CN105561578A - NPC behavior decision method - Google Patents
NPC behavior decision method Download PDFInfo
- Publication number
- CN105561578A CN105561578A CN201510920765.1A CN201510920765A CN105561578A CN 105561578 A CN105561578 A CN 105561578A CN 201510920765 A CN201510920765 A CN 201510920765A CN 105561578 A CN105561578 A CN 105561578A
- Authority
- CN
- China
- Prior art keywords
- npc
- hope
- trigger event
- hope target
- weights
- 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
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
- A63F13/55—Controlling game characters or game objects based on the game progress
- A63F13/56—Computing the motion of game characters with respect to other game characters, game objects or elements of the game scene, e.g. for simulating the behaviour of a group of virtual soldiers or for path finding
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
- A63F13/55—Controlling game characters or game objects based on the game progress
- A63F13/58—Controlling game characters or game objects based on the game progress by computing conditions of game characters, e.g. stamina, strength, motivation or energy level
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
- A63F13/80—Special adaptations for executing a specific game genre or game mode
- A63F13/822—Strategy games; Role-playing games
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses an NPC (Non-Player Character) behavior decision method. The method comprises the following steps of initializing attribute set information of an NPC; obtaining a triggering event of the NPC through a sensor; determining a willing target of the NPC according to the corresponding relationship between the triggering event and the willing target; finding the attribute set information matched with the willing target; generating at least willing target option according to the matched attribute set information; determining a behavior plan according to the willing target option and the willing target option weight; executing the behavior plan; and correcting the willing target of the NPC according to the feedback of the behavior plan. The NPC in the game can realize the artificial intelligence; and the thinking mode and the behavior action similar to the human are realized. The novelty and the interestingness of the game are enhanced, so that a game player can gain good game experience, and the game dependency of the player is enhanced.
Description
Technical field
The present invention relates to computer game field, particularly relate to a kind of behaviour decision making method of non-player control role NPC.
Background technology
Non-player control role (Non-PlayerCharacter, NPC) is made a general reference in all game not by the role that player controls.Along with the development of computer game, higher requirement be it is also proposed for the intelligent of NPC, need to consider the intelligent behavior of NPC in tactics, strategy, decision-making technique, to strengthen the playability of game.
At present, in game engine, adopt introduces artificial intelligence (ArtificialIntelligence more, AI) mode strengthens the intelligence of NPC, these introduce the game engine of artificial intelligence technology, although enhance the intelligence performance of virtual portrait to a certain extent, but still there is many weak points.Because these game engines need developer to weave rule of conduct in advance, not only development task is heavy, and the behavior pattern of non-player role is also very limited, player easily predicts its behavior in gaming, makes game lose interest and novelty soon; In addition, these game engines can not allow virtual portrait present the movement displaying consistent with game interaction situation effectively, destroy feeling of immersion when game player plays.
Summary of the invention
In view of this, the embodiment of the present invention provides a kind of behaviour decision making method of non-player control role NPC, shows the technical problem of lack of wisdom to solve non-player control role NPC in game design.
Embodiments provide a kind of behaviour decision making method of non-player control role NPC, described method comprises:
Initialize the community set information of NPC;
Obtain the trigger event of NPC by perceptron, according to the corresponding relation of trigger event and hope target, determine the hope target of NPC;
Search the community set information with described hope object matching, the community set information according to coupling generates at least one hope target selection;
According to hope target selection and hope target selection weights determination behavior plan, and perform described behavior plan;
According to the hope target selection weights of the feedback modifiers NPC of behavior plan.
The decision-making technique of the non-player control role NPC behavior that the embodiment of the present invention provides, by according to the hope target of NPC and the action behavior of community set information guiding NPC, and the hope target of feedback modifiers NPC according to the action behavior of NPC, realize to enable the NPC in game, there is artificial intelligence according to the object of feedback adjustment NPC behavior act, there is the anthropoid mode of thinking of class and behavior act.The novelty enhancing game, with interesting, enable game player produce better game experiencing, adds the game viscosity of player.
