Information processing system, program, and information processing method

Abstract

To provide an information processing system, a program, and an information processing method capable of enhancing a player's interest in a game using a non-player's character (NPC).SOLUTION: An information processing system for providing a game using a non-player's character includes: an NPC control section for controlling a non-player's character on the basis of at least one learned model; an additional information acquisition section for acquiring setting information associated with a game medium; and a model generation section for generating a learned model with a setting on the basis of setting information associated with a game medium acquired by the additional information acquisition section. The NPC control section controls the non-player's character by reflecting the setting information on the basis of the learned model with a setting.SELECTED DRAWING: Figure 5A

Description

[Technical field]

[0001] The present disclosure relates to an information processing system, a program, and an information processing method. [Background technology]

[0002] 2. Description of the Related Art Games that use non-player characters (NPCs) controlled by a computer are known as games that can be executed on player terminals such as smartphones and game terminals.

[0003] For example, Patent Document 1 discloses a game in which a player can have a conversation with an NPC that appears in the game. In the game of Patent Document 1, the contents of the conversation between the player and the NPC are stored in advance as text data in the game system, and the conversation with the NPC progresses when the player selects one line from a selection of lines. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP2010-246758A Summary of the Invention [Problem to be solved by the invention]

[0005] In the game system of Patent Document 1, a plurality of lines are prepared corresponding to the progress of the conversation and the emotional level of the NPC, and the content of the next conversation and the emotion of the NPC in the conversation can be changed according to the selection of the line by the player. However, the change of the conversation content in Patent Document 1 is limited to the range of the prepared line options. If the expression of the speech and behavior of the NPC can be diversified more than before, it is expected that the interest in the game will increase.

[0006] An object of an exemplary embodiment of the present disclosure is to provide an information processing system, a program, and an information processing method that can increase a player's interest in a game that uses non-player characters (NPCs). [Means for solving the problem]

[0007] An information processing system according to one aspect of the present disclosure includes: An information processing system for providing a game using a non-player character, comprising: An NPC control unit that controls the non-player characters based on at least one learned model; an additional information acquisition unit that acquires setting information associated with a game medium; A model generation unit that generates a learned model with settings based on the setting information associated with the game content acquired by the additional information acquisition unit, The NPC control unit controls the non-player character based on the learned model with settings and reflecting the setting information.

[0008] The information processing system has the above features, which can increase the interest of players in games that use non-player characters.

[0009] A program according to one aspect of the present disclosure includes: A program for causing a computer to execute information processing related to the provision of a game using a non-player character, controlling the non-player character based on at least one learned model; Obtaining setting information associated with a game medium; Generating a learned model with settings based on the setting information associated with the acquired game content; The computer is caused to reflect the setting information in the control of the non-player character based on the learned model with settings.

[0010] When the program has the above features, it is possible to increase the interest of the player in a game that uses non-player characters.

[0011] An information processing method according to one aspect of the present disclosure includes: 1. An information processing method in which a computer executes information processing related to the provision of a game using a non-player character, comprising: controlling the non-player character based on at least one learned model; Obtaining setting information associated with a game medium; Generating a learned model with settings based on the setting information associated with the acquired game content; The computer executes a process of reflecting the setting information in the control of the non-player character based on the learned model with settings.

[0012] The information processing method having the above features can increase the interest of a player in a game that uses non-player characters. [Brief description of the drawings]

[0013] [Figure 1] FIG. 1 is a schematic diagram illustrating a configuration example of an information processing system according to an embodiment of the present disclosure. [Diagram 2] FIG. 2 is a block diagram illustrating an example of a functional configuration of the server illustrated in FIG. [Diagram 3] FIG. 3 is a block diagram showing an example of a functional configuration of the player terminal shown in FIG. [Figure 4] FIG. 4 is a schematic diagram illustrating an example of game media information stored in the game information storage unit illustrated in FIG. [Figure 5A] FIG. 5A is a flowchart for explaining an outline of the processing of the information processing system. [Figure 5B] FIG. 5B is a flowchart for explaining an outline of the processing of the information processing system. [Figure 5C]FIG. 5C is a flowchart for explaining an outline of the processing of the information processing system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] An information processing system 10 according to an embodiment of the present disclosure will be described with reference to the drawings. Note that each drawing is an example for explaining this embodiment, and the system configuration, block diagram, flow chart, etc. shown in each drawing may be modified or changed within a range that does not cause technical problems. In addition, in this specification and drawings, components having substantially the same functional configuration are given the same reference numerals to avoid duplicated description.

[0015] The information processing system 10 according to this embodiment is a system for providing various services related to games to a player 3 via a network N such as the Internet.

[0016] 1, an information processing system 10 includes, as its main components, at least one server 20 and at least one player terminal 30. These main components are connected to each other so as to be accessible via a network N. In this information processing system 10, the server 20 provided at the business operator 1 provides a game to the player terminal 30 by having the player 3 carry out information processing relating to the game, which is composed of images, videos, sounds, etc.

[0017] <Server device configuration> The server 20 is an information processing device used to operate and manage the game service, and is deployed at the business operator 1 that provides the game service, as described above. The server 20 as an information processing device may be, for example, a general-purpose computer such as a workstation or a personal computer, or may be logically constructed using cloud computing technology.

[0018] The server 20 has a control unit 21 that controls the entire server 20, a memory unit 22 that stores various data and application programs, and a server communication unit 23 that transmits and receives data between the player terminals 30 via the network N.

