[go: up one dir, main page]

WO2018192395A1 - 角色的配置方法及装置、存储介质以及电子装置 - Google Patents

角色的配置方法及装置、存储介质以及电子装置 Download PDF

Info

Publication number
WO2018192395A1
WO2018192395A1 PCT/CN2018/082513 CN2018082513W WO2018192395A1 WO 2018192395 A1 WO2018192395 A1 WO 2018192395A1 CN 2018082513 W CN2018082513 W CN 2018082513W WO 2018192395 A1 WO2018192395 A1 WO 2018192395A1
Authority
WO
WIPO (PCT)
Prior art keywords
character
attribute
target
event
target event
Prior art date
Application number
PCT/CN2018/082513
Other languages
English (en)
French (fr)
Inventor
谢巍
Original Assignee
腾讯科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 腾讯科技（深圳）有限公司 filed Critical 腾讯科技（深圳）有限公司
Priority to JP2019534753A priority Critical patent/JP7187460B2/ja
Priority to EP18788559.5A priority patent/EP3613482A4/en
Priority to KR1020197020698A priority patent/KR102348015B1/ko
Publication of WO2018192395A1 publication Critical patent/WO2018192395A1/zh
Priority to US16/445,694 priority patent/US11620536B2/en
Priority to US18/107,918 priority patent/US12026629B2/en
Priority to US18/636,062 priority patent/US20240256907A1/en

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
    • A63F13/45—Controlling the progress of the video game
    • A63F13/47—Controlling the progress of the video game involving branching, e.g. choosing one of several possible scenarios at a given point in time
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/02—Knowledge representation; Symbolic representation
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
    • A63F13/55—Controlling game characters or game objects based on the game progress
    • A63F13/56—Computing the motion of game characters with respect to other game characters, game objects or elements of the game scene, e.g. for simulating the behaviour of a group of virtual soldiers or for path finding
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
    • A63F13/55—Controlling game characters or game objects based on the game progress
    • A63F13/57—Simulating properties, behaviour or motion of objects in the game world, e.g. computing tyre load in a car race game
    • A63F13/577—Simulating properties, behaviour or motion of objects in the game world, e.g. computing tyre load in a car race game using determination of contact between game characters or objects, e.g. to avoid collision between virtual racing cars
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
    • A63F13/55—Controlling game characters or game objects based on the game progress
    • A63F13/58—Controlling game characters or game objects based on the game progress by computing conditions of game characters, e.g. stamina, strength, motivation or energy level
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
    • A63F13/60—Generating or modifying game content before or while executing the game program, e.g. authoring tools specially adapted for game development or game-integrated level editor
    • A63F13/67—Generating or modifying game content before or while executing the game program, e.g. authoring tools specially adapted for game development or game-integrated level editor adaptively or by learning from player actions, e.g. skill level adjustment or by storing successful combat sequences for re-use
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F2300/00—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game
    • A63F2300/60—Methods for processing data by generating or executing the game program
    • A63F2300/64—Methods for processing data by generating or executing the game program for computing dynamical parameters of game objects, e.g. motion determination or computation of frictional forces for a virtual car
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F2300/00—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game
    • A63F2300/60—Methods for processing data by generating or executing the game program
    • A63F2300/65—Methods for processing data by generating or executing the game program for computing the condition of a game character

