Game character interaction control methods, devices, storage media, and electronic devices

Abstract

This disclosure relates to a game character interaction control method, device, storage medium, and electronic device, belonging to the field of computer technology. The method dynamically adjusts the target communication cycle of an intelligent agent based on current signal exchange information triggered during a game match and the current game state information, thereby adjusting the frequency with which the agent sends communication messages during the game. Thus, when real players are actively communicating, it can prevent the intelligent agent from sending too many communication messages, thus preventing conflicts with real players' messages, and it can also prevent excessive communication messages from interfering with real players. Furthermore, when real players are not communicating, it can encourage their willingness to communicate, ensuring a good competitive atmosphere in the game.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more specifically, to a method, apparatus, storage medium, and electronic device for controlling game character interaction. Background Technology

[0002] In the video game industry, applying artificial intelligence (AI) to games has become a growing trend. With the iteration of game AI technology, game AI can serve as both competitive opponents and allied partners for human players, significantly enhancing the gaming experience and player engagement.

[0003] However, existing game AI can only send communication messages at preset time intervals, resulting in extremely mechanical communication between game AI and real players during game matches, which cannot simulate the communication of real players. Summary of the Invention

[0004] This summary section is provided to briefly introduce the concepts, which will be described in detail in the detailed description section below. This summary section is not intended to identify key or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] In a first aspect, embodiments of this disclosure provide a game character interaction control method, including:

[0006] Determine the target communication messages that the agents in the game need to send;

[0007] Based on the current signal communication information triggered by the game and the current game state information, the target communication cycle corresponding to the agent is determined.

[0008] If the time interval between the last time the agent sent a communication message and the current time matches the target communication cycle, the agent is controlled to send the target communication message.

[0009] Secondly, embodiments of this disclosure provide a game character interaction control device, comprising:

[0010] The first determining module is configured to determine the target communication messages that the agents in the game are to send.

[0011] The second determining module is configured to determine the target communication cycle corresponding to the agent based on the current signal communication information triggered by the game and the current game state information of the game.

[0012] The control module is configured to control the agent to send the target communication message when the time interval between the time when the agent last sent a communication message and the current time matches the target communication cycle.

[0013] Thirdly, embodiments of this disclosure provide a non-transitory computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in the first aspect.

[0014] Fourthly, embodiments of this disclosure provide an electronic device, including:

[0015] A memory on which computer programs are stored;

[0016] A processor for executing the computer program in the memory to implement the steps of the method described in the first aspect.

[0017] Based on the above technical solution, the target communication cycle of the intelligent agent can be dynamically adjusted by using the current signal exchange information triggered during the game and the current game state information, thereby adjusting the frequency of communication messages sent by the intelligent agent during the game. This prevents the intelligent agent from sending too many communication messages, thus avoiding conflicts with real players' messages, and also prevents excessive communication messages from interfering with real players. Furthermore, when real players are not communicating, it can encourage them to communicate, ensuring a positive competitive atmosphere in the game.

[0018] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0019] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale. In the drawings:

[0020] Figure 1 This is a scene diagram illustrating a game character control method according to an exemplary embodiment.

[0021] Figure 2 This is a flowchart illustrating a game character interaction control method according to an exemplary embodiment.

[0022] Figure 3 yes Figure 2 The detailed flowchart of step 220 is shown.

[0023] Figure 4This is a flowchart illustrating the determination of weights according to an exemplary embodiment.

[0024] Figure 5 This is a structural diagram of a periodic prediction model according to an exemplary embodiment.

[0025] Figure 6 This is a schematic diagram of the structure of a game character interaction control device according to an exemplary embodiment.

[0026] Figure 7 This is a schematic diagram of the structure of an electronic device according to an exemplary embodiment. Detailed Implementation

[0027] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0028] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0029] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0030] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0031] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0032] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0033] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0034] For example, when a user uses game AI during a game, in response to receiving the user's active request, a prompt message is sent to the user to explicitly inform the user that the requested operation will require the acquisition and use of the user's personal information, such as information from the game. This allows the user to autonomously choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0035] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0036] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0037] Meanwhile, it is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0038] 1) Game Character: Also known as a virtual object, or in some games as a hero, it refers to an active object in the game. This active object can be at least one of a virtual character, a virtual animal, or an anime character. Optionally, when the game environment is a three-dimensional game environment, the game character is a three-dimensional model. Each game character has its own shape and volume in the three-dimensional game environment and occupies a portion of the space in the three-dimensional game environment. Optionally, the game character can be a hero, soldier, or neutral creature in a combat game. This embodiment uses a hero as an example.

