Virtual character detection method and device, storage medium and electronic device

Abstract

This disclosure provides a method, apparatus, storage medium, and electronic device for detecting virtual characters. The method includes: acquiring game data of a first virtual character at multiple moments in a single game session; matching the game data at multiple moments with detection conditions corresponding to abnormal behavior to determine a target time period within the single game session, wherein the game data within the target time period successfully matches the detection conditions; statistically analyzing the target time period to determine the detection frequency of abnormal behavior, wherein the detection frequency characterizes the number of times abnormal behavior is detected in a single game session; and obtaining a detection result for the first virtual character based on the detection frequency of abnormal behavior, wherein the detection result characterizes whether the first virtual character is the target virtual character. This disclosure solves the technical problem of the prevalence of cheating in FPS games negatively impacting the gaming experience of honest players.

Description

Technical Field

[0001] This disclosure relates to the field of virtual character detection, specifically to a method, apparatus, storage medium, and electronic device. Background Technology

[0002] Currently, because first-person shooter games (FPS) require a high degree of smoothness during gameplay, the game logic of FPS games is usually calculated on the client side. In addition, the core rules of the game logic are simple and easily broken, resulting in a large number of cheats in FPS games, which seriously undermines the fairness of the game, greatly affects the gaming experience of other honest players, and shortens the life cycle of the game.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This disclosure provides at least some embodiments of a method, apparatus, storage medium, and electronic device for detecting virtual characters, in order to at least solve the technical problem of the impact of numerous cheats on the gaming experience of honest players in FPS games.

[0005] According to one embodiment of this disclosure, a method for detecting a virtual character is provided, comprising: acquiring game data of a first virtual character at multiple moments in a single game; matching the game data at the multiple moments with detection conditions corresponding to abnormal behavior to determine a target time period in the single game, wherein the game data within the target time period successfully matches the detection conditions; statistically analyzing the target time period to determine the detection frequency of the abnormal behavior, wherein the detection frequency is used to characterize the number of times the abnormal behavior is detected in the single game; and obtaining a detection result of the first virtual character based on the detection frequency of the abnormal behavior, wherein the detection result is used to characterize whether the first virtual character is the target virtual character.

[0006] According to one embodiment of this disclosure, a virtual character detection device is also provided, comprising: an acquisition module, configured to acquire game data of a first virtual character at multiple moments in a single game; a matching module, configured to match the game data at the multiple moments with detection conditions corresponding to abnormal behavior to determine a target time period in the single game, wherein the game data within the target time period successfully matches the detection conditions; a statistics module, configured to perform statistics on the target time period to determine the detection frequency of the abnormal behavior, wherein the detection frequency is used to characterize the number of times the abnormal behavior is detected in the single game; and a determination module, configured to obtain a detection result of the first virtual character based on the detection frequency of the abnormal behavior, wherein the detection result is used to characterize whether the first virtual character is the target virtual character.

[0007] According to one embodiment of the present disclosure, a computer-readable storage medium is also provided, which stores a computer program, wherein the computer program is configured to execute the virtual character detection method described in any of the preceding claims when running.

[0008] According to one embodiment of this disclosure, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the virtual character detection method described in any of the preceding claims.

[0009] In at least some embodiments of this disclosure, by acquiring game data of the first virtual character at multiple moments in a single game, matching the game data at multiple moments with detection conditions corresponding to abnormal behavior, a target time period in the single game is determined. Then, statistics can be performed on the target time period to determine the detection frequency of abnormal behavior. Based on the detection frequency of abnormal behavior, the detection result of the first virtual character can be obtained, confirming that the first virtual character is using cheats to cheat during the game. This achieves the technical effect of identifying cheaters in the game, thereby solving the technical problem of the large number of cheats in FPS games affecting the gaming experience of honest players. Attached Figure Description

[0010] The accompanying drawings, which are included to provide a further understanding of this disclosure and form part of this disclosure, illustrate exemplary embodiments of the present disclosure and are used to explain the disclosure, but do not constitute an undue limitation of the disclosure. In the drawings:

[0011] Figure 1 This is a hardware structure block diagram of a mobile terminal for a virtual character detection method according to an embodiment of this disclosure.

[0012] Figure 2 This is a flowchart of a method for detecting virtual characters according to one embodiment of the present disclosure;

[0013] Figure 3 This is a schematic diagram of the drone's field of view for a virtual character detection method according to an embodiment of this disclosure;

[0014] Figure 4 This is a schematic diagram of the included angle of the aiming state in a virtual character detection method according to an embodiment of this disclosure.

[0015] Figure 5 This is a schematic diagram of a method for determining the aiming state in a virtual character detection method according to an embodiment of this disclosure;

[0016] Figure 6 yes Figure 5 A diagram illustrating the changing distance between the player's first virtual character and the enemy's second virtual character;

[0017] Figure 7 This is a schematic diagram of rendering a detection scene in a virtual character detection method according to an embodiment of this disclosure;

[0018] Figure 8a This is a schematic diagram (a) of the pre-aiming abnormal behavior of a virtual character detection method in an embodiment of this disclosure;

[0019] Figure 8b This is a schematic diagram (II) of the pre-aiming abnormal behavior of a virtual character detection method in an embodiment of this disclosure;

[0020] Figure 8c This is a schematic diagram (iii) illustrating the pre-aiming abnormal behavior of a virtual character detection method in this embodiment of the present disclosure;

[0021] Figure 9a This is a schematic diagram (a) of the abnormal behavior of a virtual character detection method in an embodiment of this disclosure;

[0022] Figure 9b This is a schematic diagram (II) of the abnormal behavior of a virtual character detection method in this embodiment of the present disclosure;

[0023] Figure 9c This is a schematic diagram (iii) of the abnormal behavior of a virtual character detection method in this embodiment of the present disclosure;

[0024] Figure 10a This is a schematic diagram (a) illustrating the abnormal behavior of killing concealed enemies in a virtual character detection method according to an embodiment of this disclosure;

[0025] Figure 10b This is a schematic diagram (II) of the abnormal behavior of killing hidden enemies in a method for detecting virtual characters in this embodiment of the present disclosure;

[0026] Figure 10cThis is a schematic diagram (III) illustrating the abnormal behavior of killing concealed enemies in a method for detecting virtual characters according to an embodiment of this disclosure;

[0027] Figure 11a This is a schematic diagram (a) of continuous aiming abnormal behavior of a virtual character detection method in an embodiment of this disclosure;

[0028] Figure 11b This is a schematic diagram (II) of the continuous aiming abnormal behavior of a virtual character detection method in an embodiment of this disclosure;

