Deck building system, deck building method, and deck building program

Abstract

Provided is a deck construction system 200 which constructs a deck for a card game in order to assist deck construction of a player or the adjustment of game balance by a developer by constructing the deck according to a designated condition. The deck construction system 200 comprises: a combat simulation unit 231 which simulates combat between a deck including a card used for a card game and a test deck determined in advance; a statistical information creation unit 232 which creates card statistical information on the basis of the result of the combat performed in the combat simulation unit; an input reception unit 233 which receives a condition satisfied by a deck to be constructed including a card to be used in the card game; and a deck construction unit 234 which replaces a card included in the deck to be constructed on the basis of the statistical information created by the statistical information creation unit so that the condition received by the input reception unit is satisfied.

Description

[Technical Field]

[0001] The present invention relates to a deck building system, a deck building method, and a deck building program that allow a computer to automatically build a deck in a competitive digital card game. [Background technology]

[0002] In recent years, many digital card games have been developed, where players play against each other on a computer. These digital card games do not have physical cards, and the ownership of cards and battles are all managed on the computer, but the way they are played is basically the same as traditional card games.

[0003] In competitive card games, with the exception of some games with special rules, there is a deck-building process before the match. Deck building involves players selecting a number of cards from their possession determined by the rules and declaring them as the set of cards they will use in the next match.

[0004] Deck construction is usually done by the player themselves, and while some players find more enjoyment in this process than in the match itself, there is a demand for systems that automatically construct decks by computer for players who just want to enjoy playing against others with a given deck, to support deck construction for beginner players who are not familiar with the game, and for developers to balance the game.

[0005] Previously, research has been published that attempted to use computers to build decks for digital card games. [Prior art documents] [Non-patent literature]

[0006] [Non-Patent Document 1] Garcia-Sanchez, P., and four others, “Evolutionary deckbuilding in hearthstone”, [online], September 2016, Computational Intelligence in Games, [searched January 13, 2022], Internet <URL:https: / / www.researchgate.net / publication / 304246423_Evolutionary_Deckbuilding_in_HearthStone> [Non-patent document 2] Garcia-Sanchez, P., and 4 others, “Automated Playtesting in Collectible Card Games using Evolutionary Algorithms: a Case Study in HearthStone”, [online], April 2018, Knowledge-Based Systems, [Retrieved January 13, 2020], Internet <URL:https: / / www.researchgate.net / publication / 324767888_Automated_Playtesting_in_Collectible_Card_Games_using_Evolutionary_Algorithms_a_Case_Study_in_HearthStone> [Non-patent document 3] Sverre Johann Bjorke and 1 other person, “Deckbuilding in Magic: The Gathering Using a Genetic Algorithm”, [online], June 2017, Norwegian University of Science and Technology, [Retrieved January 13, 2022], Internet<URL:https: / / ntnuopen.ntnu.no / ntnu-xmlui / bitstream / handle / 11250 / 2462429 / 16274_FULLTEXT.pdf> Summary of the Invention [Problem to be solved by the invention]

[0007] Although the above studies all attempted to automatically construct decks for digital card games using computers, none of them have reached practical use. Furthermore, although they were based on genetic algorithms (GA), they were limited to simple algorithms, such as randomly swapping cards.

[0008] Furthermore, when an automatic deck building system is needed, the deck that is created cannot be anything; the deck conditions that players and developers want vary depending on the situation and purpose, so there is often a need for a system that can automatically build a deck using a computer that meets the various conditions specified by the user.

[0009] In addition, in card games, there are combinations of cards that create synergy when included in a deck at the same time, but when cards are randomly swapped, the probability of these combinations appearing in a deck by chance decreases as the number of synergistic cards increases and as the number of different cards in the game increases. For these reasons, the probability of building a deck with many synergistic cards using conventional methods was extremely low.

[0010] Related to the difficulty of building decks that incorporate synergy, ensuring the diversity of the decks that are created has also been a challenge in the past. This is because, when you want to create multiple different decks, without information about which cards create synergy, it is difficult to intentionally create multiple decks that are meaningfully different in terms of deck concept (based on different synergies).

[0011] Additionally, while it is common for new cards to be added and released at regular intervals in card games, it is necessary to determine in advance whether the newly added cards will disrupt the balance of the game. This is usually achieved by conducting multiple test play sessions among test players, including the developers. However, creating the decks used in this process requires a lot of time and manpower, and the test decks must be created by people who are familiar with the abilities and effects of the cards, which increases the risk of overlooking unexpected powerful combos.

[0012] Furthermore, many card games have a variety of strategies and play styles, and it is possible that a card intended for use in a standard strategy may end up being unexpectedly powerful in a different strategy. This is also difficult to discover in advance through testing with a small number of test players, and since special strategies tend to require a very large number of cards to be effective, it was not very likely that conventional algorithms would be able to create decks that were suited to special play styles.

[0013] The object of the present invention is to assist players in deck construction and developers in adjusting game balance by constructing a deck according to specified conditions, as follows. · Build a deck that meets the conditions specified by the card game player. The conditions specified by the player vary depending on the game situation and objectives, allowing decks to be constructed to meet a variety of conditions. If there are combinations of cards that create a synergistic effect when included in a deck at the same time, it will be possible to build a deck that includes such combinations. -It is possible to build multiple decks with meaningful differences in deck concept. - Allows deck construction to accommodate a variety of tactics and play styles. [Means for solving the problem]

