CN109857552A - A kind of game artificial intelligence action planning method and system - Google Patents
A kind of game artificial intelligence action planning method and system Download PDFInfo
- Publication number
- CN109857552A CN109857552A CN201910025024.5A CN201910025024A CN109857552A CN 109857552 A CN109857552 A CN 109857552A CN 201910025024 A CN201910025024 A CN 201910025024A CN 109857552 A CN109857552 A CN 109857552A
- Authority
- CN
- China
- Prior art keywords
- task
- behavior
- optimization
- optimised
- artificial intelligence
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 18
- 230000010391 action planning Effects 0.000 title claims abstract description 16
- 238000005457 optimization Methods 0.000 claims abstract description 58
- 230000000694 effects Effects 0.000 claims abstract description 55
- 238000012913 prioritisation Methods 0.000 claims abstract description 26
- 238000013439 planning Methods 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 238000011156 evaluation Methods 0.000 claims description 22
- 230000008569 process Effects 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 5
- 230000008901 benefit Effects 0.000 abstract description 3
- 230000006399 behavior Effects 0.000 description 97
- 238000004422 calculation algorithm Methods 0.000 description 7
- 230000003542 behavioural effect Effects 0.000 description 6
- 238000003860 storage Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000006378 damage Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000008429 bread Nutrition 0.000 description 1
- 235000013351 cheese Nutrition 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 235000013372 meat Nutrition 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Technical solution of the present invention includes a kind of game artificial intelligence action planning method and system, for realizing: read the non-player role mission planning in game, all non-player role mission bit streams are obtained, wherein non-player role mission bit stream includes the content of the act, useful effect and the consumption of behavior of each task;Judge whether task can be optimised according to optimization criterion;To can optimised task optimize analysis, calculate optimal prioritization scheme, and include that multiple single task roles are merged into the optimization an of task to operate to task execution according to prioritization scheme.The invention has the benefit that allowing player that can have better game experiencing simultaneously, the AI behavior range of NPC becomes wider, and NPC can execute the behavior in multiple tasks, while obtain useful effect, high-efficient and intelligent.
Description
Technical field
The present invention relates to a kind of game artificial intelligence action planning method and system, belong to field of computer technology.
Background technique
In general game, the Behavioral effect of NPC is a complete ordering task.The Behavioral effect of one NPC may wrap
It includes and destroys one article of a target or acquisition.In the system for recording world state using NPC, effect is expressed as the phase
The world state of prestige.In traditional task system, NPC by limitation can only given place select in time one it is most important
Behavioral effect.Once this effect is selected, atom behavior can be connected into a sequence to create one and appoint by a NPC
Business.For example, if NPC determines to destroy target, the behavior that it selects to complete this effect may be attack.Behavior has premise item
Part, this precondition describe behavior execution before must be genuine condition on gaming world;Behavior is also effective,
Effect, which is described, is present in the necessary condition on gaming world when behavior is completed.In the example of attack, a premise
Condition may be NPC weapon oneself through loading, an effect will be the destruction of target.
NPC executes task according to complete ordering principle, and complete ordering task specifies the particular order of all behaviors, and
Regardless of whether individual behavior meets the precondition of other behaviors.Although can be executed in any order, one
Complete ordering task specifies the sequence for executing these behaviors.
The complete ordering task of this NPC AI effect is usually the mode of planning allocation list to configure, it main
Disadvantage has:
1. the task of all determinations during all effects must be configured explicitly, the workload of planning is very big.
2., so the behavior of NPC does not change, repeating dullness since the step of task is determining, influencing gaming world
The sense of reality and substitute into sense.
3.NPC can only have been executed every time to be further continued for executing after an effect next, can not be performed simultaneously multiple effects, be imitated
Rate is slow and seems not smart enough.
Summary of the invention
To solve the above problems, the purpose of the present invention is to provide a kind of game artificial intelligence action planning method and being
System reads the non-player role mission planning in game, obtains all non-player role mission bit streams, and wherein non-player role is appointed
Business information includes the content of the act, useful effect and the consumption of behavior of each task;Task is judged according to optimization criterion
Whether can be optimised;To can optimised task optimize analysis, calculate optimal prioritization scheme, and according to optimization side
Case includes that multiple single task roles are merged into the optimization operation an of task to task execution.