[0029] Figure 11c This is a schematic diagram (iii) of the continuous aiming abnormal behavior of a virtual character detection method in this embodiment of the present disclosure;

[0030] Figure 12 This is a schematic diagram illustrating the data source for the detection conditions of a virtual character detection method in an embodiment of this disclosure;

[0031] Figure 13 This is a schematic diagram (a) of aiming in a method for detecting virtual characters according to an embodiment of this disclosure;

[0032] Figure 14 This is a schematic diagram (II) of aiming for a virtual character detection method in an embodiment of this disclosure;

[0033] Figure 15 This is a schematic diagram illustrating the inventive concept of a method for detecting virtual characters according to an embodiment of this disclosure;

[0034] Figure 16 This is a scatter plot of pre-aiming cheaters in a virtual character detection method according to an embodiment of this disclosure;

[0035] Figure 17 This is a scatter plot of normal players in a virtual character detection method according to an embodiment of this disclosure;

[0036] Figure 18 This is a scatter plot of continuously aiming at cheating players in a virtual character detection method according to an embodiment of this disclosure;

[0037] Figure 19 This is a scatter plot of players exhibiting abnormal aiming rate behavior in a virtual character detection method according to an embodiment of this disclosure;

[0038] Figure 20 This is a scatter plot of players with normal aiming accuracy in a virtual character detection method according to an embodiment of this disclosure;

[0039] Figure 21 This is a scatter plot of pre-fire abnormal behavior players in a virtual character detection method according to an embodiment of this disclosure;

[0040] Figure 22This is a scatter plot of normal players in a virtual character detection method according to an embodiment of this disclosure;

[0041] Figure 23 This is a structural frame of a virtual character detection device according to one embodiment of the present disclosure;

[0042] Figure 24 This is a schematic diagram of an electronic device according to an embodiment of the present disclosure. Detailed Implementation

[0043] To enable those skilled in the art to better understand the present disclosure, the technical solutions of the present disclosure will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present disclosure, and not all embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present disclosure.

[0044] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0045] Based on certain game characteristics, cheating can generally be divided into two main categories. The first is data packet cheating, also known as server deception. Specifically, cheaters intercept and exchange network game data packets to modify game data or control game behavior. Data packet cheating requires analyzing the game's data packet encryption and decryption algorithms. Since most online games now use a server / client model based on the TCP / IP protocol, cheaters typically intercept data packets by monitoring network transmissions and cracking system dynamic link libraries. The second category is memory cheating. Cheaters deduce the memory location where game information is stored by speculating on the game client logic. Based on this, they can use reverse engineering techniques to find the function entry points and parameters for game behavior in the game client, and then call different alternative functions according to different cheating needs. This type of cheating is usually used in locally computed online games, especially large-scale multiplayer games.

[0046] In response to the above-mentioned data packet cheating methods, the corresponding anti-cheating methods mainly include the following: (1) Improved data packet encryption. This method increases the complexity of network data packet encryption and decryption algorithms, thereby increasing the difficulty of data packets being cracked. This method of dynamically updating data packet encryption algorithms and verification information is often used to protect network game data packet information. However, the encryption algorithm of this method is usually more complex, resulting in a longer calculation time and affecting the player's game experience. (2) Server abnormal data detection and analysis. By detecting server input packets and output packets, and using relevant algorithms to analyze player data, it is possible to see if these player data have been modified. However, this algorithm needs to be constantly updated to adapt to new cheating techniques. This not only puts a huge pressure on the server, but also increases the cost of manual development. (3) Embedded detection program. By embedding a cheat detection program in the client, it is possible to detect whether there are illegal cheat processes invading the game client in the player's system environment. However, this method involves user privacy, and cheaters can evade detection by impersonating drivers or directly reading physical memory. (4) Reporting and supervision. This method involves setting up a player reporting function in the game. Players who are reported will be manually verified. Strictly speaking, this method is not a technology for identifying and preventing cheating, but it can be combined with any anti-cheating technology and is very effective. However, if malicious or suspicious reports are widespread, the workload for manual detection in the later stages will be very large and costly.

[0047] In actual technical confrontations, features like wallhacks, which severely impact game balance, are surprisingly difficult to detect. This is because wallhacks only query data that is not normally visible in memory; they do not modify data or memory. Furthermore, due to players' own skill levels, some players who only use wallhacks are also very likely to be killed by other normal players, making it difficult to detect anomalies from a direct data perspective.

[0048] To address the technical challenge of detecting wallhacks, current methods rely on player reports followed by manual review. Once confirmed, cheaters are punished. However, this approach suffers from a significant delay in triggering the cheat, resulting in lengthy processing times. This means cheaters may not receive substantial punishment for weeks or even months, failing to mitigate the negative gaming experience caused to legitimate players. Applying artificial intelligence algorithms to rationally determine cheating based on player behavior can greatly alleviate this delay.

[0049] In one possible implementation, a common method used in the gaming context is to acquire players' social graphs and construct relationship graphs between players based on in-game social data, uncovering non-human behavioral patterns, or accurately detecting cheaters based on player behavior sequences and profiles. Alternatively, one could acquire image frame sequences corresponding to a player's game video, determine the first and second target regions for each game image frame, identify the first and second target regions to obtain key information about the game image frames, and determine whether the game video contains wallhack behavior based on the key information of at least N consecutive game image frames. After practice and careful research, the inventors found that this approach has the following four problems: First, it is difficult to determine the input data content and data preprocessing process. This is the most important factor determining the final cheat detection effect, requiring prior research into data closely related to cheating behavior. However, this data often contains a large amount of irrelevant content or the magnitude of all data is not the same dimension; for example, images may have a lot of noise, game elements may be numerous and complex, and image resolutions may be inconsistent; the timing and type of player actions may also be important factors. This necessitates designing a reasonable data preprocessing procedure, which requires a deep understanding of the game and related cheating programs, and involves continuous experimentation, making it highly challenging. Secondly, the model design is extremely complex and lacks good interpretability. It requires designing effective machine learning or deep learning models to extract features and model player behavior sequences based on the input data. However, the black-box nature of AI models makes it difficult to present intuitive and explainable evidence of cheating. Thirdly, data labels are scarce. It's impossible to exhaustively collect data on all types of cheating, causing the model to fail to learn relevant features during training and thus be unable to identify such cheats. Fourthly, the model lacks the ability to detect new types of cheats. Cheats mutate rapidly over time, and the model's poor generalization ability may prevent rapid identification, necessitating redesign and retraining.

