CN110841296A - Game character skill generation method and device, electronic equipment and storage medium - Google Patents
Game character skill generation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN110841296A CN110841296A CN201911104040.XA CN201911104040A CN110841296A CN 110841296 A CN110841296 A CN 110841296A CN 201911104040 A CN201911104040 A CN 201911104040A CN 110841296 A CN110841296 A CN 110841296A
- Authority
- CN
- China
- Prior art keywords
- target
- skill
- action
- preset
- initial
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
- A63F13/60—Generating or modifying game content before or while executing the game program, e.g. authoring tools specially adapted for game development or game-integrated level editor
- A63F13/67—Generating or modifying game content before or while executing the game program, e.g. authoring tools specially adapted for game development or game-integrated level editor adaptively or by learning from player actions, e.g. skill level adjustment or by storing successful combat sequences for re-use
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
- A63F13/80—Special adaptations for executing a specific game genre or game mode
- A63F13/822—Strategy games; Role-playing games
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F2300/00—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game
- A63F2300/60—Methods for processing data by generating or executing the game program
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F2300/00—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game
- A63F2300/80—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game specially adapted for executing a specific type of game
- A63F2300/807—Role playing or strategy games
Abstract
The application provides a method and a device for generating game role skills, electronic equipment and a storage medium, and relates to the technical field of game production. According to the method, parameter information of basic reference actions is obtained through a preset action detection algorithm, the target virtual character is redirected according to a preset skeleton redirection algorithm and the parameter information of the basic reference actions, the redirected target basic actions can be obtained, the manufacturing period of the target basic actions can be shortened, and further, when the target skills of the target virtual character are generated according to the target basic actions, preset target skill labels and a special effect generation model, new character skills can be obtained according to the basic reference actions, the manufacturing period of game character skills is greatly shortened, and the manufacturing efficiency is improved.
Description
Technical Field
The present application relates to the field of game production technologies, and in particular, to a method and an apparatus for generating game character skills, an electronic device, and a storage medium.
Background
The game role is used as an important virtual character in the game, and can comprise various game roles according to different game types, each game role has corresponding role skill and special effect, and the game playing experience of the game can be effectively improved due to the diversity of the game role skill and the special effect.
At present, most games use traditional manufacturing methods to manufacture game role skills, namely, the forms and effects of the skill are designed through game planning, skill actions and special effects are manufactured through art, skill values and skill balance are tested and adjusted, and finally the action and special effect expressions of the skill can be presented.
However, the existing manufacturing method has the problems of long manufacturing period of the character skills in the game, high testing and tuning cost and low manufacturing efficiency.
Disclosure of Invention
The present application is directed to provide a method, an apparatus, an electronic device, and a storage medium for generating game character skills, which can solve the technical problems of long game character skill creation period and low creation efficiency in the prior art.
In order to achieve the above purpose, the technical solutions adopted in the embodiments of the present application are as follows:
in a first aspect, an embodiment of the present application provides a game character skill generation method, including:
acquiring parameter information of a basic reference action by adopting a preset action detection algorithm, wherein the parameter information of the basic reference action comprises position information of a skill key point; redirecting the target virtual character according to a preset skeleton redirection algorithm and parameter information of the basic reference action, and acquiring a redirected target basic action; and generating the target skill of the target virtual character according to the target basic action, the preset target skill label and the special effect generation model.
Optionally, the generating the target skill of the target virtual character according to the target basic action, the preset target skill tag and the special effect generation model includes: acquiring a target skill special effect according to a target basic action, a preset target skill label and a special effect generation model, wherein the special effect generation model is acquired according to training of a training sample, and the training sample comprises a plurality of historical skill actions, and a skill label and a skill special effect corresponding to each historical skill action; and generating the target virtual character skill according to the target virtual character, the target basic action and the target skill special effect.
Optionally, the obtaining a target skill special effect according to the target basic action, the preset target skill label and the special effect generation model includes: training the target basic action by adopting a preset training algorithm according to the target basic action and a preset target action parameter, and acquiring an action which meets the preset target action parameter and has the minimum deviation from the target basic action as a target action; and inputting the target action and a preset target skill label into the special effect generation model to generate a target skill special effect.
Optionally, the generating the target skill of the target virtual character according to the target basic action, the preset target skill tag and the special effect generating model includes: generating an initial role skill of the target virtual role according to the target virtual role, the target basic action and the target skill special effect; acquiring initial fighting parameters of target virtual character skills under the preset initial skill parameters according to the preset initial skill parameters and the initial character skills; adjusting a preset initial skill parameter according to the target fighting parameter and the initial fighting parameter, and acquiring a target skill parameter meeting the target fighting parameter; and generating target skills meeting the target fighting parameters according to the target skill parameters and the initial role skills.
Optionally, the obtaining of the initial engagement parameter of the target virtual character skill under the preset initial skill parameter according to the preset initial skill parameter and the initial character skill includes: the method comprises the steps of training skills of an initial role skill of a target virtual role and a plurality of preset roles, and obtaining initial fighting parameters of the target virtual role skill under the preset initial skill parameters, wherein the initial fighting parameters comprise an initial skill action range parameter and an initial skill action effect parameter.
Optionally, in the above method, the skill key points comprise a combination of one or more of: the head, trunk and limbs of the character.
Optionally, before the obtaining the parameter information of the basic reference motion by using the preset motion detection algorithm, the method further includes: and acquiring a basic reference action according to a preset role action library or a multimedia resource library.
In a second aspect, an embodiment of the present application provides an apparatus for generating game character skills, including: the device comprises a first acquisition module, a second acquisition module and a generation module; the first acquisition module is used for acquiring parameter information of a basic reference action by adopting a preset action detection algorithm, wherein the parameter information of the basic reference action comprises position information of a skill key point; the second acquisition module is used for redirecting the target virtual character according to a preset skeleton redirection algorithm and parameter information of the basic reference action, and acquiring the redirected target basic action; and the generating module is used for generating the target skill of the target virtual character according to the target basic action, the preset target skill label and the special effect generating model.
Optionally, the generating module is specifically configured to obtain a target skill special effect according to the target basic motion, a preset target skill label and a special effect generating model, where the special effect generating model is obtained according to training of a training sample, and the training sample includes a plurality of historical skill motions and a skill label and a skill special effect corresponding to each historical skill motion; and generating the target virtual character skill according to the target virtual character, the target basic action and the target skill special effect.
Optionally, the generating module is specifically configured to train the target basic motion by using a preset training algorithm according to the target basic motion and a preset target motion parameter, and acquire a motion which satisfies the preset target motion parameter and has the minimum deviation from the target basic motion as the target motion; and inputting the target action and a preset target skill label into the special effect generation model to generate a target skill special effect.
Optionally, the generating module is specifically configured to generate an initial character skill of the target virtual character according to the target virtual character, the target basic action, and the target skill special effect; acquiring initial fighting parameters of target virtual character skills under the preset initial skill parameters according to the preset initial skill parameters and the initial character skills; adjusting a preset initial skill parameter according to the target fighting parameter and the initial fighting parameter, and acquiring a target skill parameter meeting the target fighting parameter;
and generating target skills meeting the target fighting parameters according to the target skill parameters and the initial role skills.
Optionally, the generating module is specifically configured to perform skill training on the initial character skills of the target virtual character and a plurality of preset characters, and obtain initial fighting parameters of the target virtual character skills under preset initial skill parameters, where the initial fighting parameters include an initial skill action range parameter and an initial skill action effect parameter.
Optionally, in the above apparatus, the skill key point comprises a combination of one or more of: the head, trunk and limbs of the character.
Optionally, the first obtaining module is further configured to obtain the basic reference action according to a preset role action library or a multimedia resource library.
In a third aspect, an embodiment of the present application provides an electronic device, including: the game character skill generating method comprises a processor, a storage medium and a bus, wherein the storage medium stores machine readable instructions executable by the processor, when the electronic device runs, the processor and the storage medium are communicated through the bus, and the processor executes the machine readable instructions to execute the steps of the game character skill generating method of the first aspect.
In a fourth aspect, the present application provides a storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the game character skill generation method as described in the first aspect.
The beneficial effect of this application is:
in the game character skill generation method, the game character skill generation device, the electronic device and the storage medium provided by the embodiment of the application, the parameter information of the basic reference action is acquired by adopting the preset action detection algorithm, the target virtual character is redirected according to the preset skeleton redirection algorithm and the parameter information of the basic reference action, the redirected target basic action can be acquired, the manufacturing period of the target basic action can be shortened, and then the target skill of the target virtual character is generated according to the target basic action, the preset target skill label and the special effect generation model, so that the new character skill can be acquired according to the basic reference action, the manufacturing period of the game character skill is greatly shortened, and the manufacturing efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a schematic flowchart of a game character skill generating method according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart of another game character skill generation method provided in the embodiment of the present application;
fig. 3 is a schematic flowchart of a method for generating skills of a game character according to an embodiment of the present application;
fig. 4 is a schematic flow chart of another game character skill generation method provided in the embodiment of the present application;
fig. 5 is a schematic flowchart of a method for generating skills of a game character according to an embodiment of the present application;
fig. 6 is a schematic flow chart of a game character skill generating apparatus according to an embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
Fig. 1 is a flowchart of a method for generating game character skills according to an embodiment of the present application, where an execution subject of the method may be a computer, a server, a processor, a mobile terminal, a wearable device, or other devices that can perform data processing, and the present application is not limited herein, as shown in fig. 1, the method includes:
s101, acquiring parameter information of a basic reference action by adopting a preset action detection algorithm, wherein the parameter information of the basic reference action comprises position information of a skill key point.
The basic reference action is taken as a reference action of the target basic action and can be obtained from historical virtual role actions, actions of other virtual roles, multimedia resources related to the actions and the like; the preset action detection algorithm can be realized based on a skeleton key point detection algorithm and is used for obtaining position information of skill key points in basic reference actions, different skill key points can be corresponding to different basic reference actions, the skill key points can comprise key points such as the head, trunk and limbs of a character in the basic reference actions, and the skill key points are not limited in the application.
For example, the basic reference motion is a jumping motion, and correspondingly, the skill key point may include position information of the head, the trunk, and the limbs of the character in the basic motion.
S102, redirecting the target virtual character according to a preset skeleton redirection algorithm and parameter information of the basic reference action, and acquiring the redirected target basic action.
The bone redirection algorithm can redirect the target virtual character according to the position information of the skill key points in the basic reference action, so that the target virtual character can obtain the target basic action with the same motion trail according to the position information of the skill key points of the basic reference action, the production period of the target basic action can be shortened, the ab initio production is avoided, and the production efficiency of the target basic action is improved.
For example, if the base virtual character is a and the corresponding base reference action is a jump, the base reference action is redirected to the target virtual character B, that is, the target base action corresponding to the target virtual character B is also a jump.
In addition, it should be noted that the implementation manners of the preset motion detection algorithm and the preset bone redirection algorithm are not limited in this application, and may be implemented based on an artificial intelligence algorithm, a machine learning algorithm, and the like.
S103, generating the target skill of the target virtual character according to the target basic action, the preset target skill label and the special effect generation model.
The preset skill label is used for describing the expression form of the skill and the expected achieved skill effect, and the target skill of the target virtual character can be generated with the obtained target basic action and special effect generation model, so that the target virtual character can execute the target basic action and simultaneously generate the target skill special effect.
To sum up, in the game character skill generation method provided in the embodiment of the present application, the parameter information of the basic reference motion is obtained by using the preset motion detection algorithm, and the target virtual character is redirected according to the preset bone redirection algorithm and the parameter information of the basic reference motion, so that the redirected target basic motion can be obtained, the production cycle of the target basic motion can be shortened, and then the target skill of the target virtual character is generated according to the target basic motion, the preset target skill tag and the special effect generation model, so that the new character skill can be obtained according to the basic reference motion, the production cycle of the game character skill is greatly shortened, and the production efficiency is improved.
Fig. 2 is a schematic flow chart of another game character skill generation method provided in the embodiment of the present application. Optionally, as shown in fig. 2, the generating of the target skill of the target virtual character according to the target basic action, the preset target skill tag, and the special effect generation model includes:
s201, obtaining a target skill special effect according to the target basic action, the preset target skill label and the special effect generation model.
The special effect generation model is obtained according to training of a training sample, and the training sample comprises a plurality of historical skill actions, and a skill label and a skill special effect which correspond to each historical skill action.
Optionally, the special effect generation model may be obtained by training the training sample through an artificial intelligence algorithm, for example, a Generative Adaptive Network (GAN) may be selected to train and obtain a plurality of historical skill actions and skill labels and skill special effects corresponding to each historical skill action, so that the target skill special effects may be obtained according to the target basic actions and preset target skill labels by the special effect generation model obtained through training.
S202, generating the target virtual character skill according to the target virtual character, the target basic action and the target skill special effect.
After the target skill special effect is generated, the target basic action and the target skill special effect can be integrated on the target virtual character, and the target virtual character skill is obtained, so that the corresponding target skill special effect can be displayed when the target virtual character executes the target basic action, and the target virtual character skill can be completely displayed.
Fig. 3 is a schematic flowchart of a method for generating skills of a game character according to an embodiment of the present application. Optionally, as shown in fig. 3, the obtaining of the target skill special effect according to the target basic action, the preset target skill label, and the special effect generation model includes:
s301, training the target basic action by adopting a preset training algorithm according to the target basic action and the preset target action parameter, and acquiring the action which meets the preset target action parameter and has the minimum deviation from the target basic action as the target action.
Optionally, based on the target basic motion, by setting a preset target parameter, training the target basic motion by using a preset training algorithm, and through the process of gradual training and adjustment, obtaining a motion which satisfies the preset target motion parameter and has the minimum deviation from the target basic motion as the target motion, so that the manufacturing cycle of the target motion can be shortened. The training process can be obtained by referring to the following process, feedback Reward is given according to the difference value between the virtual character action and the basic reference action in the training process, negative feedback Reward is given more when the difference value is larger, and more positive feedback Reward is given when the virtual character action is close to or reaches the target action, so that training is carried out, and finally, an action which can meet the preset target action parameter and has the minimum deviation from the basic reference action can be taken as the target action of the target virtual character.
For example, the basic reference action is an action of jumping on site and then landing, the target action is set as that the foot of the virtual character needs to touch a sphere 100cm away from the ground 50cm away from the body, when the foot of the virtual character jumps on site and then lands on the ground away from the sphere, negative feedback Reward of-1 is given, when the foot of the virtual character jumps on site and then lands on the ground close to the sphere, positive feedback Reward of 1 is given, finally, an action that the foot jumps on site and can kick the sphere 100cm away from the ground 50cm away from the body is obtained, and the action can be used as the target action.
S302, inputting the target action and the preset target skill label into the special effect generation model to generate the target skill special effect.
After the target action is acquired, optionally, the target action and the preset target skill tag can also be input into a special effect generation model, and a target skill special effect which is consistent with the target action and the preset target skill tag can be generated through the special effect generation model, so that the corresponding target skill special effect can be displayed when the target virtual character executes the target action, and the target virtual character skill can be completely displayed.
Fig. 4 is a schematic flow chart of another game character skill generation method according to an embodiment of the present application. Optionally, as shown in fig. 4, the generating the target skill of the target virtual character according to the target basic action, the preset target skill tag, and the special effect generating model includes:
s401, generating initial role skills of the target virtual role according to the target virtual role, the target basic action and the target skill special effect.
S402, obtaining initial fighting parameters of the target virtual character skills under the preset initial skill parameters according to the preset initial skill parameters and the initial character skills.
The initial character skill can be the initial skill state of the target virtual character and can be obtained by integrating the target virtual character, the target basic action and the target skill special effect; presetting initial skill parameters as initial skill setting parameters of the initial character skill, for example, attack force values, attack speeds and the like of the skill can be included; the initial fight parameters may describe parameters of the initial fight result achieved under the preset initial skill parameters, such as fight action range parameters, fight action effect parameters, and the like, and the application is not limited herein.
Optionally, a preset initial skill parameter may be set for the initial character skill, and the initial character skill is initially combated with a plurality of preset characters, so as to obtain an initial combat parameter of the target virtual character skill under the preset initial skill parameter, that is, a parameter of a combat result of the target virtual character skill and other combat character skills.
And S403, adjusting the preset initial skill parameters according to the target fighting parameters and the initial fighting parameters, and acquiring the target skill parameters meeting the target fighting parameters.
The target fight parameters can describe parameters of the target fight result, such as fight action range parameters, fight action effect parameters and the like, and the application is not limited herein; the initial fighting parameters can describe parameters of an initial fighting result achieved under the preset initial skill parameters, and optionally, the preset initial skill parameters can be adjusted according to the comparison result by comparing the target fighting parameters with the initial fighting parameters, so that the target skill parameters meeting the target fighting parameters are obtained. Optionally, if the target engagement parameter is greater than the initial engagement parameter, the preset initial skill parameter may be increased to obtain a corresponding target skill parameter.
It should be noted that, in the present application, the number of times of adjustment is not limited herein, and the number of times of adjustment may be repeatedly executed until the target skill parameter meeting the target engagement parameter is acquired.
And S404, generating target skills meeting the target fighting parameters according to the target skill parameters and the initial role skills.
After the target skill parameters are obtained, the target skill parameters can be set for the initial character skills based on the initial character skills, the initial character skills are enabled to fight under the target skill parameters, and the target skills meeting the target fighting parameters can be generated, so that the corresponding target skills can be selected according to the fighting scenes and the fighting characters of the target virtual characters, and the fighting rate is improved.
Optionally, the obtaining of the initial engagement parameter of the target virtual character skill under the preset initial skill parameter according to the preset initial skill parameter and the initial character skill includes:
the method comprises the steps of training skills of an initial role skill of a target virtual role and a plurality of preset roles, and obtaining initial fighting parameters of the target virtual role skill under the preset initial skill parameters, wherein the initial fighting parameters comprise an initial skill action range parameter and an initial skill action effect parameter.
The preset roles can be similar virtual roles and also can be different virtual roles, the application is not limited, the initial target virtual role and the preset virtual roles are trained in skills, the collision range and the position of the initial target virtual role during the battle can be obtained according to the skill training result, and the initial skill action range parameter and the initial skill action effect parameter are determined.
Optionally, in the above method, the skill key point may include a combination of one or more of the following: the head, trunk and limbs of the character.
According to the actual application scenario, one or more of the head, the trunk, and the limbs of the character may be selected as the key points of the skills, which is not limited herein.
Optionally, before the obtaining the parameter information of the basic reference motion by using the preset motion detection algorithm, the method further includes:
and acquiring a basic reference action according to a preset role action library or a multimedia resource library.
The preset role action library can comprise a plurality of role actions, the multimedia video library can comprise video animations of the role actions, and actions which accord with the characteristics of the target basic actions can be screened out as basic reference actions by adopting a preset action screening algorithm according to the target basic actions. The action screening algorithm may be implemented based on an artificial intelligence algorithm, a deep learning network, and the like, which is not limited herein.
Fig. 5 is a flowchart illustrating a method for generating skills of a game character according to an embodiment of the present application. Optionally, as shown in fig. 5, the method includes:
s501, obtaining basic reference actions according to a preset role action library or a multimedia resource library.
S502, acquiring parameter information of the basic reference action by adopting a preset action detection algorithm, wherein the parameter information of the basic reference action comprises position information of the skill key point.
S503, redirecting the target virtual character according to the preset skeleton redirection algorithm and the parameter information of the basic reference action, and acquiring the redirected target basic action.
S504, training the target basic action by adopting a preset training algorithm according to the target basic action and the preset target action parameter, and acquiring the action which meets the preset target action parameter and has the minimum deviation from the target basic action as the target action.
And S505, inputting the target action and the preset target skill tag into the special effect generation model to generate the target skill special effect.
S506, generating initial role skills of the target virtual role according to the target virtual role, the target basic action and the target skill special effect.
And S507, acquiring initial fighting parameters of the target virtual character skills under the preset initial skill parameters according to the preset initial skill parameters and the initial character skills.
And S508, adjusting the preset initial skill parameters according to the target fighting parameters and the initial fighting parameters, and acquiring the target skill parameters meeting the target fighting parameters.
And S509, generating a target skill meeting the target fighting parameter according to the target skill parameter and the initial role skill.
The present application is described with reference to specific examples, for example, the basic reference motion is a rongalite in multimedia data, such as a rongalite extracted from a movie theater and applied to a character, the target virtual character is M, the target motion is performed as a palm moving to two sides of a body instead of moving to the right front, a preset target skill tag is a double-palm fire-phoenix hitting, enemies on two sides are burned, the special effect of the skill is phoenix-related instead of dragon, and the target fighting parameter may be a target winning rate, that is, a winning rate of a player in the original skill system for target skill fighting.
The embodiment is described herein with an exemplary winning rate of about 60% (e.g. 59% -61% of the winning rate is acceptable), and the target virtual character skill can be obtained by the following process: the basic reference action of the descending dragon eighteen pawns is obtained according to a preset role action library or a multimedia resource library, optionally, if the preset role action library exists, the basic reference action can be directly used, if the preset role action library does not exist, a related video segment of the basic reference action can be searched from the multimedia resource library, after the related video segment is searched, the position information of the skill key points (namely key points such as the head, trunk and limbs of the role) of the role in the video can be obtained from the related video segment through a skeleton detection technology, and then a skeleton redirection algorithm is used for redirecting the skeleton action to the target virtual role M so as to obtain the target basic action. More specifically, the relevant video segments can be segmented into multiple frames, the position information of the skill key points (namely key points of the head, trunk, limbs and the like of the character) of the character in each frame is extracted, then the skeleton action is redirected to the target virtual character M by using a skeleton redirection algorithm, and the complete target basic action can be formed after the skeleton action is continuous.
Optionally, the preset target action may be that the two palms of the character collide with two spheres at the same height as the shoulders on both sides of the body, corresponding preset target action parameters may be set according to the preset target action, and the action which is minimum in the action of getting out of the palms on both sides of the body and deviating from the target base action is acquired as the target action after training; outputting a special effect generation model for target actions (palming towards two sides of a body) and preset target skill special effects (double palms play fire and phoenix, burning enemies on two sides), so as to generate corresponding target skill special effects (special effects related to phoenix) and obtain the initial character skills of the target virtual character.
Optionally, a preset initial skill parameter may be set for the initial character skill of the target virtual character (for example, the skill injury is 2 × the attack force +100), and the initial skill may be obtained; the initial skill is added into the character skill, the character with the target skill and the character without the target skill are subjected to fighting training by using the reinforcement learning skill, so that the target skill of the virtual target character can overcome the character without the target skill when fighting under the target fighting parameter, the target skill parameter can be obtained after the training is converged, and the target virtual character can obtain the optimal performance of the character with the target skill under the target skill parameter. In the training process, the value is automatically weakened if the statistical success rate is higher than the expectation, and the value is strengthened if the statistical success rate is lower than the expectation until the statistical success rate is equal to the expectation.
Fig. 6 is a schematic flow chart of a game character skill generating device provided in an embodiment of the present application, a basic principle and a generated technical effect of the device are the same as those of the corresponding method embodiment, and for brief description, reference may be made to corresponding contents in the method embodiment for a part not mentioned in this embodiment. As shown in fig. 6, the apparatus includes: a first obtaining module 110, a second obtaining module 120 and a generating module 130.
The first obtaining module 110 is configured to obtain parameter information of a basic reference motion by using a preset motion detection algorithm, where the parameter information of the basic reference motion includes location information of a skill key point; the second obtaining module 120 is configured to redirect the target virtual character according to a preset skeleton redirection algorithm and parameter information of the basic reference action, and obtain a redirected target basic action; the generating module 130 is configured to generate a target skill of the target virtual character according to the target basic action, the preset target skill tag, and the special effect generating model.
Optionally, the generating module 130 is specifically configured to obtain a target skill special effect according to the target basic motion, a preset target skill label and a special effect generating model, where the special effect generating model is obtained according to training of a training sample, and the training sample includes a plurality of historical skill motions and a skill label and a skill special effect corresponding to each historical skill motion; and generating the target virtual character skill according to the target virtual character, the target basic action and the target skill special effect.
Optionally, the generating module 130 is specifically configured to train the target basic motion by using a preset training algorithm according to the target basic motion and a preset target motion parameter, and acquire a motion that meets the preset target motion parameter and has the minimum deviation from the target basic motion as the target motion; and inputting the target action and a preset target skill label into the special effect generation model to generate a target skill special effect.
Optionally, the generating module 130 is specifically configured to generate an initial character skill of the target virtual character according to the target virtual character, the target basic action, and the target skill special effect; acquiring initial fighting parameters of target virtual character skills under the preset initial skill parameters according to the preset initial skill parameters and the initial character skills; adjusting a preset initial skill parameter according to the target fighting parameter and the initial fighting parameter, and acquiring a target skill parameter meeting the target fighting parameter; and generating target skills meeting the target fighting parameters according to the target skill parameters and the initial role skills.
Optionally, the generating module 130 is specifically configured to perform skill training on the initial character skill of the target virtual character and a plurality of preset characters, and obtain an initial engagement parameter of the target virtual character skill under a preset initial skill parameter, where the initial engagement parameter includes an initial skill action range parameter and an initial skill action effect parameter.
Optionally, in the above apparatus, the skill key point may include a combination of one or more of the following: the head, trunk and limbs of the character.
Optionally, the first obtaining module 110 is further configured to obtain the basic reference action according to a preset role action library or a multimedia resource library.
The above-mentioned apparatus is used for executing the method provided by the foregoing embodiment, and the implementation principle and technical effect are similar, which are not described herein again.
These above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), among others. For another example, when one of the above modules is implemented in the form of a processing element scheduler code, the processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).
Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 7, the electronic device may include: a processor 210, a storage medium 220, and a bus 230, wherein the storage medium 220 stores machine-readable instructions executable by the processor 210, and when the electronic device is operated, the processor 210 communicates with the storage medium 220 via the bus 230, and the processor 210 executes the machine-readable instructions to perform the steps of the above-mentioned method embodiments. The specific implementation and technical effects are similar, and are not described herein again.
Optionally, the present application further provides a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the computer program performs the steps of the above method embodiments. The specific implementation and technical effects are similar, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed 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 can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to perform some steps of the methods according to the embodiments of the present application. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (16)
1. A method for generating game character skills, comprising:
acquiring parameter information of a basic reference action by adopting a preset action detection algorithm, wherein the parameter information of the basic reference action comprises position information of a skill key point;
redirecting the target virtual character according to a preset skeleton redirection algorithm and parameter information of the basic reference action, and acquiring a redirected target basic action;
and generating the target skill of the target virtual character according to the target basic action, a preset target skill label and a special effect generation model.
2. The method according to claim 1, wherein generating the target skill of the target virtual character according to the target basic action, a preset target skill tag and a special effect generation model comprises:
acquiring a target skill special effect according to the target basic action, a preset target skill label and the special effect generation model, wherein the special effect generation model is acquired according to training of a training sample, and the training sample comprises a plurality of historical skill actions, and a skill label and a skill special effect which correspond to each historical skill action;
and generating the target virtual character skill according to the target virtual character, the target basic action and the target skill special effect.
3. The method according to claim 2, wherein obtaining a target skill special effect according to the target basic action, a preset target skill tag and the special effect generation model comprises:
training the target basic action by adopting a preset training algorithm according to the target basic action and a preset target action parameter, and acquiring an action which meets the preset target action parameter and has the minimum deviation from the target basic action as a target action;
and inputting the target action and a preset target skill label into a special effect generation model to generate a target skill special effect.
4. The method according to claim 2 or 3, wherein the generating the target skill of the target virtual character according to the target basic action, the preset target skill tag and the special effect generation model comprises:
generating an initial role skill of the target virtual role according to the target virtual role, the target basic action and the target skill special effect;
acquiring initial fighting parameters of the target virtual character skills under the preset initial skill parameters according to the preset initial skill parameters and the initial character skills;
adjusting the preset initial skill parameters according to target fighting parameters and the initial fighting parameters, and acquiring target skill parameters meeting the target fighting parameters;
and generating the target skill meeting the target fighting parameter according to the target skill parameter and the initial role skill.
5. The method according to claim 4, wherein the obtaining of the initial engagement parameters of the target virtual character skills under the preset initial skill parameters according to the preset initial skill parameters and the initial character skills comprises:
and training the initial role skills of the target virtual roles and a plurality of preset roles, and acquiring initial fighting parameters of the target virtual role skills under the preset initial skill parameters, wherein the initial fighting parameters comprise initial skill action range parameters and initial skill action effect parameters.
6. The method of claim 1, wherein the skill key points comprise a combination of one or more of: the head, trunk and limbs of the character.
7. The method according to claim 1, wherein before the obtaining the parameter information of the basic reference motion by using the preset motion detection algorithm, the method further comprises:
and acquiring the basic reference action according to a preset role action library or a multimedia resource library.
8. An apparatus for generating game character skills, comprising: the device comprises a first acquisition module, a second acquisition module and a generation module;
the first acquisition module is used for acquiring parameter information of a basic reference action by adopting a preset action detection algorithm, wherein the parameter information of the basic reference action comprises position information of a skill key point;
the second acquisition module is used for redirecting the target virtual character according to a preset skeleton redirection algorithm and parameter information of the basic reference action, and acquiring the redirected target basic action;
and the generating module is used for generating the target skill of the target virtual character according to the target basic action, a preset target skill label and a special effect generating model.
9. The device according to claim 8, wherein the generating module is specifically configured to obtain a target skill special effect according to the target basic motion, a preset target skill label, and the special effect generating model, wherein the special effect generating model is obtained according to training of a training sample, and the training sample includes a plurality of historical skill motions and a skill label and a skill special effect corresponding to each of the historical skill motions;
and generating the target virtual character skill according to the target virtual character, the target basic action and the target skill special effect.
10. The device according to claim 9, wherein the generating module is specifically configured to train the target basic motion by using a preset training algorithm according to the target basic motion and a preset target motion parameter, and obtain a motion that satisfies the preset target motion parameter and has a minimum deviation from the target basic motion as the target motion;
and inputting the target action and a preset target skill label into a special effect generation model to generate a target skill special effect.
11. The apparatus according to claim 9 or 10, wherein the generating module is specifically configured to generate an initial character skill of the target virtual character according to the target virtual character, the target basic action, and the target skill special effect;
acquiring initial fighting parameters of the target virtual character skills under the preset initial skill parameters according to the preset initial skill parameters and the initial character skills;
adjusting the preset initial skill parameters according to target fighting parameters and the initial fighting parameters, and acquiring target skill parameters meeting the target fighting parameters;
and generating the target skill meeting the target fighting parameter according to the target skill parameter and the initial role skill.
12. The apparatus according to claim 11, wherein the generating module is specifically configured to perform skill training on an initial character skill of the target virtual character and a plurality of preset characters, and obtain an initial combat parameter of the target virtual character skill under the preset initial skill parameter, where the initial combat parameter includes an initial skill action range parameter and an initial skill action effect parameter.
13. The apparatus of claim 8, wherein the skill key points comprise a combination of one or more of: the head, trunk and limbs of the character.
14. The apparatus of claim 8, wherein the first obtaining module is further configured to obtain the base reference action according to a preset role action library or a multimedia resource library.
15. An electronic device, comprising: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating via the bus when the electronic device is operating, the processor executing the machine-readable instructions to perform the steps of the method for generating game character skills according to any of claims 1-7.
16. A storage medium having stored thereon a computer program for performing the steps of the method of generating game character skills according to any of claims 1-7 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911104040.XA CN110841296B (en) | 2019-11-12 | 2019-11-12 | Game character skill generation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911104040.XA CN110841296B (en) | 2019-11-12 | 2019-11-12 | Game character skill generation method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110841296A true CN110841296A (en) | 2020-02-28 |
| CN110841296B CN110841296B (en) | 2023-09-15 |
Family
ID=69600518
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911104040.XA Active CN110841296B (en) | 2019-11-12 | 2019-11-12 | Game character skill generation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110841296B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111408140A (en) * | 2020-03-06 | 2020-07-14 | 网易（杭州）网络有限公司 | Method and device for generating character card texture in game and electronic equipment |
| CN111701240A (en) * | 2020-06-22 | 2020-09-25 | 网易（杭州）网络有限公司 | Virtual article prompting method and device, storage medium and electronic device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780681A (en) * | 2016-12-01 | 2017-05-31 | 北京像素软件科技股份有限公司 | A kind of role action generation method and device |
| CN107684720A (en) * | 2017-09-06 | 2018-02-13 | 杭州电魂网络科技股份有限公司 | Game skill generation method and device |
| CN110052031A (en) * | 2019-04-11 | 2019-07-26 | 网易（杭州）网络有限公司 | The imitation method, apparatus and readable storage medium storing program for executing of player |
-
2019
- 2019-11-12 CN CN201911104040.XA patent/CN110841296B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780681A (en) * | 2016-12-01 | 2017-05-31 | 北京像素软件科技股份有限公司 | A kind of role action generation method and device |
| CN107684720A (en) * | 2017-09-06 | 2018-02-13 | 杭州电魂网络科技股份有限公司 | Game skill generation method and device |
| CN110052031A (en) * | 2019-04-11 | 2019-07-26 | 网易（杭州）网络有限公司 | The imitation method, apparatus and readable storage medium storing program for executing of player |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111408140A (en) * | 2020-03-06 | 2020-07-14 | 网易（杭州）网络有限公司 | Method and device for generating character card texture in game and electronic equipment |
| CN111701240A (en) * | 2020-06-22 | 2020-09-25 | 网易（杭州）网络有限公司 | Virtual article prompting method and device, storage medium and electronic device |
| CN111701240B (en) * | 2020-06-22 | 2023-04-25 | 网易（杭州）网络有限公司 | Virtual article prompting method and device, storage medium and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110841296B (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109814955B (en) | Method and device for determining formation capacity and electronic equipment | |
| CN110298907B (en) | Virtual character action control method and device, computing equipment and storage medium | |
| JP6182184B2 (en) | Simulation method and system | |
| US9560131B2 (en) | Efficient synchronization of behavior trees using network significant nodes | |
| US10497163B1 (en) | Computer architecture for animation of a character in a simulation based on muscle activation data | |
| US10413829B2 (en) | System and method of implementing behavior trees when modifying attribute values of game entities based on physical token detection | |
| KR20210090239A (en) | Information prediction methods, model training methods and servers | |
| CN110841296A (en) | Game character skill generation method and device, electronic equipment and storage medium | |
| US11816772B2 (en) | System for customizing in-game character animations by players | |
| Hong et al. | AI world cup: robot-soccer-based competitions | |
| JP7031811B2 (en) | A method and system for training player characters in sports games using spatial dualization | |
| CN111957047A (en) | Checkpoint configuration data adjusting method, computer equipment and storage medium | |
| Shaker et al. | A progressive approach to content generation | |
| CN105653271B (en) | Static parsing, execution and the optimization method and device of behavior tree | |
| Ryan et al. | A simple method for evolving large character social networks | |
| CN111124125A (en) | Police affair training method and system based on virtual reality | |
| CN111530080B (en) | Behavior control method, device, equipment and storage medium of virtual object | |
| KR20200040642A (en) | Apparatus and method for virtual character in game program | |
| JP6326167B1 (en) | Learning device, learning method, learning program, moving image distribution device, activity device, activity program, and moving image generation device | |
| CN106110658B (en) | A kind of analogy method used in gaming and device | |
| Baby et al. | Implementing artificial intelligence agent within connect 4 using unity3d and machine learning concepts | |
| Miller et al. | Panoptyk: information driven mmo engine | |
| WO2023037507A1 (en) | Gameplay control learning device | |
| US20240161371A1 (en) | Asystem for customizing in-game character animations by players | |
| WO2023037508A1 (en) | Apparatus making game player model available for use |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |