Method, device and equipment for launching robot role in game and storage medium

Abstract

The application provides a method and device for putting a robot role in a game, an equipment and a storage medium, and relates to the technical field of games. The method comprises the following steps: determining a target game role; obtaining a first game starting position of the target game role in a game scene, and determining at least one second game starting position in the game scene based on the first game starting position; calculating a first game route of the target game role in the game scene based on the first game starting position and a pre-trained path decision model; predicting at least one second game route in the game scene based on the at least one second game starting position and the path decision model; and determining at least one putting position from the at least one second game starting position based on the first game route and the second game route, so as to put at least one robot role at the putting position. The scheme can help the target player improve the game kill experience, and improve the game battle experience of the player.

Description

Technical Field

[0001] This application relates to the field of game technology, and more specifically, to a method, apparatus, device, and storage medium for deploying robot characters in a game. Background Technology

[0002] In some multiplayer elimination games with the same map, there are very few winners in each round; kill count and surviving ranking are broader sources of positive experience than the final victory. However, both of these are zero-sum games, which can cause some non-core players to leave due to the strong sense of frustration, thus reducing players' enthusiasm for playing the game.

[0003] Currently, the main approach to this problem is to deploy a certain number of bot characters in each game. These bot characters move according to a simple finite-state machine (a typical game AI model where bot characters execute actions from a pre-defined list based on their current state). For example, in each game, the bot character's spawn point can be randomly determined, or it can spawn near the target player's virtual character. After spawning, the bot character goes directly to the target virtual character, allowing the target virtual character to directly engage in combat and potentially kill the bot character. This effectively improves the gaming experience for some new players or those on losing streaks.

[0004] However, the robot characters deployed in each game execute actions from a preset list based on their current state. This results in overly simplistic robot character behaviors that are easily recognizable by players, significantly diminishing the game's combat experience. Summary of the Invention

[0005] The purpose of this application is to address the shortcomings of the prior art by providing a method, device, equipment, and storage medium for deploying robot characters in a game, so as to control the robot characters to encounter a specified target game character with a high probability, thereby helping the target game character improve its game kill experience and enhancing the player's game combat experience.

[0006] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows:

[0007] In a first aspect, embodiments of this application provide a method for deploying robot characters in a game, including:

[0008] Identify the target game character;

[0009] Obtain the first game start position of the target game character in the game scene, and determine at least one second game start position in the game scene based on the first game start position. The second game start position is a candidate position for deploying the robot character in the game scene.

[0010] Based on the first game start position and the pre-trained path decision model, the first game route of the target game character in the game scene is calculated;

[0011] Based on the at least one second game start position and the path decision model, at least one second game route in the game scene is predicted;

[0012] Based on the first game route and the second game route, at least one deployment location is determined from the at least one second game start location to deploy at least one robot character at the deployment location.

[0013] In one possible implementation, determining the target game character includes:

[0014] The target game character is determined based on the game data corresponding to the game character participating in the game;

[0015] The game data includes at least the historical battle results of the game character.

[0016] In one possible implementation, determining at least one second game start position in the game scene based on the first game start position includes:

[0017] Within a preset range of the first game start position in the game scene, at least one second game start position is determined.

[0018] In one possible implementation, determining at least one drop location from the at least one second game start location based on the first game route and the second game route includes:

[0019] Obtain the robot deployment strategy that matches the target game character;

[0020] Based on the robot deployment strategy, the first game route, and the second game route, at least one deployment location is determined among the at least one second game start location.

[0021] In one possible implementation, determining at least one drop location from the at least one second game start location based on the first game route and the second game route further includes:

[0022] Based on the number of intersections between the first game route and the second game route, at least one placement location is determined from the at least one second game start location.

[0023] In one possible implementation, determining the target game character based on game data corresponding to the game character participating in the game includes:

[0024] If the number of game characters currently participating in the game is less than the preset number, the target game character is determined based on the game data corresponding to the game characters participating in the game.

[0025] In one possible implementation, after deploying at least one robot character at the deployment location, the method further includes:

[0026] Control the robot character to move along the second game route in the game scene.

[0027] In one possible implementation, the method further includes:

[0028] If the deviation between the actual route of the target game character and the first game route is greater than a first preset threshold, then based on the current position of the target game character and the path decision model, a third game route of the target game character is calculated, and the second game route is updated based on the third game route.

[0029] In one possible implementation, updating the second game route based on the third game route includes:

[0030] Obtain at least one adjustable decision point in the second game route, wherein the adjustable decision point corresponds to multiple walking strategies, and the weight difference of each walking strategy is less than a second preset threshold.

[0031] Determine the adjustable decision point among the adjustable decision points that is closest to the current position of the target game character;

[0032] Based on the third game route, determine the target walking strategy for the target adjustable decision point;

[0033] Update the second game route according to the stated target walking strategy.

[0034] In one possible implementation, before calculating the first game route of the target game character in the game scene based on the first game start position and a pre-trained path decision model, the method further includes:

[0035] Acquire historical game behavior data generated by players participating in the game during historical gameplay. The historical game behavior data includes: game parameters and environmental parameters of the game characters controlled by each player. The game parameters include at least one of the following: location information, action information, resource information, and the location of the mission point. The environmental parameters include at least one of the following: the location of popular resources and environmental attack information.

[0036] The path decision model is trained using the historical game behavior data as sample data.