[0014] In order to solve the above problems, a deck building system for building a deck for a card game is provided, which includes: a battle simulation unit that simulates a battle between a deck including cards to be used in the card game and a predetermined test deck; a statistical information creation unit that creates statistical information about cards based on the results of the battle conducted in the battle simulation unit; an input acceptance unit that accepts conditions to be satisfied by a deck to be built that includes cards to be used in the card game; and a deck building unit that replaces cards included in the deck to be built based on the statistical information created by the statistical information creation unit so as to satisfy the conditions accepted by the input acceptance unit. The statistical information created by the statistical information creation unit includes a first win rate of a deck in which a certain card exists and / or a first usage rate of the card when the certain card exists in the deck, and the deck construction unit, when there is a first card and a second card having a higher first win rate and / or a higher first usage rate than the first card, removes the first card from the deck to be constructed with a higher probability than the second card, and adds the second card to the deck to be constructed with a higher probability than the first card. A deck building system is provided. This makes it possible to provide a deck building system that builds a deck that meets the conditions specified by the player of the card game by rearranging the cards included in the deck to be built based on statistical information so as to meet the received conditions. [Effects of the Invention]

[0015] As described above, according to the present invention, it is possible to provide a deck building system, deck building method, and deck building program that builds a deck according to specified conditions, assisting players in deck building and developers in adjusting game balance. [Brief explanation of the drawings]

[0016] [Figure 1] FIG. 1 is a diagram illustrating a computer system for implementing an embodiment of the present invention. [Figure 2] FIG. 2 is a diagram showing an example of the configuration of a deck building system according to an embodiment of the present invention. [Figure 3] FIG. 3 is a diagram showing an example of functional blocks of the deck construction device according to the embodiment of the present invention. [Figure 4] FIG. 4 is a diagram showing an example of a deck building condition specification page screen accepted by the deck building device according to an embodiment of the present invention. [Figure 5]FIG. 5 is an example of a flowchart for collecting statistical information according to an embodiment of the present invention. [Figure 6] FIG. 6 is an example of a basic flowchart of a deck building algorithm in an embodiment of the present invention. [Figure 7] FIG. 7 is an example of a flowchart of a deck construction algorithm when an island model is used in an embodiment of the present invention. [Figure 8] FIG. 8 is a diagram showing a list of cards that make up card game A in an embodiment of the present invention. [Figure 9] FIG. 9 is a diagram showing the rules of card game A in an embodiment of the present invention. [Figure 10] FIG. 10 is a diagram showing an example of statistical information (statistics for a single card) in card game A according to an embodiment of the present invention. [Figure 11] FIG. 11 is a diagram showing an example of statistical information (a part of statistics of card pairs) in card game A in an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0017] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. First, referring to Figure 1, a computer system 300 for implementing embodiments of the present disclosure will be described. The mechanisms and devices of various embodiments disclosed herein may be applied to any suitable computing system. The main components of the computer system 300 include one or more processors 302, memory 304, a terminal interface 312, a storage interface 314, an I / O (input / output) device interface 316, and a network interface 318. These components may be interconnected via a memory bus 306, an I / O bus 308, a bus interface unit 309, and an I / O bus interface unit 310.

[0018] Computer system 300 may include one or more general-purpose programmable central processing units (CPUs) 302A and 302B, collectively referred to as processors 302. In some embodiments, computer system 300 may include multiple processors, while in other embodiments, computer system 300 may be a single CPU system. Each processor 302 executes instructions stored in memory 304 and may include an on-board cache.

[0019] In some embodiments, memory 304 may include random-access semiconductor memory, storage devices, or storage media (either volatile or non-volatile) for storing data and programs. Memory 304 may store all or part of the programs, software modules, and data structures that implement the functions described herein. For example, memory 304 may store deck-building application 350. In some embodiments, deck-building application 350 may include instructions or descriptions that execute the functions described below on processor 302.

[0020] In some embodiments, deck building application 350 may be implemented in hardware via semiconductor devices, chips, logic gates, circuits, circuit cards, and / or other physical hardware devices instead of or in addition to a processor-based system. In some embodiments, deck building application 350 may include data other than instructions or descriptions. In some embodiments, cameras, sensors, or other data input devices (not shown) may be provided to communicate directly with bus interface unit 309, processor 302, or other hardware in computer system 300.

[0021] Computer system 300 may include a bus interface unit 309 that provides communication between processor 302, memory 304, display system 324, and I / O bus interface unit 310. I / O bus interface unit 310 may couple to an I / O bus 308 for transferring data to and from various I / O units. I / O bus interface unit 310 may communicate via I / O bus 308 with multiple I / O interface units 312, 314, 316, and 318, also known as I / O processors (IOPs) or I / O adapters (IOAs).

[0022] Display system 324 may include a display controller, a display memory, or both. The display controller may provide video, audio, or both data to display device 326. Computer system 300 may also include one or more sensors or other devices configured to collect data and provide the data to processor 302. Display system 324 may be connected to display device 326, such as a standalone display screen, a television, a tablet, or a handheld device.

[0023] The I / O interface unit provides functionality for communicating with various storage or I / O devices. For example, the terminal interface unit 312 may be attached to user I / O devices 320, such as user output devices such as a video display, a television with speakers, and user input devices such as a keyboard, a mouse, a keypad, a touchpad, a trackball, buttons, a light pen, or other pointing device. A user may use a user interface to enter input data or instructions into the user I / O devices 320 and the computer system 300 and receive output data from the computer system 300 by operating the user input devices. The user interface may be displayed on a display, played through speakers, or printed via a printer via the user I / O devices 320, for example.

[0024] Storage interface 314 may accept one or more disk drives or direct access storage devices 322 (typically magnetic disk drive storage devices, but may also be an array of disk drives or other storage devices configured to appear as a single disk drive). In some embodiments, storage device 322 may be implemented as any secondary storage device. Contents of memory 304 may be stored in storage device 322 and retrieved as needed from storage device 322. I / O device interface 316 may provide an interface to other I / O devices, such as printers, fax machines, etc. Network interface 318 may provide a communications path that allows computer system 300 and other devices to communicate with each other. This communications path may be, for example, network 330.