Accompanying drawing explanation
By reading the detailed description done non-limiting example done with reference to the following drawings, other features, objects and advantages of the present invention will become more obvious:
Fig. 1 is the schematic flow sheet of the behaviour decision making method of the non-player control role NPC that first embodiment of the invention provides;
Fig. 2 is the schematic flow sheet of the behaviour decision making method of the non-player control role NPC that second embodiment of the invention provides;
Fig. 3 is the schematic flow sheet of the behaviour decision making method of the non-player control role NPC that third embodiment of the invention provides;
Fig. 4 is the schematic flow sheet of the behaviour decision making method of the non-player control role NPC that fourth embodiment of the invention provides.
Detailed description of the invention
Below in conjunction with drawings and Examples, the present invention is described in further detail.Be understandable that, specific embodiment described herein is only for explaining the present invention, but not limitation of the invention.It also should be noted that, for convenience of description, illustrate only part related to the present invention in accompanying drawing but not full content.
Embodiment one
The schematic flow sheet of the behaviour decision making method of the non-player control role NPC that Fig. 1 provides for the embodiment of the present invention one, the method can be performed by the decision making device of role NPC behavior, this device can be realized by software/hardware mode, and is integrated in network game platform or computer game software.
Described method specifically comprises as follows:
S110, initializes the community set information of NPC.
In computer game or online game, NPC is divided into story of a play or opera NPC, service type NPC and the types such as NPC of can fighting, and wherein story of a play or opera NPC is for promoting the development of whole story of a play or opera plot; Service type NPC is used for for the player role in game provides various service; The NPC that can fight fights for controlling personage with player.The function corresponding according to NPC, in gaming, presets the community set information of each NPC, letter.Exemplary, be set with the monster NPC that can fight in gaming, its community set information can comprise: the food that monster NPC can be enough, comprising: radish, meat, tree, grass etc., the enemy of monster NPC: people race and refreshing race.Attribute can determine the characteristic of monster NPC.Network game platform or Games Software receive the setting to the community set information of NPC, and are stored in chained list by these community set information, the attribute information of easy-to-look-up NPC, after completing storage, namely achieve the community set information initializing NPC.
S120, obtains the trigger event of NPC by perceptron, according to the corresponding relation of trigger event and hope target, determines the hope target of NPC.
Perceptron, for receiving the trigger event about NPC, in game play, can produce the event relevant to NPC.Such as: in gaming, the energy value of monitoring monster NPC, when the energy value of monster NPC is lower than preset energy threshold value, triggers the hungry event of monster NPC; Or game player attacks monster NPC, triggers by attack etc.When these events are triggered, perceptron receives these events.
After perceptron receives these events, NPC needs to produce corresponding hope target to these events.The target that described hope target can generate according to the reflection of trigger event for NPC.Concrete, according to the corresponding relation of the trigger event preset and hope target, the hope target of NPC can be determined.Exemplary, when hungry event is triggered, find the hope target corresponding with hungry event for take food, then determine that the hope target of NPC is for feed.Or, when being triggered by attack, find with by hope target corresponding to attack for attack, then determine that the hope target of NPC is for attacking.And for example, vital values be reduced to default threshold event be triggered time, find and be reduced to hope target corresponding to default threshold event for runing away with vital values, then determine that the hope target of NPC is for runing away.
S130, searches the community set information with described hope object matching, and the community set information according to coupling generates at least one hope target selection.
Hope object table understands that NPC is in the current desired target realized, and after generation hope target, needing hope goal decomposition according to the attribute information of NPC is multiple enforceable hope target selections.Because the attribute information of various NPC is different, for different NPC, even if hope congruence, but hope target selection is not identical yet.Community set information according to coupling can generate at least one hope target selection.Concrete, from the community set information of initialized NPC, search the community set information with hope object matching.Exemplary, for monster NPC, its hope target is feed, by searching, determines that the community set information corresponding to hope target of taking food is energy measuring bottle, radish, meat and grass.The hope target selection of feed energy measuring bottle, feed radish, take food meat and feed grass is then generated according to above-mentioned community set information.
S140, according to hope target selection and hope target selection weights determination behavior plan, and performs described behavior plan.