[0037] Secondly, embodiments of this application also provide a device for deploying robot characters in a game, the device comprising:

[0038] The determination module is used to identify the target game character;

[0039] The acquisition module is used to acquire the first game start position of the target game character in the game scene, and determine at least one second game start position in the game scene based on the first game start position, wherein the second game start position is a candidate position for deploying the robot character in the game scene;

[0040] The calculation module is used to calculate a first game route for the target game character in the game scene based on the first game start position and a pre-trained path decision model; and to predict at least one second game route in the game scene based on the at least one second game start position and the path decision model.

[0041] The determining module is further configured to determine at least one deployment location from the at least one second game start location based on the first game route and the second game route, so as to deploy at least one robot character at the deployment location.

[0042] In one possible implementation, the determining module is further configured to:

[0043] The target game character is determined based on the game data corresponding to the game character participating in the game;

[0044] The game data includes at least the historical battle results of the game character.

[0045] In one possible implementation, the determining module is further configured to:

[0046] Within a preset range of the first game start position in the game scene, at least one second game start position is determined.

[0047] In one possible implementation, the determining module is further configured to:

[0048] Obtain the robot deployment strategy that matches the target game character;

[0049] Based on the robot deployment strategy, the first game route, and the second game route, at least one deployment location is determined among the at least one second game start location.

[0050] In one possible implementation, the determining module is further configured to:

[0051] Based on the number of intersections between the first game route and the second game route, at least one placement location is determined from the at least one second game start location.

[0052] In one possible implementation, the determining module is further configured to:

[0053] If the number of game characters currently participating in the game is less than the preset number, the target game character is determined based on the game data corresponding to the game characters participating in the game.

[0054] In one possible implementation, the device further includes:

[0055] A control module is used to control the robot character to move along the second game route in the game scene.

[0056] In one possible implementation, the computing module is further configured to:

[0057] If the deviation between the actual route of the target game character and the first game route is greater than a first preset threshold, then a third game route of the target game character is calculated based on the current position of the target game character and the path decision model.

[0058] The device further includes:

[0059] An update module is used to update the second game route based on the third game route.

[0060] In one possible implementation, the update module is further configured to:

[0061] Obtain at least one adjustable decision point in the second game route, wherein the adjustable decision point corresponds to multiple walking strategies, and the weight difference of each walking strategy is less than a second preset threshold.

[0062] Determine the adjustable decision point among the adjustable decision points that is closest to the current position of the target game character;

[0063] Based on the third game route, determine the target walking strategy for the target adjustable decision point;

[0064] Update the second game route according to the stated target walking strategy.

[0065] In one possible implementation, the device further includes:

[0066] The acquisition module is also used to acquire historical game behavior data generated by players participating in the game during historical games. The historical game behavior data includes: game parameters and environmental parameters of the game characters controlled by each player. The game parameters include at least one of the following: location information, action information, resource information, and the location of the task point. The environmental parameters include at least one of the following: the location of popular resources and environmental attack information.

[0067] The training module is used to train the path decision model using the historical game behavior data as sample data.

[0068] Thirdly, embodiments of this application provide an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the steps of the method for deploying robot characters in a game as described in the first aspect above.

[0069] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the method for deploying robot characters in a game as described in the first aspect above.

[0070] The beneficial effects of this application are:

[0071] This application proposes a method for deploying robot characters in a game. The method includes: determining a target game character; obtaining a first game start position of the target game character in a game scene, and determining at least one second game start position in the game scene based on the first game start position, wherein the second game start position is a candidate position for deploying robot characters in the game scene; calculating a first game route of the target game character in the game scene based on the first game start position and a pre-trained path decision model; predicting at least one second game route in the game scene based on at least one second game start position and the path decision model; and determining at least one deployment position from the at least one second game start position based on the first game route and the second game route, so as to deploy at least one robot character at the deployment position. In this scheme, the first step is to use a pre-trained path decision model that conforms to all players in a real-world environment, along with the target player's game character's initial starting position (i.e., spawn point or current position in the game) within the game scene, to calculate the first possible game route the target game character will take in the subsequent game scene. Simultaneously, based on the path decision model and at least one second starting position determined by the first starting position (i.e., alternative positions where the robot character might appear within the game scene), the second possible game route the robot character might take is predicted. Then, based on the target game character's first game route and the robot character's second game route, the robot character's second possible route is predicted from at least one... The second game starts by selecting at least one robot character's spawn point, which is the spawn point of the robot character that would logically encounter the target player. Finally, at least one robot character is deployed at this selected location, causing it to move along the second game route. This creates an encounter effect between the robot character and the target player, allowing the robot character to be killed by the target player (or possibly by other characters), giving the target player a kill experience without making it obvious that they are fighting a robot. This helps new players or those on losing streaks improve their game experience and enhances the overall combat experience. Attached Figure Description

[0072] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0073] Figure 1A flowchart illustrating the method for deploying robot characters in a game, as provided in an embodiment of this application;

[0074] Figure 2 A schematic diagram of the first game position and the second game position provided for embodiments of this application;

[0075] Figure 3 Another flowchart illustrating the method for deploying robot characters in a game, as provided in this application embodiment;

[0076] Figure 4 Illustrations of the first and second game routes provided in this application embodiment Figure 1 ;

[0077] Figure 5 Illustrations of the first and second game routes provided in this application embodiment Figure 2 ;

[0078] Figure 6 Another flowchart illustrating the method for deploying robot characters in a game, as provided in this application embodiment;

[0079] Figure 7 A schematic diagram of the third game route and the second game route provided in the embodiments of this application;

[0080] Figure 8 Another flowchart illustrating the method for deploying robot characters in a game, as provided in this application embodiment;

[0081] Figure 9 This is a schematic diagram of the structure of the device for deploying robot characters in a game, provided in an embodiment of this application.