[0019] <Control unit (server)> The control unit 21 is a component that transfers data between each unit and controls the entire server 20. The control unit 21 has a function of executing various information processing required for providing game services, and the function of the control unit 21 is realized by an arithmetic processing device such as a CPU (Central Processing Unit) and / or a GPU (Graphics Processing Unit) reading data and programs stored in a predetermined storage and executing various programs in a working area of ​​the memory.

[0020] The control unit 21 has a plurality of functional units according to the type of information processing to be executed. For example, the control unit 21 may include, as functional units, a game execution unit 210, an NPC control unit 211, an additional information acquisition unit 212, a model generation unit 213, an operation information receiving unit 214, and a processing result generation unit 215.

[0021] The game execution unit 210 has a function of executing a process for progressing the game according to a game program. The categories of games provided by the information processing system 10 are not particularly limited, and may be, for example, romance games, battle games, puzzle games, action games, baseball games, soccer games, other sports games, quiz games, pinball games, card games, rhythm games, RPGs, adventure games, casino games, simulation games, strategy games, board games, racing games, and the like.

[0022] In addition, a game may include, for example, not only a "game progression part" that is the part related to actual game play, known as the "in-game," in which the player advances through stages (quests) by controlling in-game characters or puzzles, or competes against opponents in cards or races, but also a "lottery part" that is known as the "out-game," such as a "gacha" that grants game media such as in-game characters and items to the player by lottery, a "formation part" that selects game media such as characters to be used in the game, and a "strengthening part" that strengthens characters, items, etc.

[0023] The game in which the game execution unit 210 progresses is a game using non-player characters (hereinafter, referred to as NPCs). An NPC means a character that is not operated by a player, and for example, an NPC is operated by a character AI, which is an artificial intelligence. The use of an NPC in a game is not particularly limited, and for example, in a battle game, an NPC may be used as a companion character that cooperates with the player, or an enemy character that fights against the player. In addition, in a love game, an NPC may be used as a love interest character, and in a training-type simulation game, an NPC may be used as a character to be trained. In a game in which the game execution unit 210 progresses, a single NPC may be used, or multiple NPCs may be used.

[0024] Moreover, the game in which the game execution unit 210 progresses is a game that uses at least one game medium. Here, the term "game medium" is a general term for electronic data used by the player 3 in the game. For example, cards, characters operated by the player 3 (hereinafter, may be referred to as the operation character), avatars, consumable media such as in-game currency, and other items correspond to the game medium. In the game in which the game execution unit 210 progresses, the player 3 may operate an avatar or operation character that acts in the game space to progress the game. Furthermore, as the game medium used in the game, items such as weapons, armor, costumes, and ornaments may be equipped to the avatar, operation character, and NPC of the player 3 according to the selection of the player 3. In addition, as the game medium used in the game, items such as interior items may be arranged in the game space according to the selection of the player 3, and the game may be executed.

[0025] The functions of the NPC control unit 211, the additional information acquisition unit 212, and the model generation unit 213 correspond to the function of the character AI.

[0026] The NPC control unit 211 has a function of executing a process to control an NPC based on at least one learned model when a game controlled by the game execution unit 210 is executed. That is, the NPC control unit 211 is a main component of the character AI, and the learned model used in the process of the NPC control unit 211 is a decision-making model of the NPC that has been subjected to machine learning to make the NPC act autonomously. The NPC control unit 211 uses at least one data selected from, for example, a prompt sent by the player 3 to the NPC, other operation information of the player 3, information set by the player 3 before the start of the game (for example, information on the game medium used in the game determined by the selection operation of the player 3, information on the game unit to be executed (quest, event, etc.), etc.), information on the game situation collected during the progress of the game, and past game history by the player 3, etc., as input to the learned model. The NPC control unit 211 inputs the above-mentioned data into the learned model, and determines and outputs the activity (words and / or actions) to be executed by the NPC in the game space. The NPC control unit 211 transmits control information for the NPC (such as words (conversation) and / or action information to be executed by the NPC), which is the output of the learned model, to the processing result generation unit 215 described later.

[0027] In the information processing system 10, a single trained model that comprehensively controls the activities of NPCs in the game space may be used, or a combination of multiple trained models corresponding to specific control items may be used (i.e., multiple trained models may be integrated to control NPCs). For example, the NPC control unit 211 may control the NPC based on a trained model that outputs both the words (conversation) of the NPC and the actions of the NPC, or may control the NPC based on a combination of a trained model that outputs the words of the NPC and a trained model that outputs the actions of the NPC. In addition, in the information processing system 10, as a trained model for controlling the NPC, a common trained model that is used by all players 3 may be prepared, or a trained model that incorporates (is trained to) information linked to each individual player 3 may be prepared for each player 3.

[0028] The machine learning for constructing the trained model may be performed by appropriately selecting training data and a training algorithm to realize the autonomous activity of the NPC, and the machine learning method is not particularly limited. The machine learning may be unsupervised learning, supervised learning, reinforcement learning, or deep learning, and the trained model may be constructed by combining these machine learning methods.

[0029] The learning data is not particularly limited as long as it is appropriately selected so as to obtain a desired output. Examples of learning data when outputting the words of an NPC (generating a conversation) using a trained model include a large-scale corpus that aggregates sentences in natural language, a conversation dataset consisting of a combination of an input natural language (prompt) and a natural language (response) in which a person responds to the input, and an evaluation dataset in which a person evaluates the appropriateness of the response to the prompt. In addition, when outputting both the conversation of an NPC and the actions during the conversation using a trained model, in addition to the above-mentioned training data, a dataset consisting of a combination of a natural language and a gesture pattern when speaking the natural language, evaluation data in which a person evaluates the appropriateness of the actions, etc. may be used. In addition, when outputting the actions of an NPC in a fighting game, for example, data of a fighting game performed by a person operating a character may be used as the learning data. In addition to the above-mentioned training data, basic information about the game, such as the game specifications and the rules within the game, may be learned by the model.