On the one hand technical solution used by the present invention solves the problems, such as it is: a kind of game artificial intelligence action planning side
Method, which comprises the following steps: read the non-player role mission planning in game, obtain all non-player roles
Mission bit stream, wherein non-player role mission bit stream includes the content of the act, useful effect and the consumption of behavior of each task;It presses
Judge whether task can be optimised according to optimization criterion;To can optimised task optimize analysis, calculate
Optimal prioritization scheme, and include that multiple single task roles are merged into the optimization behaviour an of task to task execution according to prioritization scheme
Make.
Further, the optimization criterion includes: that behavior has the task of identical useful effect can be optimised;It is used to
Instead of behavior consumption be less than the task of consumption summation of optimised behavior can be optimised.
It further, further include for that will have the task merging of overlapping behavior for single task role.
Further, it is described to calculate optimal prioritization scheme be with result be guiding task optimization scheme, optimization method
To generate an independent task according to multiple independent tasks.
Further, described to judge whether task optimised include: according in behavior according to optimization criterion
Hold, traverses all non-player role mission bit streams, filter out the task that identical behavior number in content of the act is no less than one;By this
Deleting the task flagging selected a bit is that can optimize task.
Further, described to calculate optimal prioritization scheme include: to optimize according to optimisation strategy to task, is obtained more
A prioritization scheme, wherein optimisation strategy includes being ranked up according to useful effect to subsequent behavior;Evaluation rule is created, according to
Evaluation rule assesses prioritization scheme, and wherein evaluation rule is the length of process performing spent time and more after optimization
Whether a independent task being capable of suboptimization again;If optimization after multiple independent tasks can suboptimization again, continue to optimize,
Until there is no the capableing of suboptimization again of the tasks;Optimal prioritization scheme is obtained according to assessment result.
On the other hand technical solution used by the present invention solves the problems, such as it is: a kind of game artificial intelligence action planning system
System characterized by comprising read module obtains all non-players for reading the non-player role mission planning in game
Role's mission bit stream, wherein non-player role mission bit stream includes disappearing for the content of the act of each task, useful effect and behavior
Consumption;Judgment module, for judging whether task can be optimised according to optimization criterion;Optimization module, for can be with
Optimised task optimizes analysis, calculates optimal prioritization scheme.
Further, the optimization module further includes evaluation module, for creating evaluation rule and according to evaluation rule pair
Prioritization scheme is assessed.
Further, further include merging module, be single task role for that there will be the task merging of overlapping behavior.
The beneficial effects of the present invention are: allowing player that can have better game experiencing simultaneously, the AI behavior range of NPC becomes
Wider, NPC can execute the behavior in multiple tasks, while obtain useful effect, high-efficient and intelligent.
Detailed description of the invention
Fig. 1 show the method flow schematic diagram of preferred embodiment according to the present invention;
Fig. 2 show the system structure diagram of preferred embodiment according to the present invention;
Fig. 3 a, 3b show normal work to do content of the act example;
Fig. 4 a, 4b, 4c show the optimization citing of preferred embodiment according to the present invention.
Specific embodiment
It is carried out below with reference to technical effect of the embodiment and attached drawing to design of the invention, specific structure and generation clear
Chu, complete description, to be completely understood by the purpose of the present invention, scheme and effect.
It should be noted that unless otherwise specified, when a certain feature referred to as " fixation ", " connection " are in another feature,
It can directly fix, be connected to another feature, and can also fix, be connected to another feature indirectly.In addition, this
The descriptions such as the upper and lower, left and right used in open are only the mutual alignment pass relative to each component part of the disclosure in attached drawing
For system.The "an" of used singular, " described " and "the" are also intended to including most forms in the disclosure, are removed
Non- context clearly expresses other meaning.In addition, unless otherwise defined, all technical and scientific terms used herein
It is identical as the normally understood meaning of those skilled in the art.Term used in the description is intended merely to describe herein
Specific embodiment is not intended to be limiting of the invention.Term as used herein "and/or" includes one or more relevant
The arbitrary combination of listed item.
It will be appreciated that though various elements, but this may be described using term first, second, third, etc. in the disclosure
A little elements should not necessarily be limited by these terms.These terms are only used to for same type of element being distinguished from each other out.For example, not departing from
In the case where disclosure range, first element can also be referred to as second element, and similarly, second element can also be referred to as
One element.The use of provided in this article any and all example or exemplary language (" such as ", " such as ") is intended merely to more
Illustrate the embodiment of the present invention well, and unless the context requires otherwise, otherwise the scope of the present invention will not be applied and be limited.
