to the user.

[0136] The management means 160 manages the progress of the monster battle game.

[0137] Next, with reference to FIGS. 25 to 28, a flowchart showing control executed between the user terminal 20, the game server 10, and the AI ​​server 16 when executing an automatic lottery process according to another embodiment is shown.

[0138] When executing the automatic lottery process of this embodiment, the user presses a gacha setting button on the home screen. FIG. 26(a) is a home screen according to another embodiment, and (b) is a gacha setting screen. As shown in FIG. 26(a), the gacha setting button is displayed in the event information display area A3 of the home screen. When the user terminal 20 accepts the pressing of the gacha setting button (step S210), the management means 260 transitions the monitor 31 to the gacha setting screen.

[0139] As shown in FIG. 26(b), the gacha setting screen is a screen for setting items that the user wishes to obtain. The gacha setting screen displays a message saying, "Please input the items you wish to obtain and the number of items." Below this message, the user can input multiple items that the user wishes to obtain and the number of each item. As shown in FIG. 25, the game media setting means 210 allows the user to set items that the user wishes to obtain on the gacha setting screen (step S220). In this example, the user sets "2" "flaming swords," "1" "flaming armor," and "1" "flaming shield." Below these settings, a priority setting button is displayed.

[0140] FIG. 27 is a priority setting screen. As shown in FIG. 27, the priority setting screen is a screen for setting priorities among a plurality of items set on the gacha setting screen. The priority setting screen displays a message saying "Please input the priority." Below this message, the user can set priorities for the "flaming sword," "flaming armor," and "flaming shield" set on the gacha setting screen. As shown in FIG. 25, the priority setting means 220 allows the user to set priorities among the "flaming sword," "flaming armor," and "flaming shield" (step S230). In this example, the first priority is set to the "flaming sword," the second priority is set to the "flaming armor," and the third priority is set to the "flaming shield."

[0141] After that, the user moves to a gacha notification screen to obtain the above-mentioned item. FIG. 28(a) is a gacha notification screen according to another embodiment. In this gacha notification, an automatic lottery button is displayed. As shown in FIG. 25, when the user terminal 20 accepts pressing of the automatic lottery button (step S240), the gacha specification means 230 inputs information related to the item that the game medium setting means 210 has caused the user to set to the trained model 16b that has been trained in advance (step S250).

[0142] The AI ​​server 16 specifies a gacha that can dispense the item from among the multiple types of gacha currently implemented based on the information related to the item input from the game server 10 (step S260). At this time, the gacha specification means 230 follows the priority set by the user by the priority setting means 220 in step S230.

[0143] When the AI ​​server 16 specifies a gacha, it transmits information related to the lottery for the gacha to the game server 10, and the lottery execution means 240 executes the lottery (step S270). In this example, the lottery execution means 240 executes the fire attribute gacha displayed on the gacha announcement screen. Then, the lottery execution means 240 repeats the lottery for the fire attribute gacha until "2" "Flame Sword", "1" "Flame Armor", and "1" "Flame Shield" are dispensed in the fire attribute gacha (same step).

[0144] FIG. 28(b) is an automatic lottery result screen. The automatic lottery result screen is a screen for displaying the result of a lottery executed by automatic lottery. The automatic lottery result screen displays a message saying "10,000 coins and 1,000 gems have been consumed." Below that message, "2 Flame Swords, 1 Flame Armor, and 1 Flame Shield" are displayed, and below that, a message saying "The above items have been acquired." The granting means 250 grants the user "2 Flame Swords, 1 Flame Armor, and 1 Flame Shield" (step S280).

[0145] [Effects of other embodiments] According to the above embodiment, a user playing a monster battle game sets an item (game medium) that the user desires to acquire, and inputs information related to the item into a trained model that has been trained in advance, and a gacha that will hold a lottery that can dispense the item is identified from among a plurality of types of gacha. Then, a lottery for the identified gacha is executed until the item is dispensed (until a predetermined condition is satisfied), and the dispensed item is given to the user. Therefore, the user does not need to select a lottery that can dispense the item that the user desires to acquire, and can efficiently execute a lottery to acquire the item. This can improve the interest of the game.