[0030] The learning algorithm is not particularly limited and may be appropriately selected so as to obtain a desired output, and any known learning algorithm may be adopted. For example, one or more algorithms selected from neural networks such as deep neural networks, convolutional neural networks, and recurrent neural networks, reinforcement learning algorithms such as RLFH (Reinforcement Learning from Human Feedback) and SFT (Supervised Fine-Tuning), decision trees, random forests, and principal component analysis may be used, and it is preferable to adopt a neural network.

[0031] In the information processing system 10 according to the present embodiment, a process of adding information to a character AI that controls an NPC is executed. In the present embodiment, among the trained models that control an NPC, an existing model before the addition of information is referred to as a "predecessor model", and a model after the addition of information is referred to as a "trained model with settings". Also, the information to be added to the character AI is referred to as "additional information".

[0032] When a learned model with settings is generated by the model generation unit 213 described later, the NPC control unit 211 executes a process of controlling the NPC by reflecting additional information based on the learned model with settings. That is, when a learned model with settings is generated, the NPC control unit 211 executes a process of changing the control of the NPC from control by a predecessor model to control using the learned model with settings. When executing an output reflecting additional information, the NPC control unit 211 may execute a process of switching the learned model (hereinafter, sometimes referred to as a control model) used for controlling the NPC from the predecessor model to the learned model with settings. Alternatively, the NPC control unit 211 may control the NPC by using both the predecessor model and the learned model with settings.

[0033] In the following description, a game including a scene in which an NPC converses is mainly assumed, and a process related to adding information to a character AI is illustrated. That is, a case in which a learned model such as a learned model with settings generates a conversation of an NPC based on additional information is mainly illustrated. However, a learned model such as a learned model with settings is not limited to a model that outputs control information related to a conversation, and may be a model that outputs control information related to an activity of an NPC in a game. For example, a learned model with settings may be a model that outputs control information related to an NPC's combat activity. Note that the conversation of an NPC may be a conversation between an NPC and a player 3, or may be a conversation between an NPC and another NPC. Also, a conversation between a player 3 and an NPC may be a conversation between the player 3 and the NPC through an avatar or an operation character, or may be a conversation between the player 3 and the NPC without the mediation of an avatar or an operation character. In the case where the trained model with settings is a model that outputs control information related to conversation, the trained model with settings may be input with the conversation of player 3 (which may be in text format or audio format), and other information generated as the game progresses, etc. may also be input.

[0034] The additional information acquisition unit 212 has a function of executing a process of acquiring setting information linked to a game medium. The setting information linked to a game medium corresponds to additional information to be incorporated into a character AI that controls an NPC. That is, in this embodiment, data (additional learning data) to be additionally learned in the learned model is managed by linking it to game media that the player 3 can use in the game. Note that, in addition to the setting information linked to the game medium, the learned model may additionally learn other game-related information such as a list of game media and past game history by the player 3.

[0035] The game media used in the information processing system 10 may include game media that are linked to setting information that serves as additional learning data, and may also include game media that are not linked to setting information that serves as additional learning data. In the following description, when distinguishing between the presence and absence of setting information that serves as additional learning data, the game media that are linked to setting information that serves as additional learning data will be referred to as the "first game medium," and other game media that are not linked to setting information will be referred to as the "second game medium." When generating conversations of NPCs using a learned model with settings, items to be attached to characters (avatars, playable characters, NPCs, etc.), items to be placed in the game space, items to be consumed during game progress, and characters themselves such as NPCs may be set to the first game medium.

[0036] In addition, in the game provided by the information processing system 10, the method of acquiring the game medium is not particularly limited. For example, the game medium may be provided to the player 3 by a lottery means such as gacha, a reward for clearing the game, an exchange with paid or free consumable media consumed in the game, and a synthesis of two or more objects. An NPC that is not an object of operation by the player 3 may also be provided to the player 3 by the above-mentioned method. A special restriction different from that for the second game medium may be imposed on the method of acquiring the first game medium. For example, the first game medium may be provided to the player 3 by a method such as a time-limited gacha or a reward for a time-limited event. In addition, the game medium registered from the beginning of the operation of the game system (when the game is first provided) may be the second game medium, and the game medium added to the game system later may be the first game medium, and the setting information may be linked to the game medium.

[0037] The additional information acquisition unit 212 may execute a process of acquiring setting information linked to the first game medium, triggered by the acquisition of the first game medium by the player 3. Specifically, the additional information acquisition unit 212 detects that the player 3 has acquired the first game medium, and, triggered by the detection, acquires setting information linked to the first game medium. The additional information acquisition unit 212 then transmits the acquired setting information to the model generation unit 213, described later, as data for additional learning.

[0038] The trigger for starting the process of the additional information acquisition unit 212 is not limited to the acquisition of the first game medium described above. For example, the additional information acquisition unit 212 may execute a process of acquiring setting information linked to the first game medium, triggered by the use of the first game medium by the player 3. When the player 3 selects a game medium to be used in the game from among the owned game media during the preparation process before the execution of the game and / or during the progress of the game, the additional information acquisition unit 212 may identify the first game medium from among the game media to be used selected by the player 3, and acquire setting information linked to the first game medium, triggered by the identification. The additional information acquisition unit 212 then transmits the acquired setting information to the model generation unit 213 described later as additional learning data.