[0025] In some embodiments, computer system 300 may be a device that receives requests from other computer systems (clients) without a direct user interface, such as a multi-user mainframe computer system, a single-user system, or a server computer. In other embodiments, computer system 300 may be a desktop computer, a portable computer, a laptop, a tablet computer, a pocket computer, a telephone, a smartphone, or any other suitable electronic device.

[0026] Next, a deck building system 200 according to the present invention will be described with reference to Figure 2. The deck building system 200 according to the present invention includes a deck building device 210, a mobile terminal 270, and an external system 260, which are connected via a communications network 265. The communications network 265 may include, for example, a local area network (LAN), a wide area network (WAN), a satellite network, a cable network, a Wi-Fi network, or any combination thereof.

[0027] The deck-building device 210 is a computing device that executes the deck-building method for constructing a deck for a card game according to the present invention. The deck-building device 210 may be, for example, a desktop computer, a server computer, a laptop computer, a tablet computer, a workstation, a mobile terminal, or any other type of computing device, and is not particularly limited in the present invention.

[0028] The deck building device 210 includes a processor 211 for executing instructions stored in memory 230, an I / O interface 212 for controlling communication between internal and external devices of the deck building device 210, a network interface 213 for controlling communication via a communication network 265, a user I / O interface 214 for accepting input from a user, memory 230 storing functional units for executing each function of a deck building method according to an embodiment of the present invention, and a bus 216 for controlling communication between these components.

[0029] The memory 230 of the deck construction device 210 includes, for example, a battle simulation unit 231 that simulates a battle between a deck containing cards to be used in the card game and a predetermined test deck; a statistical information creation unit 232 that creates statistical information about cards based on the results of the battle held in the battle simulation unit 231; an input acceptance unit 233 that accepts conditions to be satisfied by the deck to be constructed that contains cards to be used in the card game; a deck construction unit 234 that rearranges cards included in the deck to be constructed based on the statistical information created by the statistical information creation unit 232 so as to satisfy the conditions accepted by the input acceptance unit 233; and an output unit 235 that outputs the cards included in the deck constructed by the deck construction unit 234.

[0030] Each functional unit included in the deck building device 210 may be a software module constituting the deck building application 350 in the computer system 300 shown in FIG. 1, or may be an independent dedicated hardware device. The functional units may be implemented in the same computing environment or in a distributed computing environment. For example, the deck building device 210 may execute only the input receiving unit 233, deck building unit 234, and output unit 235, with the remaining units, the battle simulation unit 231 and statistical information creation unit 232, executed by an external system 260 (described below). Storage units such as the state storage unit 251, card information storage unit 252, and statistical information storage unit 253 may be located in the external system 260 and configured to be accessed remotely by the deck building device 210.

[0031] As described above, the external system 260 may be arranged to execute some of the components of the deck building device 210, or may be configured to execute a competitive digital card game. The external system 260 may be, for example, a system configured from a remote personal computer, a server, a storage device, a database, cloud-based storage, or a combination of these. For the sake of convenience, one external system 260 is shown in FIG. 2, but in reality, the deck building device 210 is connected to multiple external systems.

[0032] The mobile terminal 270 may access the deck construction device 210 and be used as an operation terminal for the deck construction device 210. The mobile terminal 270 may also be used as an operation terminal for accessing an external system 260 in which the battle simulation unit 231 and the statistical information creation unit 232, which are part of the functional unit, are executed, conducting a battle in advance, and creating statistical information. The mobile terminal 270 may be, for example, a mobile terminal such as a personal computer or smartphone, a tablet computer, or the like.

[0033] The functions of the functional units included in the deck building device 210 will be described with reference to Figures 3 to 11. As described in Figure 2, the functional units included in the deck building device 210 include a battle simulation unit 231, a statistical information creation unit 232, an input reception unit 233, a deck building unit 234, and an output unit 235, and the memory units include a state memory unit 251, a card information memory unit 252, a statistical information memory unit 253, and a test deck memory unit 254. The deck building device 210 is not limited to specific battle-type card games and can be applied to various card games, but for the sake of explanation, a fictional card game (card game A) defined in Figures 8 and 9 will be used as a specific example.

[0034] The card information storage unit 252 stores the card information and game rules shown in FIGS. 8 and 9 for card game A. Card game A is composed of cards as shown in FIG. 8. Of course, the 17 cards shown in this figure are only a portion of the cards for explanation. Each card is given a name; for example, the name of card No. 1 is "Small Monster (Red)" and the name of card No. 4 is "Attack Power Enhancement (Red)". Each card is also classified into a type; for example, the type of card No. 1 is "Monster" and the type of card No. 4 is "Spell". A "Monster" card is a card that is placed on the player's field when played and attacks the opposing player or defends against attacks from the opponent. A "Spell" card is a card that does not remain on the player's field when played and has an effect that changes the game situation, such as changing the status of a monster or performing an additional action on the player. "Monster" cards have attack power values, with card No. 1 having an attack power of 100 and card No. 3 having an attack power of 300, meaning card No. 3 has the greater attack power. Attack power is a parameter that indicates ability (strength) during a battle.

[0035] Furthermore, each card is divided into attributes (in this example, the attribute of "color"), and the "colors" are red, blue, green, and black. Cards of the same color belong to the same group, and cards of different colors belong to different groups. For example, card No. 1 and card No. 4 are "red" in color, and so these cards belong to the same group, but card No. 8 is "blue" in color, and so belongs to a different group from card No. 1. There may be a synergistic effect between cards that belong to the same group.