[0039] 2) Intelligent Agent: Also known as game AI or human-machine interface, this refers to a game character capable of interacting with the game environment. For example, in a specific game environment, an intelligent agent, based on its own perception of the game environment, can communicate, cooperate, or fight with other intelligent agents according to existing instructions or through autonomous learning, autonomously completing set goals within its game environment. It should be understood that the intelligent agent's behavior in the game is controlled by artificial intelligence suitable for the game, capable of simulating various behaviors based on the needs of the game.

[0040] The technical solution of this disclosure will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0041] Figure 1 This is a scene diagram illustrating a game character control method according to an exemplary embodiment. For example... Figure 1 As shown, the game character control method provided in this embodiment is applicable to... Figure 1 The application scenario shown can include multiple terminals 101 and a server 102. The terminals 101 and the server 102 can interact with each other via wired or wireless connections.

[0042] Server 102 can be a game platform server 102. Terminal 101 accesses server 102 through a game client to play the game. For example, game players can log in to the game through this game client and select competitive mode, teammates, opponents, etc. Teammates and / or opponents can be intelligent agents; that is, the game played through terminal 101 can be a human-computer battle mode or a battle mode involving intelligent agents.

[0043] Taking the human-computer battle mode as an example, in this mode, terminal 101 can collect the current signal communication information and current game state information of the game, and send these information to server 102. Server 102 can determine the target communication cycle corresponding to the agent based on the current signal communication information and current game state information sent by terminal 101. Furthermore, server 102 can also determine the target communication message to be sent by the agent. Then, server 102 sends the target communication cycle and the target communication message to terminal 101, so that terminal 101 controls the agent to send the target communication message when the time interval between the agent's last communication message and the current time matches the target communication cycle.

[0044] Of course, in practical applications, the game character interaction control method provided in this embodiment can also be executed independently by the terminal 101.

[0045] Figure 2 This is a flowchart illustrating a game character interaction control method according to an exemplary embodiment. The method can be... Figure 1 Execute on server 102 or terminal 101. For example... Figure 2 As shown, the game character interaction control method may include the following steps:

[0046] In step 210, the target communication message to be sent by the agent in the game is determined.

[0047] Here, the game match can be a competitive game, consisting of real players and AI agents. The AI ​​agent can act as either a teammate or an opponent of the real players. Alternatively, the match could start entirely with real players, but during the game, one or more real players leave, and an AI agent takes over controlling the game character.

[0048] A target communication message refers to a communication message that an agent is about to send to inform the player character in a game about the game action the agent intends to perform. The agent can be an agent belonging to the same game faction as the player character.

[0049] It should be understood that a target communication message can include the content of the communication message and the way it is sent, i.e., what type of signal is used to send what type of communication message. For example, a communication message such as "Attack XXX building" can be output via a marker, "Give me some 5.56 bullets" can be output via text, or "Request support" can be output via voice.

[0050] It is worth noting that the detailed process of obtaining the target communication message will be described in detail in subsequent embodiments. Furthermore, in this embodiment, the target communication message refers to the communication message corresponding to an agent belonging to the same game faction as the player character. For agents belonging to different game factions than the player character, it is not necessary to determine the target communication message for that agent. Specifically, "the game faction belonging to the same agent as the player character" means that the agent and the player character belong to the same team, and that the agent and the player character controlled by the real player are teammates.

[0051] In step 220, the target communication cycle corresponding to the agent is determined based on the current signal communication information triggered by the game and the current game state information.

[0052] Here, the signal communication information includes at least one of the following: the content of the communication message triggered by the game character in the game and the signal type to which the communication message belongs.

[0053] In this context, the content of communication messages triggered by game characters refers to the content of the communication messages sent by the game character. Communication messages can be marker-type signals, such as attack signals, retreat signals, etc. Of course, communication messages can also be voice signals sent as speech, text signals sent as text, etc. The signal type of the communication message can be marker-type, voice-type, text-type, etc. It's worth noting that communication messages triggered by game characters can refer to communication messages triggered by player characters and / or other intelligent agents. However, for human-computer battle modes, prioritizing the game experience of real players, communication messages triggered by game characters can specifically refer to communication messages triggered by player characters.

[0054] It should be understood that signal communication information in a game refers to characteristic information used to reflect the communication behavior state between game characters during a game. Signal communication information changes over time during a game; the signal communication information corresponding to the current moment can be called the current signal communication information. Generally, what is acquired is the signal communication information at the current moment in order to determine the target communication content of the agent based on the current communication behavior state.

[0055] Optionally, the game status information includes at least one of the following: the character status data of the game character in the game match, the game progress of the game match, and the game environment in which the game character is located.