Definitions

  • the present application relates to the field of the Internet, and in particular to a method and device for configuring a role, a storage medium, and an electronic device.
  • AI Artificial Intelligence
  • Game AI is the artificial intelligence character in the game. In this application, it refers to the intelligent character in the game, simulating the various behaviors of the real player, and simulating the operation of the real person and playing against the player. Generally in the game, the player gains skills and experience by playing against the game AI.
  • the main control method of the game AI is the behavior of the object.
  • the design of the AI mainly includes setting rules and holding the two methods.
  • the so-called setting rule is to explicitly set a series of rules, and then assign corresponding values to related objects, and then the whole system runs according to the rules. Once the rules are set, the smart objects will follow the rules and limits. Because of the existence of existing rules, the behavior of these AIs is basically predictable, and users may learn how to circumvent these rules after many attempts. For an episode, basically all the possible behaviors of the corresponding object are conceived, and then all responses are manually determined.
  • the actual game design is designed with a single AI individual, and one or two of the above design methods are used simultaneously to achieve the purpose of AI intelligence.
  • Improve the behavior of AI individuals by building various state machines and behavioral trees to make AI individuals look as smart as possible.
  • the AI character in a match game, the AI character generally has the following actions:
  • Action 1 When no player is found, wander in a certain area;
  • Action 2 When the player is found, chase the player and attack the player character
  • Action 3 When the amount of blood is below a certain amount, the player will run away.
  • the AI individual in the escape state, it will judge in real time whether Restore the security state, if it will enter the patrol state, otherwise continue to escape; the AI individual in the attack state will also determine in real time whether the threat to the enemy is more than the enemy, if it will run away, otherwise continue to attack the player character.
  • the AI design data structure of a single individual is shown in Figure 2.
  • attribute characteristics of the AI such as the geographical location of the player
  • values of some probabilistic events can also be recorded. Scope and so on, attribute characteristics mainly include the location of the map, screen position, animation information, military rank and other information.
  • the routine is basically fixed, and there is no difference between the similar AIs, and the same operation mechanism is adopted.
  • the player tries to understand the operation mode of the robot several times, the corresponding method can be adopted. Crack the response.
  • you want to do a very good AI response mechanism the workload of exhausting all possible behaviors is too large, and general games cannot do it.
  • the embodiment of the present application provides a method and device for configuring a role, a storage medium, and an electronic device to at least solve the technical problem that the operation mechanism of the artificial intelligence character in the related art can be known.
  • a method for configuring a character comprising: detecting a target event associated with a first character in a game, wherein the first character is artificial intelligence generated in the game.
  • the target character is used to play the non-player character, the target event is used to indicate that the target attribute value of the first character is modified, and the configuration information corresponding to the target event is obtained, wherein the configuration information is used to configure the second role, so that the configured second
  • the degree of modification of the target attribute value of the target event to the second character is smaller than the modification degree of the target attribute value of the first character when the target character responds to the target event, and the second role is to be generated in the game.
  • Non-player character when generating the second character, configure the second character using the configuration information.
  • a role configuration apparatus comprising one or more processors, and one or more memories storing program units, wherein the program units are executed by a processor
  • the program unit includes: a detecting unit configured to detect a target event associated with the first character in the game, wherein the first character is a non-player character generated by the artificial intelligence and the player character pair generated in the game, the target event And the first acquiring unit is configured to acquire configuration information corresponding to the target event, where the configuration information is used to configure the second role, so that the configured second role is in response to In the target event, the target event has a modification degree to the target attribute value of the second character less than the modification degree of the first character in the first character in response to the target event, and the second role is a non-player character to be generated in the game.
  • the configuration unit is configured to configure the second role using the configuration information when the second role is generated.
  • the configuration information corresponding to the target event is acquired, and the generated second role is configured through the configuration information, so as to be configured.
  • the second character reduces the degree of modification of the target event value of the second character in response to the target event, so that as the non-player character evolves, each new character born has the same initial shape, but
  • new skill attributes for a large number of non-player characters in the game, due to different birth time, the skill attributes are different, and the skill attributes used in dealing with the same events are different, making the game characters unable to After many attempts, the skill attribute adopted by the non-player character in responding to the fixed event can be determined, and the technical problem that the operation mechanism of the artificial intelligence character can be known in the related art can be solved, thereby avoiding the operation mechanism of avoiding the artificial intelligence character being known.
  • Technical effect for a large number of non-player characters in the game, due to different birth time, the skill attributes are different, and the skill attributes used in dealing with the same events are different, making the game characters unable to After many attempts, the skill attribute
  • FIG. 1 is a schematic diagram of a state transition of an AI in the related art
  • FIG. 2 is a schematic diagram of a data structure of an AI in the related art
  • FIG. 3 is a schematic diagram of a hardware environment of a method for configuring a role according to an embodiment of the present application
  • FIG. 5 is a schematic illustration of an alternative AI snake in accordance with an embodiment of the present application.
  • FIG. 6 is a schematic illustration of an optional head hot zone in accordance with an embodiment of the present application.
  • FIG. 7 is a schematic diagram of an alternative evolution system in accordance with an embodiment of the present application.
  • FIG. 8 is a schematic diagram of an optional AI attribute according to an embodiment of the present application.
  • FIG. 9 is a schematic diagram of an optional role configuration apparatus according to an embodiment of the present application.
  • FIG. 10 is a structural block diagram of an electronic device according to an embodiment of the present application.
  • a method embodiment of a role configuration method is provided.
  • the configuration method of the foregoing role may be applied to a hardware environment formed by the server 302 and the terminal 304 as shown in FIG. 3.
  • the server 302 is connected to the terminal 304 through a network.
  • the network includes but is not limited to a wide area network, a metropolitan area network, or a local area network.
  • the terminal 304 is not limited to a PC, a mobile phone, a tablet, or the like.
  • the method of the embodiment of the present application may be performed by the server 302, may be performed by the terminal 304, or may be jointly performed by the server 302 and the terminal 304.
  • the method in which the terminal 304 performs the embodiment of the present application may also be performed by a client installed thereon.
  • FIG. 4 is a flowchart of an optional role configuration method according to an embodiment of the present application. As shown in FIG. 4, the method may include the following steps:
  • Step S402 detecting a target event associated with the first character in the game, the first character is a non-player character generated by the artificial intelligence and the player character pair generated in the game, and the target event is used to indicate that the target attribute of the first character is modified. value;
  • Step S404 Obtain configuration information corresponding to the target event, where the configuration information is used to configure the second role, so that when the configured second role responds to the target event, the target event has less modification to the target attribute value of the second role.
  • the degree of modification of the target attribute value of the first character in response to the target event, and the second role is the non-player character to be generated in the game;
  • Step S406 when the second role is generated, the second role is configured using the configuration information.
  • the configuration information corresponding to the target event is acquired, and the generated second role is configured through the configuration information, so that the configuration is performed.
  • the second role reduces the degree of modification of the target attribute value of the second character in response to the target event, so that as the non-player character evolves, each new character born has the same initial shape, but There will be new skill attributes.
  • the skill attributes are different, and the skill attributes used in dealing with the same events are also different, making the game characters
  • the skill attribute of the non-player character in dealing with the fixed event can be determined, which can solve the technical problem that the operation mechanism of the artificial intelligence character can be known in the related art, thereby avoiding the operation mechanism of the artificial intelligence character being avoided. Know the technical effects.
  • the above game may be any type of game; the first character is a non-player character attacked by a target event, the second character is a next-generation (or next-level) born non-player character; the target event is capable of causing the first character.
  • AI can be used to initially train players to familiarize themselves with various operational skills, or to interact with players when online players are not enough to attract more real players.
  • the current AI may cause poor interaction due to various reasons.
  • the present application implements a game AI (non-player character using artificial intelligence) evolution method based on the basic principles of biological evolution, and by giving the game AI system the ability to self-evolve by simulating the principle of biological evolution, thereby enabling the game AI to acquire over time.
  • the intelligence that is enhanced by natural development and various skill attributes.
  • the design idea of this method is to evolve the entire game AI group instead of just a single AI individual.
  • the specific implementation method is that when the game AI individual is killed by the real player, the evolution logic of the group is triggered, and the evolution logic will be based on the value of the current generation of the killed AI (the default is from the first generation or the first level). Get the probability that this generation can evolve an attribute property (such as a skill) and determine whether the evolution is successful. If the evolution is successful, the AI born after this time will default to the next generation or next level, and this next generation AI is inherently equipped with this attribute. Over time, game AI will have increasingly sophisticated intelligence and skill attributes.
  • detecting a target event associated with the first character in the game includes: detecting a target event generated by the player character initiating an attack on the first character when the first character plays with the player character; When the character is in the target position in the map of the game, the target event in which the target environment value of the first character is modified is detected.
  • the above target attribute may be an attribute for indicating life, skill, weapon, defense, etc.
  • the target event is an event for reducing the attribute value of the life attribute
  • the target event is Used to capture the skill attribute of the first character, or to reduce the damage of the skill attribute to the player character
  • the target event is used to capture the weapon of the first character and reduce the damage caused by the weapon. Or the event that damages the weapon.
  • this application does not enumerate one by one.
  • the weapon attribute when the first character plays against the player character, it is detected that the player character attacks the first character to capture the target event generated by the weapon, and if the weapon of the first character is successfully captured, the new event is triggered.
  • the birth of the character evolves, allowing the newly born character to escape or counterattack in time when the player captures his weapon, specifically by configuring the escape character or defensive skill attribute of the newly born character.
  • the above-mentioned target events generated by detecting that the player character attacks the first character mainly include the following two types: detecting the first event in which the player character attacks the first character, and the first event is used to reduce the target attribute of the first character.
  • the value is to the first value, the first value is smaller than the target attribute maximum value of the first role (ie, the maximum value allowed for the attribute), and is not less than the minimum value of the target attribute of the first role (ie, the attribute is allowed to be configured)
  • the minimum value is detected;
  • the second event is detected by the player character to attack the first character, and the second event is used to lower the target attribute value of the first character by a second value, the second value being a positive number.
  • the first value mentioned above is a trigger point for triggering the evolution of the non-player character
  • the attribute value of the target attribute is within a certain range (ie, between the attribute maximum value and the attribute minimum value), and the first value is the value in the range.
  • detecting that the first event of the player character attacking the first character may be detecting a first event initiated by the player character and used to reduce the target attribute value of the first character to the minimum value of the target attribute, ie, specifying
  • the occurrence of an evolution event is triggered when the attribute value of the attribute is reduced to a minimum value.
  • the target attribute takes the life attribute as an example.
  • the first value can be 50% of the value of the life attribute.
  • the life value is reduced to 50% or less, the non-player character is triggered. Evolution occurs, and the skill attribute against the first event is evolved to avoid or reduce the damage caused by the first event to the first character when the first event is encountered again.
  • the second value above indicates that when an event causes a fixed damage to the first character (ie, causes the attribute value to decrease by a second value), the new born non-player character is triggered to evolve for the event to avoid the event. Damage caused or reduced damage to the event.
  • the second value can be 30% of the value of the life attribute.
  • the life value is reduced by 30% or more, the non-player character is triggered. Evolution occurs, and the skill attribute of the second event is evolved to avoid or reduce the damage of the first event to the first character when the second event is encountered next time.
  • the method adopted is similar to the above, and the present application does not describe them one by one.
  • step S404 before the acquisition of the configuration information corresponding to the target event, if each encounter attack event can bring evolution to the non-player character, then the non-player character is too powerful, and the game player character is When playing against a non-player character, the game is too difficult, which affects the experience of the game player and reduces the interest in playing the game. Therefore, evolution can be carried out in a random manner as follows.
  • the evolution probability is a probability of allowing the second character to acquire an attribute for responding to the target event; and the case where the evolution probability is greater than the preset probability
  • the step of obtaining configuration information corresponding to the target event is performed.
  • a function for acquiring a random number between 0 and 1 may be configured in the game, and each time the evolution probability corresponding to the level of the first character is acquired, the function may be executed once, the first character is The rank parameter is used as an input parameter of the function, and the obtained random value is used as an evolution probability corresponding to the rank of the first character, and then the evolution probability is compared with a threshold (ie, a preset probability, such as 0.5, 0.6, 0.9, etc.). If it is greater than the threshold, it will evolve the next-generation non-player character, otherwise it will not evolve.
  • a threshold ie, a preset probability, such as 0.5, 0.6, 0.9, etc.
  • the method may be implemented to: determine a first attribute for the target event, and determine configuration information according to the first attribute, where the first attribute is used to indicate that the target event occurs, the target The modification degree of the target attribute value of the second role is smaller than the modification degree of the target attribute value of the first role, the configuration information is used to configure each parameter of the first attribute, and the second attribute determined for responding to the target event is determined according to the second
  • the attribute determines the configuration information, and the second attribute is used to indicate that a defense event for avoiding the occurrence of the target event is performed in the case that the target event is about to occur, and the configuration information is used to configure each parameter of the second attribute.
  • whether the first attribute or the second attribute is configured according to actual needs may be determined, and may be determined according to a specific target event. For example, for an attack event initiated by a player (which may cause a non-player character to drop blood), then the user's defense attribute (ie, the first attribute) can be configured to avoid losing blood or reducing blood loss when attacked; For the target event of the user-initiated robbing weapon, the non-player character's escape attribute (ie, the second attribute) may be configured to trigger the non-player when it is determined by some behavior of the player character that it is about to initiate a target event for robbing the weapon.
  • the escape attribute of the character escapes away from the player character (ie, the defense event); for example, when the non-player character touches the obstacle (that is, the target event in which the game environment modifies the target attribute value of the first character) It affects certain attributes of the player (such as health). At this time, it may trigger the evolution of the second attribute. Before the new non-player character touches the obstacle, it actively detects the position of the obstacle and avoids the obstacle in real time. Objects (ie, performing defensive events to avoid target events) to avoid obstacle damage.
  • the foregoing configuring the first attribute and the second attribute may refer to adding the first attribute or the second attribute, or reconfiguring the attribute parameter of the first attribute or the second attribute, so that the corresponding defense skill is further Strong, such as speeding up the escape.
  • the player character when determining the first attribute or the second attribute for responding to the target event, reference may be made to the processing manner in which other players encounter the same event, thereby determining which attributes are the first attribute or the second attribute.
  • the specific method is as follows: when detecting that the target event associated with the player character is executed, the player character is saved if the target event has a modification degree to the target character value of the player character less than the modification degree of the target attribute value of the first character.
  • the attribute used in response to the target event is the first attribute and holds various parameters of the attribute used by the player character.
  • the game developer may also define the skill attribute for the target event.
  • configuring the second role by using the configuration information includes: configuring the attributes of the plurality of second roles generated at the same time by using the configuration information when generating the second role Wherein the plurality of second characters belong to the same level, and the plurality of second characters are used to supplement to the game.
  • the evolutionary ideas in the related art are all based on the design of AI individuals.
  • Each AI entity has the same skill attributes at birth, and the AI individuals are promoted during the training process.
  • the appearance and the like will also be correspondingly changed, so that the user can judge the information such as the combat power of the individual AI according to the appearance and the like, thereby adopting a targeted processing method.
  • each generation of newly born AI individuals evolves the corresponding skill attributes with reference to the experience of dead AIs (or attacked AIs), which results in different skill attributes for each generation of AI.
  • the design of the evolution of the AI population is realized, so that when the game player plays against the AI, it is impossible to judge the level of the AI skill.
  • the game of Snake is described in detail as an example.
  • the usual design is to make the intelligence of the game AI grow with the length or value of the player.
  • the change is either based on the length or value of the game AI itself. This makes the longer the snake's intelligence higher, the newborn snake is very mentally retarded, the entire AI snake group has no probability of evolution, and the overall difficulty does not increase with time.
  • the technical solution of the present application can be used for improvement.
  • the intelligent AI snake consists of a head and a body.
  • the head area is a separate circle, which can support a variety of skins and styles.
  • the collision detection area of the body is composed of multiple circles. It is made up of multiple rectangles. The advantage of this type of composition is that the shape and position of the body can be accurately described with the least amount of geometry.
  • the concept of the head hot zone is added to each intelligent AI snake. By controlling the AI snake to actively attack other snake's head hot zone, the attack on the player or other snakes is realized.
  • the schematic diagram of the head hot zone is shown in Fig. 6.
  • the above-mentioned head hot zone refers to a certain range in which the snake's head is located in the Snake Game.
  • the intelligent AI snake will actively accelerate through this area to achieve the purpose of letting other snakes' heads hit their bodies and kill each other.
  • the head hot zone is in the front part of the head. If it passes through the hot zone of other players' heads at a certain speed, if the opponent does not avoid it in time, it will be killed.
  • the intelligent AI snake will actively attack the head hot zone of other snake heads according to its own attributes (mainly controlled by attack detection frequency, field of view, etc.).
  • the intelligence of the intelligent AI snake also includes:
  • the driving speed is related to the level of the vehicle, specifically the speed at which the snake moves under normal conditions;
  • the frequency of the steering which is related to the level of the position, specifically refers to the time interval during which the snake adjusts the direction of movement under normal conditions
  • the maximum angle of the steering is related to the level of the seat, specifically the maximum angle at which the snake adjusts the direction under normal conditions;
  • Accelerating the driving speed which is related to the level of the vehicle, specifically refers to the speed at which the snake moves in an accelerated state
  • the size of the field of view related to the level of the place, specifically refers to the size of the snake can detect (including food and other snakes within the detection range);
  • the probability of actively accelerating the competition for high-energy foods is related to the level of the occupation, specifically the probability of accelerating the competition for the death of other snakes;
  • the frequency of finding ordinary foods is related to the level of the food, specifically the time interval for detecting ordinary food.
  • an AI snake has a certain trait within a certain probability range, then its descendants will naturally have this trait, not a probability event.