[0050] Based on this, the game type targeted by this disclosure is generally FPS games. A method for detecting virtual characters is proposed. By acquiring game data of the first virtual character at multiple moments in a single game, matching the game data at multiple moments with the detection conditions corresponding to abnormal behavior, the target time period in the single game is determined. Then, the target time period can be statistically analyzed to determine the detection frequency of abnormal behavior. Based on the detection frequency of abnormal behavior, the detection result of the first virtual character can be obtained, confirming that the first virtual character is using cheats to cheat in the game. This achieves the technical effect of identifying cheaters in the game, thereby solving the technical problem of the large number of cheaters in FPS games affecting the gaming experience of honest players.

[0051] The methods and embodiments described above in this disclosure can be executed on mobile terminals, computer terminals, or similar computing devices. Taking a mobile terminal as an example, the mobile terminal can be a smartphone, tablet computer, PDA, mobile internet device, PAD, game console, or other terminal device. Figure 1 This is a hardware structure block diagram of a mobile terminal for a virtual character detection method according to an embodiment of this disclosure. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. Processor 102 (processor 102 may include, but is not limited to, a central processing unit (CPU), graphics processing unit (GPU), digital signal processing (DSP) chip, microprocessor (MCU), programmable logic device (FPGA), neural network processor (NPU), tensor processor (TPU), artificial intelligence (AI) type processor, etc.) and memory 104 for storing data. In one embodiment of this disclosure, it may also include: input / output device 108 and display device 110.

[0052] In some optional embodiments primarily focused on gaming scenarios, the aforementioned device may also provide a human-computer interaction interface with a touch-sensitive surface. This interface can sense finger contact and / or gestures to interact with a graphical user interface (GUI). The human-computer interaction functions may include the following: creating web pages, drawing, word processing, creating electronic documents, playing games, video conferencing, instant messaging, sending and receiving emails, call interfaces, playing digital videos, playing digital music, and / or web browsing, etc. Executable instructions for performing the aforementioned human-computer interaction functions are configured / stored in one or more processor-executable computer program products or readable storage media.

[0053] Those skilled in the art will understand that Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0054] According to one embodiment of this disclosure, an embodiment of a method for detecting virtual characters is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0055] Figure 2 This is a flowchart of a virtual game detection method according to one embodiment of the present disclosure, such as... Figure 2As shown, the method includes the following steps:

[0056] Step S202: Obtain game data of the first virtual character at multiple moments in a single game.

[0057] Specifically, the first virtual character can be any game character controlled by a player in an FPS game, and multiple moments can be any moment during the combat period between the first virtual character and the enemy virtual character. To eliminate interference from invalid data, the game data selected in this disclosure can be data from the in-game combat period when both the current player and the enemy player have started moving. The game data includes shooting data, kill data, and frame data. Frame data includes the coordinates, status, position, auditory information, visibility status, and aiming status of all players captured in the current image frame. Kill data includes kill time, the killing virtual character, the killed virtual character, and the weapon used for the kill. Shooting data includes: shooting time, the shooting virtual character, the shot virtual character, the damage value generated by this shot, and the shooting weapon.

[0058] Secondly, the visibility status specifically includes several scenarios: visible, invisible, and indirectly visible. Indirect visibility includes visibility on the minimap and visibility of teammate skills. For example, teammate skill visibility could mean that if a teammate is using a drone, then the teammate's vision is the drone's vision. Figure 3 This is a schematic diagram of the drone's field of view for a virtual character detection method according to an embodiment of this disclosure, such as... Figure 3 As shown, Figure 3 The dashed box in the image represents the drone's field of view, and the dashed circle represents its aiming range. The drone's field of view is superior to that of the virtual character. Secondly, visibility can be confirmed using raycasting. Raycasting involves emitting an invisible, infinitely long ray in a specific direction from an initial point. This ray is used to detect any models with added collider components; once a collider component is detected, raycasting stops. The aiming state mentioned above uses the cosine (cosine) of the angle between the player's camera and the enemy. Figure 4 This is a schematic diagram of the included angle of the aiming state in a virtual character detection method according to an embodiment of this disclosure, as shown below. Figure 4 As shown, the angle θ between the aiming line m and the line n to the enemy can be the aiming direction of the weapon held by the first virtual character, and the line n to the enemy can be the line between the weapon held by the first virtual character and the second virtual character. The cosine value of this angle θ represents the aiming state. Furthermore, this disclosure uses the cosine value because, after discarding values ​​where the enemy is beyond the player's field of vision, the angle falls within the range of (0, 180°). The characteristic of the cosine distribution is that the smaller the angle, the closer the cosine value is to 1, and vice versa. That is, the closer the crosshair is to the enemy, the larger the cosine value of the angle.

[0059] In one optional embodiment of this disclosure, the aiming state data may also be the horizontal distance between the center of the screen and the enemy, a value that is affected by the distance between the player and the enemy. Figure 5 This is a schematic diagram of a method for determining the aiming state in a virtual character detection method according to an embodiment of this disclosure, as shown below. Figure 5 As shown, point M is used to represent the crosshair of the first virtual character controlled by the player. Figure 5 MN1, located on the plate-like obstacle, represents the distance between the player and the enemy. MN2 can be a horizontal line segment passing through the player's crosshair. N1N2, perpendicular to MN2, represents the longitudinal distance between the player and the enemy. Figure 6 yes Figure 5 A diagram illustrating the changing distance between the player's first virtual character and the enemy's second virtual character, as shown below. Figure 6 As shown, point A is the position of player a, point B is the position of enemy b at the first moment, point C is the position of enemy b at the second moment, point D is the position of enemy C at the first moment, and point E is the position of enemy c at the second moment. When enemy b moves from point B to point C and enemy c moves from point D to point E, the aiming state of enemy b and enemy c in player a's field of vision changes by the same degree. However, the length of line segment DE is much greater than that of line segment BC. Therefore, this method is not accurate enough in describing the aiming process.

[0060] In an alternative embodiment, this disclosure also employs rendering detection for visibility status data. When rendering a scene, the game engine automatically reads visibility settings from a file and updates them automatically each time the visibility settings change. This allows for accurate determination of whether enemies are visible. Figure 7 This is a schematic diagram of the rendering detection scene in a virtual character detection method according to an embodiment of this disclosure. Rendering detection is more accurate than raycasting because raycasting requires setting the start and end points of the ray. In scenes with complex elements, such as bushes or gaps in walls, the enemy's location point may be obscured, but parts of the enemy's virtual character's body may be exposed, leading to a false judgment of invisibility. However, rendering detection requires the support of a game engine and involves modifying the game's low-level logic. Therefore, the method for detecting visible states needs to be determined based on the specific game project, with the principle being to ensure that the data representation is as consistent as possible with the actual visible state.