[0082] Figure 10 This is a schematic diagram of the electronic device structure provided in an embodiment of this application. Detailed Implementation

[0083] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0084] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0085] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0086] Prior to this application, existing technologies primarily involved deploying a certain number of robot characters in each game. These robot characters moved according to a simple finite-state machine (a typical game AI model where the robot character executes actions from a pre-defined list based on its current state). For example, in each game, the robot character's spawn point could be randomly determined, or it could spawn near the target player's character. After spawning, the robot character would head straight for the target player, allowing the target player to directly engage and defeat the robot character. This effectively improved the gaming experience for some new players or those experiencing losing streaks.

[0087] However, the robot characters deployed in each game execute actions from a pre-set list based on their current state. This results in overly simplistic robot behavior, making them easily identifiable by players. (For example, in some game scenarios, the target character might be in a remote location, while the robot character travels a long distance directly towards the hidden target character. Normal players rarely take this path, making it easy for the target player to spot the robot character.) This significantly degrades the game's combat experience and may even lead players to believe that there are few online players, potentially causing them to leave the game.

[0088] Based on the aforementioned problems, this application proposes a method for deploying robot characters in a game. It utilizes a pre-trained path decision model that conforms to all players in a real-world environment, and the first game starting position (i.e., spawn point or current position in the game) of the target game character controlled by the target player, to calculate the first game route the target game character might take in the subsequent game scene. Simultaneously, based on the path decision model and at least one second game starting position determined by the first game starting position (i.e., alternative positions where the robot character might appear in the game scene), it predicts the second game route the robot character might take. Then, based on the target game character's first game route... The system involves selecting at least one robot character's spawn point from at least one second game starting position. This spawn point is the point where the robot character will logically encounter the target player. Finally, at least one robot character is deployed at the selected spawn point, moving along the second game route. This creates an encounter effect between the robot character and the target player, allowing the robot character to be defeated and giving the target player a kill experience without making it obvious that they are fighting a robot. This helps new players or those on losing streaks improve their gaming experience and enhances the overall combat experience.

[0089] In one embodiment of this application, the method for deploying robot characters in a game can run on a local terminal device or a server. When the method for deploying robot characters in a game runs on a server, the method can be implemented and executed based on a cloud interaction system, wherein the cloud interaction system includes a server and client devices.

[0090] In an optional implementation, various cloud applications, such as cloud gaming, can run under the cloud interaction system. Taking cloud gaming as an example, cloud gaming refers to a gaming method based on cloud computing. In the cloud gaming operating mode, the game program and the game screen presentation are separate. The storage and execution of the robot character deployment method in the game are completed on the cloud gaming server. The client device is used for data reception, transmission, and game screen presentation. For example, the client device can be a display device with data transmission capabilities located close to the user, such as a mobile terminal, television, computer, or PDA; however, the information processing is performed by the cloud gaming server in the cloud. When playing the game, the player operates the client device to send operation commands to the cloud gaming server. The cloud gaming server runs the game according to the operation commands, encodes and compresses the game screen and other data, returns it to the client device via the network, and finally, the client device decodes and outputs the game screen.

[0091] In an optional implementation, taking a game as an example, the local terminal device stores the game program and is used to display the game screen. The local terminal device is used to interact with the player through a graphical user interface (GUI), i.e., conventionally by downloading, installing, and running the game program via an electronic device. The local terminal device can provide the GUI to the player in various ways, such as rendering it on the terminal's display screen or providing it to the player via holographic projection. For example, the local terminal device can include a display screen for displaying the GUI, which includes game screens, and a processor for running the game, generating the GUI, and controlling the display of the GUI on the display screen.

[0092] In one possible implementation, this application provides a method for deploying a robot character in a game. This method deploys the robot character to a specific location and allows it to move within the game scene along a second game route. When the robot character moves to the area where a target game character is located, the robot character can be displayed through a graphical user interface provided by a terminal device. The player can then control the target game character to perform actions such as moving and attacking. The terminal device can be either the aforementioned local terminal device or a client device in the aforementioned cloud interaction system.

[0093] The following will provide a detailed description of the specific implementation of the game robot character deployment method of this application through multiple embodiments.

[0094] Figure 1 This is a flowchart illustrating a method for deploying robot characters in a game according to an embodiment of this application. It should be noted that the method for deploying robot characters in a game provided in this application is not based on... Figure 1 The specific order described below is a limitation.

[0095] It should be understood that in other embodiments, the order of some steps in the method for deploying robot characters in a game provided in this application can be interchanged according to actual needs, or some steps can be omitted or deleted. For example... Figure 1 As shown, the method includes:

[0096] S101. Identify the target game character.

[0097] For example, the target game character could be a game character controlled by a novice player or a player on a losing streak in the game scene.

[0098] In this embodiment, the main purpose is to help target players (e.g., novice players or players on a losing streak) improve their gaming experience. It is proposed to place at least one robot character at some random (or specific) locations in the game scene to create an encounter effect between the robot character and the target player's game character. This allows the robot character to be killed by the target player's game character, giving the target player a kill experience. This improves the player's gaming combat experience, prevents player churn, and increases player engagement.

[0099] Optionally, players can be identified as novice players, losing streaks, or players who need help improving their gaming experience based on the game behavior of each player's controlled game character in multiple games, including kill ratio, number of wins and losses, and historical win rate. This allows for the precise identification of target players from multiple players, and the game character controlled by the target player can be designated as the target game character.