It show the method flow schematic diagram of preferred embodiment according to the present invention referring to Fig.1,
The non-player role mission planning in game is read, obtains all non-player role mission bit streams, wherein non-player
Role's mission bit stream includes the content of the act, useful effect and the consumption of behavior of each task;
Judge whether task can be optimised according to optimization criterion;
Optimisation criteria can be with are as follows: behavior has the task of identical useful effect can be optimised;For disappearing for the behavior that replaces
The task that consumption is less than the consumption summation of optimised behavior can be optimised.
To can optimised task optimize analysis, calculate optimal prioritization scheme, and according to prioritization scheme to appointing
It includes the optimization operation that multiple single task roles are merged into a task that business, which executes,.
According to content of the act, all non-player role mission bit streams are traversed, filter out in content of the act identical behavior number not
Task less than one;
It is that can optimize task that these are deleted to the task flagging selected.
Task is optimized according to optimisation strategy, obtains multiple prioritization schemes, wherein optimisation strategy includes according to useful
Effect is ranked up subsequent behavior;
Evaluation rule is created, prioritization scheme is assessed according to evaluation rule, wherein evaluation rule is process performing institute
Whether the length of time-consuming and multiple independent tasks after optimization being capable of suboptimization again;
If multiple independent tasks after optimization can suboptimization again, continue to optimize, until there is no can be again
The task of optimization;
Optimal prioritization scheme is obtained according to assessment result.
The system structure diagram of preferred embodiment according to the present invention is shown referring to Fig. 2,
Include:
Read module obtains all non-player role task letters for reading the non-player role mission planning in game
Breath, wherein non-player role mission bit stream includes the content of the act, useful effect and the consumption of behavior of each task;
Judgment module, for judging whether task can be optimised according to optimization criterion;
Optimization module, for can optimised task optimize analysis, calculate optimal prioritization scheme;
Merging module is included, is single task role for that there will be the task merging of overlapping behavior.
Optimization module further includes evaluation module, for creating evaluation rule and commenting according to evaluation rule prioritization scheme
Estimate.
1. task optimization providing method perceives intelligence to improve NPC in independent or group behavior.Although one has
The process consumed a bit, as long as but carefully considering, being generated by the time check for spending sub-fraction additional for task
To complete it.
2. there are many system and method for different execution task optimizations, for example task optimization algorithm is particularly suitable for strategy
Game AI opponent can complete effect with a variety of different methods, and may postpone behavior to utilize specific optimization machine
Meeting.
3. task is a multi-functional AI system, there are many chances to be extended and improve.And it is proposed
Idea can be applied in other AI systems, it is even other as being classified Task Networks in task system.It is this
The improvement for the behavior that technology provides is so that NPC has better intelligence, while allowing player that can have better game experiencing.
4. the AI behavior for creating and managing NPC with the behavior task system towards effect is a kind of powerful technology, make
Become wider with the AI behavior range that task optimization can permit NPC, in addition allow they at the same attempt to pursue multiple effects.
5. the behavior task system towards effect is decision making algorithm, it is used to that programmer is allowed to get rid of to specific NPC behavior
Selection, and by these select merging NPC itself feeling one think deeply a behavior circulation.It is using the largest benefit of this system
The complexity of design NPC AI behavior is reduced, while in the sense of reality that the head office of NPC is middle holding very high level.Using effect and
Premise can be used to the behavior sequence for reaching desired effects by listing a NPC as guidance, any heuristic search
Column are to create task.AI algorithm is used for task objective, task after the completion is exactly a series of rows that NPC is used to realize effect
For.
In general game, the Behavioral effect of NPC is a complete ordering task.The Behavioral effect of one NPC may wrap
It includes and destroys one article of a target or acquisition.In the system for recording world state using NPC, effect is expressed as the phase
The world state of prestige.In traditional task system, NPC by limitation can only given place select in time one it is most important
Behavioral effect.Once this effect is selected, atom behavior can be connected into a sequence to create one and appoint by a NPC
Business.For example, if NPC determines to destroy target, the behavior that it selects to complete this effect may be attack.Behavior has premise item
Part, this precondition describe behavior execution before must be genuine condition on gaming world;Behavior is also effective,
Effect, which is described, is present in the necessary condition on gaming world when behavior is completed.In the example of attack, a premise
Condition may be NPC weapon oneself through loading, an effect will be the destruction of target.