[0061] Step S204: Match game data from multiple time points with detection conditions corresponding to abnormal behaviors to determine the target time period in a single game, wherein game data within the target time period successfully matches the detection conditions.

[0062] Specifically, abnormal behavior can be the behavior of cheating players, such as abnormal behavior in five dimensions: pre-aiming abnormal behavior, continuous aiming abnormal behavior, pre-firing abnormal behavior, aiming rate abnormal behavior, and killing hidden enemies abnormal behavior.

[0063] As an optional implementation, pre-aiming abnormal behavior is used to characterize the abnormal behavior of the cheat player's virtual character automatically aiming at the enemy, and continuous aiming abnormal behavior is used to characterize the abnormal behavior of the cheat player knowing in advance the target location that the enemy can reach before the enemy arrives at the target location, and aiming at the target location in advance with the crosshair. Figure 8a This is a schematic diagram (a) illustrating the pre-aiming abnormal behavior of a virtual character detection method according to an embodiment of this disclosure. Figure 8b This is a schematic diagram (II) illustrating the pre-aiming abnormal behavior of a virtual character detection method in this embodiment of the present disclosure. Figure 8c This is a schematic diagram (iii) illustrating the pre-aiming abnormal behavior of a virtual character detection method in this embodiment of the present disclosure. Figure 8a , 8b As shown in 8c, the small figures with diagonal lines on their bodies represent a second virtual character that is not currently visible to the player. Figure 8b and 8c The small black dot in the image is used to represent the crosshair of the player's first virtual character, such as... Figure 8a As shown, when the player is still invisible and moves towards the target location, the player's first virtual character automatically begins to aim at the enemy's second virtual character. Figure 8b As shown, although the second virtual character is still invisible, the player's first character's crosshair is about to hit it, as... Figure 8c As shown, the second virtual character is still invisible, but it is hit by the player's first virtual character.

[0064] As an optional implementation, the pre-firing anomaly is used to indicate that the cheating player can clearly know the enemy's exact location and predict their movement, and fire at undetected enemies in advance. Figure 9a This is a schematic diagram (a) illustrating the abnormal behavior of a virtual character detection method according to an embodiment of this disclosure. Figure 9b This is a schematic diagram (II) illustrating the abnormal behavior of a virtual character detection method in this embodiment of the present disclosure. Figure 9c This is a schematic diagram (iii) illustrating the abnormal behavior of a virtual character detection method in this embodiment of the present disclosure. Figure 9a , 9b As shown in 9c, the small figures with diagonal lines on their bodies represent a second virtual character that is not currently visible to the player, such as... Figure 9a and 9bAs shown, the second virtual character is still invisible, while the cheater's first virtual character has already aimed at the location where the second virtual character is about to leave. Figure 9c As shown, when the weapon can pass through the door and hit the second virtual character who is still invisible, the cheater's first virtual character shoots the second virtual character at the door.

[0065] As an optional implementation, the aiming rate is used to characterize the proportion of time a player spends aiming at an enemy to the total statistical time, and the abnormal aiming rate behavior is used to characterize the behavior of cheating players with abnormally high aiming rates.

[0066] As an optional implementation, the "killing hidden enemies" abnormal behavior is used to characterize the abnormal behavior of cheating players who directly find and quickly kill the hidden enemy without any visible information. Figure 10a This is a schematic diagram (I) illustrating the abnormal behavior of killing concealed enemies in a virtual character detection method according to an embodiment of this disclosure. Figure 10b This is a schematic diagram (II) illustrating the abnormal behavior of killing concealed enemies in a virtual character detection method according to an embodiment of this disclosure. Figure 10c This is a schematic diagram (III) illustrating the abnormal behavior of killing concealed enemies in a virtual character detection method according to an embodiment of this disclosure. Figure 10a , 10b As shown, the small figures with diagonal lines on their bodies represent a second virtual character that is not currently visible to the player. Figure 10a and 10b As shown, the second virtual character is still invisible, while the cheater's first virtual character has already aimed at the location where the second virtual character will appear. Figure 10c As shown, when the second virtual character is visible and preparing to shoot the player's first virtual character, the player quickly kills the second virtual character.

[0067] As an optional implementation, since players using wallhacks do not search for others, the behavior of some cheaters is to locate the target, run towards the target, and attack. In the detection dimension of continuous aiming abnormal behavior, continuous aiming abnormal behavior is used to characterize the behavior of cheaters frequently locating enemies, continuously aiming at enemies, and killing them. Figure 11a This is a schematic diagram (a) illustrating the continuous aiming anomaly behavior of a virtual character detection method according to an embodiment of this disclosure. Figure 11b This is a schematic diagram (II) illustrating the continuous aiming anomaly behavior of a virtual character detection method according to an embodiment of this disclosure. Figure 11c This is a schematic diagram (iii) illustrating the continuous aiming anomaly behavior of a virtual character detection method according to an embodiment of this disclosure. Figure 11a , 11bAnd 11c, the little figure with diagonal lines on its body in the image is used to represent a second virtual character that is invisible to the player's first virtual character, such as Figure 11a , 11b As shown in 11c, the second virtual characters are all invisible, and the player's first virtual character has already aimed at and fired at the invisible second virtual character.

[0068] In one optional embodiment, the target time period can vary depending on the type of abnormal behavior. For example, if the abnormal behavior is pre-aiming, the target time period can be 1.5 seconds before the first visible moment; if the abnormal behavior is continuous aiming, the target time period can be the period from the start of the game to the first visible moment; if the abnormal behavior is pre-firing, the target time period can be within 3 seconds before the visible moment; and if the abnormal behavior is aiming rate abnormality, the target time period can be the period from the start of the game to the first visible moment. The visible moment can be the moment when the player's first virtual character and the enemy's virtual character are visible.

[0069] In one alternative embodiment, due to differences in player skill levels or other external factors such as device performance, network speed, and even player state, feel, and operating habits, the illegal behaviors of cheating players are not common. In other words, a player exhibiting a particular abnormal behavior can be considered a cheater, but cheaters may not necessarily exhibit the same abnormal behavior. Figure 12 This is a schematic diagram illustrating the data source for the detection conditions of a virtual character detection method according to an embodiment of this disclosure, such as... Figure 12 As shown, cheating players may exhibit abnormal behaviors 1, 2, and 3, but normal players may also exhibit these abnormal behaviors. Therefore, this disclosure uses the union of multiple abnormal behaviors as the data source for detection conditions.