[0036] For example, card No. 4 has the effect of "increasing the attack power of one red monster on your field by 200," but this effect is only activated when it is included in the same deck as cards Nos. 1 through 3, which have the red attribute. Conversely, this card cannot be combined with monsters of other colors, and no synergistic effect can be achieved. Therefore, when constructing a deck, if a "spell" card with card No. 4 is in a deck with a "monster" card with the red attribute, card No. 4 is judged to remain in the deck being constructed because it will exert the synergistic effect. Conversely, if it is in a deck with a "monster" card with the attribute of another color, card No. 4 is judged to be removed from the deck being constructed because it will not exert the synergistic effect.

[0037] Card game A has the rules shown in Figure 9. In card game A, players can select 10 cards from all cards in their deck before a match (rule no. 1), and can include up to three copies of the same card in the deck (rule no. 2). When the deck construction unit 234 constructs a deck, it must follow these rules.

[0038] The test deck storage unit 254 stores a predetermined test deck for playing against card game A. The test deck is created by someone who is familiar with the abilities and effects of all cards included in card game A, and is a typical deck, such as a deck with a different ratio of high-ability and low-ability cards for each attribute, or a deck containing high-ability cards that can be used in a draw. As shown in the rules of FIG. 9, there are various ways to ultimately win card game A, such as when the opponent's HP drops to 0 or less (Rule No. 12) or when the opponent's deck has 0 cards left when drawing cards (Rule No. 13). Therefore, simply including many monsters with high attack power is not enough; a strategy can also consider including card No. 8's hand destruction (blue) or card No. 16's hand destruction (black), which force the opponent to discard cards.

[0039] The battle simulation unit 231 is executed according to the flowchart shown in FIG. 5. As a preliminary preparation for deck construction, the battle simulation unit 231 references the cards for card game A stored in the card information storage unit 252 and randomly selects 10 cards to create a deck (S100 in FIG. 5). The battle simulation unit 231 references the test deck stored in the test deck storage unit 254 and simulates a match between the randomly selected deck and the test deck, acquiring information such as the outcome of the game during the match and the number of times each card has been used (S102 in FIG. 5). The battle simulation unit 231 has a learned model trained in advance by a neural network, and can handle even random decks sufficiently appropriately. In other words, the battle simulation unit 231 can make sufficiently rational choices for purposes such as winning the game, compared to players acting completely randomly.

[0040] The statistical information creation unit 232 creates statistical information on cards based on the results of the battles held in the battle simulation unit 231, and stores the updated information in the statistical information storage unit 253 (S104 in FIG. 5). Specifically, the statistical information creation unit 232 compiles the information acquired by the battle simulation unit 231 and creates the following statistical information on cards and synergies for all cards and card pairs. a. represents the average strength of each card, and c. represents the average strength of each synergy. Furthermore, by comparing b. and d., the magnitude of the synergy of each card can be known. a. The average win rate of a deck that contains a certain card b. The average number of times a card is used when it is in a deck c. The average win rate of a deck that contains a certain set of cards d. The average number of times each card in a set of cards is used when it is in a deck.

[0041] For example, Figures 10 and 11 are examples of statistical information for card game A stored in the statistical information storage unit 253. Figure 10 shows, for each card, a. the average win rate of a deck containing a certain card, b. the average number of times a certain card is used when the card is present in a deck, and the average number of times a certain card is drawn when the card is present in a deck. Figure 11 also shows, when card No. 11 "Large Monster (Green)" is included as a single card (A) and paired with another card (B), c. the average win rate of a deck containing a certain pair of cards (A and B), and d. the average number of times card A is used when the pair of cards (A and B) is present in a deck, and the average number of times a certain pair of cards (A and B) is drawn when the deck contains the same.

[0042] In Figure 10, when card No. 15 "Attack Power Up (Black)" is included in the deck, the average win rate is higher than with other cards, indicating that "Attack Power Up (Black)" is a powerful card (a card that is likely to contribute to win rate). Furthermore, when card No. 11 "Large Monster (Green)" is included in the deck, the average usage rate is approximately 0.333 times per match. However, in Figure 11, when card No. 9 "Small Monster (Green)" is included in the deck, the usage rate of card No. 11 "Large Monster (Green)" is 0.725 times per match. This indicates that adding card No. 9 "Small Monster (Green)" to the deck increases the usage rate of card No. 11 "Large Monster (Green)" (there is synergy).

[0043] The statistical information creation unit 232 creates statistical information at least once at the beginning as a preparation for deck construction, and does not need to create it each time a deck is constructed. Note that while Figure 11 shows a set consisting of a pair of two cards, some synergies between cards are effective when three or more cards are used. By limiting the information acquired to information on single cards and card pairs, it is possible to keep the size of the statistical information and the number of matches when acquiring statistics to a realistically feasible range, and it is also possible to reproduce combos with three or more cards.

[0044] The statistical information creation unit 232 repeats the above steps S100 to S104 until they are executed a sufficient number of times (S106 in FIG. 5). Here, the sufficient number of times is determined as appropriate, but for example, when updating statistical information, it is compared with the previous statistical information and the values ​​have converged.

[0045] The deck building process is executed according to the flowchart shown in FIG. 6. First, the input accepting unit 233 accepts from a user (a player or developer of card game A) the conditions that the deck to be built, including the cards used in the card game, must satisfy. The input accepting unit 233 accepts input of the conditions desired by the user building a deck via the "Card Game A" deck building condition specification page 400 shown in FIG. 4 as an example (S200 in FIG. 6). Note that the deck building condition specification page 400 is an example of a screen layout when using a web page, but is not limited to such a web page, and is not particularly limited as long as it is in a form that can appropriately receive deck building condition information from the user.