[0056] The character's status data can include their game faction (e.g., blue team, red team), or whether they belong to a different team. This data can include the character's Health Points (HP), Mana Points (MP), skill status, economic status, equipment, and so on. Of course, character status data can also be represented in other forms, such as the ratio of remaining health points between characters, economic ratios, etc.

[0057] The game progress refers to the current time in the game, such as 30 minutes into the game. Of course, the game progress can also refer to the stage of the game, such as early game, mid-game, late game, or very late game. The game stage can be divided based on the current time. For example, 0-10 minutes can be considered the early game, 10-28 minutes the mid-game, 28-40 minutes the late game, and over 40 minutes the very late game.

[0058] The game environment in which a game character is located refers to the terrain, position, and distances between game characters on the game map.

[0059] It should be understood that game state information refers to characteristic information that reflects the game situation during a match. Game state information changes over time during a game; the game state information at the current moment can be called the current game state information. Generally, what is acquired is the game state information at the current moment in order to determine the agent's target communication message based on the current game situation.

[0060] The target communication period is an indicator used to characterize how frequently an agent sends communication messages. The smaller the target communication period, the more frequently the agent sends communication messages. For example, a target communication period of 100 seconds means that the agent can send a communication message every 100 seconds or more, and a target communication period of 10 seconds means that the agent can send a communication message every 10 seconds or more.

[0061] By analyzing current signal exchange information and game state information, the current game state can be characterized and modeled, thereby obtaining a target communication cycle for the agent applicable to the current game state. For example, if the current game state indicates active communication among real players, the agent's target communication cycle can be increased to reduce the number of communication messages sent, thus avoiding conflicts with real players' messages and preventing excessive communication messages from interfering with them. Conversely, if the current game state indicates inactive communication among real players, the agent's target communication cycle can be decreased to encourage more communication messages sent, thereby stimulating real players' willingness to communicate and ensuring a positive gaming atmosphere.

[0062] It's worth noting that the target communication cycle varies depending on the game state; that is, within a single game, the target communication cycle can change at any time as the game state evolves. Of course, to reduce computational overhead, a time period can be set within which the target communication cycle remains constant. When entering the next time period, a new target communication cycle can be recalculated and used as the target communication cycle for that new time period. For example, using a 3-minute time period, the target communication cycle can be updated every 3 minutes of gameplay.

[0063] In step 230, if the time interval between the last time the agent sent a communication message and the current time matches the target communication cycle, the agent is controlled to send the target communication message.

[0064] Here, the time when the agent last sent a communication message can refer to the most recent time the agent sent a communication message. For example, the most recent time the agent sent a communication message was at game time 31:02. Alternatively, the time when the agent last sent a communication message can refer to the time when the signal type of the communication message that matches the target's communication content was sent. For example, the agent's two most recent communication message sending times were 31:02 and 33:02, where the signal type of the communication message sent at 31:02 was "attack," and the signal type of the communication message sent at 33:02 was "retreat." When the signal type of the target communication message is "attack," then the time when the agent last sent a communication message is 31:02.

[0065] It should be understood that the above embodiments provide two methods for determining the time when an agent last sent a communication message. In practical applications, one method can be selected based on the actual situation.

[0066] In this context, "time interval matching the target communication cycle" means that the time interval is greater than or equal to the target communication cycle. For example, if the target communication cycle is 50 seconds, and the time interval is greater than or equal to 50 seconds, then the controlling agent will send the target communication message. It's worth noting that "time interval matching the target communication cycle" essentially means that the agent is capable of sending a communication message at the current moment.

[0067] A target communication message can include the content of the message and the method of sending it, allowing the message to be output in the target format. For example, if the target communication message for the agent is a "request for support" message delivered in voice, then this message will be output in voice format through the user interface. By outputting the target communication message, the player character in the game can determine the game action the agent will perform based on this message, enabling the player character to cooperate with the agent.

[0068] It's worth noting that if the time interval doesn't match the target communication cycle, the target communication message can be discarded. For example, if the target communication cycle is 50 seconds, and the time interval is less than 50 seconds, the agent will not send the target communication message. Because target communication messages are time-sensitive, they can be discarded.

[0069] Therefore, by analyzing the current signal exchange information triggered during a game and the current game state, the target communication cycle of the agent can be dynamically adjusted to regulate the frequency with which the agent sends communication messages during the game. This prevents the agent from sending too many messages, thus avoiding conflicts with real players' communication, and also prevents excessive communication messages from interfering with real players. Furthermore, when real players are not communicating, it can encourage them to communicate, ensuring a positive gaming atmosphere.