[0039] Furthermore, the additional information acquisition unit 212 may execute a process of acquiring additional information when triggered by an update of the game system provided by the server 20. When new game media are registered in the storage unit 22 as a result of a system update, the additional information acquisition unit 212 may identify a first game medium from among the newly registered game media and acquire setting information associated with the first game medium. The additional information acquisition unit 212 then transmits the acquired setting information to the model generation unit 213, which will be described later, as additional learning data.

[0040] The model generation unit 213 has a function of executing a process of generating a learned model with settings based on setting information (additional information) associated with the first game medium acquired by the additional information acquisition unit 212. In other words, the model generation unit 213 executes a process of additionally learning the setting information associated with the first game medium to the learned model. When multiple learned models are registered in the information processing system 10, the model generation unit 213 may execute a process of selecting a learned model to which to add the setting information, in accordance with the setting information associated with the first game medium.

[0041] In the additional learning performed by the model generation unit 213, only the setting information linked to the first game medium may be learned in the learned model, or the learned model may be re-learned by combining the setting information linked to the first game medium with the learned data. The method of additional learning is not particularly limited, and for example, reinforcement learning, fine tuning, or transfer learning may be adopted. When the setting information linked to the first game medium is added by fine tuning, for example, a part or the whole of the learned model is re-learned using the learning data including the setting information linked to the first game medium, and the weights of the entire network of the model are updated. On the other hand, when the setting information linked to the first game medium is added by transfer learning, additional information including the setting information linked to the first game medium is learned for the output layer part of the network of the learned model, and the weights of the output layer part are updated. Note that a publicly known learning algorithm may be adopted for fine tuning or transfer learning. In addition, when generating a learned model with settings, a predecessor model before the additional learning may be left, or a learned model with settings may be generated by updating the predecessor model.

[0042] When the model generation unit 213 generates the learned model with settings, the NPC control unit 211 changes the control of the NPC from the control by the predecessor model to the control using the learned model with settings. This change of the control model may be automatically executed in association with the generation of the learned model with settings. Alternatively, the NPC control unit 211 may detect the acquisition or use of the first game medium by the player 3, and the detection may be used as a trigger to execute the change to the control using the learned model with settings. That is, the NPC control unit 211 may detect the acquisition or use of the first game medium by the player 3, and reflect the setting information associated with the first game medium in the activity of the NPC in the game. For example, when the additional information acquisition unit 212 acquires the setting information associated with the first game medium as a trigger of an update of the game system, the NPC control unit 211 may execute the change of the control model as a trigger of the acquisition or use of the first game medium by the player 3. In addition, if the additional information acquisition unit 212 acquires setting information linked to the first game medium, triggered by the acquisition of the first game medium by player 3, the NPC control unit 211 may execute a change in the control model, triggered by the use of the first game medium by player 3.

[0043] The change of the control model may be executed based on the selection by the user. For example, when a learned model with settings capable of generating conversations in a dialect is generated by additional learning of setting information linked to a game medium, the conversation of the NPC may be controlled in a standard language mode based on the predecessor model, or in a dialect mode based on the learned model with settings, and the user may select either the standard language mode or the dialect mode to switch the control of the NPC. In addition, after changing the control of the NPC from the control by the predecessor model to the control using the learned model with settings, the NPC control unit 211 may execute a process of returning the control of the NPC to the control by the predecessor model based on the progress of the game, the selection of the game medium to be used by the user, or the selection by the user. In this way, the control by the predecessor model and the control using the learned model with settings may be mutually switchable at a predetermined timing.

[0044] The operation information receiving unit 214 has a function of receiving operation information transmitted from the player terminal 30. The received operation information is used as instruction information for the game execution unit 210 to process the game program. The received operation information is also used as input information (prompt) to a control model (predecessor model, learned model with settings) when the NPC control unit 211 controls the activity of the NPC.

[0045] The processing result generating unit 215 has a function of executing a process for generating a processing result of the game program executed by the game executing unit 210. When generating the processing result of the game program, the processing result generating unit 215 receives control information of the NPC sent from the NPC control unit 211, and generates the processing result of the game program by reflecting the control information. The processing result generated by the processing result generating unit 215 is transmitted to the player terminal 30 via the server communication unit 23, and is output by the display unit 34 of the player terminal 30.

[0046] When the learned model with settings outputs control information related to an NPC's conversation, the output on the display unit 34 derived by the control information may be in text format, or may be in audio format such as an NPC's speech. The control information related to the conversation may include not only language information but also NPC's motion information accompanying the conversation. When the output (control information) of the learned model with settings includes NPC's motion information accompanying the conversation, the NPC's motion may be output on the display unit 34 by the motion information (for example, mouth movement in accordance with the NPC's lines is output, a fist pump motion accompanying the NPC's line "Yeah!" is output, etc.).

[0047] <Storage unit (server)> The storage unit 22 is a storage area of ​​the server 20 that stores programs for executing various control processes and functions in the control unit 21, input data, etc., and is configured by one or any combination of RAM (Random Access Memory), ROM (Read Only Memory), SRAM (Static Random Access Memory), flash memory, HDD (Hard Disk Drive), SSD (Solid State Drive), and other storages. The storage unit 22 may also have a function of temporarily storing the contents of communication by the server 20 when the server 20 performs communication.

[0048] The storage unit 22 of the server 20 may have a plurality of areas partitioned according to the type of information to be stored. For example, the storage unit 22 may include a game information storage unit 221, a player information storage unit 222, and a model storage unit 223.