[0100] S102. Obtain the first game start position of the target game character in the game scene, and determine at least one second game start position in the game scene based on the first game start position.

[0101] The second game start position is an alternative location for deploying robot characters within the game scene.

[0102] Optionally, the first game start position can be the spawn point of the target game character when it first enters the game, or the target game character's current position in the game. Simultaneously, at least one second game start position can be determined in the game scene based on the first game start position. For example, the location of the nearest quest point (or the location of a popular resource) to the first game start position can be used as the second game start position; or, multiple second game start positions can be randomly generated within a first distance range of the first game start position.

[0103] S103. Based on the first game start position and the pre-trained path decision model, calculate the first game route of the target game character in the game scene.

[0104] The path decision model can be a network model trained using a neural network algorithm based on historical game behavior data of a large number of players in the game.

[0105] In this embodiment, the target game character's first starting position in the game, obtained above, is input into the path decision model to obtain the target game character's possible walking path in the following game, i.e., the first game route. The first game route includes multiple location points and the walking direction of each location point.

[0106] S104. Based on at least one second game start position and path decision model, predict at least one second game route in the game scene.

[0107] Optionally, at least one second game start position is simultaneously input into the path decision model to predict at least one possible walking path for the robot character in the following game, i.e., the second game route. The second game route includes multiple location points and the walking direction at each location point.

[0108] This allows the robot character to learn from the game behavior of real players, making the predicted second game path of the robot character closer to that of real players. This makes the robot character's activities more random and realistic, avoiding overly simplistic and crude game behavior and improving the game experience for players.

[0109] S105. Based on the first game route and the second game route, determine at least one deployment position from at least one second game start position, and deploy at least one robot character at the deployment position.

[0110] It should be understood that the deployment location is a point in the game where the target game character might pass through. This allows at least one robot character to be deployed at each location, creating an encounter effect between the robot character and the target game character. This artificial encounter avoids the unpleasant experience of a robot character being easily identifiable as a robot even when the target game character is in a remote, unseen location. Furthermore, the robot character will also travel to popular resource points or mission locations, just like a real player, and encounter the target game character during this journey.

[0111] For example, the number of robot characters deployed at each deployment location can be one or more, and the deployment time of the robot characters at each deployment location can be the same time period or different time periods.

[0112] In this embodiment, based on a first game route and at least one second game route, the deployment location of the robot character (i.e., the spawn point of the robot character in the game) can be selected from at least one second game start position (i.e., candidate position), and this deployment location is used as the location point for deploying the robot character. This precise deployment of robot characters based on a path decision model ensures that the deployed robot character moves along the second game route, creating an encounter effect between the robot character and the target game character. This allows the robot character to be killed by the target game character, giving the target player a kill experience, while not making it obvious to the target player that they are fighting against a robot character. This helps some novice or losing players improve their game experience, thus enhancing the overall game combat experience.

[0113] In summary, this application proposes a method for deploying robot characters in a game. The method includes: determining a target game character; obtaining a first game start position of the target game character in a game scene, and determining at least one second game start position in the game scene based on the first game start position, wherein the second game start position is a candidate position for deploying robot characters in the game scene; calculating a first game route of the target game character in the game scene based on the first game start position and a pre-trained path decision model; predicting at least one second game route in the game scene based on at least one second game start position and the path decision model; and determining at least one deployment position from the at least one second game start position based on the first game route and the second game route, so as to deploy at least one robot character at the deployment position. This scheme primarily utilizes a pre-trained path decision model that reflects real-world conditions for all players, along with the target player's game character's initial starting position (i.e., spawn point or current position in the game) within the game scene, to calculate the first possible game route the target game character will take in the subsequent game scene. Simultaneously, based on the path decision model and at least one second starting position determined by the first starting position (i.e., alternative positions where the robot character might appear within the game scene), the scheme predicts the second possible game route the robot character might take. Then, based on the target game character's first game route and the robot character's second game route, a selection is made from at least one second starting position... At least one robot character is deployed at a location where it spawns at a point where it would logically encounter the target player. At least one robot character is then deployed at this selected location, moving along a second game route to create an encounter between the robot and the target player. This allows the robot to be killed by the target player (or possibly by other players), giving the target player a sense of accomplishment without making it obvious that they are fighting a robot. The battle result (e.g., kill / death ratio) maintains player motivation, thus helping new players or those on losing streaks improve their gaming experience and enhancing the overall combat experience.

[0114] The following examples will explain in detail how to determine the target game character in step S101 above.

[0115] As an optional implementation, step S101 above includes:

[0116] The target game character is determined based on the game data corresponding to the game character participating in the game; wherein, the game data includes at least the game character's historical battle results.

[0117] For example, the historical battle results of a game character can refer to the historical win rate (or win / loss rate), number of kills, and player skill level (Kill Death Assist, or KDA) of certain players in actual game matches; among them, the player skill level is used to represent the comparison between the kill rate and the loss rate of a player participating in the game. The higher the KDA value, the higher the player's skill level.

[0118] In this embodiment, for example, if some players' historical win rate (or win / loss rate), kill count, and skill level are all greater than or equal to their respective preset thresholds, such match results may cause these players to experience strong frustration and easily churn. Therefore, these players with strong frustration can be designated as target players, and their game characters can be designated as target game characters. This way, when the target player enters the next game (or the next game in the series), a certain number of bot characters can be strategically deployed to the target game character based on its historical match results. These bot characters can be killed by the target game character, giving the target player a killing experience and improving their overall gaming experience, thus preventing player churn.

[0119] The following embodiments will be used to explain in detail how to determine at least one second game start position in the game scene based on the first game start position in step S102 above.

