CN112619125A

CN112619125A - Game artificial intelligence module using method and electronic equipment

Info

Publication number: CN112619125A
Application number: CN202011628597.6A
Authority: CN
Inventors: 张杨
Original assignee: Shenzhen Idreamsky Technology Co ltd
Current assignee: Shenzhen Idreamsky Technology Co ltd
Priority date: 2020-12-30
Filing date: 2020-12-30
Publication date: 2021-04-09
Anticipated expiration: 2040-12-30
Also published as: CN112619125B

Abstract

The application discloses a use method of a game artificial intelligence module and electronic equipment. The game artificial intelligence module is used for achieving the intelligent function of the game unit on the map. The artificial intelligence module can determine the behavior means of the game unit according to the acquired sensing information, and the game unit or the map can determine the behavior of the game unit according to the behavior means, so that the game artificial intelligence module decoupled from the map data is realized. Furthermore, the artificial intelligence module disclosed by the application can realize cross-map multiplexing, cross-role multiplexing and cross-game unit multiplexing, so that the workload of developers is reduced, and the working efficiency is improved.

Description

Game artificial intelligence module using method and electronic equipment

Technical Field

The application relates to the field of artificial intelligence, in particular to a use method of a game artificial intelligence module and electronic equipment.

Background

With the development of computer technology and the ever-increasing cultural demands of people, games, especially timely strategy games, are sought after by a large number of players due to their excellent antagonism. The game's antagonism depends largely on the quality of the decision-making behaviour of the game units of the non-player character within the game against which the player is confronted.

At present, when the industry develops games, an independent game Artificial Intelligence (AI) module is not provided, and the game artificial intelligence is directly integrated into a map editor. The map editor provides a developer with a series of instructions for instructing the game unit of the non-player character to execute fixed instructions such as producing a unit, patrolling the unit along a specified path, and the like.

When a developer generates a game map for a game edition, the developer can combine logic control structures such as a timer and condition judgment with the AI instruction to realize the intelligent functions of the non-player character and/or the game unit and complete the AI module edition of the game map. When a developer edits and generates another game map for the game, an AI module needs to be newly manufactured for the new game map according to a logic control structure in the new game map and by combining an AI instruction.

If a large amount of game maps need to be developed for a game, even if a large number of logic control structures in the game maps have similarities, AI modules in the game maps need to be adjusted and modified one by one in the development process, and a developer needs to pay a great deal of work, so that the development efficiency is very low.

Disclosure of Invention

The application provides a use method of a game artificial intelligence module and electronic equipment, so that one AI module can be reused in a plurality of game maps in a game, the workload of developers is reduced, and the development efficiency is improved.

In a first aspect, the present application provides a method for using a game artificial intelligence module, the method comprising: the electronic equipment loads a first map and a first game artificial intelligence module, wherein the first map comprises a first game unit, and the first game artificial intelligence module is a module for realizing a map intelligence function; the electronic equipment determines a first behavior of the first game unit according to the first game artificial intelligence module; the electronic equipment loads a second map, and the second map comprises a second game unit; the electronic equipment determines a second behavior of the second game unit according to the first game artificial intelligence module, wherein the first behavior is different from the second behavior.

In the embodiment, the game artificial intelligence module for realizing the game map intelligentization function is independent, so that developers do not need to repeatedly adjust and modify the game artificial intelligence module in each game map when developing different game maps, and the workload of the developers is reduced.

With reference to some embodiments of the first aspect, in some embodiments, the electronic device determines first perception information of a first game unit according to a field of view of the first game unit; the electronic equipment determines a first behavior means of the first game unit according to the first sensing information and the first game artificial intelligence module; the electronic equipment determines a first behavior of the first game unit according to the first behavior means.

In the above-described embodiment, the behavior of the game unit is determined by the sensory information of the game unit, and an intelligent function of the game unit can be realized. Compared with the traditional AI and the trigger, the intelligent function of the game unit is realized, the intelligent function of the game unit is determined through the sensing information of the game unit, the intelligent function of the game unit is more perfect, and the game confrontation experience of the player can be improved.

With reference to some embodiments of the first aspect, in some embodiments, the electronic device determines second perception information of a second game unit according to a field of view of the second game unit; the electronic equipment determines a second behavior means of the second game unit according to the second perception information and the first game artificial intelligence module; the electronic equipment determines the second behavior of the first game unit according to the second behavior means.

In the above-described embodiment, the behavior of the game unit is determined by the sensory information of the game unit, and the process of the intelligentized function of the game unit can be realized independently of the map data. The game unit makes different behaviors on different maps according to different perception information, cross-map multiplexing of the game artificial intelligence module is achieved, and workload of game map development is reduced.

With reference to some embodiments of the first aspect, in some embodiments, the electronic device determines the first behavior of the first gaming unit based on the first perception information, the first gaming artificial intelligence module, and a decision parameter, the decision parameter including some or all of the gaming parameters of the first gaming unit.

In the embodiment, considering that in some special cases, for example, the electronic device cannot determine the behavior of the game unit according to the perception information, the electronic device may acquire the game parameters of the game unit for determining the behavior means of the game unit, so that the robustness of the game AI module in use can be effectively improved.

With reference to some embodiments of the first aspect, in some embodiments, the electronic device determines a third behavior of a third game unit according to the first game artificial intelligence module, the third game unit being a different game unit on the first map than the first game unit.

In the embodiment, the game AI module can realize the multiplexing of the cross game units, further reduce the workload of realizing the intelligent functions of the game units when developing the game map and improve the development efficiency.

In combination with some embodiments of the first aspect, in some embodiments, the third gaming unit belongs to a different or the same non-player character as the first gaming unit.

In the above embodiment, the game AI module can realize the intelligent functions of different non-player characters, realize cross-character multiplexing, further reduce the workload of realizing the intelligent functions of the game unit when developing the game map, and improve the development efficiency.

In some embodiments, in combination with some embodiments of the first aspect, the first game artificial intelligence module comprises a behavior tree and/or a state machine.

In the embodiment, the first game artificial intelligence module can be formed by the behavior tree and/or the state machine, so that the development difficulty of the game artificial intelligence module is reduced, and the development efficiency is improved.

In a second aspect, an embodiment of the present application provides an electronic device, including: one or more processors and memory; the memory is coupled with the one or more processors, the memory for storing computer program code comprising computer instructions, the one or more processors invoking the computer instructions to cause the electronic device to perform the method as described in the first aspect and any possible implementation of the first aspect.

In a third aspect, an embodiment of the present application provides a chip system, where the chip system is applied to an electronic device, and the chip system includes one or more processors, and the processor is configured to invoke a computer instruction to cause the electronic device to perform a method as described in the first aspect and any possible implementation manner of the first aspect.

In a fourth aspect, embodiments of the present application provide a computer program product including instructions, which, when run on an electronic device, cause the electronic device to perform the method described in the first aspect and any possible implementation manner of the first aspect.

In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, which includes instructions that, when executed on an electronic device, cause the electronic device to perform the method described in the first aspect and any possible implementation manner of the first aspect.

It is understood that the electronic device provided by the second aspect, the chip system provided by the third aspect, the computer program product provided by the fourth aspect, and the computer storage medium provided by the fifth aspect are all used to execute the method provided by the embodiments of the present application. Therefore, the beneficial effects achieved by the method can refer to the beneficial effects in the corresponding method, and are not described herein again.

Drawings

Fig. 1 shows an exemplary schematic diagram of one category of game AI modules in the embodiment of the present application.

FIG. 2 illustrates an exemplary diagram of one method of using a behavior tree to which the present application relates.

Fig. 3 shows an exemplary schematic diagram of a game AI module architecture formed by a behavior tree according to the present application.

Fig. 4 shows an exemplary schematic diagram of a behavior tree multiplexing method according to the present application.

Fig. 5 is an exemplary diagram of a game map architecture in the prior art.

FIG. 6 is a schematic diagram of an exemplary architecture of the intelligent functions of gaming unit 2 of FIG. 5.

FIG. 7 is an exemplary diagram of a prior art scenario in which a gaming unit is added.

FIG. 8 is an exemplary diagram of a prior art intelligent function loading process for a gaming unit.

FIG. 9 is an exemplary diagram of a method for using a gaming artificial intelligence module provided by the present application

Fig. 10 is an exemplary schematic diagram of a game AI module multiplexing scenario in the embodiment of the present application.

Fig. 11 is another exemplary diagram of a game AI module multiplexing scenario in the embodiment of the present application.

Fig. 12 is a schematic diagram illustrating a method for using the game AI module according to an embodiment of the present disclosure.

Fig. 13 is a schematic diagram illustrating another usage method of the game AI module according to the embodiment of the present application.

Fig. 14 is a schematic structural diagram of an electronic device 100 according to an embodiment of the present application.