[0070] It is worth noting that in the above embodiments, the target communication message can be determined according to a preset time interval. When it is determined that the agent needs to send a target communication message, the target communication cycle corresponding to the agent is further determined based on the current signal exchange information and the current game state information. Then, if the time interval between the time when the agent last sent a communication message and the current time matches the target communication cycle, the agent is controlled to send the target communication message.

[0071] In some feasible implementations, game state information and signal communication information of the game can be acquired; based on the game state information, the game intention of the agent can be determined, wherein the game intention represents the agent's combat objective; and the game state information, the signal communication information, and the game intention can be input into a communication prediction model to obtain the target communication message corresponding to the agent.

[0072] Here, since the game state information reflects the current game situation, the agent's game intention in the current game situation can be obtained based on this information. This game intention refers to the combat objective the agent intends to achieve. This objective can refer to a map area, strategic point, or map resource that the agent intends to defend / attack. For example, the agent's objective could be to help the player character catch enemies, accompany and protect the player character, attack a resource point, act as a lookout for the player character, attack specific monsters in the game, gain vision of dark areas on the game map, eliminate vision wards on the game map, cooperate with the player character to execute a certain game strategy, and so on.

[0073] For example, game state information can be input into an intent prediction model to obtain the game intent. This intent prediction model can include an input layer, a hidden layer, and an output layer. This neural network model is based on a policy function and outputs the game intent according to the input game state information. The output game intent can be adjusted by modifying the parameters of the hidden layer.

[0074] By inputting game state information, signal communication information, and the agent's game intent into a communication prediction model, the target communication message output by the communication prediction model can be obtained. This communication prediction model can be a neural network model.

[0075] It should be understood that, through game state information, signal communication information, and game intent, it is possible to obtain target communication messages that match the current game situation, the communication behavior of the game characters, and the combat objectives of the intelligent agent. These target communication messages can reflect the intelligent agent's game intent, enabling real players to understand and cooperate with the intelligent agent.

[0076] As other examples, the target communication message is determined based on the communication message triggered by the player character in the signal exchange information, combined with the mapping relationship between the communication message sent by the player character and the content of the agent's reply to the communication message.

[0077] This mapping relationship can be a communication message pair, which includes the communication message sent by the player character and the content of the agent's reply to the communication message sent by the player character. For example, "Requesting Support" and "On the Way" constitute a communication message pair. When the player character sends the communication message "Requesting Support", the target communication message can be "On the Way".

[0078] It is worth noting that the above embodiments only provide two methods for determining target communication messages for reference. In actual applications, other methods can also be used to determine target communication messages, and this disclosure will not provide examples of each.

[0079] Figure 3 yes Figure 2 The detailed flowchart of step 220 shown is as follows: Figure 3 As shown, in some possible implementations, step 220 may include the following steps:

[0080] In step 221, historical signal communication features are determined based on the signal communication information obtained from historical moments of the game, wherein the historical signal communication features are used to characterize the preferences of game characters in sending communication messages during the game.

[0081] Here, the signal communication information refers to the raw signal communication information obtained during the game, while the historical signal communication feature is obtained after processing the raw signal communication information. The signal communication information obtained at a historical moment can refer to all signal communication information obtained before the current moment. For example, if the current moment is 32:01, the signal communication information obtained at a historical moment would be all signal communication information obtained between 00:00 and 32:01. Alternatively, the signal communication information obtained at a historical moment can refer to all signal communication information obtained within a preset time period before the current moment. For example, if the current moment is 32:01 and the preset time period is 60 seconds, then the signal communication information obtained at a historical moment could be all signal communication information obtained between 31:01 and 32:01.

[0082] For example, the signal communication features include at least one of the following: the frequency at which game characters send communication messages during the game, the number of times the game characters send communication messages, and the time point at which the game characters send communication messages.

[0083] Here, when the signal exchange characteristic is the frequency of communication messages sent by game characters, the frequency of communication messages sent by game characters can be statistically analyzed from the signal exchange information obtained at historical moments. The frequency of communication messages sent by game characters can refer to the frequency of player characters sending preset types of communication messages, or it can refer to the frequency of player characters sending all types of communication messages.

[0084] When the signal exchange characteristic is the number of times a game character sends communication messages, the number of times a game character sends communication messages can be counted from the signal exchange information obtained at historical moments. The number of times a game character sends communication messages can refer to the total number of times a player character sends a preset type of communication message, or it can refer to the total number of times a player character sends all types of communication messages.

[0085] When the signal exchange characteristic is the time point at which a game character sends a communication message, it's possible to statistically analyze the signal exchange information obtained from historical moments, identifying the time point at which each communication message was sent. Of course, this time point can also be represented by the stage of the game, such as early game, mid-game, late game, or very late game. By analyzing the time points at which game characters send communication messages, we can determine the communication intentions of player characters at various stages of the game.