At least one hope target selection can be generated for each hope target.When hope target can generate multiple hope target selection, NPC can not implement all hope target selections, needs to generate based on hope target selection and hope target selection weights corresponding to hope target selection to judge, selects most suitable behavior plan.By comparing these plans, calculating their effect, determining the plan of most effective.Concrete, dynamic decision tree is set up according to default hope target selection input value and hope target selection weights weights, multiple hope target selection input value is in the same one-level of dynamic decision tree, described multiple hope target selection weights are in the same one-level of dynamic decision tree, and directly connect with corresponding hope target selection input value.And search the branch that dynamic decision tree has the minimum attribute of feedback entropy, and determine behavior plan according to the branch of described minimum attribute.Exemplary, monster NPC builds the dynamic decision tree about feed, by all hope target selections, the first order leaf node that such as feed energy measuring bottle, feed radish, feed meat and the input value of taking food grass are set as dynamic decision, by the weights of feed energy measuring bottle, feed radish, take food meat and feed grass as second level leaf node, and be connected with the hope target selection input value corresponding to it, ID3 algorithm is adopted according to constructed dynamic decision tree, select the branch of the minimum attribute of feedback entropy, and determine behavior plan according to the branch of described minimum attribute.Such as: about the dynamic decision tree of feed, its feed that branches into feedback entropy minimum attribute can measuring bottle, then determine the behavior plan of monster NPC for feed can measuring bottle.
S150, according to the hope target of the feedback modifiers NPC of behavior plan.
NPC is after completing act of execution plan, and game engine or the behavior plan of game player to NPC can produce feedback.Exemplary, NPC on the feed can after measuring bottle, and games system provides corresponding feedback, reduces the hunger of NPC; Or monster NPC, when attacking people race base, does not suffer the opposing of people race, then the hostility of monster NPC to people race alleviates.After receiving feedback, according to the hope target of feedback modifiers NPC.And generate new behavior plan according to the hope target revising rear NPC.To make NPC that artificial intelligence can be had, there is the anthropoid mode of thinking of class and behavior act.
The decision-making technique of the non-player control role NPC behavior that the present embodiment provides and device, by instructing the action behavior of NPC according to the community set information of NPC and trigger event, and the hope target of feedback modifiers NPC according to the behavior plan of NPC, realize the object of adjustment NPC behavior act.The NPC in game can be enable to have artificial intelligence, there is the anthropoid mode of thinking of class and behavior act.The novelty enhancing game, with interesting, enable game player produce better game experiencing, adds the game viscosity of player.
In a preferred embodiment of the present embodiment, described hope target comprise following at least one:
Take food, attack and run away.Corresponding, when described hope target is for feed, described hope target selection comprise following at least one: feed can measuring bottle, feed radish, feed meat and feed grass.When described hope target is for attacking, described hope target selection comprise following at least one: common attack, magic are attacked, individual to attack and colony attacks., when described hope target is for runing away, described hope target selection comprise following at least one: run away with role motion rightabout and to distance the nearest direction of companion run away.
In another preferred embodiment of the present embodiment, after the described behavior plan of execution, also following steps can be increased: according to the hope target selection weights of the feedback modifiers NPC of behavior plan.After the plan of NPC act of execution, game engine or the behavior plan of game player to NPC can produce feedback. and exemplary, after monster NPC takes food energy measuring bottle and radish respectively, hunger according to monster NPC reduces degree and hungry minimizing time, respectively the energy weights of measuring bottle and the weights of radish are revised, because feed can make hungry minimizing degree and hungry minimizing time be greater than radish, then the weights of energization bottle by measuring bottle, and reduce the weights of radish.Monster NPC constantly revises the weights of various food selection according to the feedback result of each feed, according to the hobby of continuous feedback result adjustment to various food selection, can mould the NPC more having distinct characteristic to make monster NPC.
Embodiment two
The schematic flow sheet of the behaviour decision making method of the non-player control role NPC that Fig. 2 provides for second embodiment of the invention.The present embodiment is optimized based on above-described embodiment, in the present embodiment, limit described hope target at least one trigger event corresponding, and the hope target of feedback modifiers NPC will be intended to according to action, be specifically optimized for: by the feedback generation feedback data of perceptron according to behavior plan; According to feedback data amendment trigger event weights; According to revised trigger event modified weight hope target.
Accordingly, the method for the present embodiment specifically comprises:
S210, initializes the community set information of NPC.
S220, obtains the trigger event of NPC by perceptron, according to the corresponding relation of trigger event and hope target, determines the hope target of NPC.
S230, searches the community set information with described hope object matching, and the community set information according to coupling generates at least one hope target selection.
S240, according to hope target selection and hope target selection weights determination behavior plan, and performs described behavior plan.
S250, generates feedback data by perceptron according to the feedback of behavior plan.