[0046] The conditions that can be specified on the deck construction condition specification page 400 can be freely set by the user, but due to the nature of the algorithm described below, it is possible to build a system that can freely specify conditions based on the rules specific to the target card game, rather than just universal conditions such as the set of cards that can be used in a deck or cards that must be included in a deck. For example, card game A is composed of cards of two types called "monsters" and "spells" and four colors (attributes) called "red," "blue," "green," and "black." The number of monsters and spells in the deck to be created and the color composition ratio are examples of conditions that can be specified. Other conditions that can be expressed numerically, such as the total attack power of the monsters included in the deck or the maximum total number of characters in card names, can also be specified as conditions.

[0047] On the deck construction condition specification page 400 shown in FIG. 4, the user indicates by "Number of decks to be created" that they can create five decks at a time that meet the conditions below. Furthermore, by "Colors of cards to be used," the user indicates that they desire a deck that includes the attributes "red" and "black" but does not include "blue" or "green." Furthermore, by "Cards that must be included in the deck," the user indicates that they desire a deck that includes "small monsters (red)" and by "Cards that must not be included in the deck," the user indicates that they desire a deck that does not include "medium monsters (red)." Note that multiple of these conditions can be specified.

[0048] Furthermore, on the deck construction condition specification page 400, the user indicates that they wish to include 4 to 7 monster cards in the "Number of monster cards to include in the deck" and 3 to 6 spell cards in the "Number of spell cards to include in the deck." According to game rule No. 1 shown in FIG. 9, the total number of cards in the deck is 10. Furthermore, the user can specify the strategy and play style of the deck to be created using the "Play Style." This figure shows that the "Normal" play style, meaning that the constructed deck will win (high win rate), has been selected. Options other than "Normal" will be described later. The input receiving unit 233 passes the conditions received from the deck construction condition specification page 400 to the deck construction unit 234.

[0049] The deck construction unit 234 rearranges cards included in the deck to be constructed based on the statistical information created by the statistical information creation unit 232, as described below, so as to satisfy the conditions received by the input reception unit 233. First, the deck construction unit 234 prepares an initial state (S202 in FIG. 6). As preparation for the initial state, the deck construction unit 234 selects a specified number (10 cards in this example) from the card information storage unit 252 and creates an initial state deck of the number (5 in this example) specified in "Number of decks to create" on the deck construction condition specification page 400. The deck prepared here may be a deck including randomly selected cards, as long as it is created so as not to violate the conditions and rules (FIG. 9) previously specified on the deck construction condition specification page 400.

[0050] The prepared initial deck is stored in the state storage unit 251, and from then until completion, information about the progress of deck construction, such as the replacement of cards, is stored in the state storage unit 251. Information recorded in the state storage unit 251 includes a breakdown of all decks currently in the deck construction unit 234 (at the time the cards were replaced), the win rate of each deck or similar indicators (indicators other than the win rate), the usage rate of each card when each deck is used in a match against a test deck (statistical information during construction), etc.

[0051] The deck construction unit 234 stores a specified number of decks in the state storage unit 251 and improves the decks by replacing cards in each deck, but before starting to replace cards, it is preferable to evaluate the fitness of each deck in its initial state prepared and the usage rate of each card in the deck by playing each deck against a test deck (S204 in FIG. 6). Fitness will be described later.

[0052] Specifically, at this timing, the battle simulation unit 231 simulates a battle between each deck in the initial state of the deck construction process and the test deck in the deck construction unit 234, and the statistical information creation unit 232 creates statistical information such as the usage rate of each card during construction based on the results of the battle during construction conducted by the battle simulation unit 231, and may use this information to evaluate and make subsequent card replacements. If evaluation is not performed at this timing, cards are replaced based on the initial statistical information obtained from the results of a match between a randomly selected deck and the test deck. This is statistical information such as the average usage rate when each card / card combination is inserted into various decks, and in deck construction, it is treated as a numerical representation of the card / card combination's ability and its relationship with other cards.

[0053] However, when actually replacing cards in Deck A that appears during the deck construction process, it can be inconvenient to refer only to the usage rates calculated in advance using a random deck. As an example, using the card from "Card Game A," "Attack Power Enhancement (Red)" is a card that strengthens your own red monsters, and statistically has a high usage rate when included in a deck, but at the same time, it is a card that is meaningless to include in a deck that does not contain red monsters.

[0054] Now, if Deck A has no red monsters and contains "Attack Boost (Red)," the usage rate of "Attack Boost (Red)" when Deck A is pitted against the test deck will be 0%, and (contrary to the usage rate calculated in advance using a random deck) it can be determined that it would be a good idea to remove "Attack Boost (Red)" from Deck A or add a red monster. In this way, when actually selecting cards to remove from / add to individual decks, a more appropriate choice can be made by simultaneously referring to not only the average usage rate calculated using a random deck, but also the usage rate when using the deck itself that is the target of the card replacement.

[0055] The deck construction unit 234 does not select cards to be added to the deck and cards to be removed from the deck when replacing cards completely randomly, but instead selects based on statistical information read from the statistical information storage unit 253 (one or both of the statistical information compiled in advance using a random deck and the statistical information under construction compiled in S204) (S206 in FIG. 6). Specifically, when the play style is specified as "normal," which desires a high win rate, cards with a higher win rate from the statistical information and the statistical information under construction are added with a higher probability to the deck. Similarly, when selecting cards to remove from the deck, the usage rate from the statistical information and the statistical information under construction is referenced, and cards with a usage count of 0 or close to 0 are removed with a higher probability.

[0056] Here, when cards are replaced, the deck must not violate the specified conditions. Although the method for doing so is not specified, if the deck violates the conditions after the cards are replaced, the deck must start over from the card selection, which can be used to deal with any conditions. Note that depending on the cards being replaced, the deck may evolve in a direction that makes it weaker. To prevent this, the original deck may be copied to the state storage unit 251 before the cards are replaced. In this case, the total number of decks may be temporarily increased.