  • Different generations of AI are unknown to the player, and the difference in AI intelligence can only be felt during the confrontation process. Therefore, the technical solution of the present application is applicable to various games that require players and game AI to play against each other. Scenes.
  • the development and verification environment may be a development tool software (such as WebStorm) used on a machine such as Windows (such as Win7), Linux (such as Mac OSX, Ubuntu, Debian, etc.), and the development used.
  • the language can be JavaScript, C++, Java, etc.
  • the game engine used can be cocos2d-js and so on.
  • the evolutionary logic will be based on the current level of the killed AI.
  • the AI management module obtains the probability of a certain feature (skill) that can be evolved at this level, and the evolutionary system (ie, the Evolution System) determines whether the evolution is successful.
  • AI Config Data some of the attributes of the AI are shown in Figure 8, for example, the current level of the snake, the initial movement speed of the snake, the initial corner speed of the snake, and so on.
  • the various attributes in the AI configuration information are transformed with the update of the AI snake generation, which defines the birth attribute of the intelligent AI snake. These attributes only define some values at the time of birth.
  • the intelligent AI snake will continue to grow, become longer and faster, and thus have more powerful aggression. For example, determine if the snake is turning, avoiding, or looking for food during the move.
  • the intelligent AI snake can judge whether to avoid the body of the snake in front according to its own attribute, and if it needs to avoid, then first decelerate, and then switch the moving direction.
  • the intelligent AI snake intelligently accelerates the grabbing of food and avoids collisions, and wanders in the game to eat food under normal conditions, which is very similar to the operation of a real player.
  • an AI individual is killed or injured, thereby triggering an evolutionary probability event of the population, and the probability of population evolution is determined by the attribute of the killed AI.
  • the population has this phase attribute by default or raises the value above the existing attribute. Offspring born after the evolution of the population will have such attributes and corresponding values.
  • Players will continue to kill which slow-moving, weak skill attributes, which is similar to the elimination mechanism of the survival of the fittest in nature.
  • the properties of the game AI will increase as the player's basic attributes increase, and this promotion is determined by the player's growth based on the difficulty of the game object he killed, rather than all pre-set, so that Let players get a similar battle fun with real players. Since there is no need to use complex state machines, there is no need to enumerate a large amount of event logic, and the development effort is greatly reduced.
  • the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, by hardware, but in many cases, the former is A better implementation.
  • the technical solution of the present application which is essential or contributes to the related art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk, CD-ROM).
  • the instructions include a number of instructions for causing a terminal device (which may be a cell phone, a computer, a server, or a network device, etc.) to perform the methods described in various embodiments of the present application.
  • the apparatus may include one or more processors, and one or more memory storing program units, wherein The program unit is executed by a processor, and the program unit includes a detecting unit 92, a first obtaining unit 94, and a configuration unit 96.
  • the detecting unit 92 is configured to detect a target event associated with the first character in the game, wherein the first character is a non-player character generated by the artificial intelligence and the player character pair generated in the game, and the target event is used to indicate the modification.
  • the first obtaining unit 94 is configured to acquire configuration information corresponding to the target event, where the configuration information is used to configure the second role, so that the configured second role is in response to the target event, and the target event is in the second role
  • the degree of modification of the target attribute value is less than the degree of modification of the target attribute value of the first character when the first character responds to the target event, and the second role is the non-player character to be generated in the game;
  • the configuration unit 96 is configured to configure the second role using the configuration information when the second role is generated.
  • the detecting unit 92 in this embodiment may be configured to perform step S402 in the foregoing embodiment of the present application
  • the first obtaining unit 94 in this embodiment may be configured to perform the foregoing embodiment in the present application
  • the configuration unit 96 in this embodiment may be configured to perform step S406 in the above embodiment of the present application.
  • the foregoing modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the contents disclosed in the foregoing embodiments. It should be noted that the foregoing module may be implemented in a hardware environment as shown in FIG. 3 as part of the device, and may be implemented by software or by hardware.
  • the configuration information corresponding to the target event is acquired, and the generated second role is configured by the configuration information, so that the configured second role is configured.
  • reduce the degree of modification of the target attribute value of the second character by the target event so that as the non-player character evolves, each new character born has the same initial shape, but will have a new one.
  • Skill attribute for a large number of non-player characters in the game, due to different birth time, the skill attributes are different, and the skill attributes used in dealing with the same event are different, so that the game character cannot pass multiple times.
  • determining the skill attributes adopted by the non-player character in response to the fixed event can solve the technical problem that the operating mechanism of the artificial intelligence character can be known in the related art, thereby achieving the technical effect of avoiding the operation mechanism of the artificial intelligence character being known. .
  • the above game may be any type of game; the first character is a non-player character attacked by a target event, the second character is a next-generation (or next-level) born non-player character; the target event is capable of causing the first character.
  • AI can be used to initially train players to familiarize themselves with various operational skills, or to interact with players when online players are not enough to attract more real players.
  • the current AI may cause poor interaction due to various reasons.
  • the present application implements a game AI (non-player character using artificial intelligence) evolution device based on the basic principles of biological evolution, by giving the game AI system the ability to self-evolve by simulating the principle of biological evolution, thereby enabling the game AI to acquire over time.
  • the intelligence that is enhanced by natural development and various skill attributes.
  • the design idea of this method is to evolve the entire game AI group instead of just a single AI individual.
  • the specific implementation method is that when the game AI individual is killed by the real player, the evolution logic of the group is triggered, and the evolution logic will be based on the value of the current generation of the killed AI (the default is from the first generation or the first level). Get the probability that this generation can evolve an attribute property (such as a skill) and determine whether the evolution is successful. If the evolution is successful, the AI born after this time will default to the next generation or next level, and this next generation AI is inherently equipped with this attribute. Over time, game AI will have increasingly sophisticated intelligence and skill attributes.
  • AI will also trigger the attribute enhancement of the existing skills, which is also the probability acquisition.
  • the next generation AI born after the birth will have this attribute value by default.
  • each AI grows in a different curve, so the experience of each game will be different.
  • the detecting unit includes: a first detecting module configured to detect a target event generated by the player character initiating an attack on the first character when the first character plays with the player character; the second detecting module is When the first character is in the target position in the map of the game, the target event in which the target environment value of the first character is modified is detected.
  • the above target attribute may be an attribute for indicating life, skill, weapon, defense, etc.
  • the target event is an event for reducing the attribute value of the life attribute
  • the target event is Used to capture the skill attribute of the first character, or to reduce the damage of the skill attribute to the player character
  • the target event is used to capture the weapon of the first character and reduce the damage caused by the weapon. Or the event that damages the weapon.
  • this application does not enumerate one by one.
  • the weapon attribute when the first character plays against the player character, it is detected that the player character attacks the first character to capture the target event generated by the weapon, and if the weapon of the first character is successfully captured, the new event is triggered.
  • the birth of the character evolves, allowing the newly born character to escape or counterattack in time when the player captures his weapon, specifically by configuring the escape character or defensive skill attribute of the newly born character.
  • the first detecting module includes: a first detecting submodule, configured to detect a first event in which the player character attacks the first character, where the first event is used to reduce the target attribute value of the first character to a first value, the first value is smaller than a target attribute maximum value of the first character, and is not smaller than a target attribute minimum value of the first character; and the second detecting submodule is configured to detect that the player character attacks the first character The second event, wherein the second event is used to lower the target attribute value of the first character by a second value, the second value being a positive number.
  • the above target attribute may be an attribute for indicating life, skill, weapon, defense, etc.
  • the target event is an event for reducing the attribute value of the life attribute
  • the target event is Used to capture the skill attribute of the first character, or to reduce the damage of the skill attribute to the player character
  • the target event is used to capture the weapon of the first character and reduce the damage caused by the weapon. Or the event that damages the weapon.
  • this application does not enumerate one by one.
  • the weapon attribute when the first character plays against the player character, it is detected that the player character attacks the first character to capture the target event generated by the weapon, and if the weapon of the first character is successfully captured, the new event is triggered.
  • the birth of the character evolves, allowing the newly born character to escape or counterattack in time when the player captures his weapon, specifically by configuring the escape character or defensive skill attribute of the newly born character.
  • the second value above indicates that when an event causes a fixed damage to the first character (ie, causes the attribute value to decrease by a second value), the new born non-player character is triggered to evolve for the event to avoid the event. Damage caused or reduced damage to the event.
  • attack events can bring evolution to the non-player character before acquiring the configuration information corresponding to the target event, then the non-player character is too powerful, and the game player character is When playing against a non-player character, the game is too difficult, which affects the experience of the game player and reduces the interest in playing the game.
  • the foregoing apparatus of the present application may further include: a second acquiring unit, configured to acquire an evolution probability corresponding to a level of the first role before the first acquiring unit acquires configuration information corresponding to the target event, where The evolution probability is a probability that the second character is allowed to acquire an attribute for responding to the target event; wherein, in a case where the evolution probability is greater than the preset probability, the first obtaining unit is instructed to acquire configuration information corresponding to the target event.
  • the first obtaining unit includes: a first determining module, configured to determine a first attribute for responding to the target event, and determining configuration information according to the first attribute, wherein the first attribute is used to indicate In the case that the target event occurs, the target event has a modification degree to the target attribute value of the second role less than the modification degree of the target attribute value of the first role, and the configuration information is used to configure each parameter of the first attribute; the second determining module And being configured to determine a second attribute for responding to the target event, and determining configuration information according to the second attribute, wherein the second attribute is used to indicate that a defense event for avoiding occurrence of the target event is performed if the target event is about to occur, The configuration information is used to configure various parameters of the second attribute.
  • a first determining module configured to determine a first attribute for responding to the target event, and determining configuration information according to the first attribute, wherein the first attribute is used to indicate In the case that the target event occurs, the target event has a modification degree to the target attribute value of the second role less
  • whether the first attribute or the second attribute is configured according to actual needs may be determined, and may be determined according to a specific target event. For example, for an attack event initiated by a player (which may cause a non-player character to drop blood), then the user's defense attribute (ie, the first attribute) can be configured to avoid losing blood or reducing blood loss when attacked; For the target event of the user-initiated robbing weapon, the non-player character's escape attribute (ie, the second attribute) may be configured to trigger the non-player when it is determined by some behavior of the player character that it is about to initiate a target event for robbing the weapon.
  • the escape attribute of the character escapes away from the player character (ie, the defense event); for example, when the non-player character touches the obstacle (that is, the target event in which the game environment modifies the target attribute value of the first character) It affects certain attributes of the player (such as health). At this time, it may trigger the evolution of the second attribute. Before the new non-player character touches the obstacle, it actively detects the position of the obstacle and avoids the obstacle in real time. Objects (ie, performing defensive events to avoid target events) to avoid obstacle damage.
  • the foregoing configuring the first attribute and the second attribute may refer to adding the first attribute or the second attribute, or reconfiguring the attribute parameter of the first attribute or the second attribute, so that the corresponding defense skill is further Strong, such as speeding up the escape.
  • the processing manner in which other players encounter the same event may be referred to, thereby determining which attributes are the first attribute or the second attribute.
  • the first determining module is further configured to: when detecting that the target event associated with the player character is executed, the target attribute value of the target event is modified to be less than the first character. In the case of the degree of modification of the target attribute value, the attribute used by the player character in responding to the target event is saved as the first attribute, and each parameter of the attribute used by the player character is saved.
  • the game developer may also define the skill attribute for the target event.
  • the configuration unit is further configured to configure, when the second role is generated, the attributes of the plurality of second roles that are simultaneously generated, by using the configuration information, where the plurality of second roles belong to the same level, and multiple The second role is used to add to the game.
  • the evolutionary ideas in the related art are all based on the design of AI individuals.
  • Each AI entity has the same skill attributes at birth, and the AI individuals are promoted during the training process.
  • the appearance and the like will also be correspondingly changed, so that the user can judge the information such as the combat power of the individual AI according to the appearance and the like, thereby adopting a targeted processing method.
  • each generation of newly born AI individuals evolves the corresponding skill attributes with reference to the experience of dead AIs (or attacked AIs), which results in different skill attributes for each generation of AI.
  • the design of the evolution of the AI population is realized, so that when the game player plays against the AI, it is impossible to judge the level of the AI skill.
  • the foregoing modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the contents disclosed in the foregoing embodiments. It should be noted that the foregoing module may be implemented in a hardware environment as shown in FIG. 3 as part of the device, and may be implemented by software or by hardware, where the hardware environment includes a network environment.
  • an electronic device for implementing the configuration method of the above character is also provided.
  • FIG. 10 is a structural block diagram of an electronic device according to an embodiment of the present application.
  • the electronic device may include: one or more (only one shown) processor 1001, memory 1003, and transmission.
  • the device 1005, as shown in FIG. 10, may further include an input and output device 1007.
  • the memory 1003 can be configured to store a computer program and a module, such as a configuration method of a character and a program instruction/module corresponding to the device in the embodiment of the present application, and the processor 1001 is configured to run a computer program stored in the memory 1003. And modules to perform various functional applications and data processing, that is, to implement the above-described role configuration method.
  • the memory 1003 may include a high speed random access memory, and may also include non-volatile memory such as one or more magnetic storage devices, flash memory, or other non-volatile solid state memory.
  • memory 1003 can further include memory remotely located relative to processor 1001, which can be connected to the terminal over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the transmission device 1005 described above is arranged to receive or transmit data via a network, and may also be configured as a data transmission between the processor and the memory. Specific examples of the above network may include a wired network and a wireless network.
  • the transmission device 1005 includes a Network Interface Controller (NIC) that can be connected to other network devices and routers via a network cable to communicate with the Internet or a local area network.
  • NIC Network Interface Controller
  • transmission device 1005 is a radio frequency (RF) module that is configured to communicate with the Internet wirelessly.
  • RF radio frequency
  • the memory 1003 is configured to store an application.
  • the processor 1001 may invoke the application stored in the memory 1003 through the transmission device 1005 to perform the steps of detecting a target event associated with the first character in the game, wherein the first character is artificial intelligence generated in the game.
  • the target character is used to play the non-player character
  • the target event is used to indicate that the target attribute value of the first character is modified
  • the configuration information corresponding to the target event is obtained, wherein the configuration information is used to configure the second role, so that the configured second
  • the degree of modification of the target attribute value of the target event to the second character is smaller than the modification degree of the target attribute value of the first character when the target character responds to the target event, and the second role is to be generated in the game.
  • Non-player character when generating the second character, configure the second character using the configuration information.
  • the configuration information corresponding to the target event is acquired, and the generated second role is configured through the configuration information, so that the configured
  • the second character reduces the degree of modification of the target attribute value of the second character in response to the target event, so that as the non-player character evolves, each new character born has the same initial shape, but will have The new skill attribute, for a large number of non-player characters in the game, has different skill attributes due to different birth time. The skill attributes used in dealing with the same event are also different, making the game character unable to pass.
  • determining the skill attributes adopted by the non-player character in response to the fixed event can solve the technical problem that the operation mechanism of the artificial intelligence character can be known in the related art, thereby avoiding the knowledge that the operation mechanism of the artificial intelligence character is known.
  • Technical effects can solve the technical problem that the operation mechanism of the artificial intelligence character can be known in the related art, thereby avoiding the knowledge that the operation mechanism of the artificial intelligence character is known.
  • the structure shown in FIG. 10 is only illustrative, and the terminal can be a smart phone (such as an Android mobile phone, an iOS mobile phone, etc.), a tablet computer, a palm computer, and a mobile Internet device (MID). Terminal equipment such as PAD.
  • FIG. 10 does not limit the structure of the above electronic device.
  • the terminal may also include more or fewer components (such as a network interface, display device, etc.) than shown in FIG. 10, or have a different configuration than that shown in FIG.
  • Embodiments of the present application also provide a storage medium.
  • a computer program is stored in the storage medium, wherein the computer program is set as a configuration method of a runtime execution role.
  • the foregoing storage medium may be located on at least one of the plurality of network devices in the network shown in the foregoing embodiment.
  • the storage medium is arranged to store program code for performing the following steps:
  • the first character is a non-player character generated by the artificial intelligence and the player character pair generated in the game, and the target event is used to indicate that the target attribute value of the first character is modified.
  • S2 Obtain configuration information corresponding to the target event, where the configuration information is used to configure the second role, so that when the configured second role responds to the target event, the target event changes the target attribute value of the second role to be less than the first The degree of modification of the target attribute value of the first character when the character responds to the target event, and the second character is the non-player character to be generated in the game;
  • the second role is configured by using the configuration information.
  • the foregoing storage medium may include, but not limited to, a USB flash drive, a Read-Only Memory (ROM), a Random Access Memory (RAM), a mobile hard disk, and a magnetic memory.
  • ROM Read-Only Memory
  • RAM Random Access Memory
  • a mobile hard disk e.g., a hard disk
  • magnetic memory e.g., a hard disk
  • the integrated unit in the above embodiment if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in the above-described computer readable storage medium.
  • the technical solution of the present application may be embodied in the form of a software product, or the whole or part of the technical solution, which is stored in the storage medium, including
  • the instructions are used to cause one or more computer devices (which may be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application.
  • the disclosed client may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, unit or module, and may be electrical or otherwise.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Computational Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Algebra (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Optimization (AREA)
  • Molecular Biology (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • Processing Or Creating Images (AREA)
  • User Interface Of Digital Computer (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种角色的配置方法及装置、存储介质以及电子装置。其中，该方法包括：检测到游戏中与第一角色关联的目标事件，其中，第一角色为在游戏中生成的采用人工智能与玩家角色对玩的非玩家角色，目标事件用于指示修改第一角色的目标属性值；获取与目标事件对应的配置信息，其中，配置信息用于配置第二角色，以使配置后的第二角色在应对目标事件时，目标事件对第二角色的目标属性值的修改程度小于第一角色在应对目标事件时对第一角色的目标属性值的修改程度，第二角色为游戏中待生成的非玩家角色；在生成第二角色时，使用配置信息对第二角色进行配置。