[0049] The game information storage unit 221 stores and stores basic information about the game. The basic information about the game stored in the game information storage unit 221 is appropriately configured according to the type of game, and is not particularly limited. For example, the game information storage unit 221 may store information such as setting information for each game unit, information about the game medium, information related to the game space such as background images, and event information. Note that a "game unit" refers to a single collection of games, and a "game unit" can be expressed in terms such as a quest, an event, a mission, a course, a story, a scenario, a chapter, a dungeon, a stage, a battle, and a match.

[0050] The information on the game media stored in the game information storage unit 221 may be assigned an ID (hereinafter referred to as a game media ID) as an identifier for uniquely identifying each game medium. The game information storage unit 221 may store the name, image data, and acquisition method of the game media as the information on the game media.

[0051] Fig. 4 illustrates information on first game media stored in the game information storage unit 221. Seven types of first game media are illustrated in Fig. 4, of which the types of first game media indicated by IDs M-A001 to M-A006 are items, and the type of first game media indicated by ID M-C001 is a character.

[0052] As shown in FIG. 4, the information on the first game medium includes setting information (additional learning data) linked to a game medium ID. The setting information linked to the first game medium may be data for additional learning used to construct a trained model with settings, and the details of the setting information are not particularly limited. When the trained model with settings is a model that outputs control information related to a conversation, the setting information may be data such as those shown in (1) to (7) below (see FIG. 4). Any combination of the data shown in (1) to (7) may be linked to the first game medium as setting information.

[0053] (1) An episode (scenario) related to the item (2) Data concerning the character's experiences or career (3) Data regarding the character's status (status, position, occupation, position, etc.) (4) Data regarding the character's personality (such as parameters based on the Big Five Personality Traits) (5) Data regarding character preferences (6) Data related to the character's speech (intonation, accent, dialect, endings, etc.) (7) Data representing the relationship between characters

[0054] The data exemplified in (2) to (7) above may be data linked to the first game medium which is a character, or may be data linked to the first game medium which is an item. When (2) to (7) are data linked to an item, the "character" in (2) to (7) refers to a character to which the item is attached, and the item may be attached to an object operated by the player 3, such as an avatar or an operable character, or may be attached to an NPC.

[0055] The data shown in (1) to (7) above are examples of setting information mainly related to conversation generation, but when mainly generating actions such as combat actions of NPCs, setting information related to NPC actions may be linked to game media such as items. For example, setting information related to a predetermined attack skill may be linked to a weapon item, and the probability of selecting a defensive action or the probability of avoiding an attack may be linked to an armor item.

[0056] The information on the first game medium stored in the game information storage unit 221 may include information for identifying a trained model to be additionally trained. For example, the column of "Target Model" in FIG. 4 corresponds to information for identifying a trained model to be additionally trained. "Conversation" in the column of target model means that a trained model for conversation generation is designated as a target for additional learning, and "Conversation / Action" means that one or more of a trained model for conversation generation, a trained model for action generation, and a trained model that generates both conversation and action are designated as a target for additional learning. When the model generation unit 213 selects a trained model to which setting information is to be added from among a plurality of trained models, the trained model to be additionally trained may be determined based on information specifying a target model included in the first game medium.

[0057] The player information storage unit 222 stores information associated with each player 3 who uses the game service. For example, the player information storage unit 222 may store a player ID (an identifier for identifying each player 3) and information such as a player name, a registration date to the game service, and a player level that are linked to the player ID. The player information storage unit 222 may also store play history information accumulated by each player 3 using the game service in association with the player ID. The play history information may include data such as, for example, login date and time, number of logins, total play time, number of times each game unit has been played, data when each game unit has been cleared, game media such as items and characters owned by the player 3, amount of paid or free in-game currency owned, amount charged, number of times charged, and number of times a lottery has been played.

[0058] The model storage unit 223 stores trained models such as predecessor models and trained models with settings used for controlling NPCs. The model storage unit 223 may store, together with the trained models, training data and trained data used for constructing and re-training the trained models.

[0059] <Server communication section> The server communication unit 23 is connected to the terminal communication unit 35 of the player terminal 30 via the network N. The server communication unit 23 and the terminal communication unit 35 of the player terminal 30 transmit and receive information to and from each other. The server 20 receives various commands (prompts, requests, etc.) from the player terminal 30 via the server communication unit 23. Based on the various commands transmitted from the player terminal 30, the control unit 21 executes processing according to the game program, and the server communication unit 23 transmits the processing results of the game program (e.g., game images, game sounds, etc.) generated by the processing result generating unit 215 to the player terminal 30. Note that a part of the game program may be transmitted to the player terminal 30 and executed on the player terminal 30.

[0060] <Player device> 3 is a functional block diagram of the player terminal 30 shown in FIG. 1. The player terminal 30 is an information processing device (for example, a smartphone, a mobile phone terminal, a tablet terminal, a game dedicated terminal, other computers, etc.) that the player 3 possesses and can use. The player terminal 30 can output (for example, game image output, game sound output, etc.) the processing result of the game program transmitted from the server 20 via a game application or a Web browser. The player terminal 30 has, for example, a control unit 31 that controls the entire player terminal 30, a storage unit 32 that stores various data and programs, an input unit 33 that allows the player to input operations, a display unit 34 that displays a game screen, an operation screen, etc., and a terminal communication unit 35 that communicates information with the server 20.

[0061] <Control unit (player terminal)> The control unit 31 has functions necessary for controlling each unit of the player terminal 30 such as the display and the camera, and each function of the control unit 31 is realized by a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit) executing a program stored in a predetermined memory. The control unit 31 of the player terminal 30 may include, for example, an operation information receiving unit 311, a game operation unit 312, and a processing result receiving unit 313.