[0120] As an optional implementation, step S102 includes: determining at least one second game start position within a preset range of the first game start position in the game scene.

[0121] In this embodiment, in order to enable players to have a kill experience as soon as possible and with low computational load, it is proposed that at least one second game start position, i.e., the alternative position of the robot character to be deployed, can be determined within a preset range of the first game start position where the target game character is located.

[0122] For example, refer to Figure 2 As shown, the first game start position of the target game character is P0. Then, within a range of 10 meters from the first game start position P0, four second game start positions are randomly generated, namely P21, P22, P23 and P24.

[0123] As an alternative implementation, to address the issue that multiple robot characters might encounter each other when determining at least one second game start position within a preset range of the target game character's first game start position, it is proposed to select at least one second game start position on the global game map. This selected second game start position can be the location of a mission point or a popular resource. This method of selecting a second game start position on the global game map avoids the target game character encountering multiple robot characters simultaneously, allowing robot characters to spawn at any location. This makes the robot characters' gameplay more random and realistic, thereby enhancing the player's gaming experience.

[0124] The following embodiments will be used to explain in detail how, in step S105 above, at least one placement position is determined from at least one second game start position based on the first game route and the second game route.

[0125] As an optional implementation method, refer to Figure 3 As shown, step S105 above includes:

[0126] S301. Obtain the robot deployment strategy that matches the target game character.

[0127] The robot deployment strategy may include the number of robot characters deployed that match the target game character and the deployment time, as well as the encounter time with the target game character.

[0128] This allows for the determination of the number and timing of robot characters deployed at each location based on the robot deployment strategy, thereby controlling when robot characters should meet the target game character and when robot characters should be killed by the target game character.

[0129] For example, if the target game character's historical battle results (or battle results in the first half of the game) are poor, the number of robot characters that need to be killed by the target game character in the entire game (or the second half of the game) must be at least 3, such as 1 in the 3rd minute, 1 in the 10th minute, and 1 in the 15th minute after the start of the game.

[0130] Optionally, a separate bot deployment strategy can be generated for each game character, or one or more bot deployment strategies can be generated for the same type of game characters. This application does not impose any specific limitations on this. For example, if certain game characters of the same level had similar game performance over a period of time prior to the current time, a common bot deployment strategy can be generated for these game characters.

[0131] Optionally, the bot deployment strategy can be dynamically updated based on the target game character's recent game performance. For example, after every three games the target game character has played, the bot deployment strategy can be updated based on the game data from those three games. This ensures that the bot deployment strategy is more closely matched to the player's actual ability or status.

[0132] S302. Based on the robot deployment strategy, the first game route, and the second game route, determine at least one deployment location in at least one second game start location.

[0133] Based on the above embodiments, at least three deployment positions can be selected from at least one second game start position according to the robot deployment strategy, the first game route, and the second game route. A robot character is deployed at the first deployment position at the 3rd minute after the game starts, a robot character is deployed at the second deployment position at the 10th minute, and a robot character is deployed at the third deployment position at the 15th minute.

[0134] As another optional implementation, step S105 above includes:

[0135] Based on the number of intersections between the first game route and the second game route, at least one placement location is determined from at least one second game start location.

[0136] The intersection of the first and second game routes is the meeting point between the robot character and the target game character in the game. The more intersections there are between the first and second game routes, the greater the probability that the robot character and the target game character will meet.

[0137] In this embodiment, reference Figure 4 As shown, for example, for ease of explanation, assume there are 2 starting positions for the second game, then there are 2 second game routes. We can calculate the intersections of the first game route and each of the second game routes. Among them, the number of intersections between the first game route L1 and the second game route L21 is 4, and the number of intersections between the first game route and the second game route L22 is 1. Since the first game route L1 and the second game route L21 have the most intersections, the second game starting position P21 of the second game route L21 is used as a drop position, and the robot character dropped to the second game starting position P21 is controlled to move according to the second game route L21, thereby effectively increasing the probability of the robot character encountering the target game character.

[0138] In addition, encounters between the target game character and the robot character can be created according to the needs of the game scene, such as "the target game character is ambushed from behind by the robot character, but the robot character is counter-killed by the target virtual character" or "the target game character happens to walk behind the robot character and takes the initiative in the ambush," which are positive game experiences and enhance the game experience.

[0139] The following examples will explain in detail when it is necessary to determine the target game character.

[0140] As an optional implementation method, the target game character is determined based on the game data corresponding to the game character participating in the game, including:

[0141] If the number of game characters currently participating in the game is less than the preset number, the target game character will be determined based on the game data corresponding to the participating game characters.

[0142] For example, in a game, if the number of currently participating game characters is too small, players may feel that there are few players online, leading to player churn. Therefore, in this embodiment, to avoid player churn, the number of currently participating game characters can be used to determine whether a target game character needs to be identified.

[0143] In this embodiment, the number of currently participating game characters can be obtained immediately upon entering the game scene (or during the game). If there are currently 6 participating game characters, but the game requires 10 players to start (or continue), meaning the current number of participating game characters (6) is less than the preset number (10), then, based on the game data corresponding to the participating game characters, a target game character can be determined from among the multiple game characters. A certain number of robot characters can then be deployed to the target game character, allowing these robot characters to be defeated by the target game character or other game characters.

[0144] The following examples will illustrate how to control the movement of at least one robot character after it has been deployed to a location.

[0145] As an optional implementation, after the step of deploying at least one robot character at the deployment location, the method further includes: controlling the robot character to move along a second game route in the game scene.