[0070] Secondly, during gameplay, if a player is using cheats, they gain extra vision. Without any auxiliary information, if a player spends a long time aiming at enemies they shouldn't be seeing and then fires at enemies whose positions haven't been revealed, that's clear evidence of cheating. However, real-world game scenarios are often more complex, and player behavior is highly random, meaning that many legitimate players might exhibit similar cheating behaviors. Figure 12 There is overlap between the behavior of cheaters and normal players in the game. The main scenarios can be roughly categorized as follows:

[0071] Firstly, it's not a deliberate act. The current enemy is not the target the player intends to attack. Figure 13 This is a schematic diagram (a) illustrating the aiming method for detecting virtual characters in an embodiment of this disclosure. Figure 13 As shown, Figure 13The small figure with diagonal lines on its body represents a second virtual character who is invisible. Previously, enemy A's location was revealed; when the player attacked enemy A, enemy A fled and went into hiding. Figure 14 This is a schematic diagram (II) of an aiming method for detecting virtual characters in an embodiment of this disclosure, as shown. Figure 14 As shown, Figure 14 The small figure with diagonal lines on its body represents a second virtual character who is invisible. Enemy A is fleeing, while enemy B is accidentally injured.

[0072] Secondly, other auxiliary information can be used to predict the enemy's location. This includes visual information, such as bullet trajectories and skill effects, as well as auditory information, such as the enemy's footsteps.

[0073] Thirdly, the players are experienced, have good awareness, and react quickly. They can ambush and aim at positions where enemies are likely to appear, such as alley entrances, and quickly kill the enemies when they happen to pass by.

[0074] Step S206: Statistical analysis is performed on the target time period to determine the detection frequency of abnormal behavior. The detection frequency is used to characterize the number of times abnormal behavior is detected in a single game.

[0075] Specifically, the frequency of detections is counted only when abnormal behavior is confirmed.

[0076] Step S208: Based on the detection frequency of abnormal behavior, obtain the detection result of the first virtual character, wherein the detection result is used to characterize whether the first virtual character is the target virtual character.

[0077] Specifically, the aforementioned target virtual character can be a virtual character used by a cheating player.

[0078] As an optional implementation, if the abnormal behavior is pre-aiming abnormal behavior and the detection frequency is greater than or equal to two times, the player is judged to be cheating; if the abnormal behavior is continuous aiming abnormal behavior and the detection frequency is greater than or equal to three times, the player is judged to be cheating; if the abnormal behavior is pre-firing abnormal behavior and the detection frequency is greater than or equal to two times, the player is judged to be cheating; if the abnormal behavior is killing a concealed enemy and the detection frequency is greater than or equal to two times, the player is judged to be cheating; if the abnormal behavior is aiming rate abnormality and the detection frequency is greater than or equal to two times, the player is judged to be cheating.

[0079] In one alternative embodiment, Figure 15 This is a schematic diagram illustrating the inventive concept of a virtual character detection method according to an embodiment of this disclosure, such as... Figure 15As shown, after acquiring single-game data, the basic condition values ​​V1, V2, ..., Vn for abnormal behavior are calculated. These basic condition values ​​can be understood as values ​​used to determine whether a player is cheating, such as aiming accuracy. Suspected time periods that meet the initial judgment conditions are identified, i.e., the time periods when the player's behavior is abnormal and the player may be cheating. If the basic condition values ​​V1, V2, ..., Vn are all higher than the threshold, the suspected time period is determined. If all false alarms cannot be ruled out, the frequency of abnormal behavior is statistically analyzed. The frequency value of each abnormal behavior is compared with the ratio, and the union of all judgment results is taken.

[0080] In at least some embodiments of this disclosure, by acquiring game data of the first virtual character at multiple moments in a single game, matching the game data at multiple moments with detection conditions corresponding to abnormal behavior, a target time period in the single game is determined. Then, statistics can be performed on the target time period to determine the detection frequency of abnormal behavior. Based on the detection frequency of abnormal behavior, the detection result of the first virtual character can be obtained, confirming that the first virtual character is using cheats to cheat during the game. This achieves the technical effect of identifying cheaters in the game, thereby solving the technical problem of the large number of cheats in FPS games affecting the gaming experience of honest players.

[0081] Optionally, the detection conditions include: judgment conditions and exclusion conditions. Matching game data from multiple time points with the detection conditions corresponding to abnormal behavior to determine the target time period in a single game session includes: determining a target time point from the multiple time points based on the game data from multiple time points, wherein the target time point represents the moment when the second virtual character first becomes visible relative to the first virtual character, or when the first virtual character successfully performs a shooting operation against the second virtual character; determining an initial time period that meets the judgment conditions from a first preset time period prior to the target time point based on the game data from multiple time points; and determining a target time period that does not meet the exclusion conditions from the initial time period based on the game data from multiple time points and the exclusion conditions.

[0082] Specifically, the aforementioned judgment conditions are related to the type of abnormal behavior. Each different type of abnormal behavior corresponds to a different target time and a different first preset time period, and is mainly determined based on the aiming degree of the first virtual character towards the second virtual character, the movement distance of the first virtual character, and the enemy's shooting status. The aforementioned second virtual character is used to represent the enemy's virtual character. The aforementioned visibility state is used to represent the state in which the first virtual character and the second virtual character can see each other. It should be noted that since there is almost no difference between the behavior of cheating players and normal players after visibility information is available, this disclosure sets the behavior calculation time within a time period without any visibility information, that is, the aforementioned first preset time period. The first preset time period is usually the time period from the initial time to the first time the player's first virtual character and the enemy's virtual character become visible, which makes it easier to confirm the clues of cheating players. From a data perspective, there are detection errors related to visibility. For example, if an enemy is moving quickly and there is a lot of cover, the enemy's direct visibility may not be reflected in the data. Therefore, in order to compensate for this error, this disclosure uses the time between the enemy's aiming and shooting and the first time the enemy becomes visible to correct the time of first visibility. Since the enemy's behavior always occurs after the player and the enemy meet, this approach can help to lock the abnormal behavior detection within the time period "without interference from external factors".

[0083] The above exclusion criteria can be used to rule out false positives about players cheating. For example, when judging whether a player has pre-aiming abnormal behavior, it is necessary to exclude situations where the player has killed other enemies before that initial time period; when judging whether a player has continuous aiming abnormal behavior, it is necessary to exclude situations where the player is in the skill release phase, and situations where the enemy's second virtual character fires; when judging whether a player has pre-firing abnormal behavior, it is necessary to exclude situations where the player uses auxiliary information to locate enemies, the player randomly aims and fires at enemies at a long distance, the player is aiming at multiple enemies, the player is camping at the start of the game, and the player is killed before firing pre-firing; when judging whether a player has aiming rate abnormal behavior, it is necessary to exclude situations where the target time period is short, the enemy is completely stationary, and the enemy has not revealed their location.