Fig. 15 is a schematic block diagram of a software structure of the electronic device 100 in the embodiment of the present application.

Fig. 16 is another schematic structural diagram of the electronic device 100 according to the embodiment of the present application.

Detailed Description

The terminology used in the following embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in the specification of the present application and the appended claims, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the listed items.

In the following, the terms "first", "second" are used for descriptive purposes only and are not to be understood as implying or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of embodiments of the application, unless stated otherwise, "plurality" means two or more. The terminology used in the description of the embodiments of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

For the sake of understanding, the related terms and related concepts related to the embodiments of the present application will be described below.

(1) A game AI module:

in the embodiment of the present application, the game AI module is a module for implementing an intelligent function of a game unit, or a module for implementing an intelligent function of a non-player character.

Wherein the intelligent function of the game unit comprises that the game unit can autonomously make at least one action without receiving the instruction of the player. Such as attack, escape, etc. by the gaming unit.

Wherein the intelligent functionality of the non-player character comprises that the non-player character controls the game unit of the non-player character to perform at least one action from a strategic level. For example, a non-player character instructs a plurality of game units to move, and the like.

The intelligent function of the game unit may be dependent on the intelligent function of the non-player character or independent of the intelligent function of the non-player character.

For convenience of description, it is considered that the intelligentization of the map includes the intelligentization function of the non-player character on the map and the intelligentization function of the game unit.

The game AI module is a system comprising a decision model and a behavior means set. The input of the system comprises perception information, and the system can select a decision model according to the perception information, and determine and output at least one behavior means from the behavior means set according to the decision model. The output of the game AI module is a pre-programmed behavior means that can occur to the in-game unit. The definition of the behavioral means that can occur is: in the case where the game unit is on a certain game map or a certain game scene, the game unit may determine at least one behavior means based on the perception information, and the game unit may make at least one specific behavior based on the at least one behavior means.

The game AI module may not have self-learning characteristics similar to those of machine learning. The perception information that the game AI module can acquire is limited and deterministic, i.e. the decision model that the game AI module can select is also limited and deterministic, i.e. the determinable behavior means of the game AI is also limited and deterministic.

In the embodiment of the application, the game AI module is configured with an interface, and the interface is used for data interaction. The data interaction includes a wide variety of data interactions, such as receiving perception information, sending behavior means, and the like, and is not limited herein. Correspondingly, an interface is configured on the game map and used for data interaction. Therefore, the game map can perform data interaction with the game AI module.

In some embodiments of the present application, the gaming unit and/or the non-player character are configured with an interface for data interaction. Therefore, the game map, the game AI module, the game unit and the non-player character can mutually perform data interaction.

In embodiments of the present application, the game AI module may be used to implement intelligent functionality for different game units within a single map and/or for the same game unit across multiple maps and/or for different game units across multiple maps.

The above-described related concepts are described in detail below:

1.1 gaming unit: the game map is the most basic unit in the game map and is the smallest unit in the game map which is responsible for executing the behavior means determined by the game AI module.

For example, the gaming units may include gaming units, terrain, objects, and the like. Wherein the game unit can be represented as a player character or a character which can be controlled by a non-player character in a game scene or a game map. The character may be a soldier, a group of tanks, etc.

The game parameters are basic parameters of the game unit and are used for distinguishing different types of game units, for example, buildings and scouts are configured with different game parameters and are different game units.

The non-player character to which the game unit belongs can acquire all game parameters of the game unit.

1.2 perception information: some or all of the game parameters of all of the game units (including the game units themselves) within the field of view of the game unit and/or the non-player character.

The field of view of the game unit may have various representations, which are not limited herein. For example, the field of view of a gaming unit may be the field of view of the gaming unit itself, or may be the union of the fields of view of the gaming unit and other gaming units sharing the field of view.

The field of view of the game unit may have a variety of determination methods, which are not limited herein. For example, the position of the game unit is used as the center of a circle, and the range covered by a sphere with the radius r is used as the visual field range of the game unit, wherein r is a positive number; or the position of the game unit is used as an origin, the visible distance and the visible angle are specified, and the range determined by the origin, the visible distance and the visible angle is used as the visual field range of the game unit.

Wherein, the perception information can be different according to different game rules designed by the game map in the game body. For example, in a game map, the perception information only includes the life value of the game unit within the visual field of the game unit; alternatively, the sensory information may include only the life value, the attack power, and the attack range of the game unit in the visual field of the game unit in the game map.

Similarly, the field of view of a non-player character is the union of the fields of view of the gaming units controlled by that non-player character.

Similarly, the manner of determining the field of view of the non-player character may refer to the manner of determining the field of view of the game unit, and will not be described herein again.

It should be noted that the perception information may be determined by the game AI module, may be determined by the game unit and/or the non-player character, or may be passed to the game AI module after being determined by the game map.

It should be noted that, in order to diversify the quality of the intelligent functions of different non-player characters, parameters of a decision model in a game AI module may be adjusted after one game AI module is developed, so as to implement the intelligent functions of non-player characters with various difficulty levels.

1.3 decision model: is a model for determining a behavioral measure. The input to the model may include perceptual information. The output of the decision model is a selection of at least one behavior measure from the behavior measures in the game AI module. There may be at least one decision model in one game AI module.

The decision model may be constructed by various methods, and is not limited herein. For example, the decision model can be constructed by methods such as a behavior tree and a state machine; the decision model can also be constructed by methods such as neural network and deep learning. The concept of the behavior tree can refer to the content in (2) the behavior tree in the term interpretation, and is not described herein again.

After the game AI module obtains the perception information and inputs the perception information into the decision model, the decision model may determine at least one behavior means from a set of behavior means in the game AI module.

In some embodiments of the present application, after obtaining the perception information, the game AI module may need other inputs, which are decision parameters. In this case, the game AI module requests the decision parameter at least once from the game unit, the non-player character to which the game unit belongs, or the game map, and determines the behavior of the game unit according to the decision parameter.

It will be appreciated that the decision model is independent of the game parameters of the game units, so that different game units may use the same decision model, i.e. different game units may use the same game AI module, thus providing support for the game AI module and the game map to be independent of each other.

It will be appreciated that, furthermore, because the decision-making model is independent of the parameters of the game unit, different non-player characters may use the same decision-making model, i.e. different non-player characters may use the same game AI module, thus providing support for the game AI module and the game map to be independent of each other.

1.4 behavior means: for instructing the gaming unit to perform at least one specific action. The behaviors comprise behavior means, behavior objects, behavior subjects and the like. The behavior means is a tool and a using method applied when the behavior subject acts on the behavior object.

The game unit may determine at least one behavior that can be executed after acquiring the behavior means determined by the game AI module. The game unit may obtain information in the game map, further obtain a behavior host and a behavior object, and determine at least one executed behavior according to the received behavior means. Wherein the game unit obtains information in a game map, the information can be determined through an interface provided by the map or scene.

The manner in which the game unit obtains the behavior means includes many ways, and after the game AI module determines the behavior means, for example, the game unit may obtain the behavior means through a map where the game unit is located, or the game unit may obtain the behavior means through a non-player character to which the game unit belongs, which is not limited herein.

The behavior means may have many expressions, and is not limited herein. For example, the behavioral means may be an attack, a mobile, a patrol, an escape, a skill in use, and the like.

The game unit may determine the behavior according to the behavior means, and the non-player character to which the game unit belongs and the game map may determine the game unit that performs the behavior and the behavior that the game unit performs according to the behavior means.

It can be understood that, since the behavior means does not relate to the behavior subject, the behavior object, and the like, the behavior means may also be independent of the game parameters of the game unit, that is, the behavior means is independent of the data on the game map, thereby also providing support for the game AI module and the game map to be independent of each other.

It can be understood that the behavior means is independent of the game parameters of the game units, so that different game units can use the same behavior means, and support is provided for multiplexing of the game AI module. The concept of game AI module multiplexing can refer to the text description in game AI module multiplexing (3) in the term explanation, and is not described herein again.

1.5 Game AI submodule:

the intelligent functions of the game unit can be divided into a plurality of different types of sub-intelligent functions according to different classification standards.

The game AI submodule is a module for realizing a sub-intelligent function of the game unit, that is, the game AI module may be synthesized by different types of game AI submodules, that is, the game AI module may be considered to include a plurality of game AI submodules.

In the game development process, different types of game AI sub-modules can be developed independently, and in the process of realizing the intelligent functions of different maps, the intelligent functions of the maps can be realized by combining at least one game AI sub-module. The intelligent function of the map means that the game units on the map have the intelligent function.

During the running process of the game, the game map can realize the intelligent functions of intelligent non-player roles and/or game units in the map according to the game AI submodule.

It can be understood that by classifying the intelligent functions, the development complexity of the game AI module is reduced and the workload of developers is reduced in the game development process.