[0146] In this embodiment, after placing at least one robot character into the determined placement location, it is also necessary to control the robot character to move along the second game route, thereby effectively increasing the probability of the robot character encountering the target game character.

[0147] The following examples will illustrate how to continue controlling the robot characters to move after the first game route changes following the deployment of at least one robot character at the deployment location.

[0148] As an optional implementation, the method further includes:

[0149] If the deviation between the actual route of the target game character and the first game route is greater than the first preset threshold, then the third game route of the target game character is calculated based on the current position of the target game character and the path decision model, and the second game route is updated based on the third game route.

[0150] Optionally, the deviation between the actual route and the first game route can be determined by the positional deviation of each point on the actual route and the first game route. For example, dynamically select the actual sub-route and the first game sub-route 5 seconds prior to the current time, and select N sampling points from each sub-route, where N is an integer greater than 1. Generate N position point pairs according to the order of the sampling points. Each position point pair includes a first position point from the actual sub-route and a second position point from the first game sub-route with the same sequential number as the first position point. For each position point pair, calculate the positional deviation between the first and second position points. This deviation can be calculated using the three-dimensional coordinates of the first and second position points. Then, fuse the calculated positional deviation values ​​of the N position point pairs to calculate the deviation between the actual route and the first game route. This fusion process can include, for example, mean or variance calculations.

[0151] It should be understood that in actual gameplay, the target character's actual route is primarily determined by the target player's actions and possesses a degree of randomness and arbitrariness. This means that the target character's actual route may deviate from the initial route calculated based on the path decision model. For example, refer to... Figure 5 As shown, the actual route of the target game character is L11, and the first game route is L1. Then, based on the differences between the positions on the actual route L11 and the positions on the first game route L1, the deviation value M between the actual route L11 and the first game route L1 can be calculated. If the deviation value M is greater than a first preset threshold, the current position P1 of the target game character is input into the path decision model to obtain the third game route of the target game character. Figure 5 (Not shown in the image), that is, the third game route is the possible walking route of the target game character in the following game.

[0152] Furthermore, to ensure that the robot character encounters the target game character in a way that more closely resembles the movement behavior of a real player, it is proposed that the previously predicted second game route of the robot character need to be adjusted in real time based on the third game route. This would allow the robot character's actual route in the game to proactively move closer to the target game character, increasing the probability of their encounter. In addition, this would make the robot character's actual route more flexible and realistic, preventing it from being easily recognizable by the target player due to overly simplistic routes, thus enhancing the gaming experience.

[0153] In another possible approach, if the deviation between the target game character's actual route and the first game route is less than or equal to a first preset threshold, then there is no need to update the robot character's second game route.

[0154] The following examples will explain in detail how to update the second game route based on the third game route.

[0155] As an optional implementation method, refer to Figure 6 As shown, the method also includes:

[0156] S601. Obtain at least one adjustable decision point in the second game route.

[0157] Among them, the adjustable decision point corresponds to multiple walking strategies, and the weight difference of each walking strategy is less than the second preset threshold.

[0158] Optionally, the adjustable decision point can be one or more locations on the second game route. The second game route output by the aforementioned path decision model can include multiple locations, each carrying a walking strategy and its weight. The walking strategy refers to the direction of movement at that location, and the weight represents the probability of moving in that direction. Each location can have multiple walking strategies. For some locations on the second game route, if the weights of the multiple walking strategies differ significantly, it indicates that the player is likely to follow the walking strategy with the highest weight at these locations. These locations can be called unadjustable decision points. For example, at location A, the weight of the walking strategy "go left" is 90%, and the weight of the walking strategy "go right" is 10%. This indicates that at this location, the vast majority of players will choose to go left, so it is not suitable to suddenly change strategies to go right at this location. Therefore, location A is an unadjustable decision point. Conversely, for other locations on the second game route, the weight differences among the multiple walking strategies are relatively small. This indicates that any of these walking strategies can be chosen at these locations, and these locations can be called adjustable decision points. For example, at location B, the weight of the walking strategy "go left" is 51%, and the weight of the walking strategy "go right" is 49%. This means that at this location, some players will choose to go left, and some players will choose to go right. Going right or left is natural and not abrupt. Therefore, at this location, one can change from going left to going right. Thus, location B is an adjustable decision point.

[0159] Optionally, the adjustable decision point corresponds to multiple walking strategies, including: moving to the next position point in a walking direction. The walking direction can be any direction in the game scene, such as walking to the left, right, upper left, or lower left, etc., and the weight difference between left, right, upper left, or lower left is less than the second preset threshold.

[0160] In this embodiment, at least one second game start position is input into the path decision model to predict each adjustable decision point on at least one second game route when the robot character moves in the game scene.

[0161] S602. Determine the target adjustable decision point that is closest to the current position of the target game character among the adjustable decision points.

[0162] In this embodiment, reference can be made to Figure 7As shown, the current position of the target game character can be P1. The adjustable decision points on the second game route include P3, P4, and P5. Based on the coordinates of each adjustable decision point and the coordinates of the target game character's current position P1, the distance between each adjustable decision point and the target game character's current position is calculated. By comparing the calculated distance values, it is found that the distance between the adjustable decision point P4 and the target game character's current position P1 is the smallest. Therefore, the adjustable decision point P4 is selected as the target adjustable decision point.

[0163] S603. Based on the third game route, determine the target walking strategy for the adjustable decision point.

[0164] Optionally, based on the third game route taken by the target game character, the walking strategy of the adjustable decision point P4 can be obtained as moving to the upper left corner, that is, the robot character moves to the next position point in the direction of moving to the upper left corner.