[0146] In addition, according to the above embodiment, the user sets a plurality of items that he / she desires to acquire, and sets priorities among the plurality of items. The information related to the priorities set by the user is input to the trained model 16b to specify the gacha. Therefore, it becomes possible to efficiently acquire items according to the user's priorities. Therefore, it is possible to further improve the interest.

[0147] In the above embodiment, since the items that the user desires to obtain are the flaming sword, the flaming armor, and the flaming shield, the fire attribute gacha is specified and the lottery for the fire attribute gacha is executed, but this is not limited to this. For example, if a gacha that is different from the fire attribute gacha and that performs a lottery for the flaming sword, the flaming armor, and the flaming shield is implemented, the gacha with the highest probability of emission may be specified. In this case, first, the gacha with the highest probability of emission of the flaming sword, which has the first priority, may be specified, but if it is still not specified, it may be specified by sequentially referring to the probability of emission of the flaming shield, which has the second priority, and the flaming armor, which has the third priority. Even in this case, the same effect as the above embodiment can be achieved. In addition, since it is possible to obtain items more efficiently, it is possible to reliably improve the interest.

[0148] In the above embodiment, since the items the user desires to acquire are the flaming sword, the flaming armor, and the flaming shield, the fire attribute gacha is specified and the lottery for the fire attribute gacha is executed, but this is not limited to this. For example, when the lottery for the fire attribute gacha is executed and the flaming sword, the flaming armor, and the flaming shield are discharged in the amount desired by the user, the lottery may be switched to a gacha that performs a lottery for discharging fire attribute items similar to these items (for example, flaming helmet, flaming shoes, etc.). In this case, the gacha specification means 230 may specify the gacha by inputting information related to fire attribute items similar to the flaming sword, the flaming armor, and the flaming shield into the trained model 16b based on the fact that the flaming sword, the flaming armor, and the flaming shield are discharged in the amount desired by the user. In this way, even after the item the user desires to acquire is discharged in the lottery, the user can obtain an item that has affinity with the desired item, and can combine various equipment, thereby increasing the degree of freedom in the game.

[0149] In the above embodiment, the case where the fire attribute gacha is specified and the lottery for the fire attribute gacha is executed, and two flaming swords, one flaming armor, and one flaming shield are obtained is described, but the present invention is not limited to this. For example, when the lottery for the fire attribute gacha is executed, if the number of flaming swords owned exceeds the upper limit, the game medium setting means 210 may set a fire attribute item similar to the flaming sword (for example, a flaming helmet, flaming shoes, etc.) instead. Even in this way, the user can obtain an item that has affinity with the desired item even after the item that the user wants to obtain is drawn in the lottery.

[0150] In the above embodiment, the user sets the flaming sword, flaming armor, and flaming shield as the items he or she wishes to obtain, and specifies a gacha that will draw a lottery that will allow these items to be obtained, but this is not limiting. For example, if the items set by the user include an item that cannot be obtained in any of the currently implemented gacha draws, the gacha specification means 230 may be configured to issue a warning to the user that the item cannot be obtained. In this way, the user can avoid drawing a lottery that will not allow the item to be obtained, and a user-friendly monster battle game can be provided.

[0151] In the above embodiment, items have been described as game media that can be dispensed by lottery, but the present invention is not limited to this. For example, decorations, clothing, body color (eyes, face, arms, legs, torso, etc.), or body parts that change only the appearance may be used, rather than decorations, characters themselves, or skills that affect abilities in the game. In particular, items related to appearance do not affect abilities in progressing through the game, so they are likely to reflect the preferences of the user, and there is a strong need for items that are to the user's taste. Therefore, history information related to appearance may be weighted heavily as learning data.