Perceptron may be used for the manipulation feedback receiving game internal event and game player, and generates corresponding feedback data based on the manipulation feedback of game internal event and game player.Feedback data comprises the Intrusion Index of event feedback.Exemplary, monster NPC is after behavior plan completes on the feed, and the hungry index of influent pH planned feedback is-1.0, then-1.0 is the feedback data of influent pH plan.
S260, according to feedback data amendment trigger event weights.
Due to hope target at least one trigger event corresponding, hope target can be generated by multiple trigger event.Exemplary, for a monster NPC, the trigger event causing monster NPC feed hope target can be hungry event, find food event and the unhappy event of mood.Each trigger event is not identical for the impact of hope target yet.Above-mentioned trigger event can generate separately or jointly the hope target of NPC.Meanwhile, the behavior plan of NPC can produce feedback data, and feedback data comprises the Intrusion Index of feedback.Based on this, can modify according to the weights of feedback data to the multiple trigger events generating same hope target.
S270, according to revised trigger event modified weight hope target.
After trigger event weights change, hope target is inevitable also can change, and the corresponding relation according to revised trigger event weights and hope target recalculates hope target, and can generate new behavior plan according to new hope target.
The present embodiment passes through the hope of the feedback modifiers NPC that will be intended to according to action, is specifically optimized for: generate feedback data by perceptron according to the feedback of behavior plan; According to feedback data amendment trigger event weights; According to revised trigger event modified weight hope target.NPC can be made constantly to adjust hope target by self study, and generate new action intention according to the hope target after adjustment, make NPC can have the anthropoid mode of thinking of class and behavior act.
Embodiment three
The schematic flow sheet of the behaviour decision making method of the non-player control role NPC that Fig. 3 provides for third embodiment of the invention.The present embodiment is optimized based on above-described embodiment, trigger event weights will be revised according to feedback data, specifically be optimized for: calculate trigger event weights changing value according to the desired value of feedback data, behavior plan, default trigger event input value and pace of learning; According to trigger event weights changing value amendment trigger event weights.
Accordingly, the method for the present embodiment specifically comprises:
S310, initializes the community set information of NPC.
S320, obtains the trigger event of NPC by perceptron, according to the corresponding relation of trigger event and hope target, determines the hope target of NPC.
S330, searches the community set information with described hope object matching, and the community set information according to coupling generates at least one hope target selection.
S340, according to hope target selection and hope target selection weights determination behavior plan, and performs described behavior plan.
S350, generates feedback data by perceptron according to the feedback of behavior plan.
S360, calculates hope target selection weights changing value according to the desired value of feedback data, behavior plan, default hope target selection input value and pace of learning.
After NPC receives extraneous feedback, its trigger event weights can change, and in the present embodiment, use increment rule to calculate trigger event weights.Exemplary, calculated by Wi ← wi+ ▲ w, wherein ▲ w is the changing value of weights, ▲ w=n* (desired value-actual value) * input value, and n is pace of learning, can be preset by empirical value, generally can adopt the value that is less.The Effect value of desired value estimated by behavior plan, the numeral expression of input value corresponding to hope target selection.
Exemplary, for monster NPC, feed hope target is generated by three trigger events: hungry, finds that delicious food is unhappy with sensation.Weights are all initialized as 0.5, and pace of learning n is 0.1, following table list monster NPC take food after, receive the situation of feedback.
S370, selects weights according to trigger event weights changing value amendment trigger event.
According to trigger event weights changing value ▲ w that S360 obtains, weights are revised.Concrete, weights are added with weights changing value and generate revised trigger event weights.
S380, according to revised trigger event modified weight hope target.
The present embodiment, by revising trigger event weights according to feedback data, is specifically optimized for: calculate trigger event weights changing value according to the desired value of feedback data, behavior plan, default trigger event input value and pace of learning; According to trigger event weights changing value amendment trigger event weights.Constantly can adjust the hope target of NPC according to the change of external world's feedback, NPC is constantly adjusted behavior plan.
Embodiment four
The schematic flow sheet of the behaviour decision making method of the non-player control role NPC that Fig. 4 provides for fourth embodiment of the invention.The present embodiment is optimized based on above-described embodiment, by the hope target of the feedback modifiers NPC according to behavior plan, specifically be optimized for: calculate the trigger event input value and the revised trigger event weights sum of products preset, and according to sum of products determination hope intensity; The hope target of NPC is redefined according to hope intensity.