[0165] S604. Update the second game route according to the target walking strategy.

[0166] Based on the above embodiments, the next movement point of the robot character can be adjusted in a timely manner according to the determined target walking strategy, that is, the second game route can be updated. In this way, the robot character will actively move closer to the target game character as much as possible during the actual route adjustment in the game, increasing the probability of the robot character and the target game character encountering each other.

[0167] In this embodiment, the second game route is updated in a timely manner based on the target game character's actual third game route and the target adjustable strategy points on the second game route, thereby increasing the probability of the robot character encountering the target game character.

[0168] The following examples will explain in detail how to train a path decision model.

[0169] As an optional implementation method, refer to Figure 8 As shown, before calculating the first game route of the target game character in the game scene based on the first game start position and a pre-trained path decision model, the method further includes:

[0170] S801. Obtain historical game behavior data generated by players participating in the game during historical game sessions.

[0171] The historical game behavior data includes: game parameters and environmental parameters of the game character controlled by each player. Game parameters include at least one of the following: location information, action information, resource information, and the location of quest points. Environmental parameters include at least one of the following: the location of popular resources and environmental attack information. For example, location information refers to the various locations of the target game character controlled by the player in the game.

[0172] In this embodiment, historical game behavior data generated by players during the game can be obtained from a game database that stores all players' game behaviors. For example, the game character's profession, the past time of the current game, the current location information of the game character, the state of the game character, the equipment information of the game character, the location and size of the area where environmental attack information is located, the distribution points of nearby popular resources, the location points of nearby mission points, etc. The player's historical game behavior data is used as the independent variable (i.e., training sample) of the function, and the movement path of the game character is used as the dependent variable.

[0173] S802. Using historical game behavior data as sample data, a path decision model is trained.

[0174] In this example, a neural network algorithm can be used as the initial path decision model, or other machine learning algorithms can be used. There are no specific restrictions on the initial path decision model selected here.

[0175] The historical game behavior data obtained above is used as sample data and input into the initial path decision model. The initial path decision model is then trained iteratively. When the accuracy of the temporary path decision model obtained after multiple iterations can no longer be significantly improved, the temporary path decision model obtained from the last training iteration is used as the final path decision model. In this way, it can be ensured that the trained path decision model can learn the game behavior of real players in the game, thereby improving the accuracy of predicting the first game route of the target game character and the second game route of the robot character.

[0176] It is worth noting that the path decision model can be trained and learned iteratively. When the game version changes, the path decision model can be retrained using newly generated game behavior data. This avoids the problem of manpower and time investment required to repeatedly adjust the rules with each game version update.

[0177] Based on the same inventive concept, this application also provides a device for deploying robot characters in the game, which corresponds to the deployment of robot characters in the game. Since the principle of the device in this application is similar to the method for deploying robot characters in the game described above, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0178] Figure 9 This is a schematic diagram of the structure of a device for deploying robot characters in a game, as provided in an embodiment of this application. The device includes:

[0179] Module 901 is used to determine the target game character;

[0180] The acquisition module 902 is used to acquire the first game start position of the target game character in the game scene, and determine at least one second game start position in the game scene based on the first game start position. The second game start position is a candidate position for deploying the robot character in the game scene.

[0181] The calculation module 903 is used to calculate the first game route of the target game character in the game scene based on the first game start position and the pre-trained path decision model; and to predict at least one second game route in the game scene based on at least one second game start position and the path decision model.

[0182] The determining module 901 is further configured to determine at least one deployment position from at least one second game start position based on the first game route and the second game route, so as to deploy at least one robot character at the deployment position.

[0183] In one possible implementation, the determining module 901 is also used for:

[0184] The target game character is determined based on the game data corresponding to the game character participating in the game;

[0185] The game data includes at least the historical battle results of the game characters.

[0186] In one possible implementation, the determining module 901 is also used for:

[0187] Within a preset range of the first game start position in the game scene, determine at least one second game start position.

[0188] In one possible implementation, the determining module 901 is also used for:

[0189] Obtain robot deployment strategies that match the target game characters;

[0190] Based on the robot deployment strategy, the first game route, and the second game route, at least one deployment location is determined in at least one second game start location.

[0191] In one possible implementation, the determining module 901 is also used for:

[0192] Based on the number of intersections between the first game route and the second game route, at least one placement location is determined from at least one second game start location.

[0193] In one possible implementation, the determining module 901 is also used for:

[0194] If the number of game characters currently participating in the game is less than the preset number, the target game character will be determined based on the game data corresponding to the participating game characters.

[0195] In one possible implementation, the device further includes:

[0196] The control module is used to control the robot character to move along the second game route in the game scene.

[0197] In one possible implementation, the computing module 903 is further used for:

[0198] If the deviation between the actual route of the target game character and the first game route is greater than the first preset threshold, then the third game route of the target game character is calculated based on the current position of the target game character and the path decision model.

[0199] The device also includes:

[0200] The update module is used to update the second game route based on the third game route.

[0201] In one possible implementation, the update module is also used for:

[0202] Obtain at least one adjustable decision point in the second game route. Each adjustable decision point corresponds to multiple walking strategies, and the weight difference between each walking strategy is less than a second preset threshold.

[0203] Identify the adjustable decision point that is closest to the current position of the target game character among the adjustable decision points;

[0204] Based on the third game route, determine the target walking strategy with adjustable target decision points;

[0205] Update the second game route according to the target walking strategy.