For example, in an instant strategy game, game AI modules can be generally divided into 4 types of game AI sub-modules:

global AI submodule: for example, the global AI submodule may include: and the module realizes intelligent functions of resources (such as gold mine, treatment god symbols, treasure box and the like) in the map, game parameters (fertile, general, barren and the like) of the terrain in the map and the like. The set of behavior means corresponding to the global AI submodule may be related to a specific play in the game, and may not include behavior means of game units belonging to a player character or a non-player character, which is not limited herein.

A resource AI submodule: for example, the resource AI submodule may include: and the module realizes the intelligent functions of game buildings (barracks, factories, defense towers and the like), game units (heroes, soldiers, tanks and the like) and the like. The set of behavior means corresponding to the resource AI submodule may include behavior means of a game unit of a non-player character, and is not limited herein.

Group AI (also known as general AI) submodule: for example, the group AI submodule may include: and a module for realizing intelligent functions such as the state of a group (shield, attack, acceleration, and the like), the movement of the group (patrol, exploration, and the like), and the like. The set of behavior means corresponding to the group AI submodule may include behavior means of game units belonging to a player character and a non-player character, and is not limited herein. The set of behavior means corresponding to the group AI is characterized in that: the main body of the behavior means in the behavior means set corresponding to the group AI submodule can be a plurality of game units of the same type.

Element AI (may also be referred to as soldier AI) submodule: for example, the unit AI submodule may include: and a module for realizing intelligent functions such as behavior means (attack, escape, skill release, etc.) of a specific game unit. The set of behavior means corresponding to the unit AI submodule may include a part of behavior means belonging to a robot unit and a player unit, and is not limited herein. The behavior means set corresponding to the unit AI is characterized in that: the main body of the behavior means in the behavior means set corresponding to the unit AI submodule can be a game unit.

The game AI modules can also be classified as: the resource management AI submodule and the war AI submodule, wherein the behavior means set corresponding to the resource management AI comprises: building a game building, building a game unit, upgrading game technology and the like, wherein the set of behavior means corresponding to the war AI comprises: specific behavior means of the game unit, etc.

It can be understood that the game AI module is divided into a plurality of game AI submodules, so that the development work difficulty and the work load for realizing the game AI module are reduced.

Illustratively, as shown in fig. 1, in a certain game map, a game AI submodule is configured, wherein the game AI submodule includes game AI submodules of three types of intelligent functions, including: the overall AI submodule, the AI submodule of the robot 1 and the AI submodule of the robot 2. Any AI submodule can be composed of a behavior tree and/or a state machine.

For example, the AI submodule is composed of a plurality of behavior trees, wherein the behavior tree corresponding to the global AI submodule is used for indicating a map unit in the game unit to complete behaviors such as refreshing a static resource point and refreshing a dynamic resource point; the behavior tree corresponding to the AI submodule of the robot 1 is used for indicating that the game unit controlled by the robot 1 completes the behaviors of construction, production, attack and the like; the behavior tree corresponding to the AI submodule of the robot 2 is used to instruct the game unit controlled by the robot 2 to complete the behaviors of construction, production, attack, and the like.

(2) Behavior tree

2.1 behavior Tree:

the behavior tree is a tree structure, and in the present application, the behavior tree is a tree structure behavior means set that controls the behavior means of the game unit, that is, the behavior tree can be used as the minimum implementation unit of the game AI module, that is, the minimum implementation unit of the game AI submodule.

The behavior tree may determine at least one behavior measure from the input parameters. One game AI module may be implemented by at least one behavior tree. A game AI submodule may be implemented by at least one behavior tree.

One gaming unit intelligence function may correspond to one or more behavior trees. The output of each behavior tree corresponds to a behavior means set of at least one behavior means, wherein one behavior means is embodied as one or more specific behaviors in the game.

As shown in fig. 2, during the running of the game, the behavior tree may be loaded according to the configuration of the game body, and the loaded behavior tree may serve as a game AI module. Data required for the operation is collected for each behavior tree, and the data can be derived from static data on a game map, such as positions, game parameters of game units and the like, and can also be derived from dynamic data on the game map, such as game map time, game parameters of game units and the like.

When a game AI submodule needs to be closed or opened during game development or game running, a behavior tree corresponding to the game AI submodule can be enabled or disabled.

2.2 Structure of the behavior Tree:

the behavior tree includes nodes of a plurality of node types. The nodes of the behavior tree may be classified in various ways, which are not limited herein. Illustratively, the node types of the nodes of the behavior tree may include: leaf Nodes, Non-Leaf Nodes. Illustratively, the node types of the nodes of the behavior tree may include: composite node (Composite), decoration node (Decorator), Condition node (Condition), Action node (Action), etc. The node in the behavior tree may return the running result of the node itself to its parent node, where the running result may include: success, failure, operation.

Leaf nodes are nodes without children nodes, and non-leaf nodes are nodes with children nodes.

The composite node may be many types of nodes in the embodiments of the present application, for example, the composite node may be any one of a sequence node (sequence), a selection node (selctor), a Parallel node (parallell), and the like. The sequence node can execute the child nodes thereof according to the sequence from left to right, when all the child nodes return success, the sequence node returns success, when any child node returns failure, the sequence node returns failure, and when the child nodes are in operation, the sequence node returns operation; the selection node can execute the child nodes from left to right, returns success when any child node returns success, returns failure when all child nodes return failure, and returns operation when the child nodes run; and the parallel nodes execute all the child nodes in sequence, and determine a final return result according to the return values of the child nodes. The compound node may be a non-leaf node.

The decoration node may be many types of nodes in the embodiments of the present application, for example, the decoration node may be any one of an interrupt node (interrupt), an Inverter node (Inverter), a relay node (Repeater), and the like. The interrupt node has a conditional task, and when the conditional task is true, the interrupt node returns failure; and when the conditional task is false, the interrupt node returns the return result of the child node. When the child node of the inversion node returns success, the inversion node returns failure; when the child node of the inversion node returns failure, the inversion node returns success; when the child node of the inversion node is in operation, the inversion node returns to operation. The relay node may repeatedly execute the child node Num times, or the relay node may repeatedly execute the child node to know that the child node returns a specific value, or the relay node may repeatedly execute its child node all the time.

The condition node is used for judging the execution specific condition, when the specific condition is judged to be true, the child node is executed, and when the child node returns success, the condition node returns success; and when the specific condition is judged to be false, the child node is not executed, and the conditional node returns failure.

Fig. 3 shows an exemplary schematic diagram of a game AI architecture formed by a behavior tree according to the present application.

The behavior tree shown in FIG. 3 includes four non-leaf nodes and four leaf nodes, where the children of the root node are parallel nodes. The left child node of the parallel node is sequence node 1, and the right child node of the parallel node is sequence node 2. The left child node of the sequence node 1 is a condition 1, and the right child node of the sequence node 1 is a behavior means 1. The left child node of the sequence node 2 is the condition 2, and the left child node of the sequence node 2 is the behavior means 2.

The behavior tree has a plurality of driving modes, and is not limited herein. For example, the behavior tree may be event driven. Where the behavior tree is driven, the root node may receive perception information for selecting a decision. In the behavior tree shown in fig. 3, the selection decision may be either condition 1 or condition 2. The behavior tree may determine the value of condition 1 or condition 2 according to the sensing information, or may obtain a parameter that needs to determine the value of condition 1 or condition 2 by requesting the decision parameter, so as to determine the value of condition 1 or condition 2.

2.3 multiplexing of behavior trees:

the behavior tree can be used as a minimum implementation unit of the game AI, and an initialized behavior tree can be divided into at least one independent sub-tree, other behavior trees can be directly referenced, and the sub-trees can also be referenced. That is, multiplexing of the game AI can be realized by multiplexing of the subtrees.

The subtree can be divided in various ways, which is not limited herein. For example, the division of the subtrees may be according to the functional division implemented by the subtrees; or the division of the subtree can be divided according to decision parameters required for entering the subtree, and the like.

As shown in FIG. 4, the behavior tree includes a root node, a parallel node, and left and right child nodes of the parallel node. The left child node of the parallel node is a behavior tree 1, and the right child node of the parallel node is a behavior tree 2. The behavior tree 1 or the behavior tree 2 may be a behavior tree or a subtree of a behavior tree. The behavior tree 1 or the behavior tree 2 is used for participating in the construction of game AI modules of the game units and further for implementing game AI of the game units. One behavior tree may reference other behavior trees or subtrees of other behavior trees.

It can be understood that the game AI modules can be multiplexed through multiplexing of the subtrees, where the concept of multiplexing the game AI modules can refer to the content of (3) multiplexing the game AI modules in the term interpretation, and details are not described here.