[0086] It's worth noting that historical signal communication characteristics actually represent a player's preference for sending communication messages. For example, if historical signal communication characteristics indicate that a player frequently sends communication messages during a game, it means that the player enjoys communicating with teammates or directing the game.

[0087] In step 222, historical game state features are determined based on the game state information obtained from the historical moments of the game, wherein the historical game state features are used to characterize the historical game situation of the game.

[0088] Here, game state information refers to the raw game state information obtained during a game match, while the historical game state feature is obtained after processing the raw game state information. Specifically, the game state information obtained at a historical moment can refer to all game state information obtained before the current moment. For example, if the current moment is 32:01, the game state information obtained at a historical moment would be all game state information obtained between 00:00 and 32:01. Alternatively, the game state information obtained at a historical moment can refer to all game state information obtained within a preset time period before the current moment. For example, if the current moment is 32:01 and the preset time period is 60 seconds, then the game state information obtained at a historical moment could be all game state information obtained between 31:01 and 32:01.

[0089] For example, the game state features include at least one of the following: a first situation indicator for characterizing the win-loss trend of the game match and a second situation indicator for characterizing the superiority or inferiority of the game characters in the battle.

[0090] Here, the first situation indicator can be determined by data such as the difference in kills between the player's team and the opponent's team, the total economic difference, and the team's strong periods. This first situation indicator is used to characterize the win-loss trend between the player's team and the opponent's team in a game. For example, the first situation indicator can represent the win rate of the player's team and the opponent's team. If the player's team has a win rate of 70% and the opponent's team has a win rate of 30%, it means that the game situation for the player's team is developing favorably in this game.

[0091] The second situation indicator can be determined using data such as the difference in kill counts, total economic difference, equipment difference, and the dominant periods of game characters. This second situation indicator is used to represent the relative strengths and weaknesses of game characters in combat. For example, the second situation indicator can represent the win rate in combat between game characters, such as the win rate of a player character relative to an AI on the opposing side.

[0092] It is worth noting that the characteristics of historical game states actually reflect the course of the game at a historical moment.

[0093] In step 223, the target communication cycle is obtained by performing a weighted average calculation based on the current signal communication information, the current game state information, the historical signal communication characteristics, and the historical game state characteristics, combined with the corresponding weights.

[0094] Here, by determining the target communication cycle based on current signal exchange information, current game state information, historical signal exchange characteristics, and historical game state characteristics, we can better characterize and model the game state based on the game situation at historical moments, the direction of changes in the communication intentions of player characters at historical moments, and the current game situation and the signals sent by the current player characters, thereby accurately predicting the target communication cycle of the agent in the current game state.

[0095] For example, by using historical signal communication characteristics, the frequency with which a player character sends communication messages in the past can be used to control the frequency with which an agent sends communication messages.

[0096] For example, the target communication cycle can be calculated using the following formula:

[0097] h = (aX + bY + cZ + dG) / 4

[0098] Where h is the target communication cycle, X is the current signal exchange information, Y is the current game state information, Z is the historical signal exchange characteristics, G is the historical game state characteristics, and a, b, c, and d are the corresponding weights.

[0099] It's worth noting that h can be a range of values, such as 0-10. Depending on the range h falls within, different target communication cycles can be represented. For example, the range [0, 1] corresponds to 100 seconds, [1, 2] corresponds to 90 seconds, [2, 3] corresponds to 80 seconds, and so on.

[0100] Therefore, by determining the target communication cycle based on current signal exchange information, current game state information, historical signal exchange characteristics, and historical game state characteristics, we can better characterize and model the game state based on the game situation at historical moments and the direction of changes in the communication intentions of player characters at historical moments, thereby accurately predicting the target communication cycle of the agent in the current game state.

[0101] Figure 4 This is a flowchart illustrating the determination of weights according to an exemplary embodiment, such as... Figure 4 As shown, in some feasible implementations, the weights of the above calculation formula can be obtained through the following steps:

[0102] In step 401, the game role type to which the agent belongs and / or the competitive level corresponding to the agent are determined.

[0103] Here, the game role type to which the agent belongs can refer to the agent's hero attribute. The game role type attribute can be categorized based on the role's position in the game, such as jungler, bottom laner, mid laner, and top laner. Junglers fight in the jungle, bottom laners coordinate in the bottom lane (e.g., support and marksman heroes are bottom laners), mid laners fight in the mid lane, and top laners fight in the top lane. For example, in FPS (First Personal Shooting Game), each team can include four role types: commander, assault, sniper, and support. The commander issues overall team commands, including searching, surveillance, attacking, retreating, and choosing movement direction. The assault role is responsible for attacking and tanking damage. The sniper role is responsible for long-range kills. The support role is responsible for reconnaissance, surveillance, and logistics.