[0084] In the above-mentioned optional embodiments of this disclosure, a target time period that does not meet the exclusion conditions can be determined from the initial time period based on game data and exclusion conditions at multiple times. This allows for the exclusion of normal behavior of some players based on the exclusion conditions during the process of confirming whether a player is cheating, avoiding misjudgment and further improving the user experience.

[0085] Optionally, based on game data from multiple moments, an initial time period satisfying the judgment conditions is determined from a first preset time period prior to the target moment. This includes: determining multiple aiming targets and a first aiming degree of the first virtual character towards the second virtual character based on game data from multiple moments, wherein the aiming target represents the virtual character being aimed at by the first virtual character, and the first aiming degree represents the angle between the orientation of the first virtual character and the second virtual character; determining an effective attention period from the first preset time period based on the aiming targets from multiple moments, wherein the aiming target during the effective attention period is the second virtual character; and determining an initial time period from the effective attention period based at least on the first aiming degree, wherein the first aiming degree during the initial time period satisfies the preset conditions.

[0086] Specifically, in an FPS game, the first virtual character can aim at the second virtual character with a weapon. When the first virtual character can aim at the second virtual character, it means that the first and second virtual characters are visible to each other. The orientation corresponding to the first virtual character can be the direction of a ray emitted from a preset point on the first virtual character's body towards the current virtual character's field of vision, for example... Figure 4 In the direction of m, the line connecting the first and second virtual characters can be a ray between a preset point of the first virtual character and a preset point of the second virtual character, such as... Figure 4 As shown in n, the angle between m and n can be the aforementioned first aiming degree. The aforementioned effective attention period can be determined by the cosine value of the first aiming degree. The aforementioned determination condition can be that within this period, the first virtual character only aims at a unique second virtual character. The aforementioned preset condition can be that the cosine value of the first aiming degree within the initial period is greater than a preset cosine value, for example, the preset cosine value can be 0.999.

[0087] In one alternative embodiment, based on game data from a single game, a scatter plot of the cosine value of the first aiming degree between the player's virtual character and a specified enemy virtual character can be suggested. Figure 16 This is a scatter plot of pre-aiming cheaters in a virtual character detection method according to an embodiment of this disclosure, such as... Figure 16 As shown, the horizontal axis represents time, the vertical axis represents the cosine value, and the vertical line in the coordinate graph represents the target time. It's easy to notice that in the scatter plot of the cheater, the cosine value is consistently high before the target time, indicating that the cheater was well-prepared and ready to aim at the enemy at any moment. Figure 17 This is a scatter plot of normal players for a virtual character detection method according to an embodiment of this disclosure, such as... Figure 17 As shown, the horizontal axis represents time, the vertical axis represents the cosine value, and the vertical lines in the coordinate graph represent the target time. Figure 17The scattered points are chaotic, and only after the target time will they continuously aim at the enemy.

[0088] In actual gameplay, there are situations where a large number of enemies are clustered together. The player's first virtual character may be aiming at multiple second virtual characters at the same time. In order to eliminate this situation of aiming at multiple second virtual characters, the effective attention period of the player's first virtual character on the second virtual characters is calculated in units of time. For example, if the player aims at multiple second virtual characters at a certain moment, then that moment can be discarded, and the set of the remaining time points can be used as the effective attention period.

[0089] Optionally, at least based on the first aiming degree, an initial time period is determined from the effective attention period, including: determining the time interval between the start time and the target time of the effective attention period, and the average value of the cosine of the first aiming degree within the effective attention period; and determining the initial time period from the effective attention period based on the average value and the time interval, wherein the average value within the initial time period is greater than a preset value, and the time interval is greater than a preset interval.

[0090] Specifically, when the abnormal behavior is a pre-aiming abnormal behavior, the time interval is determined to be 1.5 seconds. The initial time period corresponding to this time interval can be 1.5 seconds from the start of the effective attention period to the target time, and the cosine value of the first aiming degree corresponding to all times within the initial time period is greater than a preset value. The above-mentioned preset interval can be a time threshold set by the staff, usually the maximum time set based on a normal player aiming at the enemy's second virtual character.

[0091] Optionally, at least based on a first aiming degree, an initial time period is determined from within the effective attention period, including: determining a first length of the effective attention period, the average value of the cosine of the first aiming degree within the effective attention period, and the change in the cosine of the first aiming degree within the effective attention period; and determining the initial time period from within the effective attention period based on the first length, the average value, and the change, wherein the first length of the initial time period is greater than a preset length, the average value is greater than a preset value, and the change is greater than a preset change.

[0092] Specifically, the effective focus time period can be any consecutive aiming time period exceeding 18 frames within the effective aiming time period from the start of the game to the target time in a single game. The aforementioned effective aiming time period can be any time period where the cosine value of the first aiming degree is greater than 0.999. The aforementioned first length can be a continuous duration of 18 frames. The aforementioned initial time period can be the time period from the start of the game to the target time.

[0093] In one alternative embodiment, if a player exhibits abnormal behavior of continuous aiming, it indicates that the player is likely using a wallhack. Since players using wallhacks can directly see the location of the enemy's second virtual character, they essentially don't need to search for enemies and exhibit the following behavioral characteristics: upon locating a target, they immediately rush towards it and attack. Therefore, when detecting such abnormal behavior, the focus is usually on the frequency of the player's continuous aiming behavior to locate the enemy. Figure 18 This is a scatter plot of continuously aiming at cheating players in a virtual character detection method according to an embodiment of this disclosure, such as... Figure 18 The horizontal axis represents time, the vertical axis represents the cosine value of the first aiming degree, and the vertical line represents the target time. It is easy to note that, from... Figure 18 It can be clearly observed that before the target time, the scatter plot values ​​of the cheating player frequently show consecutively large cosine values, and this occurs quite frequently. Figure 18 The scattered points in the box are continuous points with very large cosine values, but the scattered points of ordinary players have no pattern.

[0094] In actual calculations, cheating players may not aim at enemies for extended periods. If the time limit is too short, many instances of unconscious aiming by players will be misjudged as abnormal behavior. Therefore, this disclosure adopts a "lenient entry, strict exit" strategy. The selected duration limit for continuous aiming—that is, the initial duration cannot be too long—and the cosine value of the initial aiming intensity before and after continuous aiming should have a small change to ensure that continuous aiming behavior is purposeful. The specific calculation process can be as follows: First, iterate through each game and accumulate the frequency of abnormal behavior, including: calculating candidate time periods: calculating the effective aiming time of the player towards the current enemy from the start of the game to the first visible moment, and calculating the set of effective attention time periods with a continuous duration exceeding 18 frames. Iterate through the set of effective attention time periods; determine whether the player's behavior within the effective attention time period is suspected of cheating. If the cosine value of the initial aiming intensity changes little before and after this effective attention time period, then this effective attention time period is confirmed as a suspected period; exclude normal player behavior: whether the player is in the skill release phase, and whether the enemy has fired. If neither is true, then count the frequency. Then, if the frequency is no less than 3 times, the player will be judged as cheating.