[0152] In the above embodiment, the items to be equipped to the character are described as the objects of the lottery, but the objects of the lottery are not limited to items, and various objects of the lottery may be determined by using a learning model such as that of the present invention. For example, the objects of the lottery for the stage when playing against other users may be determined.

[0153] In the above embodiment, an online monster battle is described as an example of a game, but the present invention is not limited to this. For example, the present invention can be applied to various online games that implement gacha. Another example of a game may be a game that is played via ad-hoc communication between user terminals 20.

[0154] Furthermore, the program according to the present invention is not limited to a single program, but may be a collection of multiple programs. Furthermore, the program according to the present invention is not limited to being executed by a single device, but may be executed by multiple devices in a shared manner. Furthermore, the division of roles between the game server 10 and the user terminal 20 is not limited to the above example. That is, part of the processing of the game server 10 may be executed by the user terminal 20, and part of the processing of the user terminal 20 may be executed by the game server 10.

[0155] Also, some or all of the means realized by the program can be realized by hardware such as an integrated circuit. Furthermore, the program may be provided by being recorded on a non-transitory recording medium that can be read by a computer. Examples of the recording medium include a hard disk, an SD card, a DVD, and a server on the Internet.

[0156] <<Additional Notes>> The contents described above can be summarized as follows, for example: <Challenges> The purpose is to provide functions that utilize learning functions. <Solution 1> The processor, An information acquisition means for acquiring user action history information in a game; a population generation means for inputting the behavioral history information into a trained model that has been trained in advance to generate a population of game media to be selected by lottery; a program that causes the program to function as a lottery execution means that executes a lottery to dispense the game medium from the population generated by the population generation means; <Solution 2> In the program according to Solution 1, the population generation means generates a new population by changing the game contents or the probability of release of the game contents included in the population from an initial state population; The processor, The program further functions as a display means for displaying the game media or the drop probability included in the new population generated by the population generation means. <Solution 3> In the program according to Solution 2, The lottery execution means is a program that enables the lottery to be executed in response to the display means displaying information on the game medium or the drop probability included in the population on a user terminal operated by the user. <Solution 4> In the program according to Solution 1, The information acquisition means is a program that acquires behavior history information of the user within a predetermined period before the lottery execution means executes the lottery. <Solution 5> In the program according to Solution 1, the information acquisition means acquires, as the behavior history information, a frequency of use of the game medium dispensed by the lottery; The population generation means is a program that causes the trained model to generate the population so that, when the frequency of use is less than a first threshold, the game medium is excluded from the population or the probability of the game medium being released is reduced. <Solution 6> In the program according to Solution 1, the information acquisition means acquires, as the behavior history information, a frequency of use of the game medium dispensed by the lottery; The population generation means is a program that causes the trained model to generate the population so as to increase the probability of issuance of the game medium when the frequency of use is greater than or equal to a second threshold. <Solution 7> In the program according to Solution 1, The information acquisition means is a program that acquires behavior history information of the user in a specific event held within the game. <Solution 8> In the program according to Solution 1, The processor, and further functioning as a reward granting means for granting a reward to the user when the lottery execution means has executed the lottery a predetermined number of times or more. The reward granting means is a program that can grant, as the reward, a right to hold the lottery free of charge. <Solution 9> In the program according to Solution 1, The processor a storage means for storing the population generated by the population generating means and the result of the lottery executed by the lottery executing means using the population in association with each other; The program further functions as a confirmation means for displaying the population and the lottery results stored in the storage means on the user terminal and allowing the user to confirm them. <Solution 10> In the program according to Solution 9, The processor, The storage means further stores the action history information acquired by the information acquisition means and the result of the lottery in association with each other; The confirmation means is a program that displays the behavior history information and the result of the lottery on the user terminal to allow the user to further confirm them. <Solution 11> An information acquisition means for acquiring user action history information in a game; a population generation means for inputting the behavioral history information into a trained model that has been trained in advance to generate a population of game media to be selected by lottery; A system comprising: a lottery execution means for executing a lottery to dispense the game medium from the population generated by the population generation means. <Solution 12> A method for a processor to execute a program, comprising the steps of: A first step of acquiring user action history information in a game; A second step of inputting the behavioral history information into a trained model that has been trained in advance to generate a population of game media to be selected by lottery; A third step of conducting a lottery to dispense the game medium from the population generated by the second step. <Solution 13> The processor, a game content setting means for allowing a user who is playing a game to set game content that the user desires to acquire; a content identification means for inputting information related to the game medium into a trained model that has been trained in advance, and identifying the content to be selected from among a plurality of types of content through a lottery for which the game medium can be dispensed; The program causes the program to function as a lottery execution means for executing the lottery for the identified content until a predetermined condition is satisfied. [Explanation of symbols]

[0157] 110 Information acquisition means 120 Population Generation Methods 130 Change display means 140 Lottery execution means

Claims

1. The processor, An information acquisition means for acquiring user action history information in a game; a population generation means for inputting the behavioral history information into a trained model that has been trained in advance to generate a population of game media to be selected by lottery; a program that causes the program to function as a lottery execution means that executes a lottery to dispense the game medium from the population generated by the population generation means;

2. The program according to claim 1, the population generation means generates a new population by changing the game contents or the probability of release of the game contents included in the population from an initial state population; The processor, The program further functions as a display means for displaying the game media or the drop probability included in the new population generated by the population generation means.

3. The program according to claim 2, The lottery execution means is a program that enables the lottery to be executed in response to the display means displaying information on the game medium or the drop probability included in the population on a user terminal operated by the user.

4. The program according to claim 1, The information acquisition means is a program that acquires behavior history information of the user within a predetermined period before the lottery execution means executes the lottery.

5. The program according to claim 1, the information acquisition means acquires, as the behavior history information, a frequency of use of the game medium dispensed by the lottery; The population generation means is a program that causes the trained model to generate the population so that, when the frequency of use is less than a first threshold, the game medium is excluded from the population or the probability of the game medium being released is reduced.

6. The program according to claim 1, the information acquisition means acquires, as the behavior history information, a frequency of use of the game medium dispensed by the lottery; The population generation means is a program that causes the trained model to generate the population so as to increase the probability of issuance of the game medium when the frequency of use is greater than or equal to a second threshold.

7. The program according to claim 1, The information acquisition means is a program that acquires behavior history information of the user in a specific event held within the game.

8. The program according to claim 1, The processor, and further functioning as a reward granting means for granting a reward to the user when the lottery execution means has executed the lottery a predetermined number of times or more. The reward granting means is a program that can grant, as the reward, a right to hold the lottery free of charge.

9. The program according to claim 1, The processor a storage means for storing the population generated by the population generating means and the result of the lottery executed by the lottery executing means using the population in association with each other; The program further functions as a confirmation means for displaying the population and the lottery results stored in the storage means on the user terminal and allowing the user to confirm them.

10. The program according to claim 9, The processor, The storage means further stores the action history information acquired by the information acquisition means and the result of the lottery in association with each other; The confirmation means is a program that displays the behavior history information and the result of the lottery on the user terminal to allow the user to further confirm them.

11. An information acquisition means for acquiring user action history information in a game; a population generation means for inputting the behavioral history information into a trained model that has been trained in advance to generate a population of game media to be selected by lottery; A system comprising: a lottery execution means for executing a lottery to dispense the game medium from the population generated by the population generation means.

12. A method for a processor to execute a program, comprising the steps of: A first step of acquiring user action history information in a game; A second step of inputting the behavioral history information into a trained model that has been trained in advance to generate a population of game media to be selected by lottery; A third step of conducting a lottery to dispense the game medium from the population generated by the second step.

Images