[0104] An agent's competitive level refers to its performance in a particular game. A higher competitive level indicates a better performance. An agent's competitive level can be measured by its KDA (Kill, Death, Assist) value, economy, level, and equipment. For example, higher KDA, higher level, better economy, or better equipment indicate a higher competitive level.

[0105] In step 402, the game character type and / or the competitive level are input into the scoring model to obtain the target evaluation index of the agent, wherein the target evaluation index is used to characterize the frequency of the agent sending communication messages in the game.

[0106] Here, the scoring model can be a neural network model, which may include an input layer, a hidden layer, and an output layer. This scoring model is based on a policy function and outputs a target evaluation metric according to the game character type and / or skill level. The output target evaluation metric can be adjusted by modifying the parameters of the hidden layer.

[0107] It is worth noting that the rating model can be obtained by training a machine learning model using training samples of historical game character types and / or competitive levels labeled with different evaluation metrics (such as scores).

[0108] The target evaluation index is used to characterize the frequency with which an agent sends communication messages during a game. For example, the higher the target evaluation index, the more frequently the agent can send communication messages.

[0109] It should be understood that the frequency of communication messages sent by different agents during a game can be determined by their game role type and / or skill level. For example, agents with higher skill levels send communication messages more frequently, while agents with lower skill levels send them less frequently. Furthermore, the frequency of communication messages sent by agents with different game role types will also vary; for instance, an agent with a commander role type can send communication messages more frequently than an agent with a support role type.

[0110] In step 403, the weight is determined according to the target evaluation index, wherein the magnitude of the weight is positively correlated with the target evaluation index.

[0111] Here, the weights used in the weighted average are positively correlated with the target evaluation index; that is, the larger the target evaluation index, the larger the weight. Correspondingly, the larger the weight, the more frequently the agent sends communication messages.

[0112] Therefore, by determining the weighted average weight based on the game role type to which the agent belongs and / or the agent's corresponding competitive level, the frequency of communication messages sent by the agent can be dynamically adjusted according to the hero attribute to which the agent belongs and / or the agent's performance in the game. This allows agents with good performance to send more communication messages, while agents with poor performance to send fewer communication messages, thereby improving the gaming experience for real players.

[0113] In some embodiments, in step 403, the current game progress of the game match can be determined, and the weight can be determined based on the current game progress and the target evaluation index.

[0114] The game progress has already been described in detail in the above embodiments and will not be repeated here. Different parameter values ​​can be set for different current game progress. Generally speaking, the later the current game progress, the larger the parameter value. For example, the game progress can be divided into early, mid, late, and very late stages. In the early stage of the game, the focus is mainly on developing or searching for equipment, and the agent sends fewer communication messages. In the mid, late, and very late stages, the focus is on team battles, and the agent can send more communication messages.

[0115] After determining the current game progress, the parameter value corresponding to the current game progress can be multiplied by the target evaluation index to obtain the adjusted target evaluation index, and then the weight can be obtained based on the target evaluation index.

[0116] Based on this, the target communication cycle for the agent to send communication messages at different game stages can be further adjusted by the game progress, so that the agent can send the target communication message at the appropriate time to avoid interfering with real players.

[0117] In some feasible implementations, the current signal communication information and the current game state information can be input into a trained cycle prediction model to obtain the target communication cycle.

[0118] The cycle prediction model is obtained by training a machine learning model with training samples, which include signal communication information marked with communication cycles and game state information.

[0119] Here, training samples can be obtained from historical game matches. These historical game matches can refer to matches involving real players. For each historical game match, signal communication information and game status information within a preset time period are extracted. The preset time period can be a pre-set duration, such as 5 seconds. Then, based on the cycle of communication messages between real players within this preset time period, the communication cycle corresponding to the signal communication information and game status information can be determined, thus obtaining training samples.

[0120] Figure 5 This is a structural diagram of a periodic prediction model illustrated according to an exemplary embodiment, such as... Figure 5 As shown, the cycle prediction model includes:

[0121] The first feature extraction layer is configured to extract a first feature vector from the current signal communication information;

[0122] The second feature extraction layer is configured to extract a second feature vector from the current game state information;

[0123] The first feature learning layer is configured to obtain a third feature vector based on the first feature vector and the first historical feature vector memorized by the first feature learning layer, wherein the first historical feature vector is obtained by the first feature learning layer based on the signal communication information of the historical input periodic prediction model.

