CN116617666A

CN116617666A - Score type behavior decision method, device and equipment for virtual object

Info

Publication number: CN116617666A
Application number: CN202310609414.3A
Authority: CN
Inventors: 许永超
Original assignee: Beijing Jiju Network Technology Co ltd
Current assignee: Beijing Jiju Network Technology Co ltd
Priority date: 2023-05-29
Filing date: 2023-05-29
Publication date: 2023-08-22

Abstract

The invention relates to the technical field of game artificial intelligence, in particular to a scoring type behavior decision-making method, a scoring type behavior decision-making device and scoring type behavior decision-making equipment for a virtual object, wherein the scoring type behavior decision-making method specifically comprises the following steps: acquiring basic behavior value points of each event or attribute change which may occur before the virtual object acts in the game; determining a physical factor of the virtual object based on the character factor, the attribute comparison weight, the wisdom degree, the action strategy and the inverse factor of the virtual object, and determining a first action value score according to the influence of the physical factor on the basic action value score; and determining the behavior decision of the virtual object according to the first behavior value score and whether a game special event occurs. The invention scores the virtual object based on the basic behavior value score of each event or attribute change which may occur before the virtual object acts through the multidimensional factors of the virtual object, and determines the behavior decision most suitable for the next behavior of the virtual object.

Description

Score type behavior decision method, device and equipment for virtual object

Technical Field

The invention relates to the technical field of game artificial intelligence, in particular to a scoring type behavior decision-making method, device and equipment of a virtual object.

Background

In games, machines are typically used to simulate human thinking to perform some game-related operations, such as participating in the game according to game rules, understanding player behavior and making feedback, etc., which is game artificial intelligence, i.e., game AI. The application of game AI in games has a long history, and AI decision schemes such as AI action tree, hierarchical state machine, finite state machine, etc. have been developed. However, the existing game AI decision scheme can only make a simple behavior decision for the NPC character, so that the player can generate a regular and reproducible feeling of the behavior decision for the NPC character operated by the game AI, and the existing game AI decision scheme directly enables the game box to enter the second stage under the condition of low blood volume and obtain new skills and AI attack logic.

Disclosure of Invention

The invention aims to provide a scoring type behavior decision-making method, device and equipment for a virtual object, which are used for scoring on the basis of basic behavior value scores of each event or attribute change possibly occurring before the action of the virtual object through multidimensional factors of the virtual object, and determining the behavior decision most suitable for the next behavior of the virtual object so as to solve at least one of the existing problems.

The invention provides a scoring type behavior decision-making method of a virtual object, which specifically comprises the following steps:

acquiring basic behavior value points of each event or attribute change which may occur before the virtual object acts in the game;

determining a physical factor of the virtual object based on the character factor, the attribute comparison weight, the wisdom degree, the action strategy and the inverse factor of the virtual object, and determining a first action value score according to the influence of the physical factor on the basic action value score;

determining a behavior decision of the virtual object according to the first behavior value score and whether a game special event occurs, wherein the game special event is a preset scenario operation which is required to be made by the virtual object at a specific time and in a specific scene;

and acquiring a first state of the virtual object, and switching the state of the virtual object according to the first behavior value score and the first state.

Further, the determining the first behavioral score according to the influence of the body factor on the basic behavioral score specifically includes:

determining a second behavior value score according to the preset weight of the character factor and the basic behavior value score of the behavior corresponding to the character factor;

Determining a third behavior value score according to the attribute comparison weight and the basic behavior value scores of the basic attributes of the virtual object;

determining a fourth behavior value score generated by high-score behavior or low-score behavior or data sampling quantity of the virtual object according to the intelligent degree;

determining a fifth behavioral value score generated by the action strategy of the virtual object according to the scene of the virtual object;

determining a sixth behavioral value component generated by the virtual object violating the command of the first virtual object according to the inverse factor;

and determining a first behavior value score according to the second behavior value score, the third behavior value score, the fourth behavior value score, the fifth behavior value score and the sixth behavior value score.

Further, the determining a second behavior value score according to the preset weight of the personality factor and the basic behavior value score of the behavior corresponding to the personality factor specifically includes:

acquiring the character factor of the virtual object and a first behavior corresponding to the character factor;

and determining a second behavior value score of the first behavior according to the preset weight of the character factor and the basic behavior value score of the first behavior.