Description

角色的配置方法及装置、存储介质以及电子装置
本申请要求于2017年04月20日提交中国专利局、申请号为201710261467.5、发明名称“角色的配置方法和装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及互联网领域，具体而言，涉及一种角色的配置方法及装置、存储介质以及电子装置。
背景技术
人工智能(Artificial Intelligence，AI)，是研究、开发用于模拟、延伸和扩展人的智能的理论、方法、技术及应用系统的一门新的技术科学。在相关技术中，人工智能在游戏中的应用非常普遍，游戏AI的主要目的是让具有AI的角色看起来非常的智能。
游戏AI即游戏中的人工智能角色，在本申请中指的是游戏中具有智能的角色，模拟真实玩家的各种行为，并且能模拟真人的操作与玩家对战。一般在游戏中，玩家通过和游戏AI对战获得技能和经验的提升。
例如，在对战游戏中，游戏AI相关的实现方法中，主要控制的是对象的行为，在此基础上AI的设计主要包括设定规则和枚举行为两种方法。所谓设定规则就是明确的设定一系列规则，然后给相关的对象进行对应的赋值，然后整个系统就按照规则运行，一旦规则设定好了，智能对象就会按照规则限制的范围循规蹈矩的执行，因为有了现有规则的存在，所以这些AI的行为基本都是可以预测的，用户在多次尝试之后就可能学会如何规避这些规则。对于枚举行为，基本上就是把对应对象所有可能的行为都设想到，然后人工确定好所有的响应。这样就把所有的行为分支构建成为一颗树形的系统，或者使用状态机来维护各个行为之间的触发条件和切换 逻辑，因为需要考虑得非常周全，为每个可能的行为设置对应的响应，故此方法的缺陷之一是工作量大，另外一个就是往往给游戏对象相同的刺激，行为是一样的，重复几次就被玩家发现是固定的机器行为了，从而影响用户的体验。
在相关技术的技术方案中，实际游戏设计中是以单个AI个体为设计目标，通过上述的设计方法中的一种或者两种同时使用来达到AI智能的目的。通过构建各种状态机和行为树来完善AI个体的行为，使AI个体看起来尽可能的智能。例如在对战游戏中，AI角色一般会有以下动作：
动作1：未发现玩家时，在一定区域内游荡；
动作2：发现玩家时，追赶玩家并攻击玩家角色；
动作3：自身血量低于一定量时，遭遇玩家就会逃跑。
这里可以针对AI的反应，抽象出巡逻中(Patrolling)、攻击中(Attacking)、逃跑中(Escaping)三个状态，每个状态接口都应该包含进入状态，执行状态动作和退出状态三个逻辑，具体状态图如图1所示，然后AI就会根据环境的触发在各种状态间切换。例如，巡逻中的AI个体遭遇到玩家角色，就会判断自身受到的威胁是否比玩家弱，若是就会逃跑，否则就会对玩家进行攻击；在AI个体处于逃跑状态时，也会实时判断是否恢复安全状态，若是就会进入巡逻状态，否则继续逃跑；处于攻击状态的AI个体也会实时判断自身受到的威胁是否比敌人若，若是则会逃跑，否则继续对玩家角色发起攻击。
当然在实际开发中可以增加状态的种类，可以让状态机更加复杂，对应的AI就会更加智能，可以处理种类更加多的场景情况。
一般情况下的单个个体的AI设计数据结构如图2所示，在此数据结构中会详细描述AI所具有的属性特征(如玩家所在的地理位置等)，还可以记载一些概率事件发生的数值范围等等，属性特征主要包括所在的地图位置、屏幕位置、动画信息、军衔等信息。
在相关的技术方案中存在的缺点包括：一方面是套路基本固定，同类AI之间没有差异化，采用相同的运行机制，玩家尝试几次就会明白机器人的运作方式，就可以采用对应的方式进行破解应对。其次，如果要做到非常完善的AI响应机制，穷举所有可能行为的工作量太大，一般小游戏无法做到。
针对相关技术中人工智能角色的运行机制能够被知晓的技术问题，目前尚未提出有效的解决方案。
发明内容
本申请实施例提供了一种角色的配置方法及装置、存储介质以及电子装置，以至少解决相关技术中人工智能角色的运行机制能够被知晓的技术问题。
根据本申请实施例的一个方面，提供了一种角色的配置方法，该方法包括：检测到游戏中与第一角色关联的目标事件，其中，第一角色为在游戏中生成的采用人工智能与玩家角色对玩的非玩家角色，目标事件用于指示修改第一角色的目标属性值；获取与目标事件对应的配置信息，其中，配置信息用于配置第二角色，以使配置后的第二角色在应对目标事件时，目标事件对第二角色的目标属性值的修改程度小于第一角色在应对目标事件时对第一角色的目标属性值的修改程度，第二角色为游戏中待生成的非玩家角色；在生成第二角色时，使用配置信息对第二角色进行配置。
根据本申请实施例的另一方面，还提供了一种角色的配置装置，该配置装置包括一个或多个处理器，以及一个或多个存储程序单元的存储器，其中，程序单元由处理器执行，程序单元包括：检测单元，被设置为检测到游戏中与第一角色关联的目标事件，其中，第一角色为在游戏中生成的采用人工智能与玩家角色对玩的非玩家角色，目标事件用于指示修改第一角色的目标属性值；第一获取单元，被设置为获取与目标事件对应的配置信息，其中，配置信息用于配置第二角色，以使配置后的第二角色在应对 目标事件时，目标事件对第二角色的目标属性值的修改程度小于第一角色在应对目标事件时对第一角色的目标属性值的修改程度，第二角色为游戏中待生成的非玩家角色；配置单元，被设置为在生成第二角色时，使用配置信息对第二角色进行配置。
在本申请实施例中，在检测到游戏中对第一角色发起的目标事件时，获取与目标事件对应的配置信息，并通过该配置信息对生成的第二角色进行配置，以使配置后的第二角色在应对目标事件时，减小目标事件对第二角色的目标属性值的修改程度，这样，随着非玩家角色的进化，每一次出生的新角色虽然具备相同的初始外形，但是会具备新的技能属性，对于游戏中的大量非玩家角色，由于出生时间不同，其所具备的技能属性也不尽相同，在应对相同的事件时所使用的技能属性也不相同，使得游戏角色不能通过多次尝试之后，确定非玩家角色在应对固定事件时采用的技能属性，可以解决了相关技术中人工智能角色的运行机制能够被知晓的技术问题，进而达到避免人工智能角色的运行机制被知晓的技术效果。
附图说明
此处所说明的附图用来提供对本申请的进一步理解，构成本申请的一部分，本申请的示意性实施例及其说明用于解释本申请，并不构成对本申请的不当限定。在附图中：
图1是相关技术中的AI的状态转变的示意图；
图2是相关技术中的AI的数据结构的示意图；
图3是根据本申请实施例的角色的配置方法的硬件环境的示意图；
图4是根据本申请实施例的一种可选的角色的配置方法的流程图；
图5是根据本申请实施例的一种可选的AI蛇的示意图；
图6是根据本申请实施例的一种可选的头部热区的示意图；
图7是根据本申请实施例的一种可选的进化系统的示意图；
图8是根据本申请实施例的一种可选的AI属性的示意图；
图9是根据本申请实施例的一种可选的角色的配置装置的示意图；以及
图10是根据本申请实施例的一种电子装置的结构框图。
具体实施方式
为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分的实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本申请保护的范围。
需要说明的是，本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
根据本申请实施例，提供了一种角色的配置方法的方法实施例。
可选地，在本实施例中，上述角色的配置方法可以应用于如图3所示的由服务器302和终端304所构成的硬件环境中。如图3所示，服务器302通过网络与终端304进行连接，上述网络包括但不限于：广域网、城域网或局域网，终端304并不限定于PC、手机、平板电脑等。本申请实施例的方法可以由服务器302来执行，也可以由终端304来执行，还可以是由服务器302和终端304共同执行。其中，终端304执行本申请实施例的方法也可以是由安装在其上的客户端来执行。
图4是根据本申请实施例的一种可选的角色的配置方法的流程图，如图4所示，该方法可以包括以下步骤：
步骤S402，检测到游戏中与第一角色关联的目标事件，第一角色为在游戏中生成的采用人工智能与玩家角色对玩的非玩家角色，目标事件用于指示修改第一角色的目标属性值；
步骤S404，获取与目标事件对应的配置信息，配置信息用于配置第二角色，以使配置后的第二角色在应对目标事件时，目标事件对第二角色的目标属性值的修改程度小于第一角色在应对目标事件时对第一角色的目标属性值的修改程度，第二角色为游戏中待生成的非玩家角色；
步骤S406，在生成第二角色时，使用配置信息对第二角色进行配置。
通过上述步骤S402至步骤S406，在检测到游戏中对第一角色发起的目标事件时，获取与目标事件对应的配置信息，并通过该配置信息对生成的第二角色进行配置，以使配置后的第二角色在应对目标事件时，减小目标事件对第二角色的目标属性值的修改程度，这样，随着非玩家角色的进化，每一次出生的新角色虽然具备相同的初始外形，但是会具备新的技能属性，对于游戏中的大量非玩家角色，由于出生时间不同，其所具备的技能属性也不尽相同，在应对相同的事件时所使用的技能属性也不相同，使得游戏角色不能通过多次尝试之后，确定非玩家角色在应对固定事件时采用的技能属性，可以解决了相关技术中人工智能角色的运行机制能够被知晓的技术问题，进而达到避免人工智能角色的运行机制被知晓的技术效果。
上述的游戏可以为任意类型的游戏；第一角色为受到目标事件攻击的非玩家角色，第二角色为下一代(或者下一等级)出生的非玩家角色；目标事件为能够造成第一角色的某个属性(即目标属性)受到伤害的事件，该目标属性包括但不局限于生命、技能、武器、防御等。
在现在的多人实时在线对战类游戏中，都会需要用到AI对象，用来增加游戏对抗性和乐趣。AI可以用来初期训练玩家熟悉各种操作技能， 或者在在线玩家不够的时候来和玩家互动，从而达到吸引更多真实玩家的目的。但是目前的AI由于种种原因会导致互动的效果较差。
本申请实现了一种基于生物进化基本原理的游戏AI(即采用人工智能的非玩家角色)进化方法，通过模拟生物进化的原理，赋予游戏AI系统自我进化的能力，从而使游戏AI获得随时间自然发展而提升的智能以及各种技能属性。此方法的设计思想是以整个游戏AI群体为进化对象，而不是仅仅以单个的AI个体为对象进行进化升级。具体实现方法是，当游戏AI个体被真实玩家杀死时会触发群体的进化逻辑，进化逻辑会根据被杀死的AI当前所在的代(默认从第一代或第一等级开始)的数值，获取此代能够进化出某项属性特性(如技能)的概率，并判断此次进化能否成功。如果进化成功，那么在此时间点之后出生的AI就会默认变成下一代或者下一等级，而这下一代的AI就天生具备了此项属性特性。随着时间的推移，游戏AI将会具备越来越完善的智能和技能属性。
同时，随着被玩家杀死的AI越来越多，AI也会触发已经具有的技能的属性提升，同样也是概率获取，一旦获取成功，之后出生的后一代AI将会默认具备此属性数值。在这样的成长系统中，每个AI成长的曲线都不相同，因此每局对战的体验都会不尽相同。下面结合图4进一步详述本申请的实施例：
在步骤S402提供的技术方案中，检测游戏中第一角色关联的目标事件包括：在第一角色与玩家角色对玩时，检测到玩家角色对第一角色发起攻击产生的目标事件；在第一角色处于游戏的地图中的目标位置时，检测到目标位置的游戏环境对第一角色的目标属性值进行修改的目标事件。
上述的目标属性可以为用于指示生命、技能、武器、防御等的属性例如，对于生命属性而言，目标事件即用于减少生命属性的属性值的事件；对于技能属性而言，目标事件即用于夺取第一角色的技能属性、或者降低该技能属性对玩家角色伤害的事件；再如，对于武器属性而言，目标事件即用于夺取第一角色的武器、降低该武器带来的伤害或者损毁该武器的事 件，对于其余属性而言，只要是能造成对应的属性的属性值发生改变的事件均为目标事件，本申请不一一列举。
对于武器属性而言，在第一角色与玩家角色对玩时，检测到玩家角色对第一角色发起攻击以夺取其武器产生的目标事件，若第一角色的武器被夺取成功，则会触发新出生的角色发生进化，使得新出生的角色能够在玩家夺取其武器时及时逃走或者反击，具体是通过配置新出生的角色的逃避技能属性或者防御技能属性等实现。
上述的检测到玩家角色对第一角色发起攻击产生的目标事件主要包括以下两种类型：检测到玩家角色对第一角色发起攻击的第一事件，第一事件用于减少第一角色的目标属性值至第一数值，第一数值小于第一角色的目标属性极大值(即该属性所允许配置的最大值)，且不小于第一角色的目标属性极小值(即该属性所允许配置的最小值)；检测到玩家角色对第一角色发起攻击的第二事件，第二事件用于将第一角色的目标属性值降低第二数值，第二数值为正数。
上述的第一数值为触发非玩家角色发生进化的触发点，目标属性的属性值会在一定的范围内(即属性极大值和属性极小值间)，第一数值即该范围内的数值。例如，检测到玩家角色对第一角色发起攻击的第一事件可以是检测由玩家角色发起的，且用于减少第一角色的目标属性值至目标属性极小值的第一事件，即指定将该属性的属性值降低至极小值时触发进化事件的发生。
例如，目标属性以生命属性为例，该第一数值可以为生命属性值的50％，在第一角色受到第一事件的攻击致使生命数值降低至50％或者以下时，就会触发非玩家角色发生进化，进而进化出抗击第一事件的技能属性，以在下次再遭遇第一事件时，避免或者减少第一事件对第一角色带来的伤害。
上述的第二数值表示当某个事件对第一角色造成固定伤害(即造成属性值减少第二数值的伤害)时，就会触发新出生的非玩家角色针对该事件 发生进化，以避免该事件造成的伤害或者减小该事件的伤害。
还是以目标属性以生命属性为例，该第二数值可以为生命属性值的30％，在第一角色受到第二事件的攻击致使生命数值降低了30％或者以上时，就会触发非玩家角色发生进化，进而进化出抗击第二事件的技能属性，以在下次再遭遇第二事件时，避免或者减少第一事件对第一角色带来的伤害。