2.4 data of behavior Tree:

there are many ways to organize the data of the behavior tree, and the data is not limited herein. For example, the data of the behavior tree may be based on a blackboard (blackboard); or the data of the behavior tree may be based on shared variables. The data of the behavior tree can also be stored on the nodes.

And based on the behavior tree of the blackboard, the subtrees of the behavior tree share the blackboard of the behavior tree, wherein the blackboard is used for storing data. There are various ways of storing data on the blackboard, and the storage is not limited herein. For example, data may be stored in a blackboard by way of key-value pairs. Nodes of the behavior tree may access the blackboard of the behavior tree through agreed fields, for example the fields may be (GroupID, Idx).

Based on a behavior tree that shares variables, multiple nodes in the behavior tree may reference the same variable.

Data in the blackboard and the shared variable can be communicated among the behavior trees, and support is provided for the behavior trees to realize sub-tree multiplexing.

For example, a game map contains 6 behavior trees, BT1, BT2, BT3, BT4, BT5, BT6, and each behavior tree is created with a corresponding blackboard: BB1, BB2, BB3, BB4, BB5, and BB 6. Each behavior tree may correspond to a robot. When the perception information is passed to the game AI module, the tree that should receive the perception information is BT2, BT2 saves the information into the corresponding blackboard BB2 or in the shared variable. When the behavior tree or the subtree of the behavior tree is in decision, reading data stored in a blackboard or reading data stored in a shared variable possibly needing to sense information; when the behavior tree or the subtree of the behavior tree is in decision making, a decision parameter is possibly needed, the behavior tree requests the decision parameter, and the received decision parameter is stored in a blackboard or a shared variable for decision making.

(3) Multiplexing of a game AI module:

the game AI module multiplexing may include: the at least two game maps can realize the intelligent functions of the game units in the respective game maps according to the same game AI module.

The game AI module multiplexing includes a wide variety of multiplexing modes, for example, the game AI module multiplexing may be cross map multiplexing, or the game AI module multiplexing may be cross character multiplexing, or the game AI module multiplexing may be cross game unit multiplexing. The game AI module multiplexing may include many multiplexing modes, which are not limited herein.

Wherein the cross-map multiplexing comprises: in different game maps, the game units and/or the non-player characters can realize respective intelligent functions according to the same game AI module.

For example, a campaign for a game may include a first map with gaming unit 1 and a second map with gaming unit 2. In the case of map switching, or in the case of coexistence of multiple maps, the game unit 1 determines the behavior 1 from the behavior means 1 determined by the game AI module, and the game unit 2 determines the behavior 2 from the behavior means 2 determined by the same game AI module. The action means 1 and the action means 2 may be the same or different. Where behavior 1 and behavior 2 are different.

For example, a campaign for a game includes a first map and a second map, where non-player characters of the first map participating in the game include: the robot 1 and the robot 2, and the non-player character of the second map participating in the game include: a robot 3. In the case of map switching or in the case of coexistence of multiple maps, each of the robots 1, 2, and 3 can realize the intelligent function of the non-player character according to the game AI module.

Wherein, the cross-role multiplexing comprises: in the same map, different player characters or non-player color-controlled game units use the same game AI module to implement the intelligent functions of the game unit, wherein the intelligent functions are embodied as at least one specific behavior.

For example, two robot characters and one player character are arranged on a certain map, wherein the robot characters are respectively a robot 1 and a robot 2, and the robot 1 controls a plurality of game units including a game unit 1, a game unit 2 and a game unit 3; the robot 2 controls a plurality of game units including a game unit 4, a game unit 5, and a game unit 6. The robot 1 and the robot 2 can determine behavior means of respective plural game units respectively according to the game AI modules. The robot 1 may determine the behavior means 1 according to the game AI module and transmit the behavior means to the game unit 1 and the game unit 2, and the game unit 1 and the game unit 2 may perform the behavior 1 upon receiving the behavior means 1.

Wherein the cross-gaming-unit multiplexing comprises: in the same map or the same game scene, different game units use the same game AI module to realize the game unit intelligent function, and at least one specific behavior of different game units may be different.

For example, a map belongs to the game unit 1 and the game unit 2 of the same non-player character, the game unit 1 determines the behavior 1 according to the behavior means 1 determined by the game AI module, and the game unit 2 determines the behavior 2 according to the behavior means 2 determined by the game AI module. The action means 1 and the action means 2 may be the same or different. Where behavior 1 and behavior 2 are different.

It should be noted that, in a map of the game, there may be at least one game AI module for implementing the intelligent function of the map. For a game unit, it can implement the intelligent functions of the game unit according to at least one game AI module. For at least two game units, it is possible to implement the intelligent functions of the game units according to at least one game AI module.

It can be understood that the workload of game developers in designing and developing games can be greatly reduced by reusing the game AI modules. And in the subsequent updating and maintaining process, the intelligent modules of the plurality of game units can be reconstructed by reconstructing the multiplexed game AI module.

The method for implementing the intelligent function of the game unit in the prior art is first described below. In order to distinguish the difference between the intelligent function of the game unit in the prior art and the intelligent function and game AI module of the game unit related to the present application, the AI editor is used to refer to a module for realizing the intelligent function of the conventional game unit.

Currently, in the industry, when a game is developed, a module for realizing an intelligent function of a game unit is directly integrated into a map editor. The map editor contains all the different functional types of sub-editors used to generate a map. The map editor may include: object editors, terrain editors, campaign editors, AI editors, and the like. Wherein the functions of the object editor may include: game parameters of in-game units such as names, skills, appearances, moving speeds, blood volumes, and the like of in-game units; the functions of the terrain editor may include: geographical units such as rivers, trees, sand, and the like, and the appearance of geographical units, and the like; the functions of the campaign editor may include: map attributes in the game, such as the environmental sound effect, title, map information, picture display and the like of a map or a scene are loaded in the game; the AI editor may include: the actions of the game unit such as running away, patrolling, picking up items, purchasing items, random routing, etc. of the game unit.

The object editor, the terrain editor, the campaign editor, and the AI editor in the map editor may have various presentation forms, wherein the editor may be embodied as visual software, a kit, or the like, or may be embodied as an editable code module, which is not limited herein. The game developer can utilize the map editor to complete the development of the game map.

When developing a game map, a game developer first needs to design game units, such as game units, terrain, articles, and the like, on the map. Game developers then need to develop intelligent functionality for the gaming units, particularly for non-player characters. The intelligent function of the game unit can be bound with the game unit, or bound with the non-player character to which the game unit belongs, and the intelligent functions of the same game unit or the non-player character can be the same or different, and the intelligent functions of different game units or the non-player character can be the same or different.

In the prior art, an intelligent module of a game unit corresponds to a set of behaviors, and the behaviors include a behavior means, a behavior subject and a behavior object.

For example, in a game map, the game unit 1 uses skill 1, where skill 1 is a directional skill and skill 1 is directed to game unit 2. The game unit 1 uses the skill 1 as the action 1 for the game unit 2, and the action 1 includes an action means 1, an action subject 1, and an action object 1. The behavior means 1 is a skill 1, the behavior subject 1 is a game unit 1, and the behavior object 1 includes a skill 1 and a game unit 2.

Further, if skill 1 of the gaming unit 1 is cancelled, the intelligent functionality of the gaming unit 1 may need to be modified; or if the gaming unit 1 has added skill 2, it may be desirable to modify the intelligence of the gaming unit 1 and add the gaming unit's behaviour to skill 2 in the intelligence of other gaming units.

It can be understood that, since the AI editor needs to configure the behavior means, the behavior object, and the behavior subject at the same time to implement the intelligent function of the game unit, the intelligent function of the game unit is bound with the map data, and the cross-map multiplexing cannot be implemented. Further, the intelligent functions of the game units are bound to the game parameters of the game units, and thus cross-character multiplexing and cross-game unit multiplexing cannot be realized. In the prior art, a map file corresponding to a game map not only includes data of game units, terrain, articles and the like in the map, but also includes an intelligent function of a game unit.

Fig. 5 is an exemplary diagram of a game map architecture in the prior art.

As shown in fig. 5, game developers configure gaming units, terrain, objects, intelligent functions, etc. through a map editor. Configuring a gaming unit on a map comprising: gaming unit 1, gaming unit 2, gaming unit 3, gaming unit 4, item 1, item 2, terrain 1, terrain 2. Taking the game unit 1 as an example, the game unit can be embodied as a visual and interactive game unit in the game; the data layer is embodied as first initialization data, the first initialization data carries the game parameters of the game unit 1, such as the model (three-dimensional model, skill animation, etc.) of the game unit 1, the attributes (vital value, armor, skill) of the game unit 1, and the like, and the first initialization data also carries the traditional game AI of the game unit 1.

As shown in FIG. 6, the intelligent functions of the gaming unit may include sensory information, decision models, and behaviors.

The related concepts of perception information, decision models and behaviors can refer to the content of (1) game AI module in term explanation, which is not described in detail herein.

As shown in FIG. 6, the decision model portion of the prior art intelligence function of the gaming unit may include a variety of specific decision models, for example, the intelligence function of gaming unit 2 includes several decision models: the decision model 1 is "move to the position of the article 2 if the resource is currently needed", and the decision model 2 is "attack the game unit 4 if the game unit 4 is sensed"; the decision model 8: "if the blood amount is less than 30%, return to the position of the article 1" and the like. Taking decision model 1 as an example, in this case, the decision parameter required for decision is whether resources are needed, and the behavior means is movement. The subject of action in action 1 is the game unit 3, and the objects of action are item 2 and the position of item 2.

After a game developer develops a game map or scene, in the subsequent maintenance or upgrading process, new game units, articles and the like can be added to the game map or scene to improve the quality of the game or develop a new game map, and in this case, for any game unit in the game map, the added new game unit or article is added in the range which can be perceived by the game unit. The perceived scope determines the scope of the set of actions that the game unit is capable of achieving, i.e. determines the scope of the decision. Therefore, the game developer needs to reconstruct the intelligent functions of all the game units interacting with the newly added game unit, so that the newly added game unit can successfully participate in the game.

As shown in fig. 7, when the game unit 5 is added to the game map shown in fig. 5, the range of perception for any game unit is increased by the game unit 5. Therefore, the game developer needs to reconstruct the intelligent functions of the game unit 1, the game unit 2, the game unit 3, the game unit 4 and other game units, and add the intelligent function of the game unit 5, so that the game unit 5 can interact with the existing game units to complete the normal game functions.

Alternatively, when the game developer adds game skill 2 to the game unit 2, in order to allow the intelligent function of the game unit 2 to instruct the game unit 2 to use game skill 2, it is necessary to reconfigure the intelligent function of the game unit 2 and reconfigure the intelligent function of the game unit which may be affected by "game skill 2 used by the game unit 2".

It can be understood that in the prior art, the intelligent function of the game unit is bound with the game parameters of the game unit, and when the data of the game unit changes, the intelligent function of the game unit related to the game map needs to be reconstructed.

As shown in fig. 5, after the game developer develops the game map, the game developer packages all data in the game map to generate a map file, where the map file may be represented as one specific file or multiple specific files related to each other. Taking the game unit 2 as an example, the corresponding data including the model, the game parameters, the sound effect, the intelligent function, etc. are all stored in the game map file. For example, each map file includes a file for implementing a map intelligence function in a storage path, and the files for implementing the map intelligence function are different for different maps.

When the player opens the game and loads the game map shown in fig. 5, the game body needs to read and load the map file of the map, including the intelligent function of reading and loading all game units in the game map, that is, reading and loading the behavior set of all game units in the map.

As shown in fig. 8, the map file includes models of the game units, game parameters, intelligentized functions, and the like. When the game map is loaded on the game body, the intelligent function of the game unit needs to be loaded. In the actual game process, for a specific game unit, the game unit generally only executes a part of behaviors, and the behavior set of the part of behaviors is a proper subset of the behavior set corresponding to the game AI.

For example, taking the game unit 2 as an example, when the game body loads the map file, the game AI of the game unit 2 is loaded, that is, the behavior set of the game unit 2 is loaded, and the behavior set includes 75 behaviors, which are behaviors 1 to 75. And in the actual game process, the actual execution of the game unit is 39 actions. That is, for the gaming unit 2 in the game, the game body loads 36 actions that are not used in the game map to the gaming unit 2.

It can be understood that, in the prior art, after a game map is developed, in the process of developing a new game map, the intelligent function of the game unit in the new game map needs to be reconstructed, and a large amount of tedious and repetitive work needs to be performed.

It can be understood that, in the prior art, the realization of the intelligent function of the non-player character to which the game unit belongs through the intelligent function of the game unit is a design idea from bottom to top. That is, when a plurality of non-player characters exist in a map, the intelligent function of each non-player character is realized, a large amount of repeated logic needs to be repeatedly developed, and a large amount of repeated behaviors are loaded in the game loading process. Further, when a new game map is developed and the intelligent function of the non-player character of the new game map is realized, the development of the intelligent function of the game unit is required, and a large amount of complicated repetitive work is required.

In summary, in the prior art, game units that can appear in a game map and behaviors of the game units need to be considered when designing an intelligent function of a game unit in the game map, so that developers need to complete map data configuration, scenario configuration, intelligent function configuration and other tasks when designing the game map at the same time, the design task is complex and difficult to maintain later, and a large amount of repeated tasks are needed when developing a new game map. Furthermore, when the game map needs to be updated, such as adding a new game unit and configuring the game parameters of the game unit, the intelligent function of the existing game unit needs to be reconstructed. Furthermore, when the game map is loaded, the game body needs to load the behavior of the game unit, and the behavior executed by the game unit in the actual game is a proper subset of the behavior set corresponding to the intelligent function of the game unit. That is, the game body is loaded with a part of the behavior that the game unit is not executed in the game map, and the game resources are wasted. Furthermore, because the intelligent function of the game unit is bound with the data of the game unit, the running state of the intelligent function of the game unit needs to be checked in a traversing way in the running process of the game, so that the game unit with the fault intelligent function is difficult to locate, and the intelligent function of the fault game unit is related to the game parameters of other game units and is difficult to repair.

In order to solve the problems in the prior art, the application provides a use method of a game artificial intelligence module and electronic equipment. Through the game artificial intelligence module provided by the application, the binding relationship between the intelligent function and the data of the game unit is decoupled, and the complexity of a developer in developing a game map is reduced. Therefore, developers can reuse the game AI module when designing a new game map, and a large amount of tedious work is reduced. Still further, through the game artificial intelligence module that this application provided, can effectively promote the quality of the intelligent function of the recreation unit.

The method for using the game artificial intelligence module provided by the application is described as follows.

FIG. 9 is an exemplary diagram of a method for using a gaming artificial intelligence module provided herein.

For ease of description, the map is used hereinafter to refer to a game map.

S501: and constructing a first map and a second map.

The first map may be constructed in a variety of ways, such as by a map editor, and the like, wherein the way of constructing the first map is not limited. The second map may be constructed from the first map or separately. The first map and the second map are respectively used for declaring game units and non-player characters participating in a game process on the map, and the game units comprise abstract classes such as game units, terrain, resources, articles and the like. The game units on the map or game scene are determined, i.e. all game units participating in the game process are known.

It should be noted that the game units of the first map and the second map may be the same or different.

For example, a first map states an item, a tank, a terrain, and a second map states an item, a monster, a soldier, a terrain.

For example, a first map is declared to have an item, a tank, a terrain, and a second map is declared to have an item, a tank, a terrain, and a monster by modifying the first map as the second map.

And S502, initializing the first map data and the second map data.

After step S501 is completed, the map data is initialized by configuring game parameters for the game units in the game map.

The first map may generate the first initialization data after declaring the game map or the game units included in the scene to the first game AI module. The first initialization data includes initializing the gaming unit, and the first initialization data may occur during loading of the game or during running of the game. Similarly, the second map generates second initialization data.

Initializing the gaming unit may include: configuring game parameters of at least one game unit, wherein the game parameters may include a perceived range, a life value, an attack force, a moving speed, etc. of the game unit. Initializing the game unit may include initializing a game unit of a different non-player character. Initializing the gaming unit may include initializing different types of gaming units.

The implementation of initializing the game unit may be a concrete implementation of an abstract class in the first map module, and the implementation of initializing the game unit may be a concrete implementation by inheriting a concrete implementation of a subclass of the abstract class in the first map module.

For example, a tank is set up in the first map, and a phantom tank is initialized data of the tank class, wherein the initialization can be implemented in a way of implementing some methods of the tank class or configuring parameters of the tank class. In a game, the initialization of the game unit may be embodied as configuring game parameters of the game unit.

It should be noted that in the case where the first map is identical to the game unit declared on the second map, the initialized game unit on the first map may be different from the initialized game unit on the second map. For example, a tank is declared on both the first map and the second map, wherein the first map is configured with different game parameters from those of the second map when the tank is initialized.

It should be noted that the non-player character is not directly represented in the game, and the initialization of the non-player character can be substantially realized by initializing the game unit of the non-player character.

S503: optionally, a second game artificial intelligence module is generated according to the first game artificial intelligence module.

In some embodiments of the present application, the first gaming artificial intelligence module may generate the second gaming artificial intelligence module based on the gaming units declared on the first map and/or the second map.

The first game AI module can determine the range of perception information according to the game unit declared by the first map module, and further determines a set of behavior means according to the range of the perception information, and further determines to generate the second game AI module.

For example, in the first game map, the game units present include game unit 1, game unit 2, and game unit 3. As for the game unit 2, the range of the perception information of the game unit 2 is the game unit 1 and the game unit 3. As another example, the existing gaming units include gaming unit 1, gaming unit 2, gaming unit 3, where gaming unit 1 has skill 1, skill 2, and the sensory information of gaming unit 2 ranges from gaming unit 1, gaming unit 3, and skill, where skill 1, skill 2. Further, when the game unit senses the game unit 1, the game parameters of the game unit 2 may be acquired by: the game unit 1 acquires the game parameters of the game unit 2 by accessing the first map.

In some embodiments of the present application, step S503 may not be executed, that is, the first game AI module is the second game AI module.

It should be noted that the second game AI module may be generated during the game loading process, or may be dynamically loaded during the game running process.

Compared with the prior art that the behavior set of the game unit needs to be loaded as the game AI module in the game loading process, the second artificial intelligence module provided by the application only loads the game AI module used for determining the behavior means, so that the resource waste in the game loading process is reduced.

S504: the first map determines a behavior means of the game unit according to the second game artificial intelligence module, and determines a behavior of the game unit according to the behavior means.

The first map and the second game AI module carry out interaction of perception information, and the second game AI module determines a behavior means of the first initialization data according to the perception information. The first map determines the behavior of the first initialization data according to the behavior means or the behavior of the first initialization data is determined by the non-player character to which the first initialization data belongs according to the behavior means. The first map causes the first initialization data to perform the action, or the action is performed by the first initialization data itself.

The concepts of the second game AI module, the perception information, and the behavior means may refer to the content of the game AI module in the term explanation (1), which is not described herein again.

The interaction between the first map and the second game AI module can be various, for example, the first initialization data in the first map directly interacts with the second game AI module; for example, the first initialization data in the first map interacts with the game AI through the first map, which is not limited herein. Specifically, the first map may interact with the second game AI module through an interface of the second game AI module. For example, the first game AI module may access a blackboard or a shared variable through an interface to enable interaction with the game AI module when the second game AI module includes a behavior tree composition game AI module.

The timing of the interaction of the perception information between the first map and the second game AI module can be various, for example, the first map interacts with the second game AI module at regular time intervals, or the first map interacts with the game AI module in response to the input of the user, which is not limited herein. The process of interaction can be initiated by the first map or the second game AI module, or the interaction time of the first map and the second game AI module is determined through a trigger.

The second game AI module selects a decision according to the perception information and determines a behavior means according to the decision.

In some embodiments of the present application, the second game AI selects a decision based on the sensory information and requests at least one decision parameter. Wherein the decision participation is used to determine the behavioral means from the decision. Since the second game AI module is not bound to the data of the first initialization data, it is necessary to request decision parameters for determining the behavior means.

The decision parameter interaction between the second game AI module and the first map may refer to the data interaction between the first map and the second game AI module, which is not described herein again.

It can be understood that, by requesting the decision parameter and obtaining more information about the first initialization data, the quality of the game AI of the first initialization data, that is, the accuracy of the behavior of the first initialization data, can be effectively improved.

It should be noted that the trigger may be located in the first map or the first game AI, which is not limited in this application.

It should be noted that the computational load related to rendering of the game unit in the game, and calculation involved in decision, decision determination process, etc. may be carried by any module, and the present application is not limited thereto.

The behavior of the game unit is determined based on the behavior approach.

After the first map acquires the behavior means determined by the second game AI module, the behavior subject of the behavior means is determined to be the first initialization data, and the behavior object of the behavior means can be determined according to the perception information. After determining the behavior means, the behavior host, and the behavior object, at least one behavior may be determined for indicating a first initialization data execution behavior.

After the first initialization data is obtained from the behavior means determined by the second game AI module, the first initialization data may determine the behavior object, and the behavior subject is the first initialization data of the received behavior means. After determining the behavior means, the behavior host, and the behavior object, at least one behavior may be determined for indicating the first initialization data execution.

S505: the second map determines a behavior means of the game unit according to the second game artificial intelligence module, and determines a behavior of the game unit according to the behavior means.

The interaction of the second map and the second game AI module, and the interaction timing may specifically refer to the content in S504.

Since the first initialization data and the second initialization data are different for the second game AI only in specific data carried by the perception information and do not affect the determination of the behavior means by the second game AI according to the perception information, the specific implementation of the game AI of the second initialization data can refer to the contents in S504.

The behavior means of the second initialization data may be the same as or different from the behavior means of the first initialization data.

The second initialization data may determine the behavior of the second initialization data according to the game behavior means. Since the first initialization data and the second initialization data are respectively located in the first map and the second map, the behavior object of the second initialization data is different from the behavior object of the first initialization data, and the behavior of the second initialization data is different from the behavior of the first initialization data.

The game AI module can be reused across maps, so that workload is reduced and development efficiency is improved when a game developer develops a new map; furthermore, through the game AI module, cross-role multiplexing is realized, workload is reduced, and development efficiency is improved; furthermore, through the game AI module, the cross-game unit multiplexing is realized, the workload is reduced, and the development efficiency is improved.

S701: and generating a second game artificial intelligence module according to the first game artificial intelligence module and the first map.

And in the game loading process, generating a second game artificial intelligence module according to the first person game artificial intelligence module and the game unit declared by the first map. Specifically, the first map, the first game artificial intelligence module, and the second artificial intelligence module in S701 may refer to the description in S503, and are not described herein again.

S702: the first map generates first initialization data.

During game loading, the first map generates first initialization data. Specifically, S702 may refer to the description in S501, and is not described herein again.

S703: in the game running process, the first initialization data sends the perception information to the second game AI module; the second game AI module selects a decision according to the perception information and requests a decision parameter from the first initialization data; the first initialization data sends a decision parameter to the second game AI module according to the requested decision parameter; the second game AI module determines the behavior according to the decision and the decision parameter and sends a behavior means to the first initialization data; after the initialized game unit receives the behavior means, at least one specific behavior is executed according to the behavior means.

And the second game AI module selects at least one decision according to the perception information after receiving the perception information sent by the first initialization data.

And the second game AI module determines a selected decision according to the acquired perception information, determines a decision parameter required by the decision, and requests the decision parameter from the first initialization data. And after receiving the request sent by the second game AI module, the first initialization data returns the decision parameter of the request to the second game AI module. And after the second game AI module obtains the decision parameters, determining at least one behavior means according to the decision parameters and the decision, and returning the behavior to the first initialization data or the non-player character to which the first initialization data belongs. The first initialization data or the non-player character to which the first initialization data belongs determines a specific action to be performed according to the action means, and instructs the first initialization data to perform the action.

For example, in the case of a certain game unit 2, the sensing range is a circle with a radius r, and the range of shared sensing is not considered. The distance between the game unit 2 and another game unit can be calculated from the coordinates of the game unit 2 and the coordinates of the other game unit in the game. For example, if the coordinates of the gaming unit 2 are (x2, y2) and the coordinates of the gaming unit 3 are (x3, y3), the distance is r₂₃＝sqrt((x2-x3)²+(y2-y3)²) Where sqrt is squared on. When r is₂₃<r, gaming unit 2 senses gaming unit 3; when r is₂₂When r is larger than r, the game unit 2 can not sense the game unit 3.

In the case where the gaming unit 2 perceives the gaming unit 3, the gaming unit 2 sends perception information to the second game AI module. The perception information includes information of the game unit 2 and game parameters of the game unit 3.

The decision model included in the second game AI module may include many kinds, and is not limited herein. For example, the decision model of the second game AI module may include: escape, attack, recourse, etc. For example, when the decision model selected in the second game AI module is an attack, the decision parameters to be requested may include attack scope, skill, article, and the like of the gaming unit 2 and/or the gaming unit 3. After the second game AI module obtains the decision parameters, the skill information of the game unit 2 is obtained, and the determining act includes: post-use skill attacks. The second game AI module, after determining the action means 2, sends the action means 2 to the gaming unit 2 or the non-player character to which the gaming unit 2 belongs. After the gaming unit 2 or the non-player character to which the gaming unit 2 belongs receives the behavior means 2, it can be determined that the gaming unit 2 performs the behavior 2, i.e., attacks the gaming unit 3 using the skill, according to the behavior means 2.

In some embodiments of the present application, the second game AI may select a decision model and determine a behavior approach based on the perception information without requesting decision parameters.

For example, for the game unit 2 as an example, after it senses the game unit 3, the decision selected in the second game AI module is a movement decision, and the parameter required by the movement decision is the location information of the game unit 2, and the location information of the second game unit is included in the sensing information. The second game AI module may determine that the behavior means is movement and transmit the behavior movement behavior means to the gaming unit 2 or the non-player character to which the gaming unit 2 belongs, and may determine that the gaming unit 2 moves to the position of the gaming unit 3 according to the behavior means 2, wherein the position information of the gaming unit 3 may be acquired by the gaming unit 2 or the non-player character to which the gaming unit 2 belongs without passing through the second game AI module.

It is understood that the first initialization data is to determine the behavior means by means of data interaction and to send the behavior means to the first initialization data or the non-player character to which the first initialization data belongs. The first initialization data or the non-player character to which the first initialization data belongs may determine the behavior subject and the behavior object associated with the behavior means according to the information of the first initialization data itself, and execute the behavior determined by the behavior means. Therefore, different initialized game units can multiplex the second game AI, and cross-game unit use of the game AI module is realized.

It can be understood that in the game development process, the intelligent function of the game unit is not required to be designed simultaneously when the game unit is designed, and the difficulty of the design work is reduced. Furthermore, when a certain game unit or the intelligent function of a certain game unit needs to be adjusted and reconstructed, the adjustment and reconstruction of the intelligent function of the game unit can be completed by adjusting and reconstructing the first game AI module. Similarly, the adjustment and reconstruction of the intelligent function of the non-player character can be completed by adjusting and reconstructing the first game AI module.

The first map module, the first game AI, the second game AI, and the first initialization data may refer to the descriptions in fig. 9 and fig. 10 and the description in the term interpretation (1) game AI module, which are not described herein again.

The player's secondary development of the game adds third initialization data. The secondary development of the game refers to the modification of game contents of the game by using unofficial map editing software. There are many expressions for secondary development of a game, for example, a player adds a new game unit to an existing official map, a player adds a new interaction method to an existing game unit, and a player creates a new map.

The third initialization data may have various expressions, and is not limited herein, for example, the third initialization data may be a new item, a new function of an existing item, a new game unit, a new terrain, and the like.

S801: the content of step S801 may refer to the text description in step S701, and is not described herein again.

S802: in the game running process, the third initialization data sends the perception information to the first game AI module; the first game AI module selects a decision according to the perception information and requests a first parameter from the third initialization data, wherein the first parameter comprises a decision parameter and a game parameter; the third initialization data sends a decision parameter to the first game AI according to the requested decision parameter; the first game AI module determines a behavior means according to the decision and the game parameters and sends the behavior means to the third initialization data; and after the third initialization data receives the behavior means, executing at least one specific behavior according to the behavior means.

For example, after adding the third initialization data, i.e. the initialized third game unit, such as the game unit 6, to a certain game map, the game unit 2 may sense the game unit 6 with respect to the already existing first initialization data, i.e. the already initialized game unit 2. The second game AI module may receive the perception information sent by the gaming unit 2.

The second game AI module may determine the game unit 6 as the third initialization data based on the perception information. Considering that the second AI module may not be able to determine the decision model or the decision model of the second module requires decision parameters to determine the behavior means according to the perception information, the second game AI module requests game parameters from the third initialization data for further determining the decision model or the decision parameters required by the decision model. Wherein the decision parameter may be part or all of the game parameter of the third initialization data.

There are many situations in which the second AI module cannot determine the decision model according to the sensing information or the decision model of the second AI module needs decision parameters to determine the behavior means, and is not limited herein. For example, according to the rules of game ontology design, the perception information only includes the life values of all the game units in the visual field of the game units, and the second AI module determines that the decision model needs to know the skill information in the game parameters of the game units 6.

For example, the second game AI module requesting the first decision parameter includes: whether the gaming unit 6 can be attacked or not, and the attack range of the gaming unit 6, and the perception information acquired by the second game AI module does not have the information about the gaming unit 6. In this case, the second game AI module requests decision parameters from the map or gaming unit 6, wherein the decision parameters include those of the gaming unit 6

The decision parameters requested by the second game AI module include: the attack range of the gaming unit 6 is 120, and the gaming unit 6 can be attacked. The second game AI module determines the behavior means including: an attack in motion and returns the behavior means to the gaming unit 2. After the game unit 2 acquires the behavior means, it can acquire a behavior subject and a behavior object, and further determine a behavior and execute the behavior.

It can be understood that, through the first game AI module provided by the present application, cross-game unit multiplexing can be realized, wherein the game unit can be generated through secondary development, the workload of game development can be reduced, and the enthusiasm of the player for secondary development of the game can be improved.

The following describes an implementation method of the game AI module provided by the present application in a game development process.

In the game development process, the game map and the game AI module can be independently developed.

The development of the game map can be completed through a map editor, and the development of the game map can comprise the development of game units, models, sound effects, interfaces and the like. The developed game map is configured with a first interface for data interaction.

The development of the game AI module can be completed by a behavior tree and/or a state machine, and the development of the game AI module can include two development modes. Firstly, a plurality of game AI sub-modules are developed and synthesized into a game AI module, wherein a second interface for data interaction can be configured on the game AI sub-modules and also on the game AI module. Secondly, a game AI module is directly developed, and a second interface for data interaction can be configured on the game AI module.

The game AI module and the game map can be implemented according to a first interface and a second interface, wherein the first interface can be a plurality of interfaces, and the second interface can be a plurality of interfaces.

For the first game AI module development approach, different game AI submodules may be provided according to different classification criteria for the intelligent functions of the game unit, further resulting in the synthesis of a game AI module by the different game AI submodules. Still further, the combining manner of combining different game AI submodules into one game AI module may also be different.

The game AI module may include a plurality of game AI submodules of the same type, such as game AI submodule 1 and game AI submodule 2. The game AI submodule 2 may determine, for example, to modify a decision model in the game AI submodule 1 and/or modify a behavior means set of the game AI submodule 1 according to the game AI submodule 1, and use the modified game AI submodule 1 as the game AI submodule 2. The game units controlled by different non-player characters can select different game AI submodules of the same type, so that the intelligent functions of different non-player characters are different, and the experience of a player is improved.

It can be understood that, in order to realize the difference of the intelligent functions of different non-player characters, the game AI submodule is added, and a new game AI module for realizing the intelligent function does not need to be developed again, so that the workload of game development is reduced, and the efficiency of game development is improved.

As shown in fig. 12, there are two maps, map 1 and map 2, respectively. The map 1 includes a terrain, a player character (a game unit controlled by the player character), a robot 1 (a game unit controlled by the robot 1), and a robot 2 (a game unit controlled by the robot 2). The game AI module can comprise two game AI submodules, namely a resource AI and a soldier AI.

As shown in fig. 12 (a), the map 1 and the map 2 can implement the intelligentized function of the map 1 and the intelligentized function of the map 2 according to the game AI module, and the specific contents may refer to the text descriptions in fig. 9 to fig. 11, which are not described herein again.

As shown in fig. 12 (B), the terrains in both map 1 and map 2 can implement an intelligent function of the terrains according to the resource AI; the player character in the map 1, the robot 2, the player character in the map 2, and the robot 1 can all realize respective intelligent functions according to the soldier AI.

As shown in fig. 12 (C), the terrains in both map 1 and map 2 can implement an intelligent function of the terrains according to the resource AI; the player character in the map 1, the robot 1, the player character in the map 2 and the robot 1 can all realize respective intelligent functions according to the soldier AI 1; the robot 2 in the map 1 can realize the intelligent function of the robot 2 according to the soldier AI 2. The soldier AI1 and the soldier AI2 are game AI submodules of the same type, the decision models of the soldier AI1 and the soldier AI2 can be different, and the behavior means sets of the soldier AI1 and the soldier AI2 can be different.

During the running of the game, the robot 1 controls the game unit 7 and the robot 2 controls the game unit 8 in the map 1. The game unit 7 and the game unit 8 have the same game parameters and are the same game unit. When the perception information received by the game AI module is the same as the perception information received by the game AI module by the game unit 8, since the intelligentized function of the game unit 7 is implemented by the soldier AI1 and the intelligentized function of the game unit 8, the behavior performed by the game unit 7 may be different from the behavior performed by the game unit 8.

As shown in FIG. 13, the game AI module can be divided into a general AI and a resource AI. The intelligent function of the terrain can be realized according to the resources AI by the terrain in the map 1 and the map 2; the non-player character robot 1 and the robot 2 in the map 1, and the robot 3 in the map 2 can realize the intelligent function of the non-player character according to the group AI.

After determining the behavior means according to the group AI, the robot 1 transmits the behavior means to the corresponding game unit. The game unit can determine the behavior means of the game unit according to the behavior means and a pre-configured fixed decision model, wherein the fixed decision model can be a decision model bound with map data.

The robot 1 determines at least one behavior measure according to the game AI module and transmits the behavior measure to the corresponding game unit. After receiving the behavior means, the game unit can make a behavior according to the behavior means, and can also make a behavior according to the behavior means and a decision model on the game unit.

Wherein the pre-configured decision model may be constituted by a behavior tree and/or a state machine and is based on map data, i.e. the output of the decision model is a behavior.

For example, the robot 1 controls game units including a game unit 1 and a game unit 2. The robot determines the behavior means of the gaming units 1 and 2 as movement. After receiving the behavior means, the gaming unit 1 and the gaming unit 2 can respectively determine the behaviors, such as the movement of the gaming unit 1 to the coordinates (185, 354), the gaming unit 2 and the movement to the coordinates (185, 355). During the gaming unit 1 execution behavior "gaming unit 1 moves to coordinates (185, 354)", when gaming unit 3 is encountered, an attack may be made according to a pre-configured decision model. That is, the game unit 1 appears to be moving and attacking in the game. Since the pre-configured decision model is bound to the map data, the behavior of "attacking the game unit 3" may not be determined according to the game AI module.

It can be understood that, in the process of game development, game AI module development can be performed for the intelligent function of the non-player character, and a game AI development mode in the prior art is adopted in the realization of the intelligent function of the game unit, so that the workload of game development is reduced, the intelligent function quality of the game unit and the non-player character is improved, and further, the player experience is improved.

The electronic device provided by the present application is described below.

In the embodiment of the present application, the electronic device may be a mobile electronic device or a PC, which is not limited herein.

For example, fig. 14 is a schematic structural diagram of an electronic device 100 according to an embodiment of the present application.

The following describes an embodiment specifically by taking the electronic device 100 as an example. It should be understood that electronic device 100 may have more or fewer components than shown, may combine two or more components, or may have a different configuration of components. The various components shown in the figures may be implemented in hardware, software, or a combination of hardware and software, including one or more signal processing and/or application specific integrated circuits.

The electronic device 100 may include: processor 110, internal memory 121, audio module 170, sensor module 180, buttons 190, display screen 194, and the like. Wherein the sensor module 180 may include a touch sensor 180K.

The configuration illustrated in the embodiment of the present invention is not particularly limited to the electronic device 100. In other embodiments of the present application, electronic device 100 may include more or fewer components than shown, or some components may be combined, some components may be split, or a different arrangement of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

A memory may also be provided in processor 110 for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory may hold instructions or data that have just been used or recycled by the processor 110. If the processor 110 needs to reuse the instruction or data, it can be called directly from the memory. Avoiding repeated accesses reduces the latency of the processor 110, thereby increasing the efficiency of the system.

The electronic device 100 implements display functions via the GPU, the display screen 194, and the application processor. The GPU is a microprocessor for image processing, and is connected to the display screen 194 and an application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 110 may include one or more GPUs that execute program instructions to generate or alter display information.

The display screen 194 is used to display images, video, and the like. The display screen 194 includes a display panel. The display panel may adopt a Liquid Crystal Display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (active-matrix organic light-emitting diode, AMOLED), a flexible light-emitting diode (FLED), a miniature, a Micro-oeld, a quantum dot light-emitting diode (QLED), and the like. In some embodiments, the electronic device 100 may include 1 or n display screens 194, with n being a positive integer greater than 1.

The internal memory 121 may include one or more Random Access Memories (RAMs) and one or more non-volatile memories (NVMs).

The random access memory may include static random-access memory (SRAM), dynamic random-access memory (DRAM), synchronous dynamic random-access memory (SDRAM), double data rate synchronous dynamic random-access memory (DDR SDRAM), such as fifth generation DDR SDRAM generally referred to as DDR5 SDRAM, and the like;

the nonvolatile memory may include a magnetic disk storage device, a flash memory (flash memory).

The FLASH memory may include NOR FLASH, NAND FLASH, 3D NAND FLASH, etc. according to the operation principle, may include single-level cells (SLC), multi-level cells (MLC), three-level cells (TLC), four-level cells (QLC), etc. according to the level order of the memory cells, and may include universal FLASH memory (UFS), embedded multimedia memory cards (eMMC), etc. according to the storage specification.

The random access memory may be read and written directly by the processor 110, may be used to store executable programs (e.g., machine instructions) of an operating system or other programs in operation, and may also be used to store data of users and applications, etc.

The nonvolatile memory may also store executable programs, data of users and application programs, and the like, and may be loaded into the random access memory in advance for the processor 110 to directly read and write.

In this embodiment, the processor 110 may call the computer instructions stored in the internal memory 121 to enable the electronic device 100 to execute the game AI module using method in this embodiment.

A map module 1601 is used to construct a game map and initialize game units and non-player characters.

A perception module 1602, configured to determine the visual fields, perception information, and the like of different game units and non-player characters in different game maps constructed by the map module 1601. Wherein, the perception module may be located in game AI module 1603 or map module 1601.

Game AI module 1603 for implementing intelligent functions of different game units and non-player characters in different game maps constructed by diagram module 1601.

For example, fig. 16 is another schematic structural diagram of the electronic device 100 according to the embodiment of the present application.

The electronic device 100 includes:

an input device 201, an output device 202, a processor 203 and a memory 204 (wherein the number of the processors 203 in the electronic device 200 may be one or more, and one processor 203 is taken as an example in fig. 15). In some embodiments of the present application, the input device 201, the output device 202, the processor 203 and the memory 204 may be connected by a bus or other means, wherein the connection by the bus is exemplified in fig. 16.

The processor 203 calls the operation instructions stored in the memory 204 to make the electronic device 100 execute the method for using the game AI module in the embodiment of the present application.

As used in the above embodiments, the term "when …" may be interpreted to mean "if …" or "after …" or "in response to a determination of …" or "in response to a detection of …", depending on the context. Similarly, depending on the context, the phrase "at the time of determination …" or "if (a stated condition or event) is detected" may be interpreted to mean "if the determination …" or "in response to the determination …" or "upon detection (a stated condition or event)" or "in response to detection (a stated condition or event)".

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The procedures or functions described in accordance with the embodiments of the present application occur, in whole or in part, when the computer program instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (e.g., coaxial cable, fiber optic, digital subscriber line) or wirelessly (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The available media may be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid state drives), among others.

One of ordinary skill in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by hardware related to instructions of a computer program, which may be stored in a computer-readable storage medium, and when executed, may include the processes of the above method embodiments. And the aforementioned storage medium includes: various media capable of storing program codes, such as ROM or RAM, magnetic or optical disks, etc.

Claims

1. A method for using a game artificial intelligence module, comprising:

the method comprises the steps that electronic equipment loads a first map and a first game artificial intelligence module, wherein the first map comprises a first game unit, and the first game artificial intelligence module is a module for realizing a map intelligence function;

the electronic equipment determines a first behavior of the first game unit according to the first game artificial intelligence module;

the electronic equipment loads a second map, and the second map comprises a second game unit;

the electronic equipment determines a second behavior of the second game unit according to the first game artificial intelligence module, wherein the first behavior is different from the second behavior.

2. The method of claim 1, wherein the determining, by the electronic device, the first behavior of the first gaming unit based on the first gaming artificial intelligence module specifically comprises:

the electronic equipment determines first perception information of a first game unit according to the visual field range of the first game unit;

the electronic equipment determines a first behavior means of the first game unit according to the first perception information and the first game artificial intelligence module;

the electronic device determines a first behavior of the first game unit according to the first behavior means.

3. The method according to claim 1, wherein the determining, by the electronic device, the second behavior of the second gaming unit based on the first gaming artificial intelligence module specifically comprises:

the electronic equipment determines second perception information of a second game unit according to the visual field range of the second game unit;

the electronic equipment determines a second behavior means of the second game unit according to the second perception information and the first game artificial intelligence module;

the electronic equipment determines a second behavior of the second game unit according to the second behavior means.

4. The method according to claim 2, wherein the determining, by the electronic device, the first behavior of the first game unit based on the first perception information and the first game artificial intelligence module, specifically comprises:

the electronic equipment determines a first behavior means of the first game unit according to the first perception information, the first game artificial intelligence module and decision parameters, wherein the decision parameters comprise part or all of game parameters of the first game unit.

5. The method of claim 1, wherein the electronic device, upon determining the first behavior of the first gaming unit based on the first gaming artificial intelligence module, further comprises:

and the electronic equipment determines a third behavior of a third game unit according to the first game artificial intelligence module, wherein the third game unit is a game unit different from the first game unit on the first map.

6. The method of claim 5, wherein the third gaming unit belongs to a different or the same non-player character as the first gaming unit.

7. The method of any of claims 1 to 6, wherein the first gaming artificial intelligence module comprises a behavioral tree and/or a state machine.

8. An electronic device, characterized in that the electronic device comprises: one or more processors and memory;

the memory coupled with the one or more processors, the memory to store computer program code, the computer program code including computer instructions, the one or more processors to invoke the computer instructions to cause the electronic device to perform: the method of any one of claims 1 to 7.

9. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the computer program, causes the computer device to implement the method of any of claims 1 to 7.

10. A computer-readable storage medium comprising instructions that, when executed on an electronic device, cause the electronic device to perform the method of any of claims 1-7.