Further, the determining a third behavior value score according to the attribute comparison weight and the basic behavior value score of each basic attribute of the virtual object specifically includes:

determining the attribute comparison weight according to the occupation type and attribute tendency of the virtual object;

and determining a third behavior value score of each basic attribute of the virtual object according to the attribute comparison weight and the basic behavior value score of each basic attribute of the virtual object.

Further, the determining, according to the degree of wisdom, a fourth behavior score generated by a high score behavior or a low score behavior or a data sampling number of the virtual object specifically includes:

determining a high-score weight, a low-score weight and a data sampling number according to the intelligent degree of the virtual object;

sorting according to the basic behavior value scores of the behaviors of the virtual objects, and then determining a high partition area and a low partition area;

determining a first high-score behavior of a plurality of high-score behaviors in the high-score interval according to the high-score weight, or determining a first low-score behavior of a plurality of low-score behaviors in the low-score interval according to the low-score weight, or predicting behavior trends of the virtual object and an adversary virtual object in a future preset round number according to the data sampling number, and then determining a basic behavior value score in the future preset round number;

Determining a fourth behavior value score, wherein the fourth behavior value score is a basic behavior value score of the first high-score behavior, or a basic behavior value score of the first low-score behavior, or a basic behavior value score in the future preset round number.

Further, the determining, according to the scene of the virtual object, a fifth behavioral score generated by the action policy of the virtual object specifically includes:

determining a forbidden instruction of the virtual object and a scoring instruction, wherein the forbidden instruction is an instruction for limiting the virtual object not to make forbidden behaviors, and the scoring instruction is an instruction for making the virtual object tend to make behaviors conforming to character settings;

determining a second behavior to be made by the virtual object according to the forbidden instruction, the scoring instruction and an action strategy corresponding to the occupation type of the virtual object;

or determining a third behavior to be made by the virtual object according to the forbidden instruction, the adding instruction and an action strategy corresponding to the movement action of the virtual object;

and determining a fifth behavior value score, wherein the fifth behavior value score is a basic behavior value score of the second behavior or a basic behavior value score of the third behavior.

Further, the determining, according to the inverse factor, a sixth behavioral score generated by the virtual object violating the command of the first virtual object specifically includes:

acquiring a command of a first virtual object, wherein the command is a common command or a forced execution command;

when the command is a common command, acquiring a basic behavior value score and an additional behavior value score of a fourth behavior corresponding to the common command, and then performing a descending operation on the additional behavior value score according to an inverse value of the inverse factor to acquire a sixth behavior value score, wherein the sixth behavior value score is a sum of the basic behavior value score of the fourth behavior corresponding to the common command and the additional behavior value score after descending;

and when the command is a forced execution command, directly obtaining a sixth behavior value score, wherein the sixth behavior value score is the sum of a basic behavior value score and an additional behavior value score of a fourth behavior corresponding to the common command.

Further, the obtaining the first state of the virtual object, and determining the second state of the virtual object according to the first behavior score and the first state specifically includes:

Acquiring identity information of the virtual object, and determining a first state of the virtual object when the identity information of the virtual object is a game BOSS, wherein the first state is a normal state of the virtual object;

switching the first state into a second state according to the first behavioral score, wherein the second state is a combat state;

switching the second state into a third state according to the first behavioral score, wherein the third state is an anger state;

or directly switching the first state into a fourth state, wherein the fourth state is a second personality state.

The invention also provides a scoring type behavior decision device of the virtual object, which specifically comprises:

the first processing module is used for acquiring basic behavior value scores of each event or attribute change possibly occurring before the virtual object acts in the game;

the second processing module is used for determining physical factors of the virtual object based on character factors, attribute comparison weights, intelligent degrees, action strategies and inverse factors of the virtual object, and determining a first behavior value score according to the influence of the physical factors on the basic behavior value score;

The behavior decision module is used for determining the behavior decision of the virtual object according to the first behavior score and whether a game special event occurs, wherein the game special event is a preset scenario operation which is required to be made by the virtual object at a specific time and a specific scene;

and the state switching module is used for acquiring a first state of the virtual object and switching the state of the virtual object according to the first behavior value score and the first state.