[0095] Optionally, at least based on a first aiming degree, an initial time period is determined from the effective attention period, including: determining the average value of the cosine of the first aiming degree within the effective attention period; determining an effective aiming time period based on the average value, wherein the average value within the effective aiming time period is greater than a preset value; obtaining the ratio of a second length of the effective aiming time period to a preset length of a first preset time period to obtain the aiming rate of the effective aiming time period; and determining an initial time period based on the aiming rate, wherein the aiming rate within the initial time period is greater than a preset aiming rate.

[0096] Specifically, the second length of the effective aiming time period can be the duration of the effective aiming time period. After obtaining the initial time period, if the total length of the initial time period is short, it is confirmed that the player's first virtual character is not the target virtual character. If the total length of the initial time period is greater than the preset duration threshold, the first virtual character is confirmed as the target virtual character.

[0097] In one alternative embodiment, Figure 19 This is a scatter plot of players exhibiting abnormal aiming behavior in a virtual character detection method according to an embodiment of this disclosure. Figure 20 This is a scatter plot of players with normal aiming accuracy in a virtual character detection method according to an embodiment of this disclosure, such as... Figure 19 and Figure 20 As shown in the figure, the vertical line represents the target time, and the horizontal line represents the preset value. Figure 19 and Figure 20 A comparison clearly shows that cheaters have a much higher aiming accuracy than normal players.

[0098] Optionally, based on game data from multiple moments, an initial time period satisfying the judgment condition is determined from a first preset time period before the target moment, including: based on game data from multiple moments, determining the shooting moment within the first preset time period and the second aiming degree of the first virtual character towards the second virtual character within a second preset time period before the shooting moment, wherein the shooting moment is used to characterize the moment when the first virtual character performs a shooting operation towards the second virtual character within the first preset time period, and the second aiming degree is used to characterize the angle between the orientation of the first virtual character and the second virtual character; based on the second aiming degree, an initial time period is determined from the second preset time period, wherein the cosine value of the second aiming degree within the initial time period is greater than the cosine value of the first preset degree.

[0099] In one alternative embodiment, if a player is using cheats, pre-firing behavior may occur, meaning the cheating player can pinpoint the exact location of the second virtual character and predict its movement, allowing them to fire at undetected enemies. Figure 21 This is a scatter plot of pre-emptive shooting abnormal behavior players in a virtual character detection method according to an embodiment of this disclosure. Figure 22 This is a scatter plot of normal players for a virtual character detection method according to an embodiment of this disclosure, such as... Figure 21 and Figure 22 As shown, the horizontal axis is the time axis, the left axis represents the number of shots, and the right axis represents the cosine value of the aiming accuracy. Figure 22 It is known that normal players only engage in shooting and aiming behavior after the target time, while cheating players have already targeted the second virtual character before it becomes visible (i.e., the cosine value of the aiming degree is close to 1 before the target time) and launch an attack prematurely. The calculation process to determine if a player is engaging in premature firing is as follows: First, iterate through each game and accumulate the frequency of abnormal behavior, including: calculating the effective attention period: the time period within 3 seconds before the first visibility time when the player engages in shooting behavior is the effective attention period; determine whether the player is suspected of cheating within the effective attention period. If the player's first virtual character has a large cosine value of the second aiming degree within 1 second before shooting (aiming at the enemy), then the effective attention period is confirmed as the suspected period; exclude normal player behavior: whether it is an indiscriminate attack with a knife and C4; whether the player has auxiliary information to roughly locate the enemy; whether the player is randomly aiming and shooting at a distance from the enemy; whether the player is aiming at multiple enemies; whether the player is camping at the start of the game; whether the player is killed after firing prematurely. If none of these are true, then the frequency is counted. Then, if the frequency is no less than 2 times, it is determined that the player's first virtual character has abnormal behavior of firing in advance, and the player is judged to be cheating.

[0100] Optionally, based on game data from multiple moments, an initial time period satisfying the judgment conditions is determined from a first preset time period prior to the target moment. This includes: determining the third aiming degree of the first virtual character towards the second virtual character and the movement distance of the second virtual character based on game data within the first preset time period, wherein the third aiming degree is used to characterize the angle between the orientation of the first virtual character and the second virtual character; and determining the initial time period from the first preset time period based on the third aiming degree and the movement distance, wherein the third aiming degree in the initial time period is greater than the second preset degree and the movement distance is less than the preset distance.

[0101] In one optional embodiment, if a player is cheating, they might be able to find and quickly eliminate a hidden second virtual character before the second virtual character has any visible information. The following method can be used to confirm whether the player's first virtual character is engaging in abnormal behavior by eliminating a hidden enemy: First, iterate through each game and accumulate the frequency of abnormal behavior. This includes: confirming the player's aiming state and the enemy's movement distance before each enemy is eliminated within the effective attention period; determining whether cheating is suspected within this effective attention period. If the first virtual character is constantly aiming and the enemy's movement distance is small, this effective attention period is confirmed as a suspected period, indicating that the player is suspected of cheating within this effective attention period; excluding normal player behavior, such as: whether the total time period is short; whether the enemy is completely stationary; whether the enemy's tracks are exposed. If none of these three situations apply, the frequency is counted. Then, if the frequency is not less than 2 times, the player has engaged in abnormal behavior by eliminating hidden enemies, and the player is determined to be cheating.

[0102] Optionally, the detection result of the first virtual character is obtained based on the detection frequency of the abnormal behavior, including: obtaining the preset frequency corresponding to the abnormal behavior; if the detection frequency is greater than or equal to the preset frequency, determining that the first virtual character is the target virtual character; if the detection frequency is less than the preset frequency, determining that the first virtual character is not the target virtual character.

[0103] Specifically, different abnormal behaviors correspond to different preset frequencies. For example, when the abnormal behavior is pre-aiming, pre-firing, or killing a concealed enemy, the preset frequency is 2; when the abnormal behavior is continuous aiming or aiming rate abnormality, the preset frequency is 3. If the detection frequency is less than the preset frequency, the detection result is determined to be that the first virtual character has not exhibited any abnormal behavior, that is, the first virtual character is not the target virtual character.

