Programs and Systems

Abstract

This invention provides a program and system that can enhance the enjoyment of AI-powered games. [Solution] The program causes the processor to function as a measurement means for measuring information about a user watching game-related gameplay videos, and a generation means for inputting the information measured by the measurement means into an AI to generate game media.

Description

Technical Field

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

Background Art

[0002] Conventionally, online games including content (so-called gacha) that enables acquisition of characters or items (game media) selected by lottery have been known (see, for example, Patent Document 1). In this type of online game, since users repeat gacha in expectation of obtaining desired characters or items, the appeal of the online game can be improved if attractive gacha can be implemented.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] An object of the present invention is to provide a program and a system capable of improving the appeal of a game using AI.

Means for Solving the Problems

[0005] To solve the above problems, a program according to the present invention causes a processor to function as measurement means for measuring information related to viewing of a user who views a play video related to a game, and generation means for inputting the information measured by the measurement means into AI to generate a game medium.

Effects of the Invention

[0006] According to the present invention, the appeal of a game using AI can be improved.

Brief Description of the Drawings

[0007] [Figure 1] This diagram shows an overview of the system according to this embodiment. [Figure 2] This is a conceptual diagram of AI-based learning (A) and generation (B) processes. [Figure 3] This diagram shows a neural network that enables AI. [Figure 4] This is a hardware configuration diagram for the game server. [Figure 5] This is a hardware configuration diagram of the user terminal. [Figure 6] This is a functional block diagram of the game server. [Figure 7] (a) is the home screen of a monster battle game, and (b) is the gacha notification screen. [Figure 8] This flowchart shows the control performed between the user terminal, the game server, and the AI ​​server when executing an AI gacha. [Figure 9] (a) is the AI ​​gacha waiting screen, and (b) is the AI ​​gacha screen (first attempt). [Figure 10] This is the initial AI gacha screen. [Figure 11] This is the AI ​​gacha lottery result screen (1st draw). [Figure 12] This is the home screen after equipping the Flame Sword obtained from the AI ​​gacha. [Figure 13] This flowchart shows the control performed between the user terminal, the game server, and the AI ​​server when executing the AI ​​Gacha (second attempt). [Figure 14] (a) is the AI ​​gacha screen (second time), and (b) is the AI ​​gacha draw result screen (second time). [Figure 15] (a) is the initial AI gacha screen, and (b) is the AI ​​gacha screen (first attempt) related to the modified example 1. [Figure 16] (a) is the event information screen, and (b) is the quest screen for the AI ​​gacha event. [Figure 17](a) is the AI gacha screen according to the related modification example 1, and (b) is the reward granting screen. [Figure 18] (a) is the gacha notification screen according to the modification example 2, and (b) is the AI learning function setting screen. [Figure 19] It is the quest screen after the AI learning function is set to ON. [Figure 20] (a) is the learning function setting screen, and (b) is the quest screen after the AI learning function is set to ON and a predetermined play is excluded from the target. [Figure 21] (a) is information related to the play video stored in the memory, the number of views of the play video, and the number of "likes", and (b) is the input data setting screen for the learned model. [Figure 22] (a) is the gacha notification screen according to the modification example 5, and (b) is the confirmation screen. [Figure 23] (a) is the registered friend screen, and (b) is the report screen. [Figure 24] It is a functional block diagram of a game server according to another embodiment. [Figure 25] It is a flowchart showing the control executed among the user terminal, the game server, and the AI server when executing the automatic lottery process. [Figure 26] (a) is the home screen according to another embodiment, and (b) is the gacha setting screen according to another embodiment. [Figure 27] It is a priority setting screen. [Figure 28] (a) is the gacha notification screen according to another embodiment, and (b) is the gacha lottery result screen according to another embodiment.

Mode for Carrying Out the Invention

[0008] Embodiments of the present invention will be described below with reference to the drawings. The embodiments of the present invention described below are merely examples of how the present invention can be implemented, and do not limit the scope of the present invention to those described in the embodiments. Therefore, the present invention can be implemented by making various modifications to the embodiments. Furthermore, the following embodiments and modifications can be combined in any combination without departing from the spirit of the present invention.

[0009] [Overview of System 1] Figure 1 is a diagram illustrating an overview of System 1 according to this embodiment. As shown in Figure 1, System 1 mainly comprises a game server 10, an AI server 16, and a plurality of user terminals 20. Although three user terminals 20 are shown in Figure 1, the number of user terminals 20 included in System 1 is not limited to these. The game server 10, the AI ​​server 16, and the user terminals 20 are connected to communicate with each other via a communication network 2. The specific example of the communication network 2 is not particularly limited, but it may consist of, 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 thereof.

[0010] As an example, System 1 can implement a cooperative online game in which users (players) on multiple user terminals 20A, 20B, and 20C play together. As another example, System 1 can implement a competitive online game in which users (players) on multiple user terminals 20A, 20B, and 20C compete against each other. As yet another example, it can implement a virtual space in which users on multiple user terminals 20A, 20B, and 20C communicate via avatars. Since these Systems 1 are already well known, a detailed explanation will be omitted.

[0011] [Configuration of AI Server 16] The AI ​​server 16 is implemented on a general-purpose computer such as a workstation or personal computer. The AI ​​server 16 implements an AI (Artificial Intelligence) 16 that includes a trained model. For 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 implemented on 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 explanation will be omitted, but for example, it may have the following configuration.

[0012] Figure 2 is a conceptual diagram of the learning process (A) and generation process (B) performed by AI16. Figure 3 is a diagram showing the neural network 17 that implements AI16. AI16, installed on the AI ​​server 16, is a so-called "generative AI" that processes input data and generates output data. AI16 performs the learning process shown in Figure 2(A) and the generation process shown in Figure 2(B). In addition, AI16 generates output data from input data using, for example, the neural network 17 shown in Figure 3.

[0013] As shown in Figure 2(A), AI16 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 then becomes a trained model 16b by receiving training data that includes input data and ground truth data. Input data refers to the data that is input to AI16. Ground truth data refers to the data that should be output when the input data is received. By inputting multiple training data into the learning model 16a, the neural network 17 is optimized as described later, resulting in the trained model 16b.

[0014] Furthermore, as shown in Figure 2(B), the trained model 16b generates and outputs output data by inputting input data into the neural network 17. The input and output data may be in any format, including text, image, and audio formats. Also, the input and output data may be in different formats. On the other hand, the format of the ground truth data is the same as the format of the output data.

[0015] Furthermore, the learning process shown in Figure 2(A) may be performed not only on the learning model 16a but also on the trained model 16b. In addition, AI16 does not need to be trained using the input data and ground truth data actually used in this invention, but may be trained with general-purpose learning data. Moreover, the learning process performed by AI16 is not limited to "supervised learning" in which input data and ground truth data are input, but may also be "unsupervised learning" in which ground truth data is not input, or it may perform reinforcement learning or transfer learning, etc.

[0016] As shown in Figure 3, the neural network 17 of the learning model 16a or the trained model 16b consists of an input layer L1 composed of multiple nodes I1, I2, and I3, an intermediate layer L2 composed of multiple nodes H1, H2, H3, H4, and H5, and an output layer L3 composed of multiple nodes O1, O2, and O3. In the example in Figure 3, the number of nodes in the input layer L1 and the output layer L3 are the same, but the number of nodes in the input layer L1 and the output layer L3 may be different. Furthermore, the neural network 17 may have multiple intermediate layers L2. In addition, Figure 3 shows a fully connected neural network 17 in which multiple nodes constituting each layer L1, L2, and L3 are connected to all nodes in adjacent layers, but the structure of the neural network 17 is not limited to this.

[0017] The learning process involves adjusting the weight coefficients and biases of each node so that when input data is input to the input layer L1, the correct answer data is output from the output layer L3. The generation process involves processing the input data input to the input layer L1 using the weight coefficients and biases that have been pre-adjusted for each node to generate output data, which is then output from the output layer L3.