The present application also provides a computer device comprising: memory and processor and computer program stored on the memory, which when executed on the processor, implements a method of scored behavior decision of a virtual object as described in any one of the above methods.

Compared with the prior art, the application has at least one of the following technical effects:

1. the application takes the integral income brought by each action as the judgment basis to make decision and interaction, and well solves the pain point of the prior state machine and the tree structure of the action tree AI in the round game.

2. Based on score type behavior decision, when the BOSS reaches the system monitoring condition, a new stage influence factor is directly overlapped into the basic form, and the decision of the BOSS-AI is changed in a score weight mode, so that the tearing sense of a player in the fight feeling can be obviously reduced.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a scoring type behavior decision method of a virtual object according to an embodiment of the present application;

FIG. 2 is a schematic flow chart of training virtual objects according to an embodiment of the present application;

FIG. 3 is a schematic listing of each event or attribute change that may occur before a virtual object is acted upon by an embodiment of the present application;

FIG. 4 is a schematic diagram of the composition of body factors of a virtual object provided by an embodiment of the present application;

FIG. 5 is a flow diagram of a conventional BOSS-AI segmented design;

FIG. 6 is a flow chart of a BOSS-AI segmented design provided in an embodiment of the application;

FIG. 7 is a schematic structural diagram of a scoring type behavior decision-making device for virtual objects according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of a computer device according to an embodiment of the present application.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It should also be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.

As used in the present description and the appended claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".

Furthermore, the terms "first," "second," "third," and the like in the description of the present specification and in the appended claims, are used for distinguishing between descriptions and not necessarily for indicating or implying a relative importance.

Reference in the specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," and the like in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless expressly specified otherwise. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.

Referring to fig. 1, an embodiment of the present invention provides a score-type behavior decision method for a virtual object, where the method specifically includes:

s101: acquiring basic behavior value points of each event or attribute change which may occur before the virtual object acts in the game;

and determining a physical factor of the virtual object based on the character factor, the attribute comparison weight, the wisdom degree, the action strategy and the inverse factor of the virtual object, and determining a first behavior value score according to the influence of the physical factor on the basic behavior value score.

In this embodiment, before the basic behavior value score of each event or attribute change that may occur before the virtual object acts in the game is obtained, the virtual object needs to be trained, referring to fig. 2, the training of the virtual object is first started from the establishment of a database, and all data of the virtual object as the game AI is established based on the basis, and the database has information such as a fight record, an equipment wear record, a skill wear record and the like of the virtual object, and this database is called a Model of the virtual object. The game setting can then be used to set some physical factors, such as character factors, attribute comparison weights, wisdom, action strategies, and inverse factors, for the current virtual object. By the arrangement, an AI combat unit with own characteristics, namely the initial anthropomorphic AI in fig. 2, and various combat data generated by subsequent combat and study can be basically completed and can be used as reference data for later behavior decision. Meanwhile, the Model can be understood as the brain memory or experience of the virtual object, the Model perfects the fight experience through continuous learning and training, and can be called as the history experience to be referred when the virtual object encounters a decision problem, but the Model only stores things related to the fight experience and the fight event, the Model cannot control the character, the fight bias and other attributes of the virtual object, the Model of each virtual object exists independently, and the virtual object cannot finish the operation of Model data sharing by itself.

Before the basic behavior value score of each event or attribute change that may occur before the virtual object acts in the game is obtained, it is also necessary to assign a certain basic behavior value score to each event or attribute change that may occur before the virtual object acts, which is fixed until no influence of the body factor is present. Referring to fig. 3, the virtual object as the game AI has different decision choices such as a priority attack target, a moving position, a range selection, a protection mechanism, an escape mechanism, a skill priority and the like, and further specific choices are provided in each decision choice, for example, the direction of the priority attack target also has a target which is not against attack by the priority attack, the priority attack causes little harm to the user, the priority attack defense is low, the priority attack hit rate is high, the priority attack avoidance rate is low, the priority attack treatment occupation is low, the priority attack can hit equally branch choices which are captured by the priority attack and are light, the priority attack is not shield, the direction of the moving position also has a branch choice which is preferentially moved to the direction of an enemy, the direction of the moving position of the priority is preferentially moved to the position which can hide the user, the direction of the range selection also has a branch choice which is nearest in the range of the user attack, the direction of the priority attack is selected to the greatest, the direction of the protection mechanism also has a branch choice which is reversely escaped and used when the HP of the user is less than 70%, the direction of the user wants to kill a blood loss is equal to the direction of the priority attack, the direction of the priority attack is far away from the skill, and the skill of the skill is far away from the range of the priority attack choice, and the user has a branch choice which is far away from the priority choice. Each event or attribute change is an optional behavior decision before the virtual object acts, and meanwhile, each event or attribute change has own basic behavior value score.