Fig. 3 a, 3b illustrate the example of the complete ordering task of production sandwich.Complete ordering task specifies all rows
For particular order, the precondition of other behaviors whether is met but regardless of individual behavior.Although can obtain in any order
Meat, cheese and bread are obtained, but a complete ordering task specifies the sequence for executing these behaviors.
The complete ordering task of this NPC AI effect is usually the mode of planning allocation list to configure, it main
Disadvantage has:
1. the task of all determinations during all effects must be configured explicitly, the workload of planning is very big.
2., so the behavior of NPC does not change, repeating dullness since the step of task is determining, influencing gaming world
The sense of reality and substitute into sense.
3.NPC can only have been executed every time to be further continued for executing after an effect next, can not be performed simultaneously multiple effects, be imitated
Rate is slow and seems not smart enough.
This programme structure is divided into two parts:
First part: with the game artificial intelligence of results-driven.Second part: in the task optimization method of results-driven.
Here is the specific descriptions of each section.
First part: with the game artificial intelligence of results-driven
Such as a NPC has a task, from collecting all stage properties in the world and they are taken back getting home.If one
NPC can only once carry a stage property, it is clear that best selection is exactly to move towards a stage property, collects it and then goes home.But
If a NPC can carry multiple stage properties, it is clear that there are many situations, NPC can be subtracted by being collected simultaneously multiple stage properties
Few total distance that it travels.
Using a task system, there can be many modes to complete this behavior.Assuming that collecting stage property and returning to home
Effect is called stage property and returns to effect.It is easier for writing some smaller, reusable atom behaviors, such as pathfinding
GoTo collects the GetItem of stage property from the world and stage property is put ReturnItem at home.These various behaviors allow to appoint
They are together in series by business person with correctly sequence, to complete complicated work, and are further allowed in the NPC of many types
Reuse behavior can complete desired behavior by task optimization.
Two the having overlapping behavior of the tasks can be generally chosen, they are optimized for one than each script task is individually performed
Low single task role is wanted in consumption.In this example, NPC can collect alone each stage property, generate two it is uncorrelated but very
Similar task, as shown in figures 4 a and 4b.The possible outcome for optimizing such two tasks is to optimize more rows as far as possible
To generate individual task, as illustrated in fig. 4 c.When NPC executes this task, it can collect two stage properties before going home.Ginseng
According to Fig. 4 a, 4b and 4c, (Fig. 4 a, 4b) is compared afterwards (Fig. 4 c) before respectively specific optimization.
Second part: in the task optimization method of results-driven
Task optimization is suitable for the process taken some independently generating for tasks and therefrom generate an independent task, usually
Along with the purpose of the task of reduction totally consumed.The reducing consumption of the task often also has the benefit for generating more rational act
Place.
Optimize two chief components of a task: finding behavior that can be optimised;If there is more than one
The method for optimizing operation, then calculate optimal method to optimize behavior.Separately processing these problems can be easier,
First step that searching can optimize behavior is accurately to find that kind of behavior can be optimised.If
There is another behavior that can replace optimised behavior with following result, any behavior can be optimised.
1. if behavior has identical useful effect.
2. if the consumption for the behavior for being used to replace is less than the consumption summation of optimised behavior.
If effect is directly the premise that another behavior in task establishes precondition either effect itself, that
They are exactly useful.Such as a NPC task destroys target with opening fire and loading behavior.The behavior of loading has many effects,
Firstly, it allows weapon to have bullet, secondly, it reduces the ammunition of NPC.First effect is useful, because it is completed
The precondition of another behavior in task.Second effect is not used, because it is unrelated with the execution of task.
If the consumption that search can optimize behavior task will be very big, so needing to find without the information of behavior itself
The behavior that can optimize known to those.In oneself system realized, it means that or to find oneself optimizable specific
Behavior or the known behavior combination that can optimize of searching.NPC has multiple-task, each there is ReturnItems row
For.Here it is the perfect candidate behaviors to be found, because can optimize two ReturnItems behaviors.It even can be with
It is begun look for from the end of task, as it is likely that the last behavior in each task can be optimised.GoTo (Base)
It can optimize together with itself, because it can complete same effect.