[0062] The operation information receiving unit 311 executes a process of receiving operation information related to the game inputted to the input unit 33 described later by the player 3. In addition, the operation information receiving unit 311 executes a process of outputting the received operation information related to the game to the game operation unit 312.

[0063] The game operation unit 312 executes a process for operating a game application. The game operation unit 312 starts and operates a game based on game software included in game operation information stored in the storage unit 22 described later and operation information related to the game input by the player from the input unit 23 described later. The game operation unit 312 generates images for the game from image data included in the game operation information in accordance with the operation of the game, and performs a control process for outputting the generated images to the display unit 34. Similarly, the game operation unit 312 generates music and sounds for the game from music data and sound data included in the game operation information in accordance with the operation of the game, and performs a control process for outputting the generated music and sounds from the player terminal 30.

[0064] Note that, here, a configuration has been described in which the native application executes some of the functions of the Web application, i.e., the game operation unit 312 of the player terminal 30 executes some of the functions of the processing result generation unit 215 of the server 20, but the control unit 31 of the player terminal 30 does not need to have the functions of the game operation unit 312. In that case, the processing result generation unit 215 of the server 20 may be configured to generate all game images and sounds as processing results. Also, the information processing system 10 may be configured so that the game operation unit 312 of the player terminal 30 generates all game images and sounds instead of the processing result generation unit 215 of the server 20.

[0065] When the control unit 31 has the game operation unit 312, predetermined parameters in the game operated by the game operation unit 312 are managed by the server 20. For example, parameters such as the level in the game and in-game currency are managed by the server 20. Therefore, when a process occurs in the game that involves a change in these predetermined parameters, the game operation unit 312 of the player terminal 30 updates the parameters managed by the server 20 by communicating with the server 20. Then, the game operation unit 312 receives the updated parameters from the server 20 and continues the operation of the game based on the updated parameters.

[0066] In the case where the server 20 has the processing result generating unit 215, the processing result receiving unit 313 of the player terminal 30 receives the processing result generated and transmitted by the processing result generating unit 215 of the server 20, and executes a process of outputting the processing result on the display unit 34. Note that the control unit 31 of the player terminal 30 may have functional units other than the operation information accepting unit 311, the game operation unit 312, and the processing result receiving unit 313 described above.

[0067] <Storage unit (player terminal)> The storage unit 32 of the player terminal 30 stores programs for executing various control processes and functions in the control unit 31, input data, etc., and is configured with one or any combination of a RAM (Random Access Memory), a ROM (Read Only Memory), a SRAM (Static Random Access Memory), a flash memory, a HDD (Hard Disk Drive), an SSD (Solid State Drive), and other storages. In addition, when the player terminal 30 performs communication, the storage unit 32 temporarily stores the communication contents of the player terminal 30. The storage unit 32 may include a player setting storage unit 321.

[0068] The player setting storage unit 321 stores player setting information such as information on payment methods, account information, etc. Such player setting information may be stored in the player information storage unit 222 of the server 20.

[0069] <Input section> The input unit 33 receives an input operation by the player 3 and generates operation information for the player 3 in the game. Examples of the input operation by the player 3 include an input operation by touching a display surface such as a touch panel, an input operation via physical buttons provided in the player terminal 30, a text input operation using a keyboard, a voice input operation using a microphone, and an input operation by the player 3 physically moving (tilting, shaking, etc.) the player terminal 30 using a sensor such as a gyro sensor built into the player terminal 30.

[0070] When the player 3 talks with an NPC in a game, the player 3 may perform an input operation by touching the display screen or using a keyboard, in which case text data is generated as operation information. Alternatively, the player 3 may perform an input operation using a microphone, in which case voice data or text data converted from the voice data is generated as operation information. In a conversation between the player 3 and an NPC, the above-mentioned operation information may be used as input information (prompt) to a trained model such as a trained model with settings.

[0071] <Display> The display unit 34 is a display on which the processing results of the game program are displayed, and this display may be a touch panel capable of receiving input operations from the player 3 by touching the display surface.

[0072] <Device communication unit> The terminal communication unit 35 is connected to the server communication unit 23 of the server 20 via the network N. The terminal communication unit 35 and the server communication unit 23 transmit and receive information to and from each other.

[0073] Next, an outline of the process of adding information to the character AI will be described with reference to the flowchart shown in FIG. 5A to FIG. 5B.

[0074] 5A illustrates an example flow of executing additional learning triggered by acquisition of a first game medium by the player 3. As illustrated in FIG 5A, in step S1, when the player 3 acquires a game medium by any method (gacha, event reward, etc.), the additional information acquisition unit 212 determines whether or not the game medium granted to the player 3 includes a first game medium having setting information (step S2). If the acquisition of the first game medium is detected by this determination, the process proceeds to the next step S3.

[0075] In step S3, the additional information acquisition unit 212 acquires setting information linked to the first game medium acquired by the player 3, and transmits the acquired setting information to the model generation unit 213. In step S4, the model generation unit 213 additionally learns the setting information acquired by the additional information acquisition unit 212 into the trained model by any method such as reinforcement learning, fine tuning, or transfer learning. At this time, the model generation unit 213 may generate additional learning data including the setting information linked to the first game medium before the additional learning. A trained model with settings is generated by the additional learning in step S4.

[0076] In the additional learning in step S4, the predecessor model used to control the NPC before the additional learning may be left in the model memory unit 223 to generate a trained model with settings, or the predecessor model may be updated to generate a trained model with settings.

[0077] In addition, FIG. 5A shows two examples of the flow of the information addition process, in which after step S4, the process may proceed to step S7 (Example 1), or the process may proceed to step S7 after steps S5 and S6 (Example 2). In the case of Example 1, after the learned model with settings is generated in step S4, the process may proceed to step S7 without going through steps S5 and S6 described below, and the control of the NPC may be executed using the generated learned model with settings. Alternatively, as shown below, after the learned model with settings is generated, the processes of steps S5 and S6 may be executed so that the control of the NPC is switched in response to the use of the first game medium by the player 3.

[0078] When the predecessor model and the learned model with settings are made to coexist in a valid state, the use of the first game medium by the player 3 may be detected to switch the control model. For example, when the player 3 selects a game medium to be used in the game during a preparation process before the game is executed, the NPC control unit 211 determines whether or not the first game medium having the additionally learned setting information is included among the game media selected by the player 3 as the game medium to be used (i.e., whether or not the first game medium has been used) (step S5). When the use of the first game medium is detected by the determination, a process of switching the control model from the predecessor model to the learned model with settings is executed (step S6). Although the switching of the control model is shown in step S6, a process equivalent to the switching of the control model may be executed by the learned model with settings detecting the use of the first game medium and reflecting the setting information associated with the first game medium in the activity of the NPC in the game, without going through the procedure of switching the model.

[0079] In step S7, control of the NPC using the learned model with settings is executed based on the function of the NPC control unit 211. Note that "control of the NPC using the learned model with settings" may be control using only the learned model with settings, or control using the learned model with settings and other learned models (such as a predecessor model) in combination.

[0080] In a conversation between the player 3 and an NPC, the conversation (question) from the player 3 is input to the trained model with settings in the form of text data and / or voice data input to the input unit 33. The trained model with settings then determines the NPC's response to the conversation from the player 3, and outputs the determined content as control information for the NPC. Since the trained model with settings reflects setting information linked to the first game medium as shown in FIG. 4, it is possible to create new interest in the conversation of the NPC that is different from the conversation before the additional learning.

[0081] For example, when an episode related to an item, such as the item "pairing" shown in FIG. 4, is incorporated as additional information into the learned model with settings, a conversation such as reminiscing on a date will be developed by executing a game using the item "pairing". In the case of the item "diary", a conversation between NPCs will be developed in a setting where lost memories are revived by executing a game using the item. In the case of the item "maid outfit", the NPC will be made to act as a maid (words and / or actions) by wearing the item. In addition, in the case of the item "T-shirt with a takoyaki design", the NPC will be made to speak in Osaka dialect by wearing the item. As shown in these examples, a new conversation that was not developed before acquiring or using the first game medium can be created, and the interest of the player 3 in a game involving conversation between NPCs can be improved. In the above examples, "conversation generation" is the main control target, but the control may be applied to character action generation, image generation, etc.

[0082] Fig. 5B illustrates a flow for performing additional learning triggered by the use of a first game medium by a player 3. As shown in Fig. 5B, in step S1a, when the player 3 selects a game medium to be used in the game, the additional information acquisition unit 212 determines whether or not the game medium selected by the player 3 as the game medium to be used includes a first game medium having setting information (step S2a). If the determination detects the use of the first game medium, the process proceeds to the next step S3. Steps S3, S4, and S7 in Fig. 5B are the same as those in Fig. 5A, and therefore will not be described.

[0083] 5C illustrates a flow for executing additional learning triggered by an update of the game system. As shown in FIG. 5C, in step S1b, when new game media are additionally registered in the game information storage unit 221 by an update, the additional information acquisition unit 212 determines whether the newly registered game media includes a first game media having setting information (step S2b). If this determination detects that new first game media has been added by an update, the process proceeds to the next step S3.

[0084] Steps 3 and S4 in Fig. 5C are the same as those in Fig. 5A, and therefore the description thereof will be omitted. Even in the case of additional learning triggered by an update, the process may proceed to step S7 after step S4. Also, in Fig. 5C, similar to Fig. 5A, two flows are shown, and the process may proceed to step S7 after step S4 via step S5b and step S6, or the process may proceed to step S7 after step S4 via step S5b, step S5c, and step S6.

[0085] When additional learning is performed in response to an update, a process of switching the control model may be executed in response to the acquisition or use of the first game medium by the player 3. For example, as shown in step S5b of FIG. 5C, after the generation of the learned model with settings, the NPC control unit 211 may detect that the player 3 has acquired the first game medium newly added by the update, and execute a process of switching the control of the NPC from the predecessor model to control using the learned model with settings (step S6). In addition, after the player 3 has acquired the first game medium in step S5b, the NPC control unit 211 may detect the use of the first game medium by the player 3 in step S5c, and execute a process of switching the control of the NPC from the predecessor model to control using the learned model with settings (step S6).

[0086] Although step S6 in Figure 5C shows switching of the control model, processing equivalent to switching of the control model may be executed without going through the procedure of switching the model by the learned model with settings detecting the acquisition or use of the first game medium and reflecting the setting information associated with the first game medium in the activities of NPCs in the game.

[0087] <Summary of the embodiment> The information processing system 10 of this embodiment is a game system that provides a game using a non-player character (NPC). The information processing system 10 includes an NPC control unit 211 that controls the non-player character based on at least one learned model, an additional information acquisition unit 212 that acquires setting information associated with a game medium (first game medium), and a model generation unit 213 that generates a learned model with settings based on the setting information associated with the game medium acquired by the additional information acquisition unit 212. The NPC control unit 211 controls the non-player character based on the learned model with settings, reflecting the setting information associated with the game medium.