Accordingly, the method for the present embodiment specifically comprises:
S410, initializes the community set information of NPC.
S420, obtains the trigger event of NPC by perceptron, according to the corresponding relation of trigger event and hope target, determines the hope target of NPC.
S430, searches the community set information with described hope object matching, and the community set information according to coupling generates at least one hope target selection.
S440, according to hope target selection and hope target selection weights determination behavior plan, and performs described behavior plan.
S450, generates feedback data by perceptron according to the feedback of behavior plan.
S460, calculates trigger event weights changing value according to the desired value of feedback data, behavior plan, default trigger event input value and pace of learning.
S470, according to trigger event weights changing value amendment hope target selection weights.
S480, calculates trigger event and the revised trigger event weights sum of products, and according to sum of products determination hope intensity.
If there is x1, x2 ... .., xn trigger event, and corresponding n trigger event weight w 1, w2, ... .wn, then according to trigger event and trigger event weight computing hope intensity, concrete, the product of trigger event and corresponding trigger event weights can be calculated, and calculate these products and, by product and with preset threshold value compare, if product and be greater than default threshold value, then setting hope intensity is 1, otherwise hope intensity is 0.Exemplary, if during Σ wi*xi>0.5, hope intensity is 1, otherwise hope intensity is 0.By compare the product of trigger event and trigger event weights and with the threshold value preset, can determine that whether the current hope intensity of NPC urgent, and generate new action intention accordingly.Exemplary, for monster NPC, exist hungry, find food and unhappy three trigger events of sensation, according to these three trigger event weights, calculate sum of products, obtain current hope intensity.If the sum of products is greater than default threshold value, then illustrate hope target need be met, if be less than default threshold value, then illustrate that hope target is not met, NPC needs to continue feed.
S490, redefines the hope target of NPC according to hope intensity.
Determine the hope intensity of NPC, when hope intensity is 1, NPC does not have corresponding hope target, and when hope intensity is 0, NPC hope target still exists.
The present embodiment, by by the hope target of the feedback modifiers NPC according to behavior plan, is specifically optimized for: calculate the hope target selection input value and the revised hope target selection sum of products preset, and according to sum of products determination hope intensity; The hope target of NPC is redefined according to hope intensity.Can judge whether the hope target of NPC is satisfied according to feedback, and the hope target of NPC can be redefined according to judged result.
Obviously, it will be understood by those skilled in the art that above-mentioned of the present invention each module or each operation can be implemented by terminal device as above.Alternatively, the embodiment of the present invention can realize by the executable program of computer installation, thus they storages can be performed by processor in the storage device, described program can be stored in a kind of computer-readable recording medium, the above-mentioned storage medium mentioned can be read-only storage, disk or CD etc.; Or they are made into each integrated circuit modules respectively, or the multiple module in them or operation are made into single integrated circuit module to realize.Like this, the present invention is not restricted to the combination of any specific hardware and software.
The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, to those skilled in the art, the present invention can have various change and change.All do within spirit of the present invention and principle any amendment, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. a behaviour decision making method of non-player control role NPC, is characterized in that, comprising:
Initialize the community set information of NPC;
Obtain the trigger event of NPC by perceptron, according to the corresponding relation of trigger event and hope target, determine the hope target of NPC;
Search the community set information with described hope object matching, the community set information according to coupling generates at least one hope target selection;
According to hope target selection and hope target selection weights determination behavior plan, and perform described behavior plan;
According to the hope target of the feedback modifiers NPC of behavior plan.
2. method according to claim 1, is characterized in that, after the described behavior plan of execution, also comprises:
According to the hope target selection weights of the feedback modifiers NPC of behavior plan.
3. method according to claim 1, is characterized in that, described hope target at least one trigger event corresponding;
The hope target of the described feedback modifiers NPC according to behavior plan, comprising:
Feedback data is generated according to the feedback of behavior plan by perceptron;
According to feedback data amendment trigger event weights;
According to revised trigger event modified weight hope target.
4. method according to claim 2, is characterized in that, described according to feedback data amendment trigger event weights, comprising:
Trigger event weights changing value is calculated according to the desired value of feedback data, behavior plan, default trigger event input value and pace of learning;
According to trigger event weights changing value amendment trigger event weights.