Second step is to create an optimal task after having found possible optimization.Create an optimization
Task can usually consume very big.For the NPC for collecting resource, it can be changed by allowing NPC once to collect multiple resources
Carry out for.
However in order to allow NPC to seem more intelligent, evaluation can be added and the inspection of specific purposes is come for remainder
Behavior sequence.It is replaced before the behavior of optimization than if any the behavior of two pairs of Goto (stage property) and GetItem, it is possible to
An evaluation is write to guarantee that NPC is first gone at nearest stage property.Evaluation be in order to reinforce desired behavior in task optimization and
The general rule of formulation.
Next optimization assignment algorithm receives two tasks generated by general AI task system.For example NPC is most heavy it
Two effects wanted issue task person, then that two independent tasks person that is sent to task optimization.For first task
Each behavior, algorithm examine Check it whether can be by an action optimization of second task, if optimization can be executed, that
Two behaviors are placed in an individual task, from two tasks place optimization behavior before behavior should be noted that for
Behavior after optimization behavior is also the same.If necessary to carry out more precise control to the sequence for the behavior that is not optimised, can be added
Evaluation rearranges the sequence of behavior to determine best sequence as needed.The possibility optimization of wider scope is come
It says, a complete task optimization algorithm should check the resultant effect of each possible behavior group in each task,
Find a series of behavior can by one individually, more cheap behavior replace the case where.Such a algorithm is to can be excellent
Change task generates considerable improvement.
It should be appreciated that the embodiment of the present invention can be by computer hardware, the combination of hardware and software or by depositing
The computer instruction in non-transitory computer-readable memory is stored up to be effected or carried out.Standard volume can be used in the method
Journey technology-includes that the non-transitory computer-readable storage media configured with computer program is realized in computer program,
In configured in this way storage medium computer is operated in a manner of specific and is predefined --- according in a particular embodiment
The method and attached drawing of description.Each program can with the programming language of level process or object-oriented come realize with department of computer science
System communication.However, if desired, the program can be realized with compilation or machine language.Under any circumstance, which can be volume
The language translated or explained.In addition, the program can be run on the specific integrated circuit of programming for this purpose.
In addition, the operation of process described herein can be performed in any suitable order, unless herein in addition instruction or
Otherwise significantly with contradicted by context.Process described herein (or modification and/or combination thereof) can be held being configured with
It executes, and is can be used as jointly on the one or more processors under the control of one or more computer systems of row instruction
The code (for example, executable instruction, one or more computer program or one or more application) of execution, by hardware or its group
It closes to realize.The computer program includes the multiple instruction that can be performed by one or more processors.
Further, the method can be realized in being operably coupled to suitable any kind of computing platform, wrap
Include but be not limited to PC, mini-computer, main frame, work station, network or distributed computing environment, individual or integrated
Computer platform or communicated with charged particle tool or other imaging devices etc..Each aspect of the present invention can be to deposit
The machine readable code on non-transitory storage medium or equipment is stored up to realize no matter be moveable or be integrated to calculating
Platform, such as hard disk, optical reading and/or write-in storage medium, RAM, ROM, so that it can be read by programmable calculator, when
Storage medium or equipment can be used for configuration and operation computer to execute process described herein when being read by computer.This
Outside, machine readable code, or part thereof can be transmitted by wired or wireless network.When such media include combining microprocessor
Or other data processors realize steps described above instruction or program when, invention as described herein including these and other not
The non-transitory computer-readable storage media of same type.When methods and techniques according to the present invention programming, the present invention
It further include computer itself.
Computer program can be applied to input data to execute function as described herein, to convert input data with life
At storing to the output data of nonvolatile memory.Output information can also be applied to one or more output equipments as shown
Device.In the preferred embodiment of the invention, the data of conversion indicate physics and tangible object, including the object generated on display
Reason and the particular visual of physical objects are described.
The above, only presently preferred embodiments of the present invention, the invention is not limited to above embodiment, as long as
It reaches technical effect of the invention with identical means, all within the spirits and principles of the present invention, any modification for being made,
Equivalent replacement, improvement etc., should be included within the scope of the present invention.Its technical solution within the scope of the present invention
And/or embodiment can have a variety of different modifications and variations.
