A method and device for controlling a game, an electronic device, and a storage medium

Abstract

The present disclosure provides a method and device for controlling a game, electronic equipment and a storage medium. The method comprises: determining an exchange strategy intention of a target object according to current game state data and exchange information of the target object, wherein the exchange strategy intention represents a game target expressed by the exchange information; determining an initial strategy intention of a virtual object in response to the game state data according to the game state data; determining a target strategy intention of the virtual object according to the initial strategy intention and the exchange strategy intention; and determining a response action of the virtual object based on the target strategy intention and controlling the virtual object to perform the response action. Thus, the virtual object can understand the exchange strategy intention of the target object and respond accordingly, improving the personification and cooperation ability of the virtual object.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, in particular, to a battle control method and device, electronic equipment and storage medium. BACKGROUND

[0002] At present, artificial intelligence is widely used in various games. For example, in a game, artificial intelligence can act as a virtual character and play the game together with a real player as a teammate. However, in the prior art, the artificial intelligence usually makes independent decisions during the game, and lacks the ability to respond to the strategic intention of the human battle, thereby resulting in poor cooperation between the artificial intelligence and the real player and reducing the participation of the real player. SUMMARY

[0003] The embodiments of the present disclosure at least provide a battle control method and device, electronic equipment and storage medium.

[0004] In a first aspect, the embodiments of the present disclosure provide a battle control method, comprising:

[0005] determining an exchange strategic intention of a target object according to current game state data and exchange information of the target object, wherein the exchange strategic intention represents a battle target expressed by the exchange information;

[0006] determining an initial strategic intention of a virtual object responding to the game state data according to the game state data;

[0007] determining a target strategic intention of the virtual object according to the initial strategic intention and the exchange strategic intention;

[0008] determining a response action of the virtual object based on the target strategic intention, and controlling the virtual object to perform the response action.

[0009] In an optional implementation, the determining of the initial strategic intention of the virtual object responding to the game state data according to the game state data comprises:

[0010] inputting the game state data and the exchange strategic intention into a pre-trained strategy model to obtain the initial strategic intention of the virtual object responding to the game state data;

[0011] The determining of the response action of the virtual object based on the target strategic intention comprises:

[0012] performing action decision according to the target strategic intention and the game state data to obtain the response action of the virtual object.

[0013] In an optional implementation, the determining the target strategic intention of the virtual object according to the communication strategic intention and the initial strategic intention comprises:

[0014] identifying the communication strategic intention based on the strategy model to obtain a response probability for the communication strategic intention;

[0015] when the response probability is greater than or equal to a preset threshold, determining the target strategic intention of the virtual object according to the communication strategic intention.

[0016] In an optional implementation, the determining the target strategic intention of the virtual object according to the communication strategic intention and the initial strategic intention comprises:

[0017] identifying the communication strategic intention based on the strategy model to obtain a response probability for the communication strategic intention;

[0018] when the response probability is less than a preset threshold, determining the initial strategic intention as the target strategic intention of the virtual object.

[0019] In an optional implementation, the method further comprises:

[0020] obtaining game match data;

[0021] obtaining a training sample set according to the game match data, wherein the training sample set comprises a plurality of first training samples, each first training sample comprising at least a first game state data sample, a strategic intention label and an action label corresponding to the first game state data sample;

[0022] training the strategy model based on the training sample set to obtain a trained strategy model;

[0023] wherein the training the strategy model based on the training sample set to obtain a trained strategy model comprises:

[0024] inputting the first game state data sample in the training sample set into the strategy model to obtain a predicted strategic intention corresponding to the first game state data sample;

[0025] obtaining a predicted response action corresponding to the first game state data sample and the predicted strategic intention or the strategic intention label, and training the strategy model according to the predicted strategic intention and the predicted response action, and the strategic intention label and the action label in the first training sample until a target loss function of the strategy model is minimized;

[0026] The target loss function includes a first loss function and a second loss function, the first loss function is a loss function between the predicted strategic intention and the strategic intention label, and the second loss function is a loss function between the predicted response action and the action label.

[0027] In an optional implementation, the determining of the communication strategic intention of the target object according to the current game state data and the communication information of the target object includes:

[0028] The game state data and the communication information of the target object are input into a pre-trained intention prediction model to obtain the communication strategic intention of the target object, wherein the intention prediction model is trained based on a plurality of second training samples, and each second training sample includes a second game state data sample, a communication information sample, and a communication strategic intention label.

[0029] In an optional implementation, the communication information includes at least one of the following: input text or voice information, signal information input for a quick communication control, and preset communication information corresponding to a specified behavior.

[0030] The game state data represents game-related description information, and includes at least one of the following: game description information of the target object, game description information of the virtual object, and game environment description information.

[0031] In an optional implementation, the determining of the communication strategic intention of the target object according to the current game state data and the communication information of the target object includes:

[0032] During the game battle, the communication strategic intention of the target object is determined according to the current game state data and the communication information of the target object, wherein the game battle includes at least a home team and an enemy team, the home team includes one or more target objects and one or more virtual objects, and the enemy team includes a plurality of game objects.

[0033] In an optional implementation, the determining of the communication strategic intention of the target object according to the current game state data and the communication information of the target object includes: during the game battle, the communication strategic intention of each target object is determined when the communication information of a plurality of target objects is obtained.

[0034] The target strategic intention of the virtual object is determined according to the initial strategic intention and the communication strategic intention, including: the target strategic intention of the virtual object for each target object is determined according to the initial strategic intention and the communication strategic intention of each target object.

[0035] The target strategic intention is determined based on the target strategic intention, and a response action of the virtual object is determined, and the virtual object is controlled to perform the response action, including: according to a preset rule, based on the target strategic intention of the virtual object for each target object, the response action of the virtual object for each target object is determined respectively, and the virtual object is controlled to perform the response action for each target object.

[0036] In a second aspect, the embodiments of the present disclosure further provide a game control device, comprising:

[0037] The first determining module is configured to determine an exchange strategic intention of the target object according to the current game state data and the exchange information of the target object, wherein the exchange strategic intention represents a game target expressed by the exchange information;

[0038] The second determining module is configured to determine an initial strategic intention of a virtual object in response to the game state data according to the game state data;

[0039] The third determining module is configured to determine a target strategic intention of the virtual object according to the initial strategic intention and the exchange strategic intention;

[0040] The fourth determining module is configured to determine a response action of the virtual object based on the target strategic intention;

[0041] The control module is configured to control the virtual object to perform the response action.

[0042] In a third aspect, the optional implementation manner of the present disclosure further provides an electronic device, comprising a processor and a memory, wherein the memory stores machine readable instructions executable by the processor, the processor is configured to execute the machine readable instructions stored in the memory, and the machine readable instructions are executed by the processor to execute the steps of the first aspect or any possible implementation manner in the first aspect.

[0043] In a fourth aspect, the optional implementation manner of the present disclosure further provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to execute the steps of the first aspect or any possible implementation manner in the first aspect.

[0044] In the embodiments of the present disclosure, according to the current game state data and the communication information of the target object, the communication strategy intention of the target object is determined, wherein the communication strategy intention represents the battle target expressed by the communication information; according to the game state data, the initial strategy intention of the virtual object responding to the game state data is determined; according to the initial strategy intention and the communication strategy intention, the target strategy intention of the virtual object is determined; and based on the target strategy intention, the response action of the virtual object is determined, and the virtual object is controlled to perform the response action. In this way, the communication strategy intention of the target object and the initial strategy intention of the virtual object are determined, the initial strategy intention and the communication strategy intention are judged, the final target strategy intention and the response action of the virtual object are determined, so that the virtual object can understand the communication strategy intention of the target object and respond, the personification and the cooperation ability with the target object of the virtual object are improved, and further the willingness of the target object to actively communicate is promoted, and the game experience and the game battle quality are further improved.

[0045] For the effect description of the above-mentioned battle control device, electronic equipment and computer readable storage medium, refer to the description of the above-mentioned battle control method, which will not be repeated here.

[0046] In order to make the above-mentioned purpose, features and advantages of the present disclosure more obvious and easy to understand, the following preferred embodiments are described in detail below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following will briefly introduce the drawings needed to be used in the embodiments. The drawings are incorporated into the specification and form a part of the specification. These drawings show the embodiments consistent with the present disclosure, and are used to illustrate the technical solutions of the present disclosure together with the specification. It should be understood that the following drawings only show some embodiments of the present disclosure, and therefore should not be regarded as a limitation on the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor.

[0048] Figure 1 A flowchart of a battle control method provided by an embodiment of the present disclosure is shown;

[0049] Figure 2 A flowchart of a training method of a strategy model provided by an embodiment of the present disclosure is shown;

[0050] Figure 3 A flowchart of another battle control method provided by an embodiment of the present disclosure is shown;

[0051] Figure 4 A schematic diagram of a battle control device provided by an embodiment of the present disclosure is shown;

[0052] Figure 5 A schematic diagram of an electronic device is shown. DETAILED DESCRIPTION

[0053] It can be understood that, before using the technical solutions disclosed in the embodiments of the present disclosure, the type of personal information involved in the present disclosure, the use range, the use scenario, etc. should be informed to the user and the authorization of the user should be obtained according to relevant laws and regulations.

[0054] To make the objects, technical solutions, and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments. The components of the embodiments of the present disclosure described and shown herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure is not intended to limit the scope of the claimed present disclosure, but only represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present disclosure.

[0055] It is found through research that artificial intelligence (AI) is widely used in various games at present. For example, in a game, the artificial intelligence can act as a virtual character and play the game together with a real human player as a teammate. However, in the prior art, the artificial intelligence usually makes independent decisions in the game process, and lacks the ability to respond to the strategic intention of the human opponent, thereby resulting in poor cooperation effect of the artificial intelligence and the real human player, and reducing the participation of the real human player. Therefore, how the artificial intelligence can understand the strategic intention of the real human player and respond is a difficult and urgent problem at present.

[0056] Based on the above research, the present disclosure provides a method for controlling a game, which determines a communication strategy intention of a target object according to current game state data and communication information of the target object, determines an initial strategy intention of a virtual object in response to the game state data according to the game state data, and determines a target strategy intention of the virtual object according to the initial strategy intention and the communication strategy intention. Then, the response action of the virtual object can be determined based on the target strategy intention, and the virtual object is controlled to perform the response action. In this way, the communication strategy intention of the target object can be understood through the communication information, and the final response action of the virtual object is determined in combination with the communication strategy intention, so that the virtual object has the ability to understand the strategy intention of the target object and respond accordingly, thereby further improving the game cooperation ability of the virtual object and the target object, improving the game participation and experience of the target object, and also improving the game teammate attribute of the virtual object.

[0057] The above-mentioned defects are the results of the inventors' practice and careful research, and therefore, the discovery process of the above-mentioned problems and the solutions proposed by the present disclosure to solve the above-mentioned problems should be the contributions of the inventors to the present disclosure.

[0058] It should be noted that similar reference numerals and letters represent similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0059] To facilitate the understanding of the present embodiment, first, a method for controlling a game disclosed by the present embodiment is introduced in detail. The execution subject of the game control method provided by the present embodiment is generally an electronic device with certain computing power. The electronic device includes, for example, a terminal device or a server or other processing device. The terminal device can be a user equipment (UE), a mobile device, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. The personal digital assistant is a handheld electronic device with some functions of an electronic computer, which can be used to manage personal information, browse the Internet, send and receive emails, etc. Generally, it does not have a keyboard and can also be called a palm computer. In some possible implementation manners, the game control method can be realized by a processor calling computer readable instructions stored in a memory.

[0060] It should be noted that the battle control method provided in the embodiments of the present disclosure can be applied to any game scenario that requires interactive control of virtual objects. For example, this includes third-person shooter games, first-person shooter games, role-playing games, action games, strategy games, fighting games, sports games, adventure games, and the like. All of these can adopt the battle control method provided in the embodiments of the present disclosure, without any specific limitation.

[0061] The game operation interface in the disclosed embodiment is a page that displays the game scene. The game scene includes virtual objects. Virtual objects may include, but are not limited to, virtual characters controlled by the player and non-player characters (NPCs). In the disclosed embodiment, for ease of description and distinction, the artificial intelligence and real player control in the game scene are described as virtual objects and target objects, respectively. Virtual characters may include, but are not limited to, at least one of virtual people and virtual animals, virtual characters that can be controlled by the player, and non-player characters, which are set according to game requirements and are not specifically limited here. Generally, the game operation interface includes multiple buttons that can be touched by the player. The player controls the virtual objects to perform corresponding operations by touching the buttons. For example, if the game is a shooting game, the game operation interface may include multiple types of buttons, such as item use buttons, movement buttons (such as joysticks), action buttons (such as aiming, jumping, crouching, crawling, etc.), attack buttons (such as skill release, shooting, etc.), etc.

[0062] The AC control method provided by the embodiment of the present disclosure is described below by taking the execution subject as a server as an example.

[0063] See also Figure 1 FIG. 1 is a flow chart of a battle control method provided by an embodiment of the present disclosure, the method comprising:

[0064] S101: Determine the communication strategic intention of the target object based on the current game status data and the communication information of the target object.

[0065] The game status data represents game-related description information, including at least one of the following: game description information of a target object, game description information of a virtual object, and game environment description information.

[0066] For example, the game description information of the target object or virtual object represents its own game status, game behavior and other information, which may include its own health, mana, economy, kills, assists, number of deaths, etc.; the game environment description information may include the survival status of wild monsters, obstacle conditions, etc.

[0067] The communication information is information used for communication, and the communication information includes at least one of the following: input text or voice information, signal information input for the shortcut communication control, and preset communication information corresponding to a specified behavior.

[0068] In the embodiment of the present disclosure, the players can communicate in real time during the game battle process, and the communication information can be output in different ways, for example, the text or voice information can be input through an input box; there is a shortcut communication control for sending signals in the game operation interface, such as attack, assembly, retreat, etc., and the communication information that the user wants to express can be quickly input by clicking the shortcut communication control; and in the embodiment of the present disclosure, the expressed communication information can also be set corresponding to different specified behaviors, so that during the current game battle, if a target object has a specified behavior, for example, the target object performs a tower pushing behavior, it can be considered that the communication information is triggered, at this time, a communication information corresponding to the tower pushing behavior can be generated by default, for example, the corresponding communication information is "come and support", and the communication strategy intention of the target object can also be determined according to the communication information, and the virtual object of the AI can respond to the communication strategy intention.

[0069] In addition, in the embodiment of the present disclosure, the output mode of the communication information is not limited, and can also include expressions, shortcut languages, etc.

[0070] The communication strategy intention represents the battle target expressed by the communication information, and in the embodiment of the present disclosure, the communication strategy intention is also associated with the current game state data, for example, it can be the area that wants to attack or defend, the strategic point and strategic resource of attack or defense, etc.

[0071] In the embodiment of the present disclosure, the artificial intelligence can cooperate with the real human players in the multi-player game scene, for example, in a possible embodiment, the game battle includes at least a home team and an enemy team, the home team includes one or more target objects and one or more virtual objects, and the enemy team includes a plurality of game objects, wherein the target object is a real human player, and the virtual object is an artificial intelligence, and the number of real human players and artificial intelligence in the same team is not limited, for example, in a 5V5 game, a five-person team can have four real human players and one artificial intelligence.

[0072] Therefore, in the embodiment of the present disclosure, when step S101 is performed, it can be during the game battle, that is, step S101 is performed, and in a possible embodiment, during the game battle, the communication strategy intention of the target object is determined according to the current game state data and the communication information of the target object.

[0073] And, in the step S101, the game state data and the communication information of the target object are input into a pre-trained intention prediction model to obtain the communication strategy intention of the target object, where the intention prediction model is trained based on a plurality of second training samples, each of which includes a second game state data sample, a communication information sample, and a communication strategy intention label.

[0074] The second training sample can be obtained according to the game data of a real player. For example, game data of a plurality of real players is obtained. To further improve the reliability, the game data can be filtered to select game data of real players with high reliability. Then, the communication information of the real players and the corresponding game state data are extracted from the game data, and the communication strategy intention is determined based on the behavior of the real players before and after sending the communication information and the game state data. The communication strategy intention can be analyzed manually or determined based on other methods, which is not limited. In this way, the second training sample can be obtained according to the extracted communication information, the corresponding game state data, and the communication strategy intention.

[0075] S102: determining an initial strategy intention of the virtual object in response to the game state data according to the game state data.

[0076] In the embodiment of the present disclosure, the virtual object is an artificial intelligence that competes in the game, for example. In the process of making decisions for the virtual object, the initial strategy intention of the virtual object is defined and displayed. Specifically, when the step S102 is performed, the game state data and the communication strategy intention are input into a pre-trained strategy model to obtain the initial strategy intention of the virtual object in response to the game state data.

[0077] In this way, by defining and displaying the initial strategy intention, the strategy model can effectively output the initial strategy intention when competing, thereby facilitating the understanding and response of the subsequent communication strategy intention of the target object.

[0078] S103: determining a target strategy intention of the virtual object according to the initial strategy intention and the communication strategy intention.

[0079] In the embodiment of the present disclosure, when the step S103 is performed, the following possible implementation manners can be included:

[0080] The first implementation manner: 1) based on the strategy model, the communication strategy intention is identified to obtain a response probability for the communication strategy intention.

[0081] In the embodiments of the present disclosure, by comparing the initial strategic intention predicted based on the strategy model with the communication strategic intention of the target object through the strategy model, the response probability of the initial strategic intention and the communication strategic intention can be determined, so that the final target strategic intention can be comprehensively predicted.

[0082] 2) When the response probability is greater than or equal to the preset threshold, the target strategic intention of the virtual object is determined according to the communication strategic intention.

[0083] The preset threshold can be set according to actual experience or determined by the decision model through training and learning, and the embodiments of the present disclosure do not limit it.

[0084] That is, when the response probability of the communication strategic intention is greater than or equal to a certain threshold, it is considered that the communication strategic intention needs to be responded to, and then the final target strategic intention can be determined according to the communication strategic intention, for example, the communication strategic intention can be directly taken as the target strategic intention of the virtual object, for example, a strategic intention that is closer or the same as the communication strategic intention but easier to understand can also be determined according to the communication strategic intention and taken as the target strategic intention of the virtual object, for example, a strategic intention that cooperates with the communication strategic intention can also be determined according to the communication strategic intention and taken as the target strategic intention of the virtual object, and the present disclosure does not limit it.

[0085] The second implementation manner is: 1) identifying the communication strategic intention based on the strategy model to obtain the response probability of the communication strategic intention.

[0086] 2) When the response probability is less than the preset threshold, the initial strategic intention is determined as the target strategic intention of the virtual object.

[0087] That is, when the response probability of the communication strategic intention is less than the preset threshold, it is considered that the communication strategic intention of the target object does not need to be responded to, and the initial strategic intention predicted by the strategy model is still taken as the final target strategic intention of the virtual object.

[0088] In addition, in the embodiments of the present disclosure, when comparing the communication strategic intention and the initial strategic intention through the strategy model, the flag bit of the communication strategic intention can also be identified to determine what the final target strategic intention is, for example, if the value of the flag bit of the communication strategic intention is 0, it means that the communication strategic intention does not need to be responded to, and the initial strategic intention can be taken as the target strategic intention, for example, if the value of the flag bit of the communication strategic intention is 1, it means that the communication strategic intention needs to be responded to, and then the target strategic intention can be determined according to the communication strategic intention.

[0089] The process of identifying the flag bit of the communication strategic intention can also be understood as a process of identifying a response probability of the communication strategic intention. When the response probability is greater than or equal to a preset threshold, the value of the flag bit is 1. When the response probability is less than the preset threshold, the value of the flag bit is 0.

[0090] In this way, in the embodiment of the present disclosure, the communication strategic intention of the target object is input into the decision model, the initial strategic intention in the decision model is influenced to realize the understanding and response of the virtual object to the communication strategic intention of the target object, and the virtual object is not completely in line with the communication strategic intention of the target object. The strategy model also compares the communication strategic intention with the initial communication strategic intention predicted by itself to determine the final target strategic intention, thereby improving the rationality of the target strategic intention and the rationality of the subsequent response action prediction, and making the virtual object more in line with the current game state data, more humanized and real, not blindly following the target object, and improving the game cooperation and the game experience.

[0091] S104: determining a response action of the virtual object based on the target strategic intention.

[0092] When the step S104 is performed, the following is included: performing action decision based on the target strategic intention and the game state data to obtain the response action of the virtual object.

[0093] In the embodiment of the present disclosure, during the response action decision process by the decision model, the initial strategic intention predicted by the decision model is displayed, and then the communication strategic intention of the target object is obtained. The communication strategic intention is compared with the initial strategic intention to determine the final target strategic intention. Action decision is performed based on the target strategic intention and the game state data to obtain the final response action. In this way, the action prediction effect of the decision model is improved, the communication strategic intention of the target object is better understood, and more reasonable and correct response behavior can be taken.

[0094] S105: controlling the virtual object to perform the response action.

[0095] It should be noted that, in the embodiment of the present disclosure, the step S101 described above can be realized by an intention prediction model, and the steps S102-S104 described above are realized by a strategy model. The intention prediction model and the strategy model can be trained independently during training. After training is completed, the communication strategic intention of the target object output by the intention prediction model is input into the decision model. The response effect of the virtual object can be realized by influencing the initial strategic intention in the decision model, and the virtual object is given the ability to understand and respond to the communication strategic intention of the target object.

[0096] Further, in the game scenario of multi-player battle, the team of the two parties in the battle includes multiple players, the players in the same team can communicate to better cooperate in the battle, and multiple target objects can output communication information. In this case, the AI virtual object can respond to the communication strategy intention of each target object. Specifically, in the embodiments of the present disclosure, possible implementation manners are provided for the case where multiple target objects output communication information.

[0097] 1) determining the communication strategy intention of the target object according to the current game state data and the communication information of the target object, including: when obtaining the communication information of multiple target objects during the game battle, determining the communication strategy intention of each target object.

[0098] For example, when multiple target objects output communication information, the communication strategy intention of each target object can be determined respectively.

[0099] 2) determining the target strategy intention of the virtual object according to the initial strategy intention and the communication strategy intention, including: determining the target strategy intention of the virtual object for each target object according to the initial strategy intention and the communication strategy intention of each target object.

[0100] In the embodiments of the present disclosure, the initial strategy intention of the virtual object is determined according to the current game state data. Since the game state data changes at different times or based on different response actions output by the virtual object and different actions performed by the target objects, when the virtual object responds to the communication strategy intention of each target object, the current game state data can be obtained after the virtual object performs a response action for a certain target object, so as to calculate the current initial strategy intention, and then determine the target strategy intention and the response action for another target object. In this way, the accuracy and rationality of the response action can be improved.

[0101] 3) determining the response action of the virtual object based on the target strategy intention, and controlling the virtual object to perform the response action, including: according to a preset rule, determining the response action of the virtual object for each target object based on the target strategy intention of the virtual object for each target object, and controlling the virtual object to perform the response action for each target object.

[0102] The preset rule can be set according to needs and experience, and is not limited in the embodiment of the present disclosure. For example, the preset rule can be to respond to each target object in turn according to the order of the time when the target object outputs the communication information, that is, the communication information of the target object with earlier time is responded to first, the target strategy intention and the response action for the target object are determined, and the virtual object is controlled to perform the response action for the target object, and then the communication strategy intention of the next target object is responded to. For another example, the preset rule can be to respond to each target object according to the priority of the target object, and the communication strategy intention of the target object with higher priority is responded to preferentially. The priority of the target object can be determined according to the position attribute of the target object. For example, the target object with the position of team leader has higher priority. Alternatively, the priority of the target object can also be determined according to the game level or win rate of the target object. The higher the game level or win rate is, the higher the priority can be considered to be.

[0103] In the embodiment of the present disclosure, the communication strategy intention of the target object is determined according to the current game state data and the communication information of the target object, the initial strategy intention of the virtual object responding to the game state data is determined according to the game state data, the target strategy intention of the virtual object is determined according to the initial strategy intention and the communication strategy intention, and then the response action of the virtual object is determined based on the target strategy intention, and the virtual object is controlled to perform the response action. In this way, by identifying and judging the initial strategy intention of the virtual object and the communication strategy intention of the target object, the final target strategy intention of the virtual object can be determined, and the response action of the virtual object is controlled, so that the virtual object can understand the communication strategy intention of the target object and respond, improve the cooperation ability of the virtual object and the target object, and also make the virtual object have higher personification and cooperation ability with the real player. In turn, it can also promote the communication desire of the player. The virtual object can respond to the communication strategy intention of the target object, which can make the target object more willing to actively communicate and further improve the game experience and the quality of the game battle.

[0104] Based on the above embodiment, the training method of the strategy model in the embodiment of the present disclosure is described below. Referring to Figure 2 The training method of the strategy model in the embodiment of the present disclosure is shown in the flow chart of the method, which comprises:

[0105] S201: Obtain game battle data.

[0106] S202: Obtain a training sample set according to the game battle data, wherein the training sample set comprises a plurality of first training samples, each first training sample comprises at least a first game state data sample, and a strategy intention label and an action label responding to the first game state data sample.

[0107] In the embodiments of the present disclosure, game battle data of multiple objects can be obtained, for example, for an object A, in a certain game battle process, actions performed by the object A under different game state data and strategic intentions are extracted, generally, the actions performed by the object A for the game state data are corresponding to the strategic intentions Figure 1 Therefore, the corresponding strategic intentions can be determined according to the performed actions, which can be determined by artificial analysis, or by other manners, and the limitation is not made, the actions performed by the object A for the certain game state data can be taken as action labels, and the corresponding strategic intentions can be taken as strategic intention labels, and then a plurality of first training samples of the object A can be obtained, so that based on the manner, the first training samples of the multiple objects can be obtained.

[0108] Further, in order to improve the reliability and accuracy of the strategy model training, the first training samples can be selected and filtered by a preset reliability index, and the first training samples of objects with higher reliability are selected.

[0109] S203: training the strategy model based on the training sample set to obtain a trained strategy model.

[0110] To implement the step S203, the present disclosure provides a possible implementation manner:

[0111] 1) inputting the first game state data sample in the training sample set into the strategy model to obtain a predicted strategic intention responding to the first game state data sample.

[0112] In the embodiments of the present disclosure, in the training process, the first game state data sample of the first training sample is input into the strategy model, the strategy model is used to identify the first game state data, and a predicted strategic intention is obtained, and the strategic intention label in the first training sample is taken as a learning target, that is, a first loss function is calculated according to the predicted strategic intention and the strategic intention label.

[0113] 2) obtaining a corresponding predicted response action according to the first game state data sample and the predicted strategic intention or the strategic intention label, and training the strategy model according to the predicted strategic intention and the predicted response action, and the strategic intention label and the action label in the first training sample, until a target loss function of the strategy model is minimum.

[0114] The target loss function includes the first loss function and a second loss function, the first loss function is a loss function between the predicted strategic intention and the strategic intention label, and the second loss function is a loss function between the predicted response action and the action label.

[0115] In the embodiments of the present disclosure, in the strategy model training process, after obtaining the predicted strategic intent, the identification of the predicted response action is performed. The process takes the action label in the first training sample as the learning target, and corresponds to the second loss function. However, the process does not only use the strategic intent label in the first training sample for training, but also mixes the predicted strategic intent determined by the strategy model. That is, in the process, the predicted response action can be obtained by identifying the first game state data sample and the predicted strategic intent, or by identifying the first game state data sample and the strategic intent label. The mixed training of the predicted strategic intent and the strategic intent label based on the first training sample in the training sample set is performed. In order to enable the strategy model to better distinguish the two states, a flag bit can be constructed in the strategy model, for example, the value of the flag bit corresponding to the strategic intent label is determined as 1, indicating that the strategic intent label needs to be responded to, and the value of the flag bit corresponding to the predicted strategic intent is determined as 0, indicating that the predicted strategic intent does not need to be responded to. Therefore, the strategy model can learn what strategic intent should be responded to and what strategic intent does not need to be responded to, and the mixing ratio can also be controlled based on the flag bit.

[0116] In the training process of the strategy model, the mixing ratio of the mixed training of the predicted strategic intent and the strategic intent label of the first training sample is not limited. The mixing ratio can be set through actual verification effect or experience, for example, the proportion of the first training sample based on the strategic intent label for predicting the response action identification can be 60%.

[0117] That is, in the embodiments of the present disclosure, the training process of the strategy model can be understood as including two stages. The input of the first stage is the first game state data sample of the first training sample, and the output is the predicted strategic intent. The loss function of the first stage is the first loss function, and the learning target is the strategic intent label. The input of the second stage is the first game state data sample and the strategic intent label of the first training sample, or the first game state data sample and the predicted strategic intent of the first training sample, and the output is the predicted response action. The loss function of the second stage is the second loss function, and the learning is the action label. The first stage and the second stage are a complete training process.

[0118] In this way, in the second stage of the policy model training, the predicted strategic intention and the strategic intention label are mixed for training, so that the policy model has the ability to determine whether to respond to a certain strategic intention. The trained policy model not only has the ability to respond to the communication strategic intention of the target object, but also has its own autonomous judgment ability. For a reasonable communication strategic intention of the target object, the virtual object selects a response through the judgment of the policy model, updates the initial strategic intention of the policy model, and performs a corresponding response action according to the communication strategic intention. For some unreasonable communication strategic intention of the target object, the virtual object can choose to ignore through the judgment of the policy model, and determine the response action according to the initial strategic intention, so that the virtual object is more humanized, the response action is more accurate and reasonable, and the game experience is improved.

[0119] The battle control method in the embodiments of the present disclosure is briefly described below in a specific application scenario. Referring to FIG. 8, which is another battle control method flowchart in the embodiments of the present disclosure, the method comprises the following steps: Figure 3

[0120] S301: inputting the game state data and the communication information of the target object into a pre-trained intention prediction model.

[0121] S302: performing state coding on the game state data and the communication information of the target object.

[0122] S303: performing communication strategic intention prediction to obtain the communication strategic intention of the target object.

[0123] The steps S301-S303 are realized by the intention prediction model.

[0124] S304: inputting the game state data into a pre-trained policy model.

[0125] S305: performing state coding on the game state data and the communication information of the target object.

[0126] S306: performing initial strategic intention prediction to obtain the initial strategic intention of the virtual object in response to the game state data.

[0127] S307: determining the target strategic intention of the virtual object according to the initial strategic intention and the communication strategic intention.

[0128] That is, the communication strategic intention output by the intention prediction model is also input into the policy model. The policy model judges the initial strategic intention and the communication strategic intention to determine the final target strategic intention.

[0129] S308: performing action decision according to the target strategic intention and the game state data to obtain the response action of the virtual object.​

[0130] The steps S304-S308 are implemented by the strategy model.

[0131] S309: controlling the virtual object to perform a response action.

[0132] It should be noted that the specific execution manner of each step is the same as the execution manner in the above embodiment, and will not be repeated here.

[0133] In this way, in the embodiment of the disclosure, by defining the strategic intention and displaying the modeling, the strategy model can obtain the initial strategic intention of the virtual object while making action decisions, and the communication strategic intention of the target object is obtained through the intention prediction model, and then the communication strategic intention of the target object is input to the strategy model, so that the virtual object can understand the communication strategic intention of the target object and make a response, improve the cooperation ability of the virtual object and the target object, and improve the game experience.

[0134] Those skilled in the art can understand that in the above method of the specific embodiment, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process, and the specific execution order of each step should be determined by its function and possible internal logic.

[0135] Based on the same inventive concept, the embodiment of the disclosure also provides a battle control method corresponding to the battle control method. Since the principle of solving the problem of the battle control device in the embodiment of the disclosure is similar to the above-mentioned battle control method, the implementation of the battle control device can be referred to the implementation of the battle control method, and the repeated parts will not be repeated.

[0136] Referring to Figure 4 Fig. 1 is a schematic diagram of a battle control device provided by an embodiment of the disclosure, which comprises:

[0137] A first determination module 41 is configured to determine a communication strategic intention of a target object according to current game state data and communication information of the target object, wherein the communication strategic intention represents a battle target expressed by the communication information;

[0138] A second determination module 42 is configured to determine an initial strategic intention of a virtual object responding to the game state data according to the game state data;

[0139] A third determination module 43 is configured to determine a target strategic intention of the virtual object according to the initial strategic intention and the communication strategic intention;

[0140] A fourth determination module 44 is configured to determine a response action of the virtual object based on the target strategic intention;

[0141] The control module 45 is configured to control the virtual object to perform the response action.

[0142] In an optional implementation, when the initial strategic intention of the virtual object in response to the game state data is determined according to the game state data, the second determination module 42 is configured to:

[0143] input the game state data and the communication strategic intention into a pre-trained strategy model to obtain the initial strategic intention of the virtual object in response to the game state data;

[0144] When the response action of the virtual object is determined based on the target strategic intention, the fourth determination module 44 is configured to:

[0145] perform action decision-making according to the target strategic intention and the game state data to obtain the response action of the virtual object.

[0146] In an optional implementation, when the target strategic intention of the virtual object is determined according to the communication strategic intention and the initial strategic intention, the third determination module 43 is configured to:

[0147] identify the communication strategic intention based on the strategy model to obtain a response probability for the communication strategic intention;

[0148] When the response probability is greater than or equal to a preset threshold, the target strategic intention of the virtual object is determined according to the communication strategic intention.

[0149] In an optional implementation, when the target strategic intention of the virtual object is determined according to the communication strategic intention and the initial strategic intention, the third determination module 43 is configured to:

[0150] identify the communication strategic intention based on the strategy model to obtain a response probability for the communication strategic intention;

[0151] When the response probability is less than a preset threshold, the initial strategic intention is determined as the target strategic intention of the virtual object.

[0152] In an optional implementation, the method further includes a training module 46, which is configured to:

[0153] obtain game battle data;

[0154] According to the game battle data, a training sample set is obtained, wherein the training sample set includes a plurality of first training samples, each first training sample at least includes a first game state data sample, a strategy intention label and an action label in response to the first game state data sample;

[0155] The strategy model is trained based on the training sample set to obtain a trained strategy model;

[0156] The training module 46 is configured to:

[0157] The first game state data sample in the training sample set is input into the strategy model to obtain a predicted strategy intention in response to the first game state data sample;

[0158] According to the first game state data sample and the predicted strategy intention or the strategy intention label, a corresponding predicted response action is obtained, and the strategy model is trained according to the predicted strategy intention and the predicted response action, and the strategy intention label and the action label in the first training sample, until a target loss function of the strategy model is minimized;

[0159] The target loss function includes a first loss function and a second loss function, the first loss function is a loss function between the predicted strategy intention and the strategy intention label, and the second loss function is a loss function between the predicted response action and the action label.

[0160] In an optional implementation, when the communication strategy intention of the target object is determined according to the current game state data and the communication information of the target object, the first determination module 41 is configured to:

[0161] The game state data and the communication information of the target object are input into a pre-trained intention prediction model to obtain the communication strategy intention of the target object; wherein the intention prediction model is trained based on a plurality of second training samples, each second training sample includes a second game state data sample, a communication information sample, and a communication strategy intention label.

[0162] In an optional implementation, the communication information includes at least one of the following: input text or voice information, signal information input for a quick communication control, and preset communication information corresponding to a specified behavior.

[0163] The game state data represents game-related description information, including at least one of the following: game description information of the target object, game description information of the virtual object, and game environment description information.

[0164] In an optional implementation, when determining the communication strategy intention of the target object according to the current game state data and the communication information of the target object, the first determining module 41 is configured to:

[0165] During the game battle, the communication strategy intention of the target object is determined according to the current game state data and the communication information of the target object, wherein the game battle includes at least a home team and an enemy team, the home team includes one or more target objects and one or more virtual objects, and the enemy team includes a plurality of game objects.

[0166] In an optional implementation, when determining the communication strategy intention of the target object according to the current game state data and the communication information of the target object, the first determining module 41 is configured to: when obtaining the communication information of a plurality of target objects during the game battle, the communication strategy intention of each target object is determined respectively.

[0167] When determining the target strategy intention of the virtual object according to the initial strategy intention and the communication strategy intention, the third determining module 43 is configured to: according to the initial strategy intention and the communication strategy intention of each target object, the target strategy intention of the virtual object for each target object is determined respectively.

[0168] When determining the response action of the virtual object based on the target strategy intention and controlling the virtual object to perform the response action, the fourth determining module 44 is configured to: according to the target strategy intention of the virtual object for each target object, the response action of the virtual object for each target object is determined respectively according to a preset rule, and the controlling module 45 is configured to control the virtual object to perform the response action for each target object respectively.

[0169] The description of the processing flow of each module in the device and the interaction flow between the modules can refer to the related description in the above method embodiments, which will not be described in detail here.

[0170] The embodiments of the present disclosure also provide an electronic device, as shown in the figure, an electronic device structure schematic diagram provided by the embodiments of the present disclosure, comprising: Figure 5 As shown in the figure, an electronic device structure schematic diagram provided by the embodiments of the present disclosure, comprising:

[0171] The processor 51 and the memory 52; the memory 52 stores machine readable instructions executable by the processor 51, and the processor 51 is configured to execute the machine readable instructions stored in the memory 52, and when the machine readable instructions are executed by the processor 51, the processor 51 executes the following steps:

[0172] determine an exchange strategy intention of the target object according to the current game state data and the exchange information of the target object, wherein the exchange strategy intention represents a battle target expressed by the exchange information;

[0173] determine an initial strategy intention of a virtual object responding to the game state data according to the game state data;

[0174] determine a target strategy intention of the virtual object according to the initial strategy intention and the exchange strategy intention;

[0175] determine a response action of the virtual object based on the target strategy intention;

[0176] control the virtual object to perform the response action.

[0177] In an optional implementation, when the initial strategy intention of the virtual object responding to the game state data is determined according to the game state data, the processor 51 is configured to:

[0178] input the game state data and the exchange strategy intention into a pre-trained strategy model to obtain the initial strategy intention of the virtual object responding to the game state data;

[0179] When the response action of the virtual object is determined based on the target strategy intention, the processor 51 is configured to:

[0180] perform action decision-making according to the target strategy intention and the game state data to obtain the response action of the virtual object.

[0181] In an optional implementation, when the target strategy intention of the virtual object is determined according to the exchange strategy intention and the initial strategy intention, the processor 51 is configured to:

[0182] identify the exchange strategy intention based on the strategy model to obtain a response probability for the exchange strategy intention;

[0183] When the response probability is greater than or equal to a preset threshold, determine the target strategy intention of the virtual object according to the exchange strategy intention.

[0184] In an optional implementation, when the target strategy intention of the virtual object is determined according to the exchange strategy intention and the initial strategy intention, the processor 51 is configured to:

[0185] identify the exchange strategy intention based on the strategy model to obtain a response probability for the exchange strategy intention;

[0186] When the response probability is less than a preset threshold, the initial strategic intention is determined as a target strategic intention of the virtual object.

[0187] In an optional implementation, the processor 51 is configured to:

[0188] obtain game battle data;

[0189] obtain a training sample set according to the game battle data, wherein the training sample set includes a plurality of first training samples, each first training sample includes at least a first game state data sample, a strategic intention label and an action label responsive to the first game state data sample;

[0190] train the policy model based on the training sample set to obtain a trained policy model;

[0191] In an optional implementation, the processor 51 is configured to:

[0192] input the first game state data sample in the training sample set into the policy model to obtain a predicted strategic intention responsive to the first game state data sample;

[0193] obtain a predicted response action corresponding to the first game state data sample and the predicted strategic intention or the strategic intention label, and train the policy model according to the predicted strategic intention and the predicted response action, and the strategic intention label and the action label in the first training sample until a target loss function of the policy model is minimized.

[0194] In an optional implementation, the target loss function includes a first loss function and a second loss function, the first loss function is a loss function between the predicted strategic intention and the strategic intention label, and the second loss function is a loss function between the predicted response action and the action label.

[0195] In an optional implementation, the processor 51 is configured to:

[0196] input the game state data and the communication information of the target object into a pre-trained intention prediction model to obtain the communication strategic intention of the target object, wherein the intention prediction model is trained based on a plurality of second training samples, each second training sample includes a second game state data sample, a communication information sample, and a communication strategic intention label.

[0197] In an optional implementation, the communication information includes at least one of the following: input text or voice information, signal information input for a quick communication control, and communication information corresponding to a preset specified behavior; and the game state data represents game-related description information, including at least one of the following: game description information of the target object, game description information of the virtual object, and game environment description information.

[0198] In an optional implementation, when determining the communication strategy intention of the target object according to the current game state data and the communication information of the target object, the processor 51 is configured to: during a game battle, determine the communication strategy intention of the target object according to the current game state data and the communication information of the target object, wherein the game battle includes at least a home team and an enemy team, the home team includes one or more target objects and one or more virtual objects, and the enemy team includes a plurality of game objects.

[0199] In an optional implementation, when determining the communication strategy intention of the target object according to the current game state data and the communication information of the target object, the processor 51 is configured to: during the game battle, obtain the communication information of a plurality of target objects, and determine the communication strategy intention of each target object respectively.

[0200] When determining the target strategy intention of the virtual object according to the initial strategy intention and the communication strategy intention, the processor 51 is configured to: determine the target strategy intention of the virtual object for each target object according to the initial strategy intention and the communication strategy intention of each target object.

[0201] When determining the response action of the virtual object based on the target strategy intention and controlling the virtual object to perform the response action, the processor 51 is configured to: according to a preset rule, determine the response action of the virtual object for each target object based on the target strategy intention of the virtual object for each target object, and control the virtual object to perform the response action for each target object respectively.

[0202] The memory 52 includes an internal memory 521 and an external memory 522. The internal memory 521 is also referred to as an internal storage, and is used to temporarily store operation data in the processor 51 and exchange data with the external memory 522 such as a hard disk. The processor 51 exchanges data with the external memory 522 through the internal memory 521.

[0203] The specific execution process of the instructions can refer to the steps of the battle control method described in the embodiments of the present disclosure, which will not be described here.

[0204] The embodiment of the present disclosure further provides a computer readable storage medium, and the computer readable storage medium stores a computer program. When the computer program is run by a processor, steps of the battle control method described in the method embodiment are executed. The storage medium can be a volatile or non-volatile computer readable storage medium.

[0205] The embodiment of the present disclosure further provides a computer program product, and the computer program product carries a program code. The program code includes instructions for executing steps of the battle control method described in the method embodiment. For details, refer to the method embodiment, which will not be described here.

[0206] The computer program product can be implemented by hardware, software or a combination thereof. In an optional embodiment, the computer program product is embodied as a computer storage medium. In another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK) and the like.

[0207] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the foregoing method embodiment, which will not be described here. In several embodiments provided by the present disclosure, it should be understood that the disclosed system, device and method can be implemented by other ways. The device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some communication interfaces, devices or units, and can be electrical, mechanical or other forms.

[0208] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the embodiment scheme. In addition, the functional units in each embodiment of the present disclosure can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0209] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a nonvolatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present disclosure essentially or the part of the prior art that contributes to the present disclosure or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for making an electronic device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in various embodiments of the present disclosure. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0210] Finally, it should be noted that: the above-described embodiments are only specific embodiments of the present disclosure, used to illustrate the technical solutions of the present disclosure, and not to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art who is familiar with the technical field of the present disclosure can make modifications or easily think of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed by the present disclosure, or make equivalent replacements to some of the technical features. The modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A method of match control, characterized by, The method comprises the following steps: determining an exchange strategy intention of the target object according to the current game state data and the exchange information of the target object, wherein the exchange strategy intention represents the battle target expressed by the exchange information, and the target object is a real human player; determining an initial strategy intention of a virtual object responding to the game state data according to the game state data, wherein the virtual object is an artificial intelligence; determining a target strategy intention of the virtual object according to the initial strategy intention and a response probability of the exchange strategy intention; determining a response action of the virtual object based on the target strategy intention, and controlling the virtual object to perform the response action.

2. The method of claim 1, wherein, The method comprises the following steps: inputting the game state data and the exchange strategy intention into a pre-trained strategy model to obtain the initial strategy intention of the virtual object responding to the game state data; The method comprises the following steps: determining a response action of the virtual object based on the target strategy intention, and controlling the virtual object to perform the response action.

3. The method of claim 2, wherein, The method comprises the following steps: identifying the exchange strategy intention based on the strategy model to obtain a response probability of the exchange strategy intention; when the response probability is greater than or equal to a preset threshold, determining the target strategy intention of the virtual object according to the exchange strategy intention.

4. The method of claim 2, wherein, The method comprises the following steps: identifying the exchange strategy intention based on the strategy model to obtain a response probability of the exchange strategy intention; when the response probability is less than a preset threshold, determining the initial strategy intention as the target strategy intention of the virtual object.

5. The method according to any one of claims 2-4, characterized in that, The method further comprises the following steps: The training method of the strategy model comprises the following steps: obtaining game battle data; obtaining a training sample set according to the game battle data, wherein the training sample set comprises a plurality of first training samples, each first training sample comprises at least a first game state data sample, and a strategy intention label and an action label responding to the first game state data sample; training the strategy model based on the training sample set to obtain a trained strategy model; The method comprises the following steps: inputting the first game state data sample in the training sample set into the strategy model to obtain a predicted strategy intention responding to the first game state data sample; According to the first game state data sample and the predicted strategic intention or the strategic intention label, a corresponding predicted response action is obtained, and the strategy model is trained according to the predicted strategic intention and the predicted response action and the strategic intention label and the action label in the first training sample until a target loss function of the strategy model is minimized. The target loss function includes a first loss function and a second loss function, the first loss function is a loss function between the predicted strategic intention and the strategic intention label, and the second loss function is a loss function between the predicted response action and the action label.

6. The method according to any one of claims 1 to 4, characterized in that, The communication strategic intention of the target object is determined according to the current game state data and the communication information of the target object, including: The game state data and the communication information of the target object are input into a pre-trained intention prediction model to obtain the communication strategic intention of the target object; wherein the intention prediction model is trained based on a plurality of second training samples, and each second training sample includes a second game state data sample, a communication information sample, and a communication strategic intention label.

7. The method of claim 1, wherein, The communication information includes at least one of the following: input text or voice information, signal information input to a quick communication control, and preset communication information corresponding to a specified behavior. The game state data represents game-related description information, including at least one of the following: game description information of the target object, game description information of the virtual object, and game environment description information.

8. The method according to any one of claims 1 to 4, characterized in that, The communication strategic intention of the target object is determined according to the current game state data and the communication information of the target object, including: During the game battle, the communication strategic intention of the target object is determined according to the current game state data and the communication information of the target object, wherein the game battle includes at least a home team and an enemy team, the home team includes one or more target objects and one or more virtual objects, and the enemy team includes a plurality of game objects.

9. The method of claim 1, wherein The communication strategic intention of the target object is determined according to the current game state data and the communication information of the target object, including: during the game battle, when the communication information of a plurality of target objects is obtained, the communication strategic intention of each target object is determined respectively; The target strategic intention of the virtual object is determined according to the initial strategic intention and the communication strategic intention, including: the target strategic intention of the virtual object for each target object is determined according to the initial strategic intention and the communication strategic intention of each target object; Based on the target strategic intention, the response action of the virtual object is determined, and the virtual object is controlled to perform the response action, including: according to a preset rule, the response action of the virtual object for each target object is determined based on the target strategic intention of the virtual object for each target object, and the virtual object is controlled to perform the response action for each target object.

10. A game control device characterized by comprising: including: The first determining module is configured to determine an exchange strategy intention of the target object according to the current game state data and exchange information of the target object, wherein the exchange strategy intention represents a battle target expressed by the exchange information, and the target object is a real human player. The second determining module is configured to determine an initial strategy intention of a virtual object in response to the game state data according to the game state data, wherein the virtual object is an artificial intelligence. The third determining module is configured to determine a target strategy intention of the virtual object according to the initial strategy intention and a response probability of the exchange strategy intention. The fourth determining module is configured to determine a response action of the virtual object based on the target strategy intention. The control module is configured to control the virtual object to perform the response action.

11. An electronic device, comprising: The processor and the memory are included. The computer readable storage medium stores a computer program, and the computer program is run by the processor.

12. A computer-readable storage medium, characterized in that, When the computer program is run by the processor, the processor executes the steps of the battle control method according to any one of claims 1 to 9.

Images