Scoring various events and attribute changes which may occur in the game, and then feeding back the score generated by each operation to the virtual object serving as the game AI, and performing final decision selection by the virtual object. However, since the physical factors (such as the style of the business, the character bias, etc.) of each virtual object are different, different decision results may be generated after the score is fed back to the virtual object. The scoring generated by various events and attribute changes in the game is well defined by game designers according to game configuration, for example, in the battle chess game, steps of walking and moving are more than those of the traditional round-making game, and the game is not surrounded by opponents, so that the game is a means for increasing living space of playing the battle chess game, and the virtual object can obtain higher score when selecting fewer positions of surrounding enemies for moving in decision making. Each behavior in the game is given a different value that the game designer specifies based on different needs.

In some embodiments, the determining the first behavioral score according to the impact of the body factor on the underlying behavioral score specifically includes:

In this embodiment, after the most basic decision logic of the virtual object is completed through the basic action value score, various physical factors are added to the most basic decision logic to enrich the behavior logic of the virtual object, so that each independent virtual object has unique characteristics. Referring to fig. 4, configuration editing of physical factors of a virtual object adopts a classical AI node editor mode, which is beneficial to a game designer to perform custom setting to expand the AI function of a game according to the requirements of the project. The AI node editor has the advantage that it can be written as a function based on the AI basic Model, or can be used for more subdivision configuration of a function.

In some embodiments, the determining the second behavior value score according to the preset weight of the personality factor and the basic behavior value score of the behavior corresponding to the personality factor specifically includes:

In this embodiment, character factors used to simulate AI's character may influence the AI evaluation behavior score, and referring to fig. 4, character factors exemplify brave, firm, peace, love, etc., such as "brave", "firm", the character of AI may obtain more behavior value scores in aggressive behavior and aggressive mobile behavior.

When the character factors are multiple and have similar properties, adding and dividing basic behavior value components of the first behavior after overlapping according to preset weights of the character factors; when the character factors are multiple and have opposite properties, the different first behaviors are added and divided respectively. The character factor describes the AI in a form similar to a "tag", so that there may be multiple descriptions at the same time. The tags with similar properties can increase the weight of the corresponding scheme of the AI identification, for example, if the description words of the bias attack behaviors such as brave, love war, aggressive and the like are input in the character description of the AI, the behavior value score obtained by the AI attack behaviors can be greatly increased, and the possibility of the AI to select the attack behaviors is higher. Sometimes there will be two polarized tag descriptions, and this will determine the scores of the corresponding behaviors according to the respective weights, for example, there are two tags in the tag descriptions, "peace" and "love war", the former will increase the score of the behavioral value of the defending class behavior, the latter will increase the score of the behavioral value of the attacking class behavior, the two will not interfere, and the AI will also change in the choice of behavior along with the change of the tag weight distribution.

The attack behavior refers to the behavior of fighting against other combat units in the game, the aggressive movement behavior refers to the movement strategy which is actively close to and against an opponent in a round game (such as a combat chess game) with the movement strategy, and the defending behavior refers to the behavior which does not directly generate an anti-conflict with other combat units in the game to actively defend.

Therefore, when the character factor of the virtual object is "brave", "fast", the first behavior corresponding to the character factor is the attack type behavior or the aggressive type movement behavior, if the basic behavior value of the attack type behavior or the aggressive type movement behavior is 1 score, the basic behavior value of the attack type behavior or the aggressive type movement behavior is improved due to the character factors such as "brave", "fast", etc., for example, the weight of the character factors such as "brave", "fast" is set to be 1.5, and then the second behavior value of the attack type behavior or the aggressive type movement behavior is changed to be 1.5, but at the same time, the second behavior value of the attack type behavior or the aggressive type movement behavior is higher considering the addition of the preset weights of the character factors close to various tags.

In some embodiments, the determining a third behavior value score according to the attribute comparison weight and the basic behavior value score of each basic attribute of the virtual object specifically includes:

In this embodiment, the attribute comparison weight may affect the score weight of the AI when performing attribute comparison with the enemy, for example, the value score of each 1 point of attack force in the game is 3 points, and the attack attribute comparison weight of the AI is 1.5 points, so that the score of each 1 point of attack attribute is 4.5 points, which is only an example of a score calculation mode, and a specific implementation mode may be due to the problem of game environment, and a simple multiplication formula is not used, but a more complex formula is used. For example, because the occupation and attribute trends of different roles are different, the attack force attribute weight of the attack type role is set higher, so that the frequency of the AI selection attack behavior can be increased, and referring to fig. 4, the attribute comparison weight in fig. 4 includes: life 1.2, attack 1.5 and defense 0.9, the attribute comparison weight is that of a typical attack-type character.

In some embodiments, the determining, according to the degree of wisdom, a fourth behavioral score generated by a high-score behavior or a low-score behavior or a data sampling number of the virtual object specifically includes:

In this embodiment, the wisdom of the virtual object may limit the behavior operation of the virtual object with a higher selection behavior score, i.e., the higher wisdom the higher the likelihood of a selection behavior score. The sum of the high-score weight and the low-score weight is equal to 100%, wherein the high-score weight refers to the frequency of occurrence of operations with higher selection action value scores, the low-score weight refers to the frequency of occurrence of operations with lower selection action value scores, the high-score weight or the low-score weight can be set as a percentage according to the requirements of game items, or the high-score operation probability or the low-score operation probability is determined in a mode of 'occurrence weight value/total weight value', that is, the higher the high-score weight is, the lower the low-score weight is, the more likely the virtual object triggers the high-score action operation, and conversely, the lower the high-score weight is, the higher the low-score weight is, and the probability that the virtual object triggers the low-score action operation is higher. Meanwhile, the system sorts all behavior operations in descending order according to the behavior value, in fig. 4, the high-score weight is 50%, the low-score weight is 50%, after the sorting work is completed, the system sets the high-score interval to be 90% -100%, when the virtual object triggers the high-score operation, the first 10% of the high-score operations in all data are selected, and the low-score interval is set to be 0% -10%, when the virtual object triggers the low-score operation, the last 10% of the low-score operations in all data are selected, namely, the virtual object has 50% possibility of triggering the high-score operation, and also has 50% possibility of triggering the low-score operation.

In addition to the limitation of high and low score weights on the intelligent degree of the virtual object, the number of data samples is also a configuration option for performing supplementary editing on the AI intelligent program of the virtual object, by increasing the number of analysis samples and predicting the action trends of the user and the opponent after the end of the present round. As shown in fig. 4, the number of sampling steps of the virtual object is 10, which can be understood as predicting the action trend of the virtual object and the hostile virtual object of the virtual object in the next 10 rounds in the round game, and performing a calculation of a behavior value score. The higher the number of data samples, the more intelligent the virtual object is.

In some embodiments, the determining the fifth behavioral score generated by the action policy of the virtual object according to the scene of the virtual object specifically includes:

In this embodiment, referring to fig. 4, the action policies are classified into an attack class, a treatment assistance class, and a displacement class, where the attack class and the treatment assistance class correspond to professional types of virtual objects, and the displacement class corresponds to movement actions of the virtual objects. In addition, the action policy of the virtual object further includes a disable instruction and a score instruction, where the disable instruction is used to limit the virtual object from never making an operation, such as never attacking a certain character, and the score instruction is used to make the virtual object more prone to make an operation, and most of cases, to match with a character setting in a scenario, such as letting a soldier AI preferentially crack a mechanism and not attack an enemy. In the action strategies of the attack class, enemies with high priority attack life values are included, a range of more enemies is preferentially attacked when group skills are used, a certain occupation is preferentially attacked, a certain person is preferentially attacked, the attack is not carried out on the certain person, the attack is not carried out on a certain building, and branch action strategies such as a certain skill and the like are not used under special conditions; among the action strategies of the treatment assistance class, there are action strategies such as releasing treatment skills preferentially to teammates with lower life values, releasing treatment skills preferentially to someone, and the like; among the movement strategies of the displacement type, there are movement strategies such as movement to a grid close to the enemy and movement to a grid with a higher topography, in which the enemy's occupation is a therapeutic grid.

In the case of the prohibition instruction and the score adding instruction, one action strategy is selected according to action strategies of different occupation types or movement actions, and under the condition that no other physical factors affect, the action strategy with the highest action value score and which is not prohibited is generally selected.

In some embodiments, the determining, according to the inverse factor, a sixth behavioral score generated by the virtual object violating the command of the first virtual object specifically includes:

In this embodiment, typically, when the virtual object is a soldier AI, the virtual object is often required to be affected by a command of a first virtual object as a command authority AI, and thus the inverse factor is used to determine the degree to which the virtual object selects to execute or resists executing when a temporary instruction is issued by the command authority AI. In the case of no inverse factor, the virtual object defaults to 100% to execute the temporary instruction sent by the director AI, but if the node of the inverse factor is added in the AI node editor, it will be determined whether to select according to the percentage set by the node. For example, after the soldier AI has analyzed the behavioral score of each behavioral operation, the attacking enemy will obtain 120 branch behavioral scores, a certain teammate will be treated to obtain 100 branch behavioral scores, and the commander AI issues instructions to tell this soldier AI that if a certain teammate is treated, this soldier AI will typically perform up to 160 branch therapeutic teammate options, but because of the presence of the inverse factor (as shown in fig. 4, it may be assumed here that the inverse value is 50%), this additional score given by the commander will become 40×50% = 20 points, i.e. the additional behavioral score will be reduced according to the inverse value of the inverse factor, at this time both options are 120 points, and the soldier AI will not be 100% instructions to perform the commander AI arrangement. Meanwhile, the command of the commander AI has two types of common commands and forced execution, and the forced execution commands cannot use the inverse factors to make inverse judgment.

S102: determining a behavior decision of the virtual object according to the first behavior value score and whether a game special event occurs, wherein the game special event is a preset scenario operation which is required to be made by the virtual object at a specific time and in a specific scene;

In some embodiments, the obtaining the first state of the virtual object, and determining the second state of the virtual object according to the first behavioral score and the first state specifically includes:

In this embodiment, in order to ensure a specific function established by deduction of a scenario, etc., some scenario operations set up for a specific person are performed at a specific time, a scene, for example, an enemy NPC present in a certain scenario scene does not attack a certain my character but is selected as its return life value. Therefore, it is necessary to determine whether the virtual object has a game special event, if yes, make a behavior decision according to the game special event, otherwise make a behavior decision according to the first behavior value score.

In addition, the design of the fight AI for the BOSS in stages can be better simulated by the score type behavior decision mode, and the design is more intelligent. Referring to FIG. 5, in a conventional BOSS-AI segmented design, the system monitors the BOSS status and switches the form of the BOSS, such as by monitoring the blood level of the BOSS to get the new skill and AI attack logic in the second phase when the life value is less than 50%, which sometimes gives the player a noticeable phase tearing sensation when experiencing the BOSS combat. Referring to fig. 6, according to the method provided by the embodiment of the present invention, when the BOSS reaches the system monitoring condition, a new stage influencing factor is directly superimposed into the basic form, and the decision of the bos-AI is changed by means of the score weight, so that the tearing feeling of the player in the fight feeling can be obviously reduced, and meanwhile, the bos can be directly converted into the second personality by means of completely erasing the normal state.

Referring to fig. 7, the embodiment of the present invention further provides a scoring type behavior decision device 7 of a virtual object, where the device 7 specifically includes:

a first processing module 701, configured to obtain a basic behavior value score of each event or attribute change that may occur before the virtual object acts in the game;

a second processing module 702, configured to determine a physical factor of the virtual object based on the character factor, the attribute comparison weight, the wisdom degree, the action policy, and the inverse factor of the virtual object, and determine a first behavior value score according to an effect of the physical factor on the basic behavior value score;

a behavior decision module 703, configured to determine a behavior decision of the virtual object according to the first behavior score and whether a game special event occurs, where the game special event is a preset scenario operation required to be made by the virtual object at a specific time and a specific scene;

and the state switching module 704 is configured to obtain a first state of the virtual object, and switch the state of the virtual object according to the first behavior score and the first state.