5. method according to claim 1, is characterized in that, described according to hope target selection and hope target selection weights determination behavior plan, comprising:
Dynamic decision tree is set up according to default hope target selection input value and hope target selection weights weights, wherein, multiple hope target selection input value is in the same one-level of dynamic decision tree, described multiple hope target selection weights are in the same one-level of dynamic decision tree, and directly connect with corresponding hope target selection input value;
Search the branch that dynamic decision tree has the minimum attribute of feedback entropy, and determine behavior plan according to the branch of described minimum attribute.
6. method according to claim 6, is characterized in that, described, according to revised trigger event modified weight hope target, comprising:
Calculate the trigger event input value and the revised trigger event weights sum of products preset, and according to sum of products determination hope intensity;
The hope target of NPC is redefined according to hope intensity.
7. method according to claim 1, is characterized in that, described hope target comprise following at least one:
Take food, attack and run away.
8. method according to claim 7, is characterized in that, described hope target for feed time, described hope target selection comprise following at least one:
Feed energy measuring bottle, feed radish, feed meat and feed grass.
9. method according to claim 7, is characterized in that, described hope target for attack time, described hope target selection comprise following at least one:
Common attack, magic are attacked, individuality is attacked and colony attacks.
10. method according to claim 7, is characterized in that, when described hope target is for runing away, described hope target selection comprise following at least one:
Run away with role motion rightabout and run away to the distance nearest direction of companion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510920765.1A CN105561578A (en) | 2015-12-11 | 2015-12-11 | NPC behavior decision method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510920765.1A CN105561578A (en) | 2015-12-11 | 2015-12-11 | NPC behavior decision method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105561578A true CN105561578A (en) | 2016-05-11 |
Family
ID=55872550
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510920765.1A Pending CN105561578A (en) | 2015-12-11 | 2015-12-11 | NPC behavior decision method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105561578A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106621334A (en) * | 2016-09-27 | 2017-05-10 | 网易（杭州）网络有限公司 | Control method and device of non-player-controlled character |
| CN107019912A (en) * | 2017-04-20 | 2017-08-08 | 腾讯科技（深圳）有限公司 | The collocation method and device of role |
| CN107145948A (en) * | 2017-04-12 | 2017-09-08 | 四川大学 | A kind of NPC control methods based on multi-agent Technology |
| CN107256174A (en) * | 2017-05-27 | 2017-10-17 | 武汉秀宝软件有限公司 | The implementation method and device of artificial intelligence |
| CN107633302A (en) * | 2016-07-19 | 2018-01-26 | 珠海金山网络游戏科技有限公司 | System and method are realized in a kind of dependence of tactics of the game |
| CN107890675A (en) * | 2017-11-13 | 2018-04-10 | 杭州电魂网络科技股份有限公司 | AI behaviors implementation method and device |
| CN107890674A (en) * | 2017-11-13 | 2018-04-10 | 杭州电魂网络科技股份有限公司 | AI behaviors call method and device |
| CN107943707A (en) * | 2017-12-19 | 2018-04-20 | 网易（杭州）网络有限公司 | Test method, device and the storage medium and terminal of behavior tree |
| CN108057249A (en) * | 2017-11-29 | 2018-05-22 | 腾讯科技(成都)有限公司 | A kind of business data processing method and device |
| CN108283809A (en) * | 2018-02-11 | 2018-07-17 | 腾讯科技（深圳）有限公司 | Data processing method, device, computer equipment and storage medium |
| CN109200583A (en) * | 2018-08-02 | 2019-01-15 | 苏州蜗牛数字科技股份有限公司 | Control method, system and the storage medium of game NPC behavior |