对于其他属性而言，采用的方法与上述类似，本申请不一一赘述。
在步骤S404提供的技术方案中，在获取与目标事件对应的配置信息之前，若每一次遭遇攻击事件都能为非玩家角色带来进化，那么就会造成非玩家角色过于强大，在游戏玩家角色与非玩家角色对战时，游戏难度过大，从而影响游戏玩家的体验，降低其玩游戏的兴趣。故而可以通过如下随机的方式进行进化。
在获取与目标事件对应的配置信息之前，获取与第一角色的等级对应的进化概率，进化概率为允许第二角色获取用于应对目标事件的属性的概率；在进化概率大于预设概率的情况下，执行获取与目标事件对应的配置信息的步骤。
可选地，可以在游戏中配置一个用于获取0至1之间的随机数的函数，每一次获取与第一角色的等级对应的进化概率时，可以执行一次该函数，将第一角色的等级参数作为该函数的输入参数，利用得到的随机数值作为与第一角色的等级对应的进化概率，然后将该进化概率与阈值(即预设概率，如0.5、0.6、0.9等)相比较，若大于阈值就对下一代出生的非玩家角色进行进化，否则就不进化。
需要说明的是，在获取与第一角色的等级对应的进化概率时，除了上述的方式以外，还可以根据实际需求采用其它方式。
在获取与目标事件对应的配置信息时，可以通过如下方式实现：确定用于应对目标事件第一属性，根据第一属性确定配置信息，第一属性用于 指示在目标事件发生的情况下，目标事件对第二角色的目标属性值的修改程度小于对第一角色的目标属性值的修改程度，配置信息用于配置第一属性的各个参数；确定用于应对目标事件第二属性，根据第二属性确定配置信息，第二属性用于指示在目标事件即将发生的情况下，执行用于避免目标事件发生的防御事件，配置信息用于配置第二属性的各个参数。
在实际应用中，可以根据实际需要确定是配置上述的第一属性还是第二属性，具体可以根据具体的目标事件确定。例如，对于由玩家发起的攻击事件(可能会造成非玩家角色掉血)，此时就可以配置用户的防御属性(即第一属性)，避免在受到攻击时掉血或者减少掉血；再如，对于用户发起的抢夺武器的目标事件，则可以配置非玩家角色的逃跑属性(即第二属性)，在通过玩家角色的某些行为判断出其即将发起抢夺武器的目标事件时，触发非玩家角色的逃跑属性，逃跑远离玩家角色(即防御事件)；再如，在非玩家角色触碰到障碍物(也即游戏环境对第一角色的目标属性值进行修改的目标事件)时，也可能对玩家的某些属性(如生命值)造成影响，此时也可能触发进化出第二属性，在新出生的非玩家角色触碰到障碍物之前，主动检测确定障碍物的位置，实时避让障碍物(即执行用于避免目标事件发生的防御事件)，避免障碍物的伤害。
可选地，上述的配置第一属性和第二属性，可以是指新增第一属性或者第二属性，也可以是重新配置第一属性或者第二属性的属性参数，让对应的防御技能更强，例如加快逃跑的速度等。
在上述实施例中，在确定用于应对目标事件第一属性或第二属性时，可以参考其它玩家遇到相同事件的处理方式，进而确定哪些属性时第一属性或者第二属性。具体方法如下：在检测到关联于玩家角色的目标事件被执行时，在目标事件对玩家角色的目标属性值的修改程度小于对第一角色的目标属性值的修改程度的情况下，保存玩家角色在应对目标事件时所使用的属性为第一属性，并保存玩家角色所使用的属性的各个参数。
可选地，在确定用于应对目标事件第一属性或第二属性时，也可以由 游戏开发商自己定义用于应付目标事件的技能属性。
在步骤S406提供的技术方案中，在生成第二角色时，使用配置信息对第二角色进行配置包括：在生成第二角色时，使用配置信息对同时生成的多个第二角色的属性进行配置，其中，多个第二角色归属于同一等级，且多个第二角色用于补充至游戏中。
相关技术中的进化思路都是基于AI个体的设计，每个AI个体在出生时所具备的技能属性都是完全相同的，AI个体在训练过程中提升，随着AI个体在训练中的提升，其外观等也会产生相应的变化，这样用户就可以根据其外观等判断个体AI的战斗力等信息，从而采用针对性的处理方式。
在本申请中，每一代新出生的AI个体都是参照已死亡的AI(或者受到过攻击的AI)的经验进化出相应的技能属性，这就会造成每一代AI的技能属性各不相同，实现了对AI种群进行进化的设计，这样在游戏玩家与AI进行对战时，就无法判断出AI技能的高低。
为了便于进一步了解本申请的技术方案，以贪吃蛇这一对战游戏为例进行详述，对于贪吃蛇而言，通常的设计是让游戏AI的智力随着玩家的长度或者数值的成长而变化，或者是根据游戏AI自己的长度或者数值的提升而变化。这样就导致越长的蛇的智能越高，刚出生的小蛇非常弱智，整个AI蛇的群体没有进化的概率，整体的难度其实并没有随着时间的增加而加大。为了克服上述问题，可以采用本申请的技术方案进行改进。
在此方案中，如图5所示，智能AI蛇由头部和身体组成，头部区域是一个独立的圆形，这样可以支持多种皮肤和样式，身体的碰撞检测区域是由多个圆和多个矩形拼接而成。这样的组成方式的优点就是，用最少的几何形体就可以准确的描述出身体的形状和位置。
给每个智能AI蛇增加了头部热区的概念，通过控制AI蛇主动冲击其它蛇的头部热区，来实现对玩家或其他蛇的攻击，头部热区示意图如图6 所示。
上述的头部热区是指贪吃蛇游戏中蛇的头部所在的一定范围。智能AI蛇会主动加速经过此区域，达到让其他蛇的头部撞到自己的身体从而杀死对方的目的。
因为在游戏中的所有蛇都会默认有一个行进速度，如果蛇头撞到了其它玩家的身体，就会死掉。因此头部热区在头部之前一部分，如果以一定的速度快速经过其它玩家的头部热区，如果对方没有及时躲避，那就会被杀死。
智能AI蛇会根据自身的属性(主要由攻击检测频率、视野范围等控制)主动攻击其他蛇头部的头部热区，除此之外，智能AI蛇的智力还包括：
(1)行驶速度，与所在等级相关，具体是指蛇在常规状态下移动的速度；
(2)转向的频率，与所在等级相关，具体是指蛇在常规状态下调整移动方向的时间间隔；
(3)转向最大角度，与所在等级相关，具体是指蛇在常规状态下调整方向的最大角度；
(4)加速行驶速度，与所在等级相关，具体是指蛇在加速状态下移动的速度；
(5)加速转向最大角度，与所在等级相关，具体是指蛇在加速状态下调整方向的最大角度；
(6)视野大小，与所在等级相关，具体是指蛇能检测的范围大小(包括检测范围内的食物和其它蛇)；
(7)主动加速争抢高能食物的概率，与所在等级相关，具体是指加速争抢其它蛇死亡尸体的概率；
(8)寻找普通食物的频率，与所在等级相关，具体是指检测普通食物的时间间隔。
在实现上，如果一个AI蛇在一定概率的范围内具有了某项特质，那么它的后代天生就会具有了此项特质，而不再是概率事件。而不同的代别的AI对玩家来说是不可知的，只有在对抗过程中才能感觉到AI智能的差异，因此，本申请的技术方案的设计适用于各种需要玩家和游戏AI对战的游戏场景。
在实现本申请的技术方案时，开发和验证环境可以是Windows(如Win7等版本)、Linux(如Mac OSX、Ubuntu、Debian等)等机器上使用的开发工具软件(如WebStorm)，使用的开发语言可以为JavaScript、C++、Java等，使用的游戏引擎可以为cocos2d-js等。
如图7所示，当客户端侧的游戏AI个体被真实玩家杀死时(即AI被杀死的事件)会触发群体的进化逻辑，进化逻辑会根据被杀死的AI当前所在的等级，AI管理模块获取此等级能够进化出的某项特性(技能)的概率，并由进化系统(即Evolution System)判断此次进化能否成功。如果进化成功，那么在此时间点之后出生的AI个体就会默认升级一个等级，而这个等级的AI就天生具备了此项特性或技能(比如快速闪躲、限时无敌、限时隐身等等，可以根据产品需求来配置)，具体由属性管理模块管理相关属性，随着时间的推移，游戏AI个体将会具备越来越完善的智能和技能属性，每一代的AI个体的属性会保存在AI配置信息(即AI Config Data)中，AI的部分属性如图8所示，例如，蛇当前所在的等级、蛇的初始移动速度、蛇的初始转弯角速度等。
在完成进化后新出生的蛇就会具备相应的技能。
AI配置信息(也即进化配置)里面的各个属性都是随着AI蛇一代一代的更新而变换的，这里面定义了智能AI蛇的出生的属性。这些属性只是定义刚出生的时候的一些数值，在不断的吃食物和攻击其它蛇的过程中，智能AI蛇也会不断成长，变得更长更快，从而具有更强大的攻击性。如 判断蛇在移动过程中是否转向、躲避，或者寻找食物。这里可以用Math.random()函数会获取一个值在0到1的随机小数，在基础之上乘以每一帧的时间和对应的属性配置时间，会得出一个数值，然后利用函数math.round对这个数值取四舍五入，如果小于0.5就为0，如果大于0.5就为1。在这里如果为0那么就会触发对应的转向、寻找食物、或者加速等等智能事件，否则不触发对应的事件。
可选地，智能AI蛇可根据自身的属性判断是否要躲避前面的蛇的身体，如果需要躲避那么首先减速，然后切换移动方向。在本申请的实现方案中，智能AI蛇会智能加速抢夺食物并躲避碰撞，在正常状态下在游戏中游荡吃食物，非常类似真人玩家的操作。
利用本申请的技术方案，根据基因的进化理论，伴随着AI个体被杀死或者受到伤害，从而触发种群的一个进化的概率事件，种群进化的概率由被杀死的AI的属性来决定。一旦进化成功，那么种群就默认具备此相属性或者是在已有属性之上提升数值。在种群进化之后出生的后代都会具有这样的属性和对应的数值。
玩家会不断杀掉哪些移动慢的，技能属性弱的，这样就类似于自然界中的优胜劣汰的淘汰机制。游戏AI的属性会随着玩家的基本属性的提升而提升，而且这个提升是紧随玩家的成长是根据他击杀的游戏对象的难度来判断，而不是预先全部设定好的，这样就可以让玩家获得与真人玩家类似的对战乐趣。由于不需要使用复杂的状态机，无需枚举大量的事件逻辑，开发工作量也会大幅降低。
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制，因为依据本申请，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本申请所必须的。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到根 据上述实施例的方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对相关技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，或者网络设备等)执行本申请各个实施例所述的方法。
根据本申请实施例，还提供了一种用于实施上述角色的配置方法的角色的配置装置。图9是根据本申请实施例的一种可选的角色的配置装置的示意图，如图9所示，该装置可以包括一个或多个处理器，以及一个或多个存储程序单元的存储器，其中，程序单元由处理器执行，程序单元包括检测单元92、第一获取单元94以及配置单元96。
检测单元92，被设置为检测到游戏中与第一角色关联的目标事件，其中，第一角色为在游戏中生成的采用人工智能与玩家角色对玩的非玩家角色，目标事件用于指示修改第一角色的目标属性值；
第一获取单元94，被设置为获取与目标事件对应的配置信息，其中，配置信息用于配置第二角色，以使配置后的第二角色在应对目标事件时，目标事件对第二角色的目标属性值的修改程度小于第一角色在应对目标事件时对第一角色的目标属性值的修改程度，第二角色为游戏中待生成的非玩家角色；
配置单元96，被设置为在生成第二角色时，使用配置信息对第二角色进行配置。
需要说明的是，该实施例中的检测单元92可以被设置为执行本申请上述实施例中的步骤S402，该实施例中的第一获取单元94可以被设置为执行本申请上述实施例中的步骤S404，该实施例中的配置单元96可以被设置为执行本申请上述实施例中的步骤S406。
此处需要说明的是，上述模块与对应的步骤所实现的示例和应用场景相同，但不限于上述实施例所公开的内容。需要说明的是，上述模块作为装置的一部分可以运行在如图3所示的硬件环境中，可以通过软件实现，也可以通过硬件实现。
通过上述模块，在检测到游戏中对第一角色发起的目标事件时，获取与目标事件对应的配置信息，并通过该配置信息对生成的第二角色进行配置，以使配置后的第二角色在应对目标事件时，减小目标事件对第二角色的目标属性值的修改程度，这样，随着非玩家角色的进化，每一次出生的新角色虽然具备相同的初始外形，但是会具备新的技能属性，对于游戏中的大量非玩家角色，由于出生时间不同，其所具备的技能属性也不尽相同，在应对相同的事件时所使用的技能属性也不相同，使得游戏角色不能通过多次尝试之后，确定非玩家角色在应对固定事件时采用的技能属性，可以解决了相关技术中人工智能角色的运行机制能够被知晓的技术问题，进而达到避免人工智能角色的运行机制被知晓的技术效果。
上述的游戏可以为任意类型的游戏；第一角色为受到目标事件攻击的非玩家角色，第二角色为下一代(或者下一等级)出生的非玩家角色；目标事件为能够造成第一角色的某个属性(即目标属性)受到伤害的事件，该目标属性包括但不局限于生命、技能、武器、防御等。
在现在的多人实时在线对战类游戏中，都会需要用到AI对象，用来增加游戏对抗性和乐趣。AI可以用来初期训练玩家熟悉各种操作技能，或者在在线玩家不够的时候来和玩家互动，从而达到吸引更多真实玩家的目的。但是目前的AI由于种种原因会导致互动的效果较差。
本申请实现了一种基于生物进化基本原理的游戏AI(即采用人工智能的非玩家角色)进化装置，通过模拟生物进化的原理，赋予游戏AI系统自我进化的能力，从而使游戏AI获得随时间自然发展而提升的智能以及各种技能属性。此方法的设计思想是以整个游戏AI群体为进化对象，而不是仅仅以单个的AI个体为对象进行进化升级。具体实现方法是，当 游戏AI个体被真实玩家杀死时会触发群体的进化逻辑，进化逻辑会根据被杀死的AI当前所在的代(默认从第一代或第一等级开始)的数值，获取此代能够进化出某项属性特性(如技能)的概率，并判断此次进化能否成功。如果进化成功，那么在此时间点之后出生的AI就会默认变成下一代或者下一等级，而这下一代的AI就天生具备了此项属性特性。随着时间的推移，游戏AI将会具备越来越完善的智能和技能属性。