[0104] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this disclosure.

[0105] This embodiment also provides an apparatus for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the terms "unit" and "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0106] Figure 23 This is a structural block diagram of a virtual character detection device according to one embodiment of the present disclosure, such as... Figure 23 As shown, the device includes:

[0107] The acquisition module 2302 is used to acquire game data of the first virtual character at multiple moments in a single game.

[0108] The matching module 2304 is used to match game data from multiple time points with detection conditions corresponding to abnormal behaviors to determine the target time period in a single game, where the game data within the target time period successfully matches the detection conditions.

[0109] The statistics module 2306 is used to perform statistics on the target time period and determine the detection frequency of abnormal behavior. The detection frequency is used to characterize the number of times abnormal behavior is detected in a single game.

[0110] The determination module 2308 is used to obtain the detection result of the first virtual character based on the detection frequency of abnormal behavior, wherein the detection result is used to characterize whether the first virtual character is the target virtual character.

[0111] Optionally, the detection conditions include: judgment conditions and exclusion conditions. The matching module includes: a target time determination unit, used to determine a target time among multiple time periods based on game data at multiple time periods, wherein the target time is used to characterize the moment when the second virtual character first becomes visible relative to the first virtual character, or when the first virtual character successfully performs a shooting operation on the second virtual character; an initial time period determination unit, used to determine an initial time period that meets the judgment conditions from a first preset time period before the target time period based on game data at multiple time periods; and an exclusion unit, used to determine a target time period that does not meet the exclusion conditions from the initial time period based on game data at multiple time periods and the exclusion conditions.

[0112] Optionally, the initial time period determination unit includes: a determination subunit, used to determine multiple aiming targets at multiple times based on game data at multiple times, and a first aiming degree of the first virtual character towards the second virtual character, wherein the aiming target is used to represent the virtual character being aimed at by the first virtual character, and the first aiming degree is used to represent the angle between the orientation of the first virtual character and the second virtual character; an effective attention time period determination subunit, used to determine an effective attention time period from a first preset time period based on the aiming targets at multiple times, wherein the aiming target within the effective attention time period is the second virtual character; and an initial time period determination subunit, used to determine an initial time period from the effective attention time period based at least on the first aiming degree, wherein the first aiming degree within the initial time period satisfies a preset condition.

[0113] Optionally, the initial time period determination subunit is also used to determine the time interval between the start time and the target time of the effective attention period, as well as the average value of the first aiming degree within the effective attention period; based on the average value and the time interval, an initial time period is determined from the effective attention period, wherein the average value within the initial time period is greater than a preset value, and the time interval is greater than a preset interval.

[0114] Optionally, the initial time period determination subunit is further used to determine the first length of the effective attention period, the average value of the cosine of the first aiming degree within the effective attention period, and the change in the cosine of the first aiming degree within the effective attention period; based on the first length, the average value, and the change, an initial time period is determined from the effective attention period, wherein the first length within the initial time period is greater than a preset length, the average value is greater than a preset value, and the change is greater than a preset change.

[0115] Optionally, the initial time period determination subunit is further configured to determine the average value of the cosine of the first aiming degree within the effective attention period; based on the average value, determine the effective aiming time period from within the effective attention period, wherein the average value within the effective aiming time period is greater than a preset value; obtain the ratio of the second length of the effective aiming time period to the preset length of the first preset time period to obtain the aiming rate of the effective aiming time period; based on the aiming rate, determine the initial time period from within the effective aiming time period, wherein the aiming rate within the initial time period is greater than a preset aiming rate.

[0116] Optionally, the initial time period determination unit further includes an aiming degree determination subunit, used to determine, based on game data from multiple moments, the second aiming degree of the first virtual character towards the second virtual character within a first preset time period and within a second preset time period prior to the shooting moment, wherein the shooting moment is used to characterize the moment when the first virtual character performs a shooting operation towards the second virtual character within the first preset time period, and the second aiming degree is used to characterize the angle between the orientation of the first virtual character and the second virtual character; and a second initial time period confirmation subunit, used to determine an initial time period from within the second preset time period based on the second aiming degree, wherein the cosine value of the second aiming degree within the initial time period is greater than the cosine value of the first preset degree.

[0117] Optionally, the initial time period determination unit further includes: an aiming degree and movement distance determination subunit, used to determine the third aiming degree of the first virtual character towards the second virtual character and the movement distance of the second virtual character based on game data within the first preset time period, wherein the third aiming degree is used to characterize the angle between the orientation of the first virtual character and the second virtual character; and a third initial time period determination subunit, used to determine an initial time period from the first preset time period based on the third aiming degree and movement distance, wherein the third aiming degree within the initial time period is greater than the second preset degree and the movement distance is less than the preset distance.

[0118] Optionally, the determining module includes: a preset frequency acquisition unit, used to acquire a preset frequency corresponding to the abnormal behavior; a first determining unit, used to determine that the detection result is that the first virtual character is the target virtual character when the detection frequency is greater than or equal to the preset frequency; and a second determining unit, used to determine that the detection result is that the first virtual character is not the target virtual character when the detection frequency is less than the preset frequency.

[0119] It should be noted that the above-mentioned units and modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but not limited to these: all the above-mentioned units and modules are located in the same processor; or, the above-mentioned units and modules are located in different processors in any combination.

[0120] Embodiments of this disclosure also provide a computer-readable storage medium storing a computer program configured to execute the steps in any of the above-described embodiments of the virtual object detection method.

[0121] Optionally, in this embodiment, the computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0122] Optionally, in this embodiment, the computer-readable storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0123] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0124] S1, retrieves game data of the first virtual character at multiple moments in a single game;

[0125] S2, match game data from multiple moments with the detection conditions corresponding to abnormal behavior to determine the target time period in a single game, where the game data within the target time period successfully matches the detection conditions;

[0126] S3, perform statistics on the target time period to determine the detection frequency of abnormal behavior, where the detection frequency is used to characterize the number of times abnormal behavior is detected in a single game.

[0127] S4. Based on the detection frequency of abnormal behavior, the detection result of the first virtual character is obtained, wherein the detection result is used to characterize whether the first virtual character is the target virtual character.

[0128] Optionally, the aforementioned computer-readable storage medium is further configured to store program code for performing the following steps: the detection conditions include: judgment conditions and exclusion conditions; based on game data at multiple times, determining a target time among the multiple times, wherein the target time is used to characterize the moment when the second virtual character first becomes visible relative to the first virtual character, or when the first virtual character successfully performs a shooting operation on the second virtual character; based on game data at multiple times, determining an initial time period that satisfies the judgment conditions from a first preset time period prior to the