[0057] As described above, taking the deck's win rate and card usage rate as examples of fitness, the statistical information created by the statistical information creation unit 232 includes the win rate of a deck in which a certain card is present (first win rate) and / or the usage rate of that card when that card is present in the deck (first usage rate). In this case, there may be a certain card and other cards with higher win rates and / or usage rates than that card. In this case, the deck construction unit 234 removes that certain card from the deck to be constructed with a higher probability than other cards, and conversely, adds other cards to the deck to be constructed with a higher probability than that certain card. In other words, the deck construction unit 234 references one or both of the first win rate and first usage rate, and adds cards with a high win rate or usage rate to the deck with a high probability, and removes cards with a low win rate or usage rate from the deck with a high probability.

[0058] In this way, the deck construction unit 234 replaces cards included in the deck to be constructed based on the statistical information created by the statistical information creation unit 232. In this example, the deck is constructed with the aim of achieving a "normal" play style, i.e., a high win rate, and this allows the player of the card game to construct a deck that satisfies the conditions specified by the player, i.e., has a high win rate.

[0059] Furthermore, when replacing cards in S206, the deck construction unit 234 may select one card from the deck and add a card with a higher probability of having a greater synergistic effect with the selected card. Specifically, taking the deck's win rate and card usage rate as examples of fitness, the statistical information created by the statistical information creation unit 232 may include, for example, statistical information such as c. the average win rate (second win rate) of a deck containing a certain pair of cards (A and B) and d. the average number of uses / usage rate (second usage rate) of card A when a certain pair of cards (A and B) is present in the deck, as shown in FIG. 11. The deck construction unit 234 then refers to one or both of the second win rate and second usage rate, and adds cards with a high win rate or usage rate to the deck with a high probability, and removes cards with a low win rate or usage rate from the deck with a high probability.

[0060] This allows for the construction of a deck that contains a combination of cards that, when incorporated into a deck at the same time, create a synergistic effect. Generally, as deck construction progresses, the number of useful cards in the deck increases and the number of unnecessary cards decreases. This means that if replacement cards were selected completely randomly, the probability of removing useful cards from the deck and replacing them with unnecessary cards would increase. However, in this embodiment, by replacing cards according to a probability distribution based on statistical information, the probability of always removing unnecessary cards and replacing them with useful cards is maintained high, allowing for efficient deck construction.

[0061] Here, the deck construction unit 234 may incorporate the concept of a genetic algorithm to crossover decks (an operation of selecting two decks and creating a new deck using cards contained in the two decks). In this case, the deck construction unit 234 can also use this probability distribution to efficiently extract synergy. Specifically, the deck construction unit 234 first randomly incorporates a certain number of cards from the two original decks (called parents), then selects one card to be included in the new deck, and then selects cards from the parents that have high synergy with the selected card and incorporates them up to a specified number, thereby creating a new deck that inherits the synergy contained in the parents. In this way, the deck construction unit 234 may use a genetic algorithm to construct a deck.

[0062] The deck construction unit 234 replaces the cards included in the deck to be constructed based on the statistical information, and then again evaluates the fitness of each deck at that time, and the usage rate of each card when the players were matched in S204 if S204 was executed, or the usage rate of each card when the players were matched in S102 if S204 was not executed (S208 in Figure 6).

[0063] In order to select the best decks from those currently under construction, it is necessary to set an index for each deck that indicates how good it is. In the context of deck construction, decks can be constructed with the aim of creating a strong deck by using factors such as the win rate against pre-prepared test decks as a measure of fitness. In this case, the target deck is actually used in automated matches against multiple test decks, and the win rate is calculated as fitness. Furthermore, by aggregating the card usage rates at this time, there is no need to replay matches when "changing cards in each deck."

[0064] Here, while deck construction can be performed with the aim of creating a strong deck by using the win rate against a normal test deck as a deck's fitness, the deck construction unit 234 may also use a different indicator of fitness to replace cards included in the deck being constructed. An indicator different from the win rate could be, for example, the draw rate of a deck containing a certain card or the discard rate of forcing the opponent to discard cards. In this case, a deck can be created that corresponds to a special strategy that frequently performs actions corresponding to the indicator used. The indicators that can be specified here can be freely set by the user, but due to the nature of the algorithm, they are not limited to relatively general conditions such as draw rate and discard rate, and conditions (indicators) based on the rules specific to the target card game can also be freely specified. For example, in card game A, there are two types of cards called "monsters" and "spells." However, any indicator that can be expressed as a number, such as the "number of times spells are used during battle," can be set as an indicator of play style.

[0065] Such strategies and play styles can be specified by the user using the "Play Style" shown as an example in Figure 4. In addition to "Normal," which aims for a high win rate, it is possible to adopt a high-draw strategy that aims for a high draw rate, a high-discard strategy that aims for a high discard rate, or a strategy that selects actions to maximize the value of the corresponding index. This allows deck construction to accommodate a variety of conditions, strategies, and play styles, as the conditions specified by the player vary depending on the game situation and objectives.

[0066] In general, fitness is an index used in a genetic algorithm (GA) to capture the overall ability of an individual to thrive as a living organism, and in this specification, it is used as a score indicating how well each deck meets the objectives (conditions). When a genetic algorithm is implemented, the current deck of the deck construction unit 234 in the information recorded in the state storage unit 251 is considered to be the latest generation deck in terms of the GA, and in the case of deck construction using the island model described below, it is considered to be information on probability fluctuations specific to each deck construction unit 234.