同时，随着被玩家杀死的AI越来越多，AI也会触发已经具有的技能的属性提升，同样也是概率获取，一旦获取成功，之后出生的后一代AI将会默认具备此属性数值。在这样的成长系统中，每个AI成长的曲线都不相同，因此每局对战的体验都会不尽相同。
在上述实施例中，检测单元包括：第一检测模块，被设置为在第一角色与玩家角色对玩时，检测到玩家角色对第一角色发起攻击产生的目标事件；第二检测模块，被设置为在第一角色处于游戏的地图中的目标位置时，检测到目标位置的游戏环境对第一角色的目标属性值进行修改的目标事件。
上述的目标属性可以为用于指示生命、技能、武器、防御等的属性例如，对于生命属性而言，目标事件即用于减少生命属性的属性值的事件；对于技能属性而言，目标事件即用于夺取第一角色的技能属性、或者降低该技能属性对玩家角色伤害的事件；再如，对于武器属性而言，目标事件即用于夺取第一角色的武器、降低该武器带来的伤害或者损毁该武器的事件，对于其余属性而言，只要是能造成对应的属性的属性值发生改变的事件均为目标事件，本申请不一一列举。
对于武器属性而言，在第一角色与玩家角色对玩时，检测到玩家角色对第一角色发起攻击以夺取其武器产生的目标事件，若第一角色的武器被夺取成功，则会触发新出生的角色发生进化，使得新出生的角色能够在玩家夺取其武器时及时逃走或者反击，具体是通过配置新出生的角色的逃避技能属性或者防御技能属性等实现。
可选地，第一检测模块包括：第一检测子模块，被设置为检测到玩家角色对第一角色发起攻击的第一事件，其中，第一事件用于减少第一角色的目标属性值至第一数值，第一数值小于第一角色的目标属性极大值，且不小于第一角色的目标属性极小值；第二检测子模块，被设置为检测到玩家角色对第一角色发起攻击的第二事件，其中，第二事件用于将第一角色的目标属性值降低第二数值，第二数值为正数。
上述的目标属性可以为用于指示生命、技能、武器、防御等的属性例如，对于生命属性而言，目标事件即用于减少生命属性的属性值的事件；对于技能属性而言，目标事件即用于夺取第一角色的技能属性、或者降低该技能属性对玩家角色伤害的事件；再如，对于武器属性而言，目标事件即用于夺取第一角色的武器、降低该武器带来的伤害或者损毁该武器的事件，对于其余属性而言，只要是能造成对应的属性的属性值发生改变的事件均为目标事件，本申请不一一列举。
对于武器属性而言，在第一角色与玩家角色对玩时，检测到玩家角色对第一角色发起攻击以夺取其武器产生的目标事件，若第一角色的武器被夺取成功，则会触发新出生的角色发生进化，使得新出生的角色能够在玩家夺取其武器时及时逃走或者反击，具体是通过配置新出生的角色的逃避技能属性或者防御技能属性等实现。
上述的第二数值表示当某个事件对第一角色造成固定伤害(即造成属性值减少第二数值的伤害)时，就会触发新出生的非玩家角色针对该事件发生进化，以避免该事件造成的伤害或者减小该事件的伤害。
在一个可选地实施例中，在获取与目标事件对应的配置信息之前，若每一次遭遇攻击事件都能为非玩家角色带来进化，那么就会造成非玩家角色过于强大，在游戏玩家角色与非玩家角色对战时，游戏难度过大，从而影响游戏玩家的体验，降低其玩游戏的兴趣。
为了克服上述问题，本申请的上述装置还可以包括：第二获取单元，被设置为在第一获取单元获取与目标事件对应的配置信息之前，获取与第 一角色的等级对应的进化概率，其中，进化概率为允许第二角色获取用于应对目标事件的属性的概率；其中，在进化概率大于预设概率的情况下，指示第一获取单元获取与目标事件对应的配置信息。
在另一个可选地实施例中，第一获取单元包括：第一确定模块，被设置为确定用于应对目标事件第一属性，根据第一属性确定配置信息，其中，第一属性用于指示在目标事件发生的情况下，目标事件对第二角色的目标属性值的修改程度小于对第一角色的目标属性值的修改程度，配置信息用于配置第一属性的各个参数；第二确定模块，被设置为确定用于应对目标事件第二属性，根据第二属性确定配置信息，其中，第二属性用于指示在目标事件即将发生的情况下，执行用于避免目标事件发生的防御事件，配置信息用于配置第二属性的各个参数。
在实际应用中，可以根据实际需要确定是配置上述的第一属性还是第二属性，具体可以根据具体的目标事件确定。例如，对于由玩家发起的攻击事件(可能会造成非玩家角色掉血)，此时就可以配置用户的防御属性(即第一属性)，避免在受到攻击时掉血或者减少掉血；再如，对于用户发起的抢夺武器的目标事件，则可以配置非玩家角色的逃跑属性(即第二属性)，在通过玩家角色的某些行为判断出其即将发起抢夺武器的目标事件时，触发非玩家角色的逃跑属性，逃跑远离玩家角色(即防御事件)；再如，在非玩家角色触碰到障碍物(也即游戏环境对第一角色的目标属性值进行修改的目标事件)时，也可能对玩家的某些属性(如生命值)造成影响，此时也可能触发进化出第二属性，在新出生的非玩家角色触碰到障碍物之前，主动检测确定障碍物的位置，实时避让障碍物(即执行用于避免目标事件发生的防御事件)，避免障碍物的伤害。
可选地，上述的配置第一属性和第二属性，可以是指新增第一属性或者第二属性，也可以是重新配置第一属性或者第二属性的属性参数，让对应的防御技能更强，例如加快逃跑的速度等。
在上述实施例中，在确定用于应对目标事件第一属性或第二属性时， 可以参考其它玩家遇到相同事件的处理方式，进而确定哪些属性时第一属性或者第二属性。具体可以通过第一确定模块实现，第一确定模块还被设置为在检测到关联于玩家角色的目标事件被执行时，在目标事件对玩家角色的目标属性值的修改程度小于对第一角色的目标属性值的修改程度的情况下，保存玩家角色在应对目标事件时所使用的属性为第一属性，并保存玩家角色所使用的属性的各个参数。
可选地，在确定用于应对目标事件第一属性或第二属性时，也可以由游戏开发商自己定义用于应付目标事件的技能属性。
可选地，配置单元还被设置为在生成第二角色时，使用配置信息对同时生成的多个第二角色的属性进行配置，其中，多个第二角色归属于同一等级，且多个第二角色用于补充至游戏中。
相关技术中的进化思路都是基于AI个体的设计，每个AI个体在出生时所具备的技能属性都是完全相同的，AI个体在训练过程中提升，随着AI个体在训练中的提升，其外观等也会产生相应的变化，这样用户就可以根据其外观等判断个体AI的战斗力等信息，从而采用针对性的处理方式。
在本申请中，每一代新出生的AI个体都是参照已死亡的AI(或者受到过攻击的AI)的经验进化出相应的技能属性，这就会造成每一代AI的技能属性各不相同，实现了对AI种群进行进化的设计，这样在游戏玩家与AI进行对战时，就无法判断出AI技能的高低。
此处需要说明的是，上述模块与对应的步骤所实现的示例和应用场景相同，但不限于上述实施例所公开的内容。需要说明的是，上述模块作为装置的一部分可以运行在如图3所示的硬件环境中，可以通过软件实现，也可以通过硬件实现，其中，硬件环境包括网络环境。
根据本申请实施例，还提供了一种用于实施上述角色的配置方法的电子装置。
图10是根据本申请实施例的一种电子装置的结构框图，如图10所示，该电子装置可以包括：一个或多个(图中仅示出一个)处理器1001、存储器1003、以及传输装置1005，如图10所示，该电子装置还可以包括输入输出设备1007。
其中，存储器1003可被设置为存储计算机程序以及模块，如本申请实施例中的角色的配置方法和装置对应的程序指令/模块，处理器1001被设置为通过运行存储在存储器1003内的计算机程序以及模块，从而执行各种功能应用以及数据处理，即实现上述的角色的配置方法。存储器1003可包括高速随机存储器，还可以包括非易失性存储器，如一个或者多个磁性存储装置、闪存、或者其他非易失性固态存储器。在一些实例中，存储器1003可进一步包括相对于处理器1001远程设置的存储器，这些远程存储器可以通过网络连接至终端。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
上述的传输装置1005被设置为经由一个网络接收或者发送数据，还可以被设置为处理器与存储器之间的数据传输。上述的网络具体实例可包括有线网络及无线网络。在一个实例中，传输装置1005包括一个网络适配器(Network Interface Controller，NIC)，其可通过网线与其他网络设备与路由器相连从而可与互联网或局域网进行通讯。在一个实例中，传输装置1005为射频(Radio Frequency，RF)模块，其被设置为通过无线方式与互联网进行通讯。
其中，可选地，存储器1003被设置为存储应用程序。
处理器1001可以通过传输装置1005调用存储器1003存储的应用程序，以执行下述步骤：检测到游戏中与第一角色关联的目标事件，其中，第一角色为在游戏中生成的采用人工智能与玩家角色对玩的非玩家角色，目标事件用于指示修改第一角色的目标属性值；获取与目标事件对应的配置信息，其中，配置信息用于配置第二角色，以使配置后的第二角色在应对目标事件时，目标事件对第二角色的目标属性值的修改程度小于第一角 色在应对目标事件时对第一角色的目标属性值的修改程度，第二角色为游戏中待生成的非玩家角色；在生成第二角色时，使用配置信息对第二角色进行配置。
采用本申请实施例，在检测到游戏中对第一角色发起的目标事件时，获取与目标事件对应的配置信息，并通过该配置信息对生成的第二角色进行配置，以使配置后的第二角色在应对目标事件时，减小目标事件对第二角色的目标属性值的修改程度，这样，随着非玩家角色的进化，每一次出生的新角色虽然具备相同的初始外形，但是会具备新的技能属性，对于游戏中的大量非玩家角色，由于出生时间不同，其所具备的技能属性也不尽相同，在应对相同的事件时所使用的技能属性也不相同，使得游戏角色不能通过多次尝试之后，确定非玩家角色在应对固定事件时采用的技能属性，可以解决了相关技术中人工智能角色的运行机制能够被知晓的技术问题，进而达到避免人工智能角色的运行机制被知晓的技术效果。
可选地，本实施例中的具体示例可以参考上述实施例中所描述的示例，本实施例在此不再赘述。
本领域普通技术人员可以理解，图10所示的结构仅为示意，终端可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌上电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。图10其并不对上述电子装置的结构造成限定。例如，终端还可包括比图10中所示更多或者更少的组件(如网络接口、显示装置等)，或者具有与图10所示不同的配置。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令终端设备相关的硬件来完成，该程序可以存储于一计算机可读存储介质中，存储介质可以包括：闪存盘、只读存储器(Read-Only Memory，ROM)、随机存取器(Random Access Memory，RAM)、磁盘或光盘等。
本申请的实施例还提供了一种存储介质。可选地，在本实施例中，上 述存储介质中存储有计算机程序，其中，所述计算机程序被设置为运行时执行角色的配置方法。
可选地，在本实施例中，上述存储介质可以位于上述实施例所示的网络中的多个网络设备中的至少一个网络设备上。
可选地，在本实施例中，存储介质被设置为存储用于执行以下步骤的程序代码：
S1，检测到游戏中与第一角色关联的目标事件，第一角色为在游戏中生成的采用人工智能与玩家角色对玩的非玩家角色，目标事件用于指示修改第一角色的目标属性值；
S2，获取与目标事件对应的配置信息，配置信息用于配置第二角色，以使配置后的第二角色在应对目标事件时，目标事件对第二角色的目标属性值的修改程度小于第一角色在应对目标事件时对第一角色的目标属性值的修改程度，第二角色为游戏中待生成的非玩家角色；
S3，在生成第二角色时，使用配置信息对第二角色进行配置。
可选地，本实施例中的具体示例可以参考上述实施例中所描述的示例，本实施例在此不再赘述。
可选地，在本实施例中，上述存储介质可以包括但不限于：U盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
上述实施例中的集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在上述计算机可读取的存储介质中。基于这样的理解，本申请的技术方案本质上或者说对相关技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计 算机软件产品存储在存储介质中，包括若干指令用以使得一台或多台计算机设备(可为个人计算机、服务器或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。
在本申请的上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。
在本申请所提供的几个实施例中，应该理解到，所揭露的客户端，可通过其它的方式实现。其中，以上所描述的装置实施例仅仅是示意性的，例如所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，单元或模块的间接耦合或通信连接，可以是电性或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
以上所述仅是本申请的优选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本申请原理的前提下，还可以做出若干改进和润饰，这些改进和润饰也应视为本申请的保护范围。