| CN109857552A (en) * | 2019-01-11 | 2019-06-07 | 珠海金山网络游戏科技有限公司 | A kind of game artificial intelligence action planning method and system |
| CN110947182A (en) * | 2019-11-26 | 2020-04-03 | 上海米哈游网络科技股份有限公司 | Event handling method, device, game terminal and medium |
| CN111544889A (en) * | 2020-04-27 | 2020-08-18 | 腾讯科技（深圳）有限公司 | Behavior control method and device of virtual object and storage medium |
| CN111760294A (en) * | 2020-07-07 | 2020-10-13 | 网易（杭州）网络有限公司 | Method and device for controlling non-player game role in game |
| CN112245924A (en) * | 2020-10-29 | 2021-01-22 | 北京冰封互娱科技有限公司 | Method and device for generating non-player character, storage medium and electronic equipment |
| CN112337090A (en) * | 2020-11-06 | 2021-02-09 | 完美世界(重庆)互动科技有限公司 | Event message broadcasting method and device, storage medium and electronic device |
| CN114040806A (en) * | 2019-06-14 | 2022-02-11 | 战斗机基地出版公司 | Method and system for artificial intelligence driven user interface |
| CN115957510A (en) * | 2023-02-03 | 2023-04-14 | 北京畅游时代数码技术有限公司 | Method and system for controlling role behaviors |
Citations (3)
| 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 |
| CN102136025A (en) * | 2010-12-31 | 2011-07-27 | 北京像素软件科技股份有限公司 | Intelligent controlling method of non player characters |
| CN102298673A (en) * | 2011-09-20 | 2011-12-28 | 北京像素软件科技股份有限公司 | Behavioral decision method for non-player controlled character (NPC) |
-
2015
- 2015-12-11 CN CN201510920765.1A patent/CN105561578A/en active Pending
Patent Citations (3)
| 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 |
| CN102136025A (en) * | 2010-12-31 | 2011-07-27 | 北京像素软件科技股份有限公司 | Intelligent controlling method of non player characters |
| CN102298673A (en) * | 2011-09-20 | 2011-12-28 | 北京像素软件科技股份有限公司 | Behavioral decision method for non-player controlled character (NPC) |
Non-Patent Citations (2)
| Title |
|---|
| 张玉孔: "电脑游戏中的人工智能", 《科技信息（学术研究）》 * |
| 蒋美云: "信念空间下智能NPC助手的意图识别与决策", 《计算机与数字工程》 * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107633302A (en) * | 2016-07-19 | 2018-01-26 | 珠海金山网络游戏科技有限公司 | System and method are realized in a kind of dependence of tactics of the game |
| CN106621334B (en) * | 2016-09-27 | 2020-03-20 | 网易（杭州）网络有限公司 | Method and device for controlling non-player control role |
| CN106621334A (en) * | 2016-09-27 | 2017-05-10 | 网易（杭州）网络有限公司 | Control method and device of non-player-controlled character |
| CN107145948A (en) * | 2017-04-12 | 2017-09-08 | 四川大学 | A kind of NPC control methods based on multi-agent Technology |
| CN107145948B (en) * | 2017-04-12 | 2021-05-18 | 四川大学 | NPC control method based on multi-agent technology |
| US12026629B2 (en) | 2017-04-20 | 2024-07-02 | Tencent Technology (Shenzhen) Company Limited | Generation-based evolution of non-player characters in a game |
| CN107019912A (en) * | 2017-04-20 | 2017-08-08 | 腾讯科技（深圳）有限公司 | The collocation method and device of role |
| US11620536B2 (en) | 2017-04-20 | 2023-04-04 | Tencent Technology (Shenzhen) Company Limited | Character configuration method and apparatus, storage medium, and electronic apparatus |
| WO2018192395A1 (en) * | 2017-04-20 | 2018-10-25 | 腾讯科技（深圳）有限公司 | Character configuration method and apparatus, storage medium and electronic apparatus |
| CN107256174A (en) * | 2017-05-27 | 2017-10-17 | 武汉秀宝软件有限公司 | The implementation method and device of artificial intelligence |
| CN107890674A (en) * | 2017-11-13 | 2018-04-10 | 杭州电魂网络科技股份有限公司 | AI behaviors call method and device |
| CN107890675A (en) * | 2017-11-13 | 2018-04-10 | 杭州电魂网络科技股份有限公司 | AI behaviors implementation method and device |
| CN108057249A (en) * | 2017-11-29 | 2018-05-22 | 腾讯科技(成都)有限公司 | A kind of business data processing method and device |
| WO2019105377A1 (en) * | 2017-11-29 | 2019-06-06 | 腾讯科技（深圳）有限公司 | Service processing method and apparatus, and storage medium |
| CN107943707A (en) * | 2017-12-19 | 2018-04-20 | 网易（杭州）网络有限公司 | Test method, device and the storage medium and terminal of behavior tree |
| CN108283809A (en) * | 2018-02-11 | 2018-07-17 | 腾讯科技（深圳）有限公司 | Data processing method, device, computer equipment and storage medium |