[0067] After the above evaluation, the deck construction unit 234 selects the decks to be retained for the next step, or, in GA terms, the next generation (S210 in Figure 6). When crossover of decks is performed or the original deck is duplicated when cards are swapped, the total number of decks stored in the state storage unit 251 at this point increases from the initial number. However, proceeding to the next step as is would significantly impede the progress of deck construction due to the exponential increase in processing time. Therefore, decks with low fitness must be periodically deleted. In this case, a predetermined number of decks with high fitness may be simply selected, or a selection algorithm similar to that used in conventional GAs may be used. Specific examples include basic algorithms such as roulette wheel selection and ranking selection, as well as more advanced algorithms such as stochastic universal sampling.

[0068] After selecting a deck, the deck construction unit 234 returns to S206 and repeats the process of replacing each deck, evaluating fitness, etc., and selecting a deck a specified number of times (S212 in FIG. 6). The specified number of times can be determined by setting a predetermined number of loops (for example, 50 or 100 times) before deck construction, or by terminating the loop when the fitness value exceeds a certain value. After the deck construction unit 234 repeats S206 to S212 the specified number of times, it transmits information about the deck that has finally remained to the output unit 235.

[0069] The output unit 235 outputs a list of cards included in the deck constructed by the deck construction unit 234 (S214 in FIG. 6). The output unit 235 may output the list of cards included in the deck constructed by the deck construction unit 234 to the I / O interface 212 as a string of characters listing the card names on a pre-prepared web page and display it on a display device, or may output the list of cards to the network interface 213 and send it to another computing device such as the mobile terminal 270.

[0070] The deck building system 200 having the above-mentioned functional units can build a deck that meets the conditions specified by the player of the card game by rearranging the cards included in the deck to be built based on statistical information so as to meet the received conditions.

[0071] Furthermore, deck building system 200 employs an algorithm known as the island model in GA, enabling it to simultaneously create multiple decks characterized by different synergies. This increases the efficiency of the GA by running multiple GAs (each GA is called an island) in parallel and periodically exchanging or crossing over the individuals (which correspond to decks in this embodiment) contained in each island. In other words, deck building system 200 employing the island model has one deck building unit 234 for each island, and has multiple deck building units 234 overall.

[0072] The process of building each deck in the deck building unit 234 that uses the island model is carried out according to the flowchart shown in Figure 7. To avoid duplication, the same processes as S200 to S214 in Figure 6 will be described briefly. First, the input receiving unit 233 receives from the user the conditions that the deck to be built, including cards to be used in the card game, must satisfy via the "Card Game A" deck building condition specification page 400 shown in Figure 4 (S300 in Figure 7).

[0073] Next, each deck construction unit 234 selects a specified number from the card information storage unit 252, creates the number of initial decks specified in the "Number of decks to create" field on the deck construction condition specification page 400, and prepares the initial state (S302 in Figure 7).

[0074] Each deck construction unit 234 stores a specified number of decks in its state memory unit 251 and improves the decks by replacing cards in each deck, but before starting to replace cards, it is preferable to evaluate the fitness of each deck in its initial state and the usage rate of each card in the deck by playing each deck against a test deck (S304 in Figure 7).

[0075] Next, each deck building unit 234 checks the interactions between the islands (S306 in FIG. 7). Specifically, for each island in the island model, the deck building unit 234 checks the breakdown of the decks in the construction process included on each island and the distribution of synergies possessed by the decks, and adjusts the probability so that the breakdown of cards or card combinations that are dominant on one island are less likely to appear on other islands.

[0076] After adjusting the probabilities, each deck construction unit 234 performs an operation of crossing the decks, i.e., selecting two decks and creating a new deck using the cards contained therein (S308 in FIG. 7). The deck construction unit 234 may also simultaneously store progress information for two or more islands in the state storage unit 251 and sequentially reference that information to exchange some of the cards contained in the decks between islands, or exchange decks (individuals). Adjusting the probabilities refers to an operation such as lowering the probability that one or both cards contained in a set of cards to be restricted will be included in a deck or increasing the probability that they will be removed from a deck when swapping or crossing cards. By adjusting the probabilities in this way, the deck construction unit 234 can build decks featuring different synergies on each island.

[0077] Next, each deck construction unit 234 replaces cards in its respective deck (S310 in FIG. 7). When replacing cards, each deck construction unit 234 makes selections based on statistical information read from the statistical information storage unit 253. Also, similar to S206, each deck construction unit 234 may select one card from the deck, and add cards with a greater synergistic effect with that card with a higher probability.

[0078] Each deck construction unit 234 replaces the cards included in the deck to be constructed based on the statistical information, and then evaluates the fitness and usage rate of each deck at that time again (S312 in FIG. 7). After the evaluation, each deck construction unit 234 selects a deck to be left for the next generation (S314 in FIG. 7).

[0079] After selecting a deck, the deck construction unit 234 returns to S306 and repeats the steps of checking interactions between islands, crossing over decks, replacing each deck, evaluating fitness, etc., and selecting a deck a prescribed number of times (S316 in FIG. 7). After the deck construction unit 234 repeats S306 to S316 the prescribed number of times, it transmits information about the deck that has finally remained to the output unit 235. Then, the output unit 235 outputs a list of cards included in the deck constructed by the deck construction unit 234 (S318 in FIG. 7).

[0080] As described above, the deck construction unit 234 employs the island model, and in parallel, swaps cards included in the decks being constructed based on the statistical information created by the statistical information creation unit 232 and the breakdown of the decks being constructed in the deck construction unit 234, and performs an exchange process or a crossover process using a genetic algorithm on some of the cards included in the decks being constructed in each deck construction unit 234 at a predetermined cycle. This enables the deck construction system 200 to construct multiple decks with meaningful differences in deck concept. Note that the predetermined cycle may be determined as appropriate, and may be performed for each loop in the loop in FIG. 7, or may be performed every few loops.