Claims (16)

  1. 一种角色的配置方法，包括：
    检测到游戏中与第一角色关联的目标事件，其中，所述第一角色为在所述游戏中生成的采用人工智能与玩家角色对玩的非玩家角色，所述目标事件用于指示修改所述第一角色的目标属性值；
    获取与所述目标事件对应的配置信息，其中，所述配置信息用于配置第二角色，以使配置后的所述第二角色在应对所述目标事件时，所述目标事件对所述第二角色的目标属性值的修改程度小于所述第一角色在应对所述目标事件时对所述第一角色的目标属性值的修改程度，所述第二角色为所述游戏中待生成的非玩家角色；
    在生成所述第二角色时，使用所述配置信息对所述第二角色进行配置。
  2. 根据权利要求1所述的方法，其中，获取与所述目标事件对应的配置信息包括：
    确定用于应对所述目标事件第一属性，根据所述第一属性确定所述配置信息，其中，所述第一属性用于指示在所述目标事件发生的情况下，所述目标事件对所述第二角色的目标属性值的修改程度小于对所述第一角色的目标属性值的修改程度，所述配置信息用于配置所述第一属性的各个参数；和/或
    确定用于应对所述目标事件第二属性，根据所述第二属性确定所述配置信息，其中，所述第二属性用于指示在所述目标事件即将发生的情况下，执行用于避免所述目标事件发生的防御事件，所述配置信息用于配置所述第二属性的各个参数。
  3. 根据权利要求2所述的方法，其中，确定用于应对所述目标事件第一属性包括：
    在检测到关联于所述玩家角色的所述目标事件被执行时，在所述 目标事件对所述玩家角色的目标属性值的修改程度小于对所述第一角色的目标属性值的修改程度的情况下，保存所述玩家角色在应对所述目标事件时所使用的属性为所述第一属性，并保存所述玩家角色所使用的属性的各个参数。
  4. 根据权利要求1至3中任意一项所述的方法，其中，在获取与所述目标事件对应的配置信息之前，所述方法还包括：
    获取与所述第一角色的等级对应的进化概率，其中，所述进化概率为允许所述第二角色获取用于应对所述目标事件的属性的概率；
    其中，在所述进化概率大于预设概率的情况下，执行获取与所述目标事件对应的配置信息的步骤。
  5. 根据权利要求1所述的方法，其中，在生成所述第二角色时，使用所述配置信息对所述第二角色进行配置包括：
    在生成所述第二角色时，使用所述配置信息对同时生成的多个所述第二角色的属性进行配置，其中，多个所述第二角色归属于同一等级，且多个所述第二角色用于补充至所述游戏中。
  6. 根据权利要求1所述的方法，其中，检测游戏中第一角色关联的目标事件包括：
    在所述第一角色与所述玩家角色对玩时，检测到所述玩家角色对所述第一角色发起攻击产生的所述目标事件；
    在所述第一角色处于所述游戏的地图中的目标位置时，检测到所述目标位置的游戏环境对所述第一角色的所述目标属性值进行修改的所述目标事件。
  7. 根据权利要求6所述的方法，其中，检测到所述玩家角色对所述第一角色发起攻击产生的所述目标事件包括：
    检测到所述玩家角色对所述第一角色发起攻击的第一事件，其中，所述第一事件用于减少所述第一角色的所述目标属性值至第一数值， 所述第一数值小于所述第一角色的目标属性极大值，且不小于所述第一角色的目标属性极小值；和/或，
    检测到所述玩家角色对所述第一角色发起攻击的第二事件，其中，所述第二事件用于将所述第一角色的所述目标属性值降低第二数值，所述第二数值为正数。
  8. 根据权利要求7所述的方法，其中，检测到所述玩家角色对所述第一角色发起攻击的第一事件包括：
    检测由所述玩家角色发起的，且用于减少所述第一角色的所述目标属性值至所述目标属性极小值的所述第一事件。
  9. 一种角色的配置装置，包括一个或多个处理器，以及一个或多个存储程序单元的存储器，其中，所述程序单元由所述处理器执行，所述程序单元包括：
    检测单元，被设置为检测到游戏中与第一角色关联的目标事件，其中，所述第一角色为在所述游戏中生成的采用人工智能与玩家角色对玩的非玩家角色，所述目标事件用于指示修改所述第一角色的目标属性值；
    第一获取单元，被设置为获取与所述目标事件对应的配置信息，其中，所述配置信息用于配置第二角色，以使配置后的所述第二角色在应对所述目标事件时，所述目标事件对所述第二角色的目标属性值的修改程度小于所述第一角色在应对所述目标事件时对所述第一角色的目标属性值的修改程度，所述第二角色为所述游戏中待生成的非玩家角色；
    配置单元，被设置为在生成所述第二角色时，使用所述配置信息对所述第二角色进行配置。
  10. 根据权利要求9所述的装置，其中，所述第一获取单元包括：
    第一确定模块，被设置为确定用于应对所述目标事件第一属性，根据所述第一属性确定所述配置信息，其中，所述第一属性用于指示 在所述目标事件发生的情况下，所述目标事件对所述第二角色的目标属性值的修改程度小于对所述第一角色的目标属性值的修改程度，所述配置信息用于配置所述第一属性的各个参数；和/或
    第二确定模块，被设置为确定用于应对所述目标事件第二属性，根据所述第二属性确定所述配置信息，其中，所述第二属性用于指示在所述目标事件即将发生的情况下，执行用于避免所述目标事件发生的防御事件，所述配置信息用于配置所述第二属性的各个参数。
  11. 根据权利要求10所述的装置，其中，所述第一确定模块还被设置为在检测到关联于所述玩家角色的所述目标事件被执行时，在所述目标事件对所述玩家角色的目标属性值的修改程度小于对所述第一角色的目标属性值的修改程度的情况下，保存所述玩家角色在应对所述目标事件时所使用的属性为所述第一属性，并保存所述玩家角色所使用的属性的各个参数。
  12. 根据权利要求9至11中任意一项所述的装置，其中，所述装置还包括：
    第二获取单元，被设置为在所述第一获取单元获取与所述目标事件对应的配置信息之前，获取与所述第一角色的等级对应的进化概率，其中，所述进化概率为允许所述第二角色获取用于应对所述目标事件的属性的概率；
    其中，在所述进化概率大于预设概率的情况下，指示所述第一获取单元获取与所述目标事件对应的配置信息。
  13. 根据权利要求9所述的装置，其中，所述配置单元还被设置为在生成所述第二角色时，使用所述配置信息对同时生成的多个所述第二角色的属性进行配置，其中，多个所述第二角色归属于同一等级，且多个所述第二角色用于补充至所述游戏中。
  14. 根据权利要求9所述的装置，其中，所述检测单元包括：
    第一检测模块，被设置为在所述第一角色与所述玩家角色对玩时， 检测到所述玩家角色对所述第一角色发起攻击产生的所述目标事件；
    第二检测模块，被设置为在所述第一角色处于所述游戏的地图中的目标位置时，检测到所述目标位置的游戏环境对所述第一角色的所述目标属性值进行修改的所述目标事件。
  15. 一种存储介质，其中，所述存储介质中存储有计算机程序，所述计算机程序被设置为运行时执行所述权利要求1至8任一项中所述的方法。
  16. 一种电子装置，包括存储器和处理器，其中，所述存储器中存储有计算机程序，所述处理器被设置为通过所述计算机程序执行所述权利要求1至8任一项中所述的方法。
PCT/CN2018/082513 2017-04-20 2018-04-10 角色的配置方法及装置、存储介质以及电子装置 WO2018192395A1 (zh)