[0206] In one possible implementation, the device further includes:

[0207] The acquisition module 902 is also used to acquire historical game behavior data generated by players participating in the game during historical games. The historical game behavior data includes: game parameters and environmental parameters of the game characters controlled by each player. The game parameters include at least one of the following: location information, action information, resource information, and the location of the task point. The environmental parameters include at least one of the following: the location of popular resources and environmental attack information.

[0208] The training module is used to train a path decision model using historical game behavior data as sample data.

[0209] The above-described device is used to execute the method provided in the foregoing embodiments, and its implementation principle and technical effect are similar, so they will not be described again here.

[0210] These modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more digital signal processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs). Alternatively, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together as a system-on-a-chip (SOC).

[0211] This application also provides an electronic device, which may include the terminal device or server described in the foregoing embodiments, such as... Figure 10 The schematic diagram of the electronic device structure provided in this application embodiment includes: a processor 1001, a memory 1002, and a bus 1003. The memory 1002 stores machine-readable instructions executable by the processor 1001 (e.g., ...). Figure 7 The device contains response modules, control modules, and corresponding execution instructions. When the electronic device is running, the processor 1001 and the memory 1002 communicate via bus 1003. When the machine-readable instructions are executed by the processor 1001, the method steps in the above method embodiments are performed.

[0212] Optionally, this application also provides a program product, such as a computer-readable storage medium, including a program that, when executed by a processor, performs the above-described method embodiments.

[0213] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0214] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0215] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in a combination of hardware and software functional units.

[0216] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for deploying robot characters in a game, characterized in that, include: Identify the target game character; The first game start position of the target game character in the game scene is obtained, and at least one second game start position is determined in the game scene based on the first game start position. The second game start position is a candidate position for deploying the robot character in the game scene. Based on the first game start position and the pre-trained path decision model, the first game route of the target game character in the game scene is calculated; Based on the at least one second game start position and the path decision model, at least one second game route in the game scene is predicted; Based on the first game route and the second game route, at least one deployment location is determined from the at least one second game start location to deploy at least one robot character at the deployment location.

2. The method for deploying robot characters in a game according to claim 1, characterized in that, The determination of the target game character includes: The target game character is determined based on the game data corresponding to the game character participating in the game; The game data includes at least the historical battle results of the game character.

3. The method for deploying robot characters in a game according to claim 1, characterized in that, Determining at least one second game start position in the game scene based on the first game start position includes: Within a preset range of the first game start position in the game scene, at least one second game start position is determined.

4. The method for deploying robot characters in a game according to claim 1, characterized in that, The step of determining at least one placement location from the at least one second game start location based on the first game route and the second game route includes: Obtain the robot deployment strategy that matches the target game character; Based on the robot deployment strategy, the first game route, and the second game route, at least one deployment location is determined among the at least one second game start location.

5. The method for deploying robot characters in a game according to claim 1, characterized in that, The step of determining at least one placement location from the at least one second game start location based on the first game route and the second game route further includes: Based on the number of intersections between the first game route and the second game route, at least one placement location is determined from the at least one second game start location.

6. The method for deploying robot characters in a game according to claim 2, characterized in that, The step of determining the target game character based on the game data corresponding to the game character participating in the game includes: If the number of game characters currently participating in the game is less than the preset number, the target game character is determined based on the game data corresponding to the game characters participating in the game.

7. The method for deploying robot characters in a game according to claim 1, characterized in that, After deploying at least one robot character at the deployment location, the method further includes: Control the robot character to move along the second game route in the game scene.

8. The method for deploying robot characters in a game according to claim 7, characterized in that, The method further includes: If the deviation between the actual route of the target game character and the first game route is greater than a first preset threshold, then based on the current position of the target game character and the path decision model, a third game route of the target game character is calculated, and the second game route is updated based on the third game route.

9. The method for deploying robot characters in a game according to claim 8, characterized in that, The updating of the second game route based on the third game route includes: Obtain at least one adjustable decision point in the second game route, wherein the adjustable decision point corresponds to multiple walking strategies, and the weight difference of each walking strategy is less than a second preset threshold. Determine the adjustable decision point among the adjustable decision points that is closest to the current position of the target game character; Based on the third game route, determine the target walking strategy for the target adjustable decision point; Update the second game route according to the stated target walking strategy.

10. The method according to any one of claims 1-9, characterized in that, The method of calculating the first game route for the target game character in the game scene based on the first game start position and a pre-trained path decision model further includes: Acquire historical game behavior data generated by players participating in the game during historical gameplay. The historical game behavior data includes: game parameters and environmental parameters of the game characters controlled by each player. The game parameters include at least one of the following: location information, action information, resource information, and the location of the mission point. The environmental parameters include at least one of the following: the location of popular resources and environmental attack information. The path decision model is trained using the historical game behavior data as sample data.

11. A device for dispensing robot characters in a game, characterized in that, The device includes: The determination module is used to identify the target game character; The acquisition module is used to acquire the first game start position of the target game character in the game scene, and determine at least one second game start position in the game scene based on the first game start position, wherein the second game start position is a candidate position for deploying the robot character in the game scene; The calculation module is used to calculate a first game route for the target game character in the game scene based on the first game start position and a pre-trained path decision model; and to predict at least one second game route in the game scene based on the at least one second game start position and the path decision model. The determining module is further configured to determine at least one deployment location from the at least one second game start location based on the first game route and the second game route, so as to deploy at least one robot character at the deployment location.

12. An electronic device, characterized in that, include: The device includes a processor, a storage medium, and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is in operation, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the method as described in any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which is executed by a processor to perform the method as described in any one of claims 1-10.

Images