[0081] Furthermore, the above is a deck building method for building a deck for a card game, the deck building method being executed by a computer and including the steps of: simulating a match between a deck containing cards to be used in the card game and a predetermined test deck; creating statistical information about the cards based on the results of the simulated match; accepting conditions to be satisfied by the deck to be built containing cards to be used in the card game; and replacing cards included in the deck to be built based on the created statistical information so as to satisfy the accepted conditions. This makes it possible to provide a deck building method that builds a deck according to the specified conditions, assisting players in deck building and developers in adjusting the game balance.

[0082] The above-described deck building method may also be provided as a program that causes a computer to function as a method including a battle simulation function, a statistical information creation function, an input acceptance function, and a deck building function. This program may be configured so that it can be used by downloading it from a server on which it is stored, or it may be stored on a computer-readable recording medium and provided by this recording medium.

[0083] It should be noted that the present invention is not limited to the illustrated examples, and can be implemented in configurations that do not deviate from the scope of the claims. That is, although the present invention has been particularly shown and described primarily with reference to specific embodiments, those skilled in the art can make various modifications to the above-described embodiments in terms of the number and other details without departing from the scope of the technical idea and purpose of the present invention. [Explanation of symbols]

[0084] 200 Deck Building System 210 Deck Building Equipment 231 Battle Simulation Club 232 Statistical Information Creation Department 233 Input Reception Unit 234 Deck Construction Department 235 Output section 251 State memory unit 252 Card information storage unit 253 Statistical information storage unit

Claims

1. A deck building system for building a deck for a card game, a match simulation unit that simulates a match between a deck including cards used in a card game and a predetermined test deck; a statistical information creation unit that creates statistical information about cards based on the results of the battles performed in the battle simulation unit; an input receiving unit that receives conditions to be satisfied by a deck to be constructed that includes cards used in a card game; a deck construction unit that rearranges cards included in the deck to be constructed based on the statistical information created by the statistical information creation unit so as to satisfy the condition accepted by the input acceptance unit; Equipped with the statistical information created by the statistical information creation unit includes a first win rate of a deck in which a certain card exists, and / or a first usage rate of a certain card when the certain card exists in a deck, The deck construction department When there is a first card and a second card having a first winning rate and / or a first usage rate higher than the first card, removing the first card from the deck to be constructed with a higher probability than the second card; adding the second card to the deck to be constructed with a higher probability than adding the first card to the deck to be constructed; A deck building system characterized by:

2. the statistical information created by the statistical information creation unit includes a second win rate of a deck including a set of a certain plurality of cards and / or a second usage rate of each card when the set of a certain plurality of cards is included in a deck; The deck construction department If there is a third card and a fourth card that has a higher second winning rate and / or a higher second usage rate than the third card, removing the third card from the deck to be constructed with a higher probability than the fourth card; Adding the fourth card to the deck to be constructed with a higher probability than adding the third card to the deck to be constructed; 2. The deck building system of claim 1.

3. the battle simulation unit simulates a battle between a deck being constructed in the deck construction unit and a test deck; the statistical information creation unit creates construction statistical information of cards based on the results of the construction battles performed in the battle simulation unit; the deck construction unit replaces cards included in the deck to be constructed based on the construction statistical information created by the statistical information creation unit; 3. The deck building system according to claim 1 or 2.

4. 4. The deck building system according to claim 1, wherein the deck building section uses a genetic algorithm to build the deck.

5. A plurality of the deck construction sections are provided, each of the deck construction units replaces cards included in the deck to be constructed in parallel based on the statistical information created by the statistical information creation unit and the breakdown of the deck being constructed in the deck construction unit; In each of the deck construction units, some of the cards included in the deck being constructed are subjected to an exchange process or a crossover process using a genetic algorithm at a predetermined cycle.

5. The deck building system of claim 4.

6. the statistical information created by the statistical information creation unit includes an index other than winning percentage, the deck construction unit replaces cards included in the deck to be constructed using a fitness other than a win rate as a fitness in the genetic algorithm.

6. A deck building system according to claim 4 or 5.

7. A deck building method for building a deck for a card game, comprising: simulating a match between a deck including cards used in a card game and a predetermined test deck; generating card statistics based on the results of the simulated matches; receiving conditions to be satisfied by a deck to be constructed that includes cards to be used in a card game; a step of replacing cards included in the deck to be constructed based on the created statistical information so as to satisfy the accepted conditions; Including, The generated statistical information includes a first win rate of a deck in which a certain card is present and / or a first usage rate of a certain card when the certain card is present in a deck; When there is a first card and a second card having a first winning rate and / or a first usage rate higher than the first card, removing the first card from the deck to be constructed with a higher probability than the second card; adding the second card to the deck to be constructed with a higher probability than adding the first card to the deck to be constructed; A computer-implemented deck-building method comprising:

8. A deck building program for causing a computer to execute a process for building a deck for a card game, On the computer, a battle simulation function for simulating a battle between a deck including cards used in a card game and a predetermined test deck; a statistical information creation function that creates statistical information on cards based on the results of the battles performed by the battle simulation function; An input function that accepts the conditions that the deck to be constructed, including the cards used in the card game, must meet; a deck construction function that rearranges cards included in the deck to be constructed based on the statistical information created by the statistical information creation function so as to satisfy the conditions accepted by the input acceptance function; Realize this, the statistical information created by the statistical information creation function includes a first win rate of a deck in which a certain card exists, and / or a first usage rate of a certain card when the certain card exists in a deck; The deck building function includes: When there is a first card and a second card having a first winning rate and / or a first usage rate higher than the first card, removing the first card from the deck to be constructed with a higher probability than the second card; adding the second card to the deck to be constructed with a higher probability than adding the first card to the deck to be constructed; A deck building program characterized by:

Images