Priority Applications (6)

Application Number Priority Date Filing Date Title
JP2019534753A JP7187460B2 (ja) 2017-04-20 2018-04-10 キャラクターの配置方法及び装置、記憶媒体並びに電子装置
EP18788559.5A EP3613482A4 (en) 2017-04-20 2018-04-10 CHARACTER CONFIGURATION METHOD AND APPARATUS, STORAGE MEDIA AND ELECTRONIC APPARATUS
KR1020197020698A KR102348015B1 (ko) 2017-04-20 2018-04-10 캐릭터 구성 방법 및 장치, 저장 매체 및 전자 장치
US16/445,694 US11620536B2 (en) 2017-04-20 2019-06-19 Character configuration method and apparatus, storage medium, and electronic apparatus
US18/107,918 US12026629B2 (en) 2017-04-20 2023-02-09 Generation-based evolution of non-player characters in a game
US18/636,062 US20240256907A1 (en) 2017-04-20 2024-04-15 Evolution of non-player characters

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710261467.5A CN107019912B (zh) 2017-04-20 2017-04-20 角色的配置方法和装置
CN201710261467.5 2017-04-20

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/445,694 Continuation US11620536B2 (en) 2017-04-20 2019-06-19 Character configuration method and apparatus, storage medium, and electronic apparatus

Publications (1)

Publication Number Publication Date
WO2018192395A1 true WO2018192395A1 (zh) 2018-10-25

Family

ID=59526434

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/082513 WO2018192395A1 (zh) 2017-04-20 2018-04-10 角色的配置方法及装置、存储介质以及电子装置

Country Status (7)

Country Link
US (3) US11620536B2 (zh)
EP (1) EP3613482A4 (zh)
JP (1) JP7187460B2 (zh)
KR (1) KR102348015B1 (zh)
CN (1) CN107019912B (zh)
MA (1) MA51444A (zh)
WO (1) WO2018192395A1 (zh)

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107019912B (zh) 2017-04-20 2020-12-01 腾讯科技（深圳）有限公司 角色的配置方法和装置
CN107450957B (zh) * 2017-08-09 2020-10-27 网易（杭州）网络有限公司 游戏配置的处理方法、装置、存储介质、处理器及终端
CN107694091A (zh) * 2017-08-23 2018-02-16 杭州电魂网络科技股份有限公司 游戏数据处理方法及系统
CN107890675A (zh) * 2017-11-13 2018-04-10 杭州电魂网络科技股份有限公司 Ai行为实现方法和装置
CN108211357A (zh) * 2018-01-15 2018-06-29 腾讯科技（上海）有限公司 虚拟控制对象的控制方法、装置、存储介质和电子装置
US20190385090A1 (en) * 2018-06-14 2019-12-19 Honeywell International Inc. Systems and methods for using artificial intelligence models to identify a current threat scenario
CN110215710B (zh) * 2019-06-05 2023-04-14 网易（杭州）网络有限公司 游戏中事件确定方法及装置、电子设备和存储介质
CN110292773B (zh) * 2019-07-04 2023-03-21 珠海西山居数字科技有限公司 一种角色运动跟随方法及装置、计算设备及存储介质
KR102579203B1 (ko) * 2019-12-31 2023-09-15 한국전자통신연구원 게임 결과 예측 장치 및 방법
CN111760294B (zh) * 2020-07-07 2023-10-13 网易(上海)网络有限公司 控制游戏中非玩家游戏角色的方法及装置
CN112774200B (zh) 2021-01-22 2023-05-09 北京字跳网络技术有限公司 角色交互控制方法、装置、计算机设备以及存储介质
CN113952726A (zh) * 2021-07-12 2022-01-21 海南元游信息技术有限公司 一种虚拟游戏对象的行为控制方法、装置、设备以及存储介质
US11724194B2 (en) * 2021-07-28 2023-08-15 Blizzard Entertainment, Inc. Initial results of a reinforcement learning model using a heuristic
CN113577781B (zh) * 2021-07-30 2023-06-16 腾讯科技（深圳）有限公司 非玩家角色npc的控制方法、装置、设备及介质
JP7295999B1 (ja) 2022-07-22 2023-06-21 株式会社Cygames プログラム、情報処理装置、方法、及びシステム

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103472756A (zh) * 2013-09-27 2013-12-25 腾讯科技（深圳）有限公司 一种实现人工智能的方法、服务器和设备
CN103785170A (zh) * 2012-10-26 2014-05-14 株式会社得那 游戏提供装置
CN105561578A (zh) * 2015-12-11 2016-05-11 北京像素软件科技股份有限公司 一种非玩家控制角色npc的行为决策方法
US20160279522A1 (en) * 2015-03-26 2016-09-29 Warner Bros. Entertainment, Inc. Nemesis characters, nemesis forts, social vendettas and followers in computer games
CN107019912A (zh) * 2017-04-20 2017-08-08 腾讯科技（深圳）有限公司 角色的配置方法和装置

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7452279B2 (en) * 2001-08-09 2008-11-18 Kabushiki Kaisha Sega Recording medium of game program and game device using card
KR100850913B1 (ko) * 2006-12-05 2008-08-07 한국전자통신연구원 게임 캐릭터 형성방법
EP2327050A4 (en) * 2008-07-22 2017-10-04 Daybreak Game Company LLC System and method for progressing character abilities in a simulation
US20100056275A1 (en) * 2008-09-04 2010-03-04 United States Of America As Represented By The Secretary Of The Army Massively Multiplayer Online Game Technologies
KR101231798B1 (ko) * 2009-04-30 2013-02-08 한국전자통신연구원 게임 난이도 조절 장치 및 방법
US9452363B2 (en) * 2013-10-18 2016-09-27 Sony Interactive Entertainment America Llc Multi-player video game environment for single-player use
CN104102522B (zh) * 2014-07-30 2017-11-07 厦门大学 交互式游戏中智能非玩家角色的人工情感驱动方法
JP5827434B2 (ja) * 2015-04-13 2015-12-02 グリー株式会社 コンピュータプログラム、ゲームシステム、及びその制御方法
US10213688B2 (en) * 2015-08-26 2019-02-26 Warner Bros. Entertainment, Inc. Social and procedural effects for computer-generated environments
CN106371797A (zh) * 2016-08-31 2017-02-01 腾讯科技（深圳）有限公司 配置音效的方法及装置
CN106390456B (zh) * 2016-09-30 2018-09-18 腾讯科技（深圳）有限公司 游戏中角色行为的生成方法和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103785170A (zh) * 2012-10-26 2014-05-14 株式会社得那 游戏提供装置
CN103472756A (zh) * 2013-09-27 2013-12-25 腾讯科技（深圳）有限公司 一种实现人工智能的方法、服务器和设备
US20160279522A1 (en) * 2015-03-26 2016-09-29 Warner Bros. Entertainment, Inc. Nemesis characters, nemesis forts, social vendettas and followers in computer games
CN105561578A (zh) * 2015-12-11 2016-05-11 北京像素软件科技股份有限公司 一种非玩家控制角色npc的行为决策方法
CN107019912A (zh) * 2017-04-20 2017-08-08 腾讯科技（深圳）有限公司 角色的配置方法和装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3613482A4

Also Published As

Publication number Publication date
US12026629B2 (en) 2024-07-02
EP3613482A1 (en) 2020-02-26
EP3613482A4 (en) 2020-11-04
KR102348015B1 (ko) 2022-01-05
US11620536B2 (en) 2023-04-04
JP7187460B2 (ja) 2022-12-12
US20240256907A1 (en) 2024-08-01
JP2020504653A (ja) 2020-02-13
CN107019912A (zh) 2017-08-08
KR20190097177A (ko) 2019-08-20
US20230186110A1 (en) 2023-06-15
US20190303769A1 (en) 2019-10-03
CN107019912B (zh) 2020-12-01
MA51444A (fr) 2020-02-26

Similar Documents

Publication Publication Date Title
WO2018192395A1 (zh) 角色的配置方法及装置、存储介质以及电子装置
US11173400B2 (en) Data exchange method and apparatus, storage medium and electronic device
US12121822B2 (en) Method, apparatus, and terminal for transmitting message in multiplayer online battle program, and medium
WO2022033209A1 (zh) 虚拟角色的控制方法、装置、存储介质及计算机设备
US9361067B1 (en) System and method for providing a software development kit to enable configuration of virtual counterparts of action figures or action figure accessories
CN112870721B (zh) 一种游戏互动方法、装置、设备及存储介质
JP2004065987A (ja) グループの相互作用によりキャラクタグループの動作を修正する電子装置および方法
US20240216815A1 (en) Method and apparatus for controlling virtual race car, storage medium, and device
WO2022165991A1 (zh) 游戏中进行信号播报的方法、装置、电子设备及存储介质
US12226704B2 (en) Virtual operation object control method and apparatus, storage medium, and electronic device
US20230019216A1 (en) Method and apparatus for controlling virtual object, and storage medium
KR20220157930A (ko) 가상 보상 자원에 대한 할당 방법 및 장치, 전자 장치, 컴퓨터 판독 가능 저장 매체 및 컴퓨터 프로그램 제품
US8480492B2 (en) Game device, game control method, and game control program for controlling game in which player's character located in game field is manipulated
JP6577706B2 (ja) ゲームプログラムおよびゲームシステム
Udagawa et al. Fighting zombies in minecraft with deep reinforcement learning
Lukina et al. Resilient control and safety for cyber-physical systems
US20240350922A1 (en) Method and apparatus for interaction in virtual scene, electronic device, computer-readable storage medium, and computer program product
US20240293744A1 (en) Virtual world-based capture information display method and apparatus, device, and medium
Winnicka The opponent’s movement mechanism in simple games using heuristic method
CN118718405A (zh) 虚拟对象的控制方法和装置、存储介质及电子设备
CN119215412A (zh) 虚拟场景中的交互方法、装置、设备、介质及程序产品
CN119185941A (zh) 虚拟角色的控制方法和装置、存储介质及电子设备
CN118787950A (zh) 虚拟对象的控制方法和装置、存储介质及电子设备
Papahristou Decision making in multiplayer environments: application in backgammon variants

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18788559

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2019534753

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20197020698

Country of ref document: KR

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2018788559

Country of ref document: EP

Effective date: 20191120