[0124] The second feature learning layer is configured to obtain a fourth feature vector based on the second feature vector and the second historical feature vector memorized by the second feature learning layer, wherein the second historical feature vector is obtained by the second feature learning layer based on the game state information of the periodic prediction model input from history.

[0125] The fusion layer is configured to fuse the third feature vector and the fourth feature vector to obtain a fused feature;

[0126] The prediction layer is configured to determine the target communication cycle based on the fusion features.

[0127] Here, the first feature extraction layer and the second feature extraction layer can be coding layers, which extract and encode features from the current signal communication information and the current game state information to form the first feature vector and the second feature vector.

[0128] The first and second feature learning layers can be Long Short-Term Memory (LSTM) networks. This LSTM network stores information from the input network; that is, it determines historical signal communication features based on signal communication information obtained from historical game moments, or it determines historical game state features based on game state information obtained from historical game moments. The fusion layer is used to concatenate the third and fourth feature vectors to obtain the fused feature.

[0129] It is worth noting that since both the current signal exchange information and the current game state information are one-dimensional features, they can be processed together. Therefore, the first feature extraction layer and the second feature extraction layer can be merged into a single network layer, and the first feature learning layer, the second feature learning layer, and the fusion layer can also be merged into a single network layer.

[0130] Figure 6 This is a schematic diagram of the structure of a game character interaction control device according to an exemplary embodiment, such as... Figure 6 As shown, this disclosure provides a game character interaction control device, the device 600 including:

[0131] The first determining module 601 is configured to determine the target communication message to be sent by the agent in the game;

[0132] The second determining module 602 is configured to determine the target communication cycle corresponding to the agent based on the current signal communication information triggered by the game and the current game state information of the game.

[0133] The control module 603 is configured to control the intelligent agent to send the target communication message when the time interval between the time when the intelligent agent last sent a communication message and the current time matches the target communication cycle.

[0134] Optionally, the second determining module 602 includes:

[0135] The first determining unit is configured to determine historical signal communication features based on signal communication information obtained from historical moments of the game, wherein the historical signal communication features are used to characterize the preferences of game characters in sending communication messages during the game.

[0136] The second determining unit is configured to determine historical game state features based on game state information obtained from historical moments of the game, wherein the historical game state features are used to characterize the historical game situation of the game.

[0137] The third determining unit is configured to perform a weighted average calculation based on the current signal communication information, the current game state information, the historical signal communication features, and the historical game state features, combined with corresponding weights, to obtain the target communication cycle.

[0138] Optionally, the third determining unit includes:

[0139] The attribute determination unit is configured to determine the game role type to which the agent belongs and / or the competitive level corresponding to the agent.

[0140] The evaluation unit is configured to input the game character type and / or the competitive level into a scoring model to obtain the target evaluation index of the agent, wherein the target evaluation index is used to characterize the frequency of the agent sending communication messages in the game.

[0141] The weight determination unit is configured to determine the weight based on the target evaluation index, wherein the magnitude of the weight is positively correlated with the target evaluation index.

[0142] Optionally, the weight determination unit is specifically configured as follows:

[0143] Determine the current game progress of the game;

[0144] The weight is determined based on the current game progress and the target evaluation metric.

[0145] Optionally, the second determining module 602 is specifically configured as follows:

[0146] The current signal communication information and the current game state information are input into the trained cycle prediction model to obtain the target communication cycle.

[0147] The cycle prediction model is obtained by training a machine learning model with training samples, which include signal communication information marked with communication cycles and game state information.

[0148] Optionally, the signal exchange information includes at least one of the following:

[0149] The content of the communication messages triggered by the game characters in the game and the signal type to which the communication messages belong;

[0150] The game status information includes at least one of the following:

[0151] The game includes the character status data of the game character in the game, the game progress of the game, and the game environment in which the game character is located.

[0152] Optionally, the signal exchange characteristics include at least one of the following:

[0153] The frequency of communication messages sent by game characters during the game, the number of times the game characters send communication messages, and the time points at which the game characters send communication messages;

[0154] The game state features include at least one of the following:

[0155] A first situation indicator is used to characterize the outcome of the game match, and a second situation indicator is used to characterize the relative strengths and weaknesses of the game characters in the battle.