| CN108283809B (en) * | 2018-02-11 | 2021-10-26 | 腾讯科技（深圳）有限公司 | Data processing method, data processing device, computer equipment and storage medium |
| CN109200583A (en) * | 2018-08-02 | 2019-01-15 | 苏州蜗牛数字科技股份有限公司 | Control method, system and the storage medium of game NPC behavior |
| CN109857552A (en) * | 2019-01-11 | 2019-06-07 | 珠海金山网络游戏科技有限公司 | A kind of game artificial intelligence action planning method and system |
| CN114040806A (en) * | 2019-06-14 | 2022-02-11 | 战斗机基地出版公司 | Method and system for artificial intelligence driven user interface |
| CN110947182A (en) * | 2019-11-26 | 2020-04-03 | 上海米哈游网络科技股份有限公司 | Event handling method, device, game terminal and medium |
| CN110947182B (en) * | 2019-11-26 | 2024-02-02 | 上海米哈游网络科技股份有限公司 | Event handling method, event handling device, game terminal and medium |
| CN111544889A (en) * | 2020-04-27 | 2020-08-18 | 腾讯科技（深圳）有限公司 | Behavior control method and device of virtual object and storage medium |
| CN111760294B (en) * | 2020-07-07 | 2023-10-13 | 网易(上海)网络有限公司 | Method and device for controlling non-player game characters in game |
| CN111760294A (en) * | 2020-07-07 | 2020-10-13 | 网易（杭州）网络有限公司 | Method and device for controlling non-player game role in game |
| CN112245924A (en) * | 2020-10-29 | 2021-01-22 | 北京冰封互娱科技有限公司 | Method and device for generating non-player character, storage medium and electronic equipment |
| CN112337090A (en) * | 2020-11-06 | 2021-02-09 | 完美世界(重庆)互动科技有限公司 | Event message broadcasting method and device, storage medium and electronic device |
| CN115957510B (en) * | 2023-02-03 | 2023-11-10 | 北京畅游时代数码技术有限公司 | Role behavior control method and system |
| CN115957510A (en) * | 2023-02-03 | 2023-04-14 | 北京畅游时代数码技术有限公司 | Method and system for controlling role behaviors |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105561578A (en) | NPC behavior decision method | |
| Wu et al. | Training agent for first-person shooter game with actor-critic curriculum learning | |
| Xiong et al. | Parametrized deep q-networks learning: Reinforcement learning with discrete-continuous hybrid action space | |
| Perez-Liebana et al. | The 2014 general video game playing competition | |
| Tan et al. | Dynamic game difficulty scaling using adaptive behavior-based AI | |
| Andrade et al. | Challenge-sensitive action selection: an application to game balancing | |
| Stanescu et al. | Predicting army combat outcomes in StarCraft | |
| US20080207330A1 (en) | Artificial player character for massive multi-player on-line game | |
| CN102682196A (en) | Method and system for graphical display | |
| Da Silva et al. | Hearthbot: An autonomous agent based on fuzzy art adaptive neural networks for the digital collectible card game hearthstone | |
| Muñoz-Avila et al. | Learning and game AI | |
| Recio et al. | AntBot: Ant colonies for video games | |
| Nam et al. | Generation of diverse stages in turn-based role-playing game using reinforcement learning | |
| US11007441B2 (en) | Systems and methods for evolving content for computer games | |
| Liu et al. | Evolving effective micro behaviors in RTS game | |
| Pelling et al. | Two human-like imitation-learning bots with probabilistic behaviors | |
| Zhen et al. | Neuroevolution for micromanagement in the real-time strategy game StarCraft: Brood War | |
| Tsay et al. | Evolving intelligent mario controller by reinforcement learning | |
| Armanto et al. | Evolutionary Algorithm in Game–A Systematic Review | |
| Asayama et al. | Prediction as faster perception in a real-time fighting video game | |
| Vázquez-Fernández et al. | Assessing the positional values of chess pieces by tuning neural networks' weights with an evolutionary algorithm | |
| Ito et al. | Procedural play generation according to play arcs using monte-carlo tree search | |
| Parker et al. | The evolution of multi-layer neural networks for the control of xpilot agents | |
| Hartley et al. | In-game tactic adaptation for interactive computer games | |
| On et al. | Rule-based procedural generation of item in role-playing game |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160511 |