[0018] However, the specific example of processing by AI16 described above is just one example, and the AI ​​server 16 can employ various well-known methods. As another example, AI16 may have a network structure such as a CNN (Convolutional Neural Network). As yet another example, the network structure may have configurations such as an LLM (Large Language Model), RNN (Recurrent Neural Network), or LSTM (Long Short-Term Memory). In other words, AI16 may have a network structure other than deep learning.

[0019] This embodiment describes an AI gacha in which the target of a lottery is generated by a trained model 16b (AI server 16) according to the user's behavior history. As will be described in detail later, in the AI ​​gacha, the user's behavior history information is input to the trained model 16b to generate the population of targets for the lottery.

[0020] [Game Server 10 Configuration] Figure 2 is a hardware configuration diagram of the game server 10. The game server 10 is implemented on a general-purpose computer such as a workstation or personal computer. As shown in Figure 2, the game server 10 mainly comprises a processor 11, memory 12, storage 13, input / output interface 14, and communication interface 15. Each component of the game server 10 is connected to the communication bus 19.

[0021] The processor 11 performs the processing described later by executing a series of instructions contained in the server program 13P stored in memory 12 or storage 13. The processor 11 can be implemented as, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an MPU (Micro Processor Unit), an FPGA (Field-Programmable Gate Array), or other device.

[0022] Memory 12 temporarily holds the server program 13P and data. The server program 13P is loaded, for example, from storage 13. The data includes data input to the game server 10 and data generated by the processor 11. For example, memory 12 can be implemented as RAM (Random Access Memory) or other volatile memory.

[0023] Storage 13 permanently holds the server program 13P and data. Storage 13 can be implemented as, for example, ROM (Read-Only Memory), a hard disk drive, flash memory, or other non-volatile storage device. Alternatively, storage 13 may be implemented as a removable storage device, such as a memory card. In yet another example, instead of being built into the game server 10, storage 13 may be connected to the game server 10 as an external storage device. With such a configuration, for example, in a scenario where multiple user terminals 20 are used, such as in an amusement facility, it becomes possible to update the server program 13P and data all at once.

[0024] The input / output interface 14 is an interface for connecting external devices such as monitors, input devices (e.g., keyboards, pointing devices), external storage devices, speakers, cameras, microphones, and sensors to the game server 10. The processor 11 communicates with external devices through the input / output interface 14. The input / output interface 14 can be implemented using, for example, USB (Universal Serial Bus), DVI (Digital Visual Interface), HDMI (High-Definition Multimedia Interface, registered trademark), or other terminals.

[0025] The communication interface 15 communicates with other devices (e.g., user terminal 20) connected to the communication network 2. The communication interface 15 can be implemented as a wired communication interface such as a LAN (Local Area Network), or a wireless communication interface such as Wi-Fi (Wireless Fidelity), Bluetooth (registered trademark), or NFC (Near Field Communication).

[0026] [Configuration of User Terminal 20] The user terminal 20 can be implemented as, for example, an HMD set, a tablet device, a smartphone, a feature phone, a laptop computer, or a desktop computer. In this embodiment, an example of the user terminal 20 as a tablet device is described, as shown in Figure 1.

[0027] Figure 4 is a hardware configuration diagram of the user terminal 20. As shown in Figure 4, the user terminal 20 mainly comprises a processor 21, memory 22, storage 23, communication interface 25, monitor 31, cameras 33 and 34, microphone 35, speaker 36, motion sensor 41, and operating device 42 (operating unit). Each component of the user terminal 20 is connected to the communication bus 29.

[0028] The processor 21 performs the processing described later by executing a series of instructions contained in the terminal program 23P stored in memory 22 or storage 23. The processor 21 can be implemented as, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an MPU (Micro Processor Unit), an FPGA (Field-Programmable Gate Array), or other device.

[0029] Memory 22 temporarily holds the terminal program 23P and data. The terminal program 23P is loaded, for example, from storage 23. The data includes data input to the user terminal 20 and data generated by the processor 21. For example, memory 22 can be implemented as RAM (Random Access Memory) or other volatile memory.

[0030] The storage 23 permanently holds the terminal program 23P and data. The storage 23 can be implemented as, for example, ROM (Read-Only Memory), a hard disk drive, flash memory, or other non-volatile storage device. Alternatively, the storage 23 may be implemented as a removable storage device, such as a memory card. In yet another example, instead of being built into the user terminal 20, the storage 23 may be connected to the user terminal 20 as an external storage device. With such a configuration, for example, in situations where multiple user terminals 20 are used, such as in an amusement facility, it becomes possible to update the terminal program 23P and data all at once.

[0031] The communication interface 25 communicates with other devices connected to the communication network 2 (e.g., game server 10, AI server 16). The communication interface 25 can be implemented as a wired communication interface such as LAN (Local Area Network), or a wireless communication interface such as Wi-Fi (Wireless Fidelity), Bluetooth (registered trademark), or NFC (Near Field Communication).

[0032] The monitor 31 is mounted on the surface of a flat casing, as shown in Figure 1, for example. The monitor 31 is a display device (display unit) that displays images or videos. The camera 33 is mounted on the surface of the flat casing and is a so-called in-camera that captures the face of the user viewing the monitor 31. The camera 34 is mounted on the back of the flat casing (the side opposite the monitor 31) and is a so-called out-camera that captures the surroundings.

[0033] 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 back into speech and outputs it to the user. The user terminal 20 may include earphones instead of the speaker 36.

[0034] The motion sensor 41 detects the movement of the housing (for example, rotation around three mutually orthogonal axes). The motion sensor 41 may be implemented as, for example, an angular velocity sensor, a geomagnetic sensor, or an acceleration sensor.

[0035] The operating device 42 receives commands (operations) from the user to the user terminal 20. The operating device 42 is, for example, a touch panel superimposed on the monitor 31 that receives various touch operations from 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 example described above.

[0036] [Functional block diagram of game server 10] Figure 6 is a functional block diagram of the game server 10. As shown in Figure 6, the server program 13P loaded into 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 assignment means 150, and a management means 160.

[0037] The information acquisition means 110 acquires user activity history information from the user terminal 20. The information acquisition means 110 then transmits the acquired activity history information to the population generation means 120. Here, activity history information refers to information about the weapons or armor equipped by the user, the attributes of said weapons or armor, and the weapons, armor, and items (e.g., recovery items) used by the user in quests within the game. Furthermore, the activity history information acquired by the information acquisition means 110 reflects the user's activity history during the period from when the AI ​​gacha is implemented in the game until the user executes the AI ​​gacha.

[0038] The population generation means 120 inputs the behavior history information received from the information acquisition means 110 into a pre-trained model 16b. Then, the population generation means 120 causes the pre-trained model 16b to generate a population of game items (weapons, armor, recovery items, etc.) that will be the target of the AI ​​gacha (lottery) according to the user's behavior history. Here, the population is a list (see, for example, Figure 9(b)) that associates multiple game items that can be drawn with the probability of each of those game items being drawn.

[0039] Furthermore, the trained model 16b is a dedicated AI configured specifically for the game. The trained model 16b may be pre-tuned, for example, by setting the frequency of item use as a hyperparameter. For example, the trained model 16b may increase the probability of dropping items whose frequency of use is above an upper threshold (first threshold), or add such items to the population. As another example, the trained model 16b may decrease the probability of dropping items whose frequency of use is below a lower threshold (second threshold), or exclude such items from the population. Alternatively, the trained model 16b may be pre-trained using training data that exhibits the above tendencies. Note that the AI ​​is not limited to a dedicated AI; it may also be a general-purpose AI.

[0040] Furthermore, the population generation means 120 generates a new population by changing the game media included in the initial population or the probability of obtaining the game media. The population generation means 120 then acquires data related 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.