Claims (9)
1. a kind of game artificial intelligence action planning method, which comprises the following steps:
The non-player role mission planning in game is read, obtains all non-player role mission bit streams, wherein non-player role
Mission bit stream includes the content of the act, useful effect and the consumption of behavior of each task;
Judge whether task can be optimised according to optimization criterion;
To can optimised task optimize analysis, calculate optimal prioritization scheme, and hold to task according to prioritization scheme
Row includes the optimization operation that multiple single task roles are merged into a task.
2. game artificial intelligence action planning method according to claim 1, which is characterized in that the optimization criterion
Include:
Behavior has the task of identical useful effect can be optimised;
The task for the consumption summation that the consumption of behavior for replacing is less than optimised behavior can be optimised.
3. game artificial intelligence action planning method according to claim 1, which is characterized in that further include for that will have weight
The task merging of folded behavior is single task role.
4. game artificial intelligence action planning method according to claim 1, which is characterized in that it is described calculate it is optimal excellent
It is the task optimization scheme being oriented to that change scheme, which is with result, and optimization method is to generate one according to multiple independent tasks individually to appoint
Business.
5. game artificial intelligence action planning method according to claim 1, which is characterized in that described to determine according to optimization
Standard come judge task whether can optimised include:
According to content of the act, all non-player role mission bit streams are traversed, identical behavior number in content of the act is filtered out and is no less than
One task;
The task flagging that these are filtered out is that can optimize task.
6. game artificial intelligence action planning method according to claim 1, which is characterized in that it is described calculate it is optimal excellent
Change scheme includes:
Task is optimized according to optimisation strategy, obtains multiple prioritization schemes, wherein optimisation strategy includes according to useful effect
Subsequent behavior is ranked up;
Create evaluation rule, prioritization scheme is assessed according to evaluation rule, wherein evaluation rule by process performing time-consuming
Between length and optimization after multiple independent tasks whether being capable of suboptimization again;
If multiple independent tasks after optimization can suboptimization again, continue to optimize, until there is no being capable of suboptimization again
Task;
Optimal prioritization scheme is obtained according to assessment result.
7. a kind of using any game artificial intelligence action planning system of claim 1-6 characterized by comprising
Read module obtains all non-player role mission bit streams for reading the non-player role mission planning in game,
Middle non-player role mission bit stream includes the content of the act, useful effect and the consumption of behavior of each task;
Judgment module, for judging whether task can be optimised according to optimization criterion;
Optimization module, for can optimised task optimize analysis, calculate optimal prioritization scheme.
8. game artificial intelligence action planning system according to claim 7, which is characterized in that the optimization module is also wrapped
Evaluation module is included, for creating evaluation rule and assessing according to evaluation rule prioritization scheme.
9. game artificial intelligence action planning system according to claim 7, which is characterized in that it further include merging module,
It is single task role for that will have the task merging of overlapping behavior.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910025024.5A CN109857552A (en) | 2019-01-11 | 2019-01-11 | A kind of game artificial intelligence action planning method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910025024.5A CN109857552A (en) | 2019-01-11 | 2019-01-11 | A kind of game artificial intelligence action planning method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109857552A true CN109857552A (en) | 2019-06-07 |
Family
ID=66894463
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910025024.5A Pending CN109857552A (en) | 2019-01-11 | 2019-01-11 | A kind of game artificial intelligence action planning method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109857552A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113144590A (en) * | 2021-03-23 | 2021-07-23 | 苏州乐志软件科技有限公司 | Artificial intelligence engine based on AI Designer |
CN113350796A (en) * | 2021-05-27 | 2021-09-07 | 北京中新互娱科技有限公司 | Virtual character behavior control method and device |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101158897A (en) * | 2007-10-09 | 2008-04-09 | 南京大学 | Intelligent non-player roles implementing method in interactive game and system |