It can be understood that the content in the embodiment of the score-type behavior decision method of the virtual object shown in fig. 1 is applicable to the embodiment of the score-type behavior decision device of the virtual object, and the functions of the embodiment of the score-type behavior decision device of the virtual object are the same as those of the embodiment of the score-type behavior decision method of the virtual object shown in fig. 1, and the advantages achieved are the same as those achieved by the embodiment of the score-type behavior decision method of the virtual object shown in fig. 1.

It should be noted that, because the content of information interaction and execution process between the above devices is based on the same concept as the method embodiment of the present application, specific functions and technical effects thereof may be referred to in the method embodiment section, and will not be described herein.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.

Referring to fig. 8, an embodiment of the present invention further provides a computer device 8, including: a memory 802 and a processor 801 and a computer program 803 stored on the memory 802, which computer program 803, when executed on the processor 801, implements a method for scored behavior decision of a virtual object according to any one of the above methods.

The computer device 8 may be a desktop computer, a notebook computer, a palm computer, a cloud server, or the like. The computer device 8 may include, but is not limited to, a processor 801, a memory 802. It will be appreciated by those skilled in the art that fig. 8 is merely an example of computer device 8 and is not intended to be limiting of computer device 8, and may include more or fewer components than shown, or may combine certain components, or different components, such as may also include input-output devices, network access devices, etc.

The processor 801 may be a central processing unit (Central Processing Unit, CPU), the processor 801 may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 802 may in some embodiments be an internal storage unit of the computer device 8, such as a hard disk or a memory of the computer device 8. The memory 802 may also be an external storage device of the computer device 8 in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the computer device 8. Further, the memory 802 may also include both internal storage units and external storage devices of the computer device 8. The memory 802 is used to store an operating system, application programs, boot loader (BootLoader), data, and other programs, etc., such as program code for the computer program, etc. The memory 802 may also be used to temporarily store data that has been output or is to be output.

The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when being run by a processor, implements the score-type behavior decision method of the virtual object according to any one of the above methods.

In this embodiment, the integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiments, and may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code to a photographing device/terminal apparatus, recording medium, computer Memory, read-Only Memory (ROM), random access Memory (RAM, random Access Memory), electrical carrier signals, telecommunications signals, and software distribution media. Such as a U-disk, removable hard disk, magnetic or optical disk, etc. In some jurisdictions, computer readable media may not be electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the disclosed embodiments of the application, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the apparatus/terminal device embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical function division, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

Claims

1. A method for scoring behavior decision-making of a virtual object, the method comprising:

2. The method according to claim 1, wherein said determining a first behavioral score based on the impact of said body factor on said underlying behavioral score comprises:

3. The method according to claim 2, wherein the determining the second behavior value score according to the preset weight of the personality factor and the basic behavior value score of the behavior corresponding to the personality factor specifically includes:

4. The method according to claim 2, wherein the determining a third behavioral score according to the attribute comparison weight and the basic behavioral score of each basic attribute of the virtual object specifically comprises:

5. The method according to claim 2, wherein determining the fourth behavioral score generated by the high-score or low-score behaviors or the number of data samples of the virtual object according to the degree of wisdom, specifically comprises:

6. The method according to claim 2, wherein the determining the fifth behavioral score generated by the action policy of the virtual object according to the scene in which the virtual object is located specifically comprises:

7. The method according to claim 2, wherein the determining, according to the inverse factor, a sixth behavioral value score generated by the virtual object violating the command of the first virtual object, specifically comprises:

8. The method according to claim 1, wherein the obtaining the first state of the virtual object, and the determining the second state of the virtual object according to the first behavioral score and the first state, specifically comprises:

9. A scoring type behavior decision-making device for a virtual object, which is characterized by comprising the following specific components:

10. A computer device, comprising: memory and processor and computer program stored on the memory, which when executed on the processor, implements the score-wise behavior decision method of a virtual object according to any one of claims 1 to 8.