[0088] The information processing system 10 having the above features can diversify the activities of the non-player characters in the game depending on the ownership status of the game media of the player 3. As a result, the interest of the player 3 in the game using the non-player characters can be improved.

[0089] In the information processing system 10, the additional information acquisition unit 212 may acquire setting information associated with a game medium when detecting acquisition or use of the game medium by the player 3. Additionally, the additional information acquisition unit 212 may acquire setting information associated with a game medium in response to an update of the game system.

[0090] In the information processing system 10, when the NPC control unit 211 detects the acquisition or use of a game medium by the player 3, the NPC control unit 211 may reflect setting information associated with the game medium in the activities of non-player characters in the game.

[0091] As described above, the acquisition of a game medium by the player 3 is triggered by the execution of additional learning or the change of control, which is expected to increase the motivation to acquire the game medium. In addition, the execution of additional learning or the change of control is triggered by the selection of the game medium by the player 3, so that a variety of developments can be presented in a game using non-player characters based on the player 3's own will in selecting the game medium to be used.

[0092] The learned model with settings may be a model that outputs control information related to the activities of non-player characters in the game, and in particular, may be a model that outputs control information related to the conversations of non-player characters.

[0093] The above-described embodiment is merely an example for facilitating understanding of the present invention, and is not intended to limit the present invention. The present invention can be modified or improved without departing from the spirit of the present invention, and it goes without saying that the present invention includes equivalents thereof.

[0094] The present disclosure has the following configuration. (Item 1) An information processing system for providing a game using a non-player character, comprising: An NPC control unit that controls the non-player characters based on at least one learned model; an additional information acquisition unit that acquires setting information associated with a game medium; A model generation unit that generates a learned model with settings based on the setting information associated with the game content acquired by the additional information acquisition unit, The NPC control unit controls the non-player character based on the configured learned model and reflects the configuration information. (Item 2) 2. The information processing system according to item 1, wherein the learned model with settings is a model that outputs control information related to conversations of non-player characters. (Item 3) The information processing system according to item 1 or 2, wherein the additional information acquisition unit detects the acquisition or use of the game medium by a player and acquires the setting information associated with the game medium. (Item 4) Further comprising a storage unit for storing game information; The information processing system according to item 1 or 2, wherein the additional information acquisition unit acquires the setting information associated with the game medium when the game medium is registered in the memory unit. (Item 5) The information processing system according to item 1 or 2, wherein the NPC control unit detects the acquisition or use of the game medium by a player and reflects the setting information in the activities of the non-player character in the game. (Item 6) A program for causing a computer to execute information processing related to the provision of a game using a non-player character, controlling the non-player character based on at least one learned model; Obtaining setting information associated with a game medium; Generating a learned model with settings based on the setting information associated with the acquired game content; and reflecting the setting information in the control of the non-player character based on the learned model with settings. (Item 7) 1. An information processing method in which a computer executes information processing related to the provision of a game using a non-player character, comprising: controlling the non-player character based on at least one learned model; Obtaining setting information associated with a game medium; Generating a learned model with settings based on the setting information associated with the acquired game content; and reflecting the setting information in the control of the non-player character based on the learned model with settings. [Explanation of symbols]

[0095] 1 … Business operator 3 … Player 10. Game System 20 ... Server (information processing device) 21 ... Control section 210 ... Game execution section 211 … NPC control unit 212…Additional information acquisition department 213 ... Model generation section 214 … Operation information reception unit (server side) 215 ... Processing result generation unit 22 … Storage section 221 ... Game information storage unit 222 ... Player information storage unit 223 … Model memory section 23 ... Server communication section 30 … Player terminal 31 ... Control unit (player terminal side) 311 ... Operation information reception unit (player terminal side) 312 ... Game operation section 313 ... Processing result receiving unit 32 ... Memory unit (player terminal side) 321 ... Player setting memory unit 33 … Input section 34 … Display section 35 … Terminal communication section

Claims

1. An information processing system for providing a game using a non-player character, comprising: An NPC control unit that controls the non-player characters based on at least one learned model; an additional information acquisition unit that acquires setting information associated with a game medium; A model generation unit that generates a learned model with settings based on the setting information associated with the game content acquired by the additional information acquisition unit, The NPC control unit controls the non-player characters based on the learned model with settings and reflects the setting information.

2. The information processing system according to claim 1 , wherein the learned model with settings is a model that outputs control information related to conversations of non-player characters.

3. The information processing system according to claim 1 or 2, wherein the additional information acquisition unit detects acquisition or use of the game medium by a player, and acquires the setting information associated with the game medium.

4. Further comprising a storage unit for storing game information; The information processing system according to claim 1 or 2, wherein the additional information acquisition unit acquires the setting information associated with the game medium when the game medium is registered in the storage unit.

5. 3. The information processing system according to claim 1, wherein the NPC control unit detects acquisition or use of the game medium by a player, and reflects the setting information in the activities of the non-player characters in the game.

6. A program for causing a computer to execute information processing related to the provision of a game using a non-player character, controlling the non-player character based on at least one learned model; Obtaining setting information associated with a game medium; Generating a learned model with settings based on the setting information associated with the acquired game content; A program that causes the computer to execute the following: reflecting the setting information in the control of the non-player character based on the learned model with settings.

7. 1. An information processing method in which a computer executes information processing related to the provision of a game using a non-player character, comprising: controlling the non-player character based on at least one learned model; Obtaining setting information associated with a game medium; Generating a learned model with settings based on the setting information associated with the acquired game content; and reflecting the setting information in the control of the non-player character based on the learned model with settings.

Images