[0041] The change display means 130 retrieves the population data stored in the memory 12 and displays the new population on the monitor 31 of the user terminal 20. The change display means 130 also transmits the retrieved population data to the lottery execution means 140.

[0042] The lottery execution means 140 performs a lottery to dispense game media from a new population generated by the population generation means 120, based on the population data received from the change display means 130.

[0043] The granting means 150 grants the game medium, which was obtained by lottery, to the user.

[0044] The management means 160 manages the progress of the game. For example, when the user terminal 20 receives a user input, the management means 160 identifies the game account used by the user, obtains the game progress information for that identified account, and switches the monitor 31 to a predetermined game progress screen.

[0045] Furthermore, the management means 160 stores save data in memory 12 for each user account. When the game is started on the user terminal 20, the management means 160 identifies the save data corresponding to the user account and starts the game by reading the identified save data. When updating save data, the management means 160 obtains the information to be updated (for example, information that the game has progressed, information that the user has acquired an item, etc.) from the user terminal 20 and updates the save data by saving it in the corresponding memory 12. Note that the configuration is not limited to the management means 160 storing save data in memory 12 for each user account; the user terminal 20 itself may have a memory for storing and updating game save data.

[0046] Next, a game according to this embodiment will be described with reference to Figures 7 to 13. In the following, a monster battle game in which the user defeats monsters will be described as an example of a game. Furthermore, items (weapons, etc.) will be given as an example of a game medium.

[0047] Figure 7(a) shows the home screen of the monster battle game. Based on a command from the game server 10 (e.g., management means 160), 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 received from the user.

[0048] As shown in Figure 7(a), the management means 160 displays the home screen on the monitor 31 of the user terminal 20. The home screen includes a coins display area A1, a main area A2, and an event information display area A3.

[0049] Area A1, which displays the amount of coins and gems a user possesses, as well as the user's rank, is used to display this information. Coins and gems are items that users can acquire by playing battles (versus-player battles in the monster battle game). However, gems can also be acquired by users through in-app purchases. The rank indicates the user's position within the monster battle game and can be increased by playing battles.

[0050] 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 to proceed to battle play, and a button to proceed to the item exchange screen. When the user terminal 20 detects that any of the buttons have been pressed, the management means 160 moves the monitor 31 to the screen corresponding to the pressed button.

[0051] Event information display area A3 is an area for displaying buttons to transition to the event information screen and buttons to transition to the gacha notification screen. When the user terminal 20 detects that either button has been pressed, the management means 160 transitions the monitor 31 to the screen corresponding to the pressed button.

[0052] Figure 7(b) shows the gacha notification screen. As shown in Figure 7(b), the gacha notification screen is a screen used to inform users about the gacha currently implemented in the monster battle game. In this example, the gacha notification screen displays AI gacha, summer vacation gacha, and daily gacha, among others.

[0053] As described above, the AI ​​Gacha is a gacha in which the target of the draw is generated by a trained model 16b (AI server 16) according to the user's behavior history. The Summer Vacation Gacha is a special gacha implemented during a predetermined period in the summer. The Daily Gacha is a gacha implemented every day. When the user terminal 20 receives a press on the area that announces any of the gachas, the management means 160 switches the monitor 31 of the user terminal 20 to the corresponding gacha screen. At the bottom of the gacha announcement screen, a gem purchase button and a home button that returns to the home screen are displayed. The following describes the control performed between the user terminal 20, the game server 10, and the AI ​​server 16 after the user terminal 20 receives a press on the AI ​​Gacha announcement area.

[0054] Figure 8 is a flowchart showing the control performed between the user terminal 20, the game server 10, and the AI ​​server 16 when executing the AI ​​Gacha. When the user presses the AI ​​Gacha notification area (see Figure 7(b)) and the user terminal 20 accepts the selection of the AI ​​Gacha as shown in Figure 8 (step S10), the information acquisition means 110 acquires the user's behavior history information in the monster battle game from the user terminal 20 (step S20).

[0055] Next, the population generation means 120 inputs the behavior history information received from the information acquisition means 110 into the pre-trained model 16b (step S30). Then, the population generation means 120 causes the pre-trained model 16b to generate a population of game media that will be the target of the AI ​​gacha, according to the user's behavior history (step S40). At this time, the management means 160 switches the monitor 31 to the AI ​​gacha waiting screen.

[0056] Figure 9(a) shows the AI ​​Gacha waiting screen. As shown in Figure 9(a), the AI ​​Gacha waiting screen is the waiting screen when the population generation means 120 generates the population to be used for the AI ​​Gacha. The AI ​​Gacha waiting screen displays the message, "We will generate the optimal population 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 that changes the items to be dispensed by the AI ​​Gacha, or the probability of dispensing those items, based on the user's behavior history information.

[0057] When the AI ​​server 16 generates a population, the population generation means 120 retrieves the population data from the AI ​​server 16 and stores it in the memory 12 (step S50).

[0058] Next, the change display means 130 retrieves 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 switches the monitor 31 to the AI ​​gacha screen.

[0059] Figure 9(b) shows the AI ​​Gacha screen. The AI ​​Gacha screen is a screen for displaying the population generated by the population generation means 120 as the target of the draw. The change display means 130 displays the Flame Sword, Flame Shield, Flame Armor, and Wooden Staff as items that are the target of the draw on the AI ​​Gacha screen. The change display means 130 also displays the probability of obtaining the Flame Sword as 0.50000%, the probability of obtaining the Flame Shield as 0.50000%, the probability of obtaining the Flame Armor as 0.50000%, and the probability of obtaining the Wooden Staff as 0.23809%.

[0060] Here, we will explain the initial state of the AI ​​Gacha screen. Figure 10 shows the initial state of the AI ​​Gacha screen. As shown in Figure 10, the initial state of the AI ​​Gacha screen displays items that can be drawn, such as the Water Sword, Fire Shield, Dark Armor, and Wooden Staff. The drop rates for the Water Sword are set to 0.50000%, the Fire Shield to 0.50000%, the Dark Armor to 0.50000%, and the Wooden Staff to 0.23809%.

[0061] Comparing Figure 9(b) and Figure 10, we see that in Figure 9(b), the AI ​​gacha draw targets include the Fire Sword instead of the Water Sword in Figure 10, and the Fire Armor instead of the Dark Armor in Figure 10. The reason the AI ​​gacha draw targets were changed in Figure 9(b) is because the user (Hanako in this example) frequently used fire-attribute characters, weapons, or armor in the monster battle game.

[0062] At the bottom of the AI ​​Gacha screen, a button to draw the AI ​​Gacha is displayed. When the user checks the items to be drawn in the AI ​​Gacha and their probabilities, and the user terminal 20 accepts the press of the button to draw the AI ​​Gacha (step S70), the draw execution means 140 executes the AI ​​Gacha (step S80). Here, when executing the AI ​​Gacha, the draw execution means 140 draws items from the population generated by the AI ​​server 16 according to their probabilities. The user can also execute the AI ​​Gacha once the items to be drawn in the AI ​​Gacha and their probabilities are 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 switches the monitor 31 to the AI ​​Gacha draw results screen.

[0063] Figure 11 shows the AI ​​Gacha draw result screen (1st draw). As shown in Figure 11, the AI ​​Gacha draw result screen (1st draw) is a screen that shows the user the result of the AI ​​Gacha draw (1st draw). In this example, it is shown that the Flame Sword was drawn from the AI ​​Gacha. The granting means 150 then grants the Flame Sword to the user. In this way, a user who was using a fire-attribute character, etc., will receive the benefit of the AI ​​Gacha by obtaining the Flame Sword, which is compatible with the item the user was using.

[0064] Afterward, the user who obtained the Flame Sword is configured to equip it by pressing the equip button after returning to the home screen. Figure 12 shows the home screen after equipping the Flame Sword obtained from the AI ​​gacha. As shown in Figure 12, the character equipped with the Flame Sword is displayed in the main area A2 of the home screen. Subsequently, the user uses the Flame Sword to defeat monsters in multiple battle play sessions.

[0065] Next, referring to Figure 13, we will explain the case where the user performs an AI gacha (second time) after using the Flame Sword multiple times in battle play. Figure 13 is a flowchart showing the control performed between the user terminal 20, the game server 10, and the AI ​​server 16 when performing the AI ​​gacha (second time).

[0066] Figure 13 differs from Figure 8 in that it takes into account the usage status of the Flame Sword obtained from the AI ​​gacha. The following explanation will start from the process of step S90 in Figure 7.

[0067] The user obtains an item (Flame Sword) dispensed by the lottery execution means 140 (step S90) and uses that item in multiple battle plays (step S100). Subsequently, when the user presses the AI ​​gacha notification area (see Figure 7(b)) and the user terminal 20 accepts the selection of the AI ​​gacha as shown in Figure 13 (step S110), the information acquisition means 110 obtains the user's behavior history information in the game from the user terminal 20 (step S120). At this time, the information acquisition means 110 obtains the frequency of use of the Flame Sword as behavior history information.

[0068] Next, the population generation means 120 inputs the behavioral history information received from the information acquisition means 110 into the pre-trained model 16b (step S130). Here, the behavioral history information includes information that the user used the Flame Sword.

[0069] 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 S140). In this example, it is assumed that the trained model 16b determined at this point that the frequency of use of the Flame Sword was above the upper threshold. After that, the management means 160 switches the monitor 31 to the AI ​​gacha waiting screen. Here, the management means 160 displays an AI gacha waiting screen similar to that in Figure 9.

[0070] When the AI ​​server 16 generates a population, the population generation means 120 retrieves the population data from the AI ​​server 16 and stores it in memory 12 (step S150).

[0071] Next, the change display means 130 retrieves 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 switches the monitor 31 to the AI ​​gacha screen (second time).

[0072] Figure 14(a) shows the AI ​​Gacha screen (second time). The change display means 130 displays the following items as items to be drawn on the AI ​​Gacha screen (second time): the Flame Sword, Flame Shield, Flame Armor, and Wooden Staff. The change display means 130 also displays the probability of obtaining the Flame Sword as 0.60000%, the Flame Shield as 0.60000%, the Flame Armor as 0.60000%, and the Wooden Staff as 0.23809%.

[0073] Here, before the population for the second AI gacha is generated, the population for the first AI gacha (see Figure 9(b)) is set. Comparing Figure 14(b) and Figure 9(b), the probability of obtaining the Flame Sword, Flame Shield, and Flame Armor from Figure 9(b) has increased in the AI ​​gacha draw targets in Figure 14(b). This change in the probability of obtaining items from the AI ​​gacha is due to the user using the Flame Sword, which was obtained in the first AI gacha, multiple times in battle mode.

[0074] When the user confirms the items to be drawn in the AI ​​gacha and their probabilities, and the user terminal 20 accepts the press of the button to draw the AI ​​gacha (step S170), the drawing execution means 140 executes the AI ​​gacha (step S180). At this time, the management means 160 switches the monitor 31 to the AI ​​gacha drawing results screen (second time).

[0075] Figure 14(b) shows the AI ​​gacha draw result screen (second draw). As shown in Figure 14(b), the AI ​​gacha draw result screen (second draw) indicates that the Flame Sword was drawn from the AI ​​gacha. The granting means 150 then grants the Flame Sword to the user. In this way, a user who has used the Flame Sword multiple times in battle mode will obtain the Flame Sword again through the AI ​​gacha and once again receive the benefits of the AI ​​gacha.

[0076] [Effects of the Embodiment] According to the above embodiment, user behavior history information in the monster battle game (game) is acquired, and the acquired behavior history information is input into a pre-trained model 16b to generate a population of items (game media) that are the target of the AI ​​gacha (lottery). Then, the AI ​​gacha is executed to dispense items from the generated population, and the items dispensed by the AI ​​gacha are given to the user. As a result, the items dispensed by the AI ​​gacha change according to the user's behavior history, making it easier for the user to get the item they want. Therefore, the level of interest can be improved.

[0077] Furthermore, according to the above embodiment, a new population is generated by changing the items (game media) included in the initial population, and the items included in the newly generated population are displayed. Therefore, users can check the AI ​​gacha population, which can attract their interest in the AI ​​gacha population.

[0078] Furthermore, according to the above embodiment, user behavior history information is acquired during the period between the implementation of AI gacha in the monster battle game and the execution of AI gacha (drawing) (within a predetermined period), and the AI ​​gacha population is generated. As a result, users can concentrate on the game in order to make the AI ​​gacha population more favorable to them.

[0079] Furthermore, in the above embodiment, the frequency of use of the Flame Sword (game medium) obtained by the AI ​​gacha (lottery) is acquired as behavioral history information, and when the frequency of use exceeds an upper threshold, a population is generated such that the probability of obtaining the Flame Sword increases. Therefore, it becomes easier to strengthen the Flame Sword by combining it with another identical Flame Sword.

[0080] Furthermore, in the above embodiment, since the lottery can be executed in response to the display of information relating to the items included in the population on the user terminal 20, the user will execute the lottery after accurately recognizing the population. Therefore, a fair lottery based on the user's consent can be achieved.

[0081] Furthermore, in the above embodiment, the probability of obtaining the Flame Sword, Flame Shield, and Flame Armor shown in Figure 9(b) increased because the user used the Flame Sword obtained from the AI ​​Gacha (1st time) multiple times in battle mode, but this is not limited to this. For example, even if the user has used the Flame Sword multiple times in battle mode, if the AI ​​Gacha (2nd time) yields an item of another attribute (water attribute, wood attribute, light attribute, dark attribute, etc.) that is stronger than the Flame Sword (i.e., has higher parameters such as the base value of attack power), the user may choose to use that item of the other attribute. Therefore, even if the user has used the Flame Sword multiple times in battle mode, an item of another attribute that is stronger than the Flame Sword may be added to the AI ​​Gacha population, or the probability of obtaining that item of the other attribute may be increased. Doing so can achieve the same effects as in the above embodiment.

[0082] In the above embodiment, the population was generated such that the probability of obtaining the Flame Sword increases when the frequency of use of the Flame Sword is above an upper threshold, but this is not limited to this. For example, the population may be generated such that the probability of obtaining the Flame Sword decreases when the frequency of use of the Flame Sword is below a lower threshold. This would make it more difficult for users to acquire items with a usage frequency below a threshold, which would be advantageous for the user.

[0083] In the above embodiment, a new population was generated by changing the probability of items being drawn from an initial population, and the items included in the newly generated population were displayed. However, the embodiment is not limited to this. For example, a new population could be generated by changing the items themselves that are included in the initial population, and the items included in the newly generated population could be displayed.

[0084] Figure 15(a) shows the initial state of the AI ​​gacha screen, and (b) shows the AI ​​gacha screen (first draw). As shown in Figure 15(a), the initial state of the AI ​​gacha screen displays items that can be drawn, such as the Flame Sword, Flame Shield, Flame Armor, and Wooden Staff. The probability of obtaining the Flame Sword is set to 0.40000%, the probability of obtaining the Flame Shield is 0.40000%, the probability of obtaining the Flame Armor is 0.40000%, and the probability of obtaining the Wooden Staff is 0.23809%.

[0085] On the other hand, as shown in Figure 15(b), the AI ​​gacha screen displaying the newly generated population shows items different from the initial state. Comparing Figure 15(a) and Figure 15(b), in Figure 15(b), the Flame Sword has been replaced with the Extreme Flame Sword, the Flame Shield with the Extreme Flame Shield, and the Flame Armor with the Extreme Flame Armor. This also produces the same effect as the embodiment described above.

[0086] Furthermore, while the above embodiment obtained user behavior history information during the period between the implementation of AI gacha in the monster battle game and the execution of AI gacha (drawing) (within a predetermined period), it is not limited to this. For example, a specific event could be implemented, and user behavior history information within that specific event could be obtained. Here, an event refers to content that is held periodically within the game. This content includes various quests. In this example, a quest is a mission assigned to the user to defeat monsters.

[0087] Figure 16(a) shows the event information screen. As shown in Figure 16(a), the event information screen indicates that an AI gacha event is being held as a specific event. In this AI gacha event, the user's behavior history information is stored in the user terminal 20. When the AI ​​gacha is executed, the information acquisition means 110 acquires this behavior history information.

[0088] In this way, by acquiring user behavior history information during AI gacha events (specific events) held within the monster battle game, users can clearly understand the period during which their behavior history information is acquired when performing AI gacha. Therefore, users can concentrate on enjoying the monster battle game during that acquisition period.

[0089] [Example 1] Originally, users can obtain gems by paying or completing quests, and then use a predetermined number of these gems to draw from the AI ​​gacha. However, in Modification 1, if a user draws 10 consecutive gacha draws 10 times, they are granted the right to draw from the AI ​​gacha for free.

[0090] In the monster battle game according to Modification 1, the server program 13P loaded into memory 12 functions as a reward granting means that grants a reward to the user when the game server 10 (processor 21) performs an AI gacha (lottery) by the lottery execution means 140 10 times at once (more than a predetermined number of times). The reward granting means differs from the above embodiment in that it can grant the right to perform a lottery free of charge to dispense game media from a new population generated by the population generation means 120 as a reward.

[0091] Figure 17(a) shows the AI ​​gacha screen according to Modification 1. As shown in Figure 17(a), at the bottom of the AI ​​gacha screen, there are buttons for drawing the AI ​​gacha once (a so-called single draw button) and for drawing the AI ​​gacha 10 times (a so-called 10-draw button). In this modification, predetermined items are awarded to the user as a reward each time a 10-draw gacha is performed.

[0092] Figure 17(b) shows the reward distribution screen. As shown in Figure 17(b), the reward distribution screen displays "10 AI Gacha Rewards," with rewards numbered 1 through 10 shown below it. Users can obtain the rewards in order from number 1 each time they perform a 10-pull gacha. In this modified version, when a user performs a 10-pull gacha 10 times, the reward distribution method grants the user an AI Gacha Ticket. An AI Gacha Ticket is a ticket that grants the user the right to draw the AI ​​Gacha once for free.

[0093] According to Modification 1, when a user performs a 10-pull AI gacha (lottery), the user is given a reward, and if the user performs the 10-pull gacha 10 times, the user is given an AI gacha ticket. This makes it possible to attract the user's interest in the AI ​​gacha and motivates them to perform as many 10-pull AI gacha as possible.

[0094] In the above modified example 1, the reward method involved granting the user an AI gacha ticket after performing 10 consecutive gacha draws. However, this is not limited to 10 draws and can be set as appropriate. Even in this case, the same effect as in the above modified example 1 can be achieved.

[0095] [Differentiation 2] The monster battle game according to Modification 2 differs from the above embodiment in that the AI ​​learning function (hereinafter referred to as "AI learning function") can be turned ON or OFF.

[0096] Figure 18(a) shows the gacha notification screen according to the modified example 2. The gacha notification screen displays the AI ​​gacha, and below it, the AI ​​learning function setting button is displayed. When the user terminal 20 receives confirmation that the user has pressed the AI ​​learning function setting button, the management means 160 switches the monitor 31 to the AI ​​learning function setting screen.

[0097] Figure 18(b) shows the AI ​​learning function settings screen. The AI ​​learning function settings screen is used to set the AI ​​learning function to ON or OFF. The AI ​​learning function settings screen displays the message, "Please set the AI ​​learning function." Below this message, there are radio buttons for selecting whether to turn the AI ​​learning function ON or OFF. The AI ​​learning function is set to ON or OFF when the user terminal 20 receives a press from the user of one of the radio buttons. In this example, the AI ​​learning function is set to ON.

[0098] Figure 19 shows the quest screen after the AI ​​learning function has been turned ON. As shown in Figure 19, the quest screen displays the messages "AI learning in progress" and "User actions here will be reflected in the AI ​​gacha." Based on the action history information from this quest, the population generation means 120 generates a new population (see, for example, Figure 10(b)).

[0099] According to the above modified example 2, users can turn the AI ​​learning function ON or OFF, thereby increasing the freedom of playing the AI ​​gacha. Furthermore, users can simply turn the AI ​​learning function ON when they want to improve the AI ​​gacha's pool of items, allowing them to efficiently customize the items included in the AI ​​gacha's pool or the probability of obtaining those items according to their preferences.

[0100] [Difference 3] The monster battle game according to Modification 3 differs from Modification 2 in that certain gameplay can be excluded from AI learning in the AI ​​learning function settings screen.

[0101] Figure 20(a) shows the AI ​​learning function settings screen for Modification Example 3. Below the display for the ON or OFF setting of the AI ​​learning function, the message "Please select items to exclude from the AI ​​learning function" is displayed on the AI ​​learning function settings screen. Below this message, several items to exclude from 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 "Lost Plays," "Play in Auto-Response Mode," "Difficult Plays," "Playing Against Weak Opponents," "Playing Against Strong Opponents," and "Playing Against Bosses." In this example, "Lost Plays" and "Playing Against Bosses" are selected.

[0102] Figure 20(b) shows the quest screen after the AI ​​learning function has been turned ON and certain types of play have been excluded. As shown in Figure 20(b), below the messages "AI Learning in Progress" and "User actions here will be reflected in the AI ​​Gacha," the quest screen displays the message, "However, the following cases are excluded: (i) Lost plays (ii) Boss battles." This message reflects the items selected by the user in Figure 19(a).

[0103] According to the above modified example 3, certain plays can be excluded from AI learning in the AI ​​learning function settings screen, so that users can avoid including plays that are disadvantageous to them in their action history information. Therefore, a user-friendly monster battle game can be provided.

[0104] [Differentiation Example 4] In the monster battle game according to Modification 4, the population generation means 120 differs from the above embodiment in that it inputs information related to user gameplay videos published on social media and video distribution sites into a trained model 16b to generate a new population.

[0105] In this modified version, based on a user sharing a video of themselves playing the monster battle game with other users on social media or video streaming sites, the game server 10 stores information related to the video in memory 12 and is configured to obtain the number of views and "likes" from other users for that video. The information acquisition means 110 then acquires the information related to the number of views and "likes" of the video and stores it in memory 12, and the population generation means 120 inputs this information into a trained model to generate a new population.

[0106] Figure 21(a) shows the play data stored in memory 12 and information related to the number of views and "likes" of that play data. As shown in Figure 21(a), play videos 1 to 3 are stored in memory 12. Play video 1 has 10,000 views and 500 likes. Play video 2 has 30,000 views and 1,000 likes. Play video 3 has 5,000 views and 3,000 likes. The population generation means 120 inputs this data into the trained model 16b.

[0107] Figure 21(b) shows the input data setting screen for the trained model. As shown in Figure 21(b), the input data setting screen is for setting the data to be input to the trained model from play videos 1 to 3. The AI ​​learning function setting screen shown in Figure 20(a) above has an input data setting screen button, which is not shown. When the user terminal 20 receives confirmation from the user that the input data setting screen button has been pressed, the management means 160 switches the monitor 31 to the input data setting screen. The input data setting screen displays the message, "Please select the data to input." Below this message, the display order of play videos 1 to 3 can be selected. Specifically, the videos are displayed in order of most views and in order of most likes, and radio buttons are provided to the left of these displays for the user to select. In this example, the most views order is selected. Therefore, on the input data setting screen, "1st place: Play video 2, 30,000 views" is displayed at the top, followed by "2nd place: Play video 1, 10,000 views," and further down, "3rd place: Play video 3, 5,000 views." When the user terminal 20 receives a press from the user for "1st place: Play video 1, 30,000 views," the population generation means 120 inputs play video 2 into the trained model to generate a new population.

[0108] According to the above modification 4, the AI ​​gacha population can be generated according to the preferences of users who have viewed content published on social media, video streaming sites, etc. For example, by inputting gameplay videos of skilled players, the probability of obtaining items owned by that user increases. Therefore, the level of interest can be further enhanced.

[0109] In the above-described modification 4, three gameplay videos were stored, but this is not limited to this; one, two, or more than three gameplay videos can be stored. In this case as well, the same effect as in the above-described modification 4 can be achieved.

[0110] Furthermore, while the above modification 4 uses the example of inputting the play video 2 with the most views into the trained model 16b, it is not limited to this. For example, the play video 3 with the most likes could be used, or both the play video with the most likes and the play video with the most views could be used. In this case as well, the same effect as in the above modification 4 can be achieved.

[0111] Furthermore, in the above modified example 4, the game server 10 was configured to store information related to a gameplay video in memory 12 based on a user publishing a gameplay video of the monster battle game, and to obtain the number of views of the gameplay video from other users. The information acquisition means 110 was configured to obtain the number of views of the gameplay video and store it in memory 12, and the population generation means 120 was configured to input this information into a trained model to generate a new population, but is not limited to this.

[0112] Based on a user publishing a video of themselves playing a monster battle game, the game server 10 may be configured to store information relating to a specific scene in the video in which a predetermined character is battling in memory 12, and to obtain the number of times other users have viewed that specific scene. The information acquisition means 110 may then obtain the number of views of the specific scene in the video and store it in memory 12, and the population generation means 120 may be configured to input this information into a trained model to generate a new population. For example, if the number of views of the specific scene exceeds a predetermined number, the population generation means 120 may add the predetermined character to the population or increase the probability of obtaining the predetermined character. On the other hand, if the number of views of the specific scene is less than a predetermined number, the population generation means 120 may remove the predetermined character from the population or decrease the probability of obtaining the predetermined character. Even in this way, the same effect as in the modified example 4 above can be achieved.

[0113] Furthermore, while the above modification 4 uses the number of views and likes on a gameplay video as examples, it is not limited to these. For example, the viewing time of the gameplay video could also be used. Here, since the viewing time varies depending on the content of the gameplay video, for example, rather than a user watching a short 1-minute gameplay video 10 times, the game server 10 may acquire the character setting information shown in the gameplay video and store it in memory 12 when the user is watching a 1-hour gameplay video in its entirety.

[0114] Furthermore, for long gameplay videos, it is preferable for the game server 10 to extract information about the time periods the user watched. This makes it possible to reflect information about characters appearing in the parts of the gameplay video that the user is truly interested in into the AI ​​gacha, thereby improving the accuracy of the AI ​​gacha. Here, if a live stream or recorded video is watched from the beginning, the game server 10 can simply store the information related to the gameplay video within the viewing time in memory 12. However, in reality, the actual viewing targets in the gameplay video change depending on where the user started watching the live stream or where they started playing the recorded video. Therefore, it is preferable for the game server 10 to measure the start and end times of the playback time (playback position) and store them in memory 12.

[0115] Furthermore, in the above modified example 4, the game server 10 stored information related to the gameplay video in memory 12 based on the user publishing the gameplay video of the monster battle game to other users on social media or video streaming sites, but it is not limited to this. For example, the game server 10 may acquire the user's gaze information via smart glasses or a smartphone (camera 33) capable of acquiring the user's gaze information to obtain information about which parts of the gameplay video the user is paying attention to while watching. In this way, the parts that the user is fixating on in the gameplay video can be reflected as learning data, further improving the accuracy of the AI ​​gacha.

[0116] [Difference 5] In the monster battle game according to Modification 5, the server program 13P loaded into memory 12 further causes the game server 10 (processor 11) to function as a storage means that stores the population generated by the population generation means 120 and the results of the lottery executed by the lottery execution means 140 using that population in association with each other, and as a confirmation means that allows the user to confirm the population stored by the storage means and the results of the lottery.

[0117] In this case, the memory means first stores in memory 12 the population displayed on the AI ​​gacha screen (first time) in Figure 9(b), such as the Flame Sword, Flame Shield, Flame Armor, and Wooden Staff, as well as information related to the probability of obtaining these items. Next, the memory means stores in memory 12 the information related to the Flame Sword displayed on the AI ​​gacha lottery result screen in Figure 11 (i.e., the information that the Flame Sword was obtained in the AI ​​gacha (first time)). Finally, the memory means associates the population displayed on the AI ​​gacha screen (first time) in Figure 9(b) with the Flame Sword displayed on the AI ​​gacha lottery result screen in Figure 11. The confirmation means displays the population displayed on the AI ​​gacha screen (first time) in Figure 9(b) and the information that the Flame Sword was obtained in the AI ​​gacha (first time) stored in memory 12 on the user terminal 20 for the user to confirm.

[0118] Figure 22(a) shows the gacha notification screen according to Modification 5. As shown in Figure 22(a), a confirmation button is displayed within the AI ​​gacha notification area. When the user terminal 20 receives a press of the confirmation button, it moves to the confirmation screen. Figure 22(b) is the confirmation screen. The confirmation screen is for checking the results of past AI gacha draws. The confirmation screen displays buttons for AI gacha (1st time), AI gacha (2nd time), ..., and AI gacha (Nth time). When the user presses any of the buttons, the confirmation means displays the result of the AI ​​gacha draw corresponding to the user terminal 20 and the population at which the draw was performed, allowing the user to confirm.

[0119] According to the above modified example 5, users can view the population at the time of the AI ​​gacha in relation to the results of the draw, thus preventing users from getting bored even after they have run the AI ​​gacha.

[0120] Furthermore, according to the above modification 5, it is possible to enjoy the process of analyzing the population of past AI gacha and their draw results, and then reflecting that analysis in the AI ​​gacha that is planned to be executed later.

[0121] [Modification 6] In the monster battle game according to Modification 5, the server program 13P loaded into memory 12 has a storage means that further stores the action history information acquired by the information acquisition means 110 and the lottery results in association, and a confirmation means that allows the user to further confirm the action history information and the lottery results.

[0122] 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 Flame Sword displayed on the AI ​​Gacha lottery result screen in Figure 11 (i.e., the information that the Flame Sword was dispensed in the first AI Gacha) in the memory 12. Finally, the storage means associates the user's behavior history information with the Flame Sword displayed on the AI ​​Gacha lottery result screen in Figure 11. The confirmation means displays the user's behavior history information and the information that the Flame Sword was dispensed in the first AI Gacha on the user terminal 20 for the user to confirm.

[0123] Similar to Figure 22(b) above, when the user presses any of the buttons on the confirmation screen—the AI ​​Gacha (1st time), the AI ​​Gacha (2nd time), ..., or the AI ​​Gacha (Nth time)—the confirmation means displays the behavioral history information acquired by the AI ​​Gacha corresponding to the user terminal 20, and the result of the draw in the corresponding AI Gacha, allowing the user to confirm.

[0124] Furthermore, in this modified version, as shown in Figure 23(a), a registered friends screen is provided that displays a list of registered friends. On the registered friends screen, a report button is provided for each friend to submit a report about the AI ​​gacha to the friend. When the user presses the report button and the user terminal 20 receives confirmation of the press, the system transitions to the report screen.

[0125] Figure 23(b) shows the report screen. As shown in Figure 23(b), the report screen displays the message, "To Person A: Before you do the AI ​​Gacha, you should use XX in XX!!" and a send button is displayed below the message. "XX" is the quest name and "XX" is the item name. When user terminal 20 receives a press of the send button, the above message is sent to Person A.

[0126] According to the above modified example 6, a user can send a report about the AI ​​gacha to a friend, and the friend who receives the report can generate a similar AI gacha population to the user's by setting similar conditions to the user's.

[0127] Furthermore, according to the above modification 6, users can view their behavioral history information in association with the results of the lottery at that time, allowing them to enjoy analyzing their behavioral history information and reflecting it in the AI ​​gacha that is executed afterward.

[0128] [Another embodiment] Next, with reference to Figures 24 to 28, a monster battle game according to another embodiment will be described. Figure 24 is a functional block diagram of the game server 10 according to another embodiment. This embodiment aims to facilitate the execution of the lottery and differs from the above embodiment in that, based on information related to items set by the user, one gacha is identified from multiple gacha currently implemented, and that gacha is continued to be executed until, for example, that item is dispensed. Hereinafter, the process of executing the gacha in this manner will be referred to as the automatic lottery process. This reduces the effort required for the user to perform operations to execute the lottery in order to obtain the item that the user desires. That is, when a predetermined automatic lottery is executed, the lottery can be performed automatically without any intermediate operations by the user during that time.

[0129] As shown in Figure 24, the server program 13P loaded into 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, a granting means 250, and a management means 260.

[0130] The game medium setting means 210 allows a user playing a monster battle game to set the items (game mediums) that the user wishes to acquire.

[0131] The priority setting means 220 allows the user to set a priority among multiple items when there are multiple items that the user wishes to acquire.

[0132] The gacha identification means 230 inputs information about the item set by the user by the game medium setting means 210 into a pre-trained model 16b, and identifies a gacha that can dispense the item from among the multiple types of gacha currently implemented in the game. In doing so, the gacha identification means 230 follows the priority set by the user by the priority setting means 220.

[0133] The lottery execution means 240 performs the lottery for the gacha identified by the gacha identification means 230 until predetermined conditions are met. Here, predetermined conditions include, for example, that an item desired by the user is drawn in the lottery.

[0134] The granting means 250 grants the user the items that were drawn by the lottery executed by the lottery execution means 240.

[0135] The management means 160 manages the progress of the monster battle game.

[0136] Next, referring to Figures 25 to 28, the flowchart shows the control performed between the user terminal 20, the game server 10, and the AI ​​server 16 when executing an automatic lottery process according to another embodiment.

[0137] When executing the automatic lottery process of this embodiment, the user presses the gacha setting button on the home screen. Figure 26(a) is the home screen according to another embodiment, and (b) is the gacha setting screen. As shown in Figure 26(a), the gacha setting button is displayed in the event information display area A3 of the home screen. When the user terminal 20 receives confirmation that the gacha setting button has been pressed (step S210), the management means 260 switches the monitor 31 to the gacha setting screen.

[0138] As shown in Figure 26(b), the gacha settings screen is a screen for setting the items that the user wants to obtain. The gacha settings screen displays the message, "Please enter the items and quantities you want." Below this message, the user can enter multiple items and quantities of each item they wish to obtain. As shown in Figure 25, the game medium setting means 210 allows the user to set the items they want on the gacha settings screen (step S220). In this example, the user has set "2" "Flame Swords," "1" "Flame Armor," and "1" "Flame Shield." Below these settings, priority setting buttons are displayed.

[0139] Figure 27 shows the priority setting screen. As shown in Figure 27, the priority setting screen is for setting the priority of multiple items set on the gacha setting screen. The priority setting screen displays the message, "Please enter the priority." Below this message, the user can set the priority of "Flame Sword," "Flame Armor," and "Flame Shield" that they set on the gacha setting screen. As shown in Figure 25, the priority setting means 220 allows the user to set the priority from "Flame Sword," "Flame Armor," and "Flame Shield" (step S230). In this example, the priority is set as follows: 1st place is "Flame Sword," 2nd place is "Flame Armor," and 3rd place is "Flame Shield."

[0140] Subsequently, the user proceeds to the gacha notification screen to obtain the above items. Figure 28(a) shows a gacha notification screen according to another embodiment. This gacha notification displays an automatic draw button. As shown in Figure 25, when the user terminal 20 receives a press of the automatic draw button (step S240), the gacha identification means 230 inputs information relating to the items set by the game medium setting means 210 to a pre-trained model 16b (step S250).

[0141] Based on the item information input from the game server 10, the AI ​​server 16 identifies a gacha that can dispense the item from among the multiple types of gacha currently implemented (step S260). In this process, the gacha identification means 230 follows the priority set by the user in step S230 using the priority setting means 220.

[0142] When the AI ​​server 16 identifies a gacha, it sends information related to the gacha's draw to the game server 10, and the draw execution means 240 executes the draw (step S270). In this example, the draw execution means 240 executes the fire attribute gacha displayed on the gacha announcement screen. The draw execution means 240 then repeats the draw for the fire attribute gacha until it dispenses "2" "Flame Swords", "1" "Flame Armor", and "1" "Flame Shield" (same step).

[0143] Figure 28(b) is the automatic lottery results screen. The automatic lottery results screen is a screen for displaying the results of the lottery performed by the automatic lottery. The automatic lottery results screen displays the message, "You have consumed 10,000 coins and 1,000 gems." Below that message, "2 Flame Swords, 1 Flame Armor, 1 Flame Shield" is displayed, and further below that, the message "You have obtained the above items" is displayed. The granting means 250 grants "2 Flame Swords, 1 Flame Armor, 1 Flame Shield" to the user (step S280).

[0144] [Effects of another embodiment] According to the above embodiment, a user playing a monster battle game is instructed to set the item (game medium) they wish to acquire. Information related to this item is input into a pre-trained model, and a gacha (loot box) that can dispense the item is identified from among several types of gacha. The draw of the identified gacha is then performed until the item is dispensed (until predetermined conditions are met), and the dispensed item is given to the user. Therefore, the user does not need to choose a gacha that can dispense the item they wish to acquire, and can acquire the item efficiently by performing the draw. Thus, the level of enjoyment can be improved.

[0145] Furthermore, according to the above embodiment, the user is instructed to set multiple items they wish to acquire and to set a priority among these items. The information regarding the priority set by the user is then input to the trained model 16b to identify the gacha. As a result, items can be acquired efficiently according to the user's priority. Consequently, the level of interest can be further enhanced.

[0146] In the above embodiment, the items the user desired to obtain were the Flame Sword, Flame Armor, and Flame Shield, so the Fire attribute gacha was identified and the draw for that Fire attribute gacha was performed. However, the system is not limited to this. For example, if there are other gachas besides the Fire attribute gacha that can draw for the Flame Sword, Flame Armor, and Flame Shield, the system can identify the gacha with the highest probability of obtaining these items. In this case, the system can first identify the gacha with the highest probability of obtaining the Flame Sword, which has the highest priority. If it is still not possible to identify the Flame Sword, the system can then identify it by sequentially checking the probability of obtaining the Flame Shield, which has the second highest priority, and the Flame Armor, which has the third highest priority. Even in this case, the same effects as in the above embodiment can be achieved. Furthermore, since items can be obtained more efficiently, the level of enjoyment can be reliably improved.

[0147] Furthermore, in the above embodiment, since the items the user desired were the Flame Sword, Flame Armor, and Flame Shield, the fire attribute gacha was identified and the draw for that fire attribute gacha was performed. However, the system is not limited to this. For example, if the draw for the fire attribute gacha is performed and the desired number of Flame Swords, Flame Armor, and Flame Shields are dispensed, the system may switch to a gacha that dispenses fire attribute items similar to these items (e.g., Flame Helmet, Flame Boots, etc.). In this case, the gacha identification means 230 can identify the gacha by inputting information relating to fire attribute items similar to Flame Swords, Flame Armor, and Flame Shields into the trained model 16b based on the fact that the desired number of Flame Swords, Flame Armor, and Flame Shields have been dispensed. In this way, even after the items the user desired are dispensed in the draw, the user can still acquire items that are compatible with the items they want, allowing for various equipment combinations and increasing the degree of freedom within the game.

[0148] Furthermore, in the above embodiment, we described a case where a fire-attribute gacha was identified and a draw was performed on that fire-attribute gacha, resulting in the acquisition of two fire swords, one fire armor, and one fire shield. However, the invention is not limited to this. For example, if the number of fire swords held exceeds the upper limit while a draw is being performed on the fire-attribute gacha, the game medium setting means 210 may set a fire-attribute item similar to a fire sword (e.g., a fire helmet, fire boots, etc.) instead. Even in this way, after the item the user wishes to acquire has been drawn in the draw, the user can still acquire an item that is compatible with the item they want.

[0149] Furthermore, in the above embodiment, the user set the Flame Sword, Flame Armor, and Flame Shield as items they wished to obtain and identified a gacha that could draw these items, but the system is not limited to this. For example, if the items set by the user include items that cannot be obtained from any of the currently implemented gacha draws, the gacha identification means 230 may issue a warning to the user that they cannot obtain those items. In this way, the user can avoid drawing items that cannot be obtained, thus providing a user-friendly monster battle game.

[0150] Furthermore, while the above embodiment described items as game media that can be dispensed by lottery, it is not limited to these. For example, it could be decorations, clothing, body (eyes, face, arms, legs, torso, etc.) color, or body parts that only change appearance, rather than accessories, characters themselves, or skills that affect abilities in the game. In particular, since appearance-related items do not affect abilities in progressing through the game, they easily reflect the user's preferences, and there is a strong need for items that the user likes. Therefore, historical information related to appearance may be given a greater weight as learning data.

[0151] In the above embodiment, items to be equipped to a character were described as the subject of the lottery, but the subject of the lottery is not limited to items, and various subjects may be determined using a learning model like the present invention. For example, the subject of the lottery may be the stage for when playing against other users.

[0152] Furthermore, while the above embodiment described an online monster battle as an example of a game, the present invention is not limited to this. For example, the present invention can be applied to various online games that implement gacha (loot boxes). Another example of a game may be a game conducted via ad-hoc communication between user terminals 20.

[0153] Furthermore, the program according to the present invention is not limited to a single program, but may be a collection of multiple programs. Also, the program according to the present invention is not limited to being executed on a single device, but may be executed by multiple devices in a shared manner. Moreover, the division of roles between the game server 10 and the user terminal 20 is not limited to the examples described above. That is, a part of the processing of the game server 10 may be executed by the user terminal 20, and a part of the processing of the user terminal 20 may be executed by the game server 10.

[0154] Furthermore, some or all of the means implemented by the program can also be implemented by hardware such as integrated circuits. In addition, the program may be provided by being recorded on a non-transient recording medium readable by a computer. Recording mediums include, for example, hard disks, SD cards, DVDs, and servers on the internet.

[0155] <<Note>> To summarize what has been explained, for example, it is as follows: <Challenges> The objective is to provide functions that utilize learning capabilities. <Solution 1> The processor, A means of acquiring information to obtain user behavior history information in a game, A population generation means that inputs the behavioral history information into a pre-trained model to generate a population of game media to be subject to lottery, A program that functions as a lottery execution means for executing a lottery to draw the game medium from the population generated by the population generation means. <Solution 2> In the program described in Solution 1, The population generation means generates a new population by changing the game medium or the probability of the game medium being dispensed from the initial population, The aforementioned processor, A program that further functions as a display means for displaying the game medium or the probability of dropping included in the new population generated by the population generation means. <Solution 3> In the program described in Solution 2, The lottery execution means is a program that enables the execution of the lottery in response to the display means displaying information on the game medium or the probability of winning that is included in the population on a user terminal operated by the user. <Solution 4> In the program described in Solution 1, The information acquisition means is a program that acquires the user's behavioral history information during a predetermined period before the lottery execution means executes the lottery. <Solution 5> In the program described in Solution 1, The information acquisition means acquires the usage frequency of the game medium dispensed by the lottery as the behavioral history information. The population generation means is a program that causes the trained model to generate the population such 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 decreases. <Solution 6> In the program described in Solution 1, The information acquisition means acquires the usage frequency of the game medium dispensed by the lottery as the behavioral history information. The population generation means is a program that causes the trained model to generate the population such that the probability of the game medium being dispensed increases when the frequency of use is equal to or greater than a second threshold. <Solution 7> In the program described in Solution 1, The information acquisition means is a program that acquires the user's behavioral history information during a specific event held within the game. <Solution 8> In the program described in Solution 1, The aforementioned processor, If the lottery execution means performs the lottery a predetermined number of times or more, it further functions as a reward granting means that grants a reward to the user. The reward-granting means is a program that can grant the right to perform the lottery free of charge as the reward. <Solution 9> In the program described in Solution 1, The aforementioned processor A storage means for storing, in association with, the population generated by the population generation means and the result of the lottery performed by the lottery execution means using the population; A program that further functions as a confirmation means, which displays the population stored in the storage means and the results of the lottery on the user terminal and allows the user to confirm them. <Solution 10> In the program described in Solution 9, The aforementioned processor, The storage means further stores the behavioral history information acquired by the information acquisition means and the result of the lottery in association with each other. The verification means is a program that displays the behavioral history information and the lottery results on the user terminal and allows the user to further verify them. <Solution 11> A means of acquiring information to obtain user behavior history information in a game, A population generation means that inputs the behavioral history information into a pre-trained model to generate a population of game media to be subject to lottery, A system comprising: a lottery execution means for performing a lottery to draw the game medium from the population generated by the population generation means. <Solution 12> The way in which a processor executes a program, The first step is to obtain user behavior history information in the game, The second step involves inputting the aforementioned behavioral history information into a pre-trained model to generate a population of game media to be subject to the lottery, A method comprising: a third step of performing a lottery to select the game medium from the population generated in the second step. <Solution 13> The processor, A game media setting means that allows a user to set the game media they wish to acquire while playing the game, A content identification means that inputs information relating to the game medium into a pre-trained model and identifies the content that can be selected from among multiple types of content by drawing lots to dispense the game medium, A program that functions as a lottery execution means, which performs the lottery of the identified content until predetermined conditions are met. [Explanation of symbols]

[0156] 110 Information acquisition means 120 Population generation means 130 Change Indicator 140. Lottery execution method

Claims

1. The processor, A measurement method for measuring viewing information of users who watch game-related gameplay videos, A program that functions as a generation means for generating game media by inputting information measured by the aforementioned measurement means into an AI.

2. In the program described in claim 1, The aforementioned processor is configured to function as a means for identifying the equipment information or setting information of the character displayed in the gameplay video. The generation means is a program that inputs the equipment information or setting information of the character identified by the identification means into the AI ​​to generate the game medium.

3. In the program described in claim 1, The processor is configured to function as a means for identifying the portion of the gameplay video that the user was looking at, based on the user's gaze information acquired by an imaging means connected to the user terminal while the user is watching the gameplay video on the user terminal. The generation means is a program that inputs information about the location where the user's gaze is directed, as identified by the identification means, into the AI ​​to generate the game medium.

4. In the program described in claim 1, The measurement means further acquires information regarding reactions, including the number of views or ratings of the gameplay video by other users. The generation means is a program that changes the influence on the game medium being generated in response to the feedback.

5. In the program described in claim 1, A program that further enables the processor to function as an input data setting means for displaying a list of play videos on a user terminal and allowing the user to select a play video from the list to input to the AI.

6. In the program described in claim 1, A program that further causes the processor to function as a transmission means for transmitting to another user message information including generation conditions for the game medium generated by viewing the gameplay video, and information regarding the gameplay video that corresponds to the generation conditions, based on the user's operation.

7. A measurement method for measuring viewing information of users who watch game-related gameplay videos, A system comprising a generation means that inputs information measured by the aforementioned measurement means into an AI to generate a game medium.

Images