[0156] Regarding the apparatus 600 in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0157] The following is for reference. Figure 7 It illustrates an electronic device suitable for implementing embodiments of the present disclosure (e.g., Figure 1 The diagram below shows the structure of the terminal or server 700. The terminal in this embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and vehicle terminals (e.g., vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0158] like Figure 7As shown, the electronic device 700 may include a processing unit (e.g., a central processing unit, a graphics processor, etc.) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage device 708 into a random access memory (RAM) 703. The RAM 703 also stores various programs and data required for the operation of the electronic device 700. The processing unit 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0159] Typically, the following devices can be connected to I / O interface 705: input devices 706 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 707 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 708 including, for example, magnetic tapes, hard disks, etc.; and communication devices 709. Communication device 709 allows electronic device 700 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 7 An electronic device 700 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0160] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 709, or installed from storage device 708, or installed from ROM 702. When the computer program is executed by processing device 701, it performs the functions defined in the methods of embodiments of this disclosure.

[0161] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0162] In some implementations, terminals and servers can communicate using any currently known or future-developed network protocol, such as HTTP (Hypertext Transfer Protocol), and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0163] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0164] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: determine a target communication message to be sent by an agent in a game; determine a target communication period corresponding to the agent based on the current signal exchange information triggered by the game and the current game state information; and, if the time interval between the time when the agent last sent a communication message and the current time matches the target communication period, control the agent to send the target communication message.

[0165] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0166] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0167] The modules described in the embodiments of this disclosure can be implemented in software or hardware. The names of the modules are not, in some cases, intended to limit the functionality of the module itself.

[0168] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0169] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0170] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0171] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0172] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative forms of implementing the claims. Regarding the apparatus in the above embodiments, the specific manner in which the various modules perform their operations has been described in detail in the embodiments relating to the method, and will not be elaborated upon here.

Claims

1. A game character interaction control method, characterized by, The method comprises: determining a target communication message to be sent by an agent in a game match; determining a target communication period corresponding to the agent according to current signal communication information triggered by the game match and current game state information of the game match; controlling the agent to send the target communication message in a case where a time interval between a time when the agent last sent a communication message and a current time matches the target communication period.

2. The method of claim 1, wherein, The determining of the target communication period corresponding to the agent according to the current signal communication information triggered by the game match and the current game state information of the game match comprises: determining historical signal communication features according to signal communication information obtained at historical time points of the game match, wherein the historical signal communication features are used to represent a preference of a game character in the game match for sending a communication message; determining historical game state features according to game state information obtained at the historical time points of the game match, wherein the historical game state features are used to represent historical game situations of the game match; performing weighted average operation on the current signal communication information, the current game state information, the historical signal communication features and the historical game state features combined with corresponding weights to obtain the target communication period.

3. The method of claim 2, wherein, The weights are obtained by the following steps: determining a game character type to which the agent belongs and / or a competitive level corresponding to the agent; inputting the game character type and / or the competitive level into a scoring model to obtain a target evaluation index of the agent, wherein the target evaluation index is used to represent a frequency of sending a communication message by the agent in the game match; determining the weights according to the target evaluation index, wherein the weights are positively correlated with the target evaluation index.

4. The method of claim 3, wherein, The determining of the weights according to the target evaluation index comprises: determining a current game progress of the game match; determining the weights according to the current game progress and the target evaluation index.

5. The method of claim 1, wherein, The determining of the target communication period corresponding to the agent according to the current signal communication information triggered by the game match and the current game state information of the game match comprises: inputting the current signal communication information and the current game state information into a trained period prediction model to obtain the target communication period; wherein the period prediction model is obtained by training a machine learning model with training samples, and the training samples comprise signal communication information and game state information marked with a communication period.

6. The method according to any one of claims 1 to 5, characterized in that, The signal communication information comprises at least one of: contents of a communication message triggered by a game character in the game match and a signal type to which the communication message belongs; The game state information comprises at least one of: character state data of a game character in the game match, a game progress at which the game match is located, and a game environment in which the game character is located.

7. The method according to any one of claims 2 to 4, characterized in that, The signal communication features comprise at least one of: a frequency of sending the communication message by the game character in the game session, a number of times of sending the communication message by the game character, and a time node of sending the communication message by the game character; the game state feature comprises at least one of the following: a first situation index for representing a winning and losing trend of the game session and a second situation index for representing a battle advantage between the game characters.

8. A game character interaction control apparatus, characterized by, comprise: a first determining module configured to determine a target communication message to be sent by an agent in a game session; a second determining module configured to determine a target communication period corresponding to the agent according to current signal communication information triggered by the game session and current game state information of the game session; a control module configured to control the agent to send the target communication message in a case where a time interval between a time when the agent last sent a communication message and a current time matches the target communication period.

9. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the steps of the method of any one of claims 1-7.

10. An electronic device, comprising: comprise: a memory having a computer program stored thereon; a processor configured to execute the computer program in the memory to implement the steps of the method of any one of claims 1-7.

Images