JP2015180271A (en) * | 2015-05-22 | 2015-10-15 | 株式会社スクウェア・エニックス | Video game device, game progressing method, server device, and video game processing program |
CN105446742A (en) * | 2015-12-11 | 2016-03-30 | 珠海金山网络游戏科技有限公司 | Optimization method for artificial intelligence performing task |
CN105561578A (en) * | 2015-12-11 | 2016-05-11 | 北京像素软件科技股份有限公司 | NPC behavior decision method |
CN106178509A (en) * | 2016-07-07 | 2016-12-07 | 深圳市豹风网络股份有限公司 | The game role digital data recording system of mobile terminal network game |
US9672190B1 (en) * | 2013-01-08 | 2017-06-06 | Aftershock Services, Inc. | Consideration-based non-player character counseling |
CN107875632A (en) * | 2017-12-06 | 2018-04-06 | 广州多益网络股份有限公司 | Realize the method, system and artificial intelligence behavior editing machine of artificial intelligence behavior |
CN109011588A (en) * | 2018-10-16 | 2018-12-18 | 杭州电魂网络科技股份有限公司 | Scene of game exchange method and device |
-
2019
- 2019-01-11 CN CN201910025024.5A patent/CN109857552A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101158897A (en) * | 2007-10-09 | 2008-04-09 | 南京大学 | Intelligent non-player roles implementing method in interactive game and system |
US9672190B1 (en) * | 2013-01-08 | 2017-06-06 | Aftershock Services, Inc. | Consideration-based non-player character counseling |
JP2015180271A (en) * | 2015-05-22 | 2015-10-15 | 株式会社スクウェア・エニックス | Video game device, game progressing method, server device, and video game processing program |
CN105446742A (en) * | 2015-12-11 | 2016-03-30 | 珠海金山网络游戏科技有限公司 | Optimization method for artificial intelligence performing task |
CN105561578A (en) * | 2015-12-11 | 2016-05-11 | 北京像素软件科技股份有限公司 | NPC behavior decision method |
CN106178509A (en) * | 2016-07-07 | 2016-12-07 | 深圳市豹风网络股份有限公司 | The game role digital data recording system of mobile terminal network game |
CN107875632A (en) * | 2017-12-06 | 2018-04-06 | 广州多益网络股份有限公司 | Realize the method, system and artificial intelligence behavior editing machine of artificial intelligence behavior |
CN109011588A (en) * | 2018-10-16 | 2018-12-18 | 杭州电魂网络科技股份有限公司 | Scene of game exchange method and device |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113144590A (en) * | 2021-03-23 | 2021-07-23 | 苏州乐志软件科技有限公司 | Artificial intelligence engine based on AI Designer |
CN113350796A (en) * | 2021-05-27 | 2021-09-07 | 北京中新互娱科技有限公司 | Virtual character behavior control method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Sindhya et al. | A hybrid framework for evolutionary multi-objective optimization | |
Zeballos | A constraint programming approach to tool allocation and production scheduling in flexible manufacturing systems | |
CN114721833B (en) | Intelligent cloud coordination method and device based on platform service type | |
CN113703775B (en) | Compiling method, compiling device, compiling equipment and storage medium | |
CN105446742B (en) | A kind of artificial intelligence executes the optimization method of task | |
CN106909543B (en) | Pattern matching method and device of rule engine | |
US9953284B2 (en) | Systems and methods for prioritizing funding of projects | |
Basseur et al. | The efficiency of indicator-based local search for multi-objective combinatorial optimisation problems | |
JP5845813B2 (en) | A node computation initialization method for efficient parallel analysis of software in distributed computing environments | |
CN112632744A (en) | Combat system architecture modeling method and space exploration algorithm based on hyper-network model | |
CN109857552A (en) | A kind of game artificial intelligence action planning method and system | |
CN113469372A (en) | Reinforcement learning training method, device, electronic equipment and storage medium | |
JP5845810B2 (en) | Efficient partial computation for parallel analysis of software in distributed computing environments | |
Fontes et al. | On multi-objective evolutionary algorithms | |
CN110325965A (en) | Object processing method, equipment and storage medium in virtual scene | |
Ansótegui et al. | Boosting evolutionary algorithm configuration | |
Park et al. | Practical Human Resource Allocation in Software Projects Using Genetic Algorithm. | |
CN106874215B (en) | Serialized storage optimization method based on Spark operator | |
CN114581220A (en) | Data processing method and device and distributed computing system | |
CN114841664A (en) | Method and device for determining multitasking sequence | |
Bosse et al. | Optimizing IT service costs with respect to the availability service level objective | |
Martin et al. | A generic agent-based framework for cooperative search using pattern matching and reinforcement learning | |
Khan et al. | Near Feasibility Driven Adaptive Penalty Functions Embedded MOEA/D | |
Saravanakumar et al. | Problem solving in cross over line balancing using HHO | |
CN112015426A (en) | Code management method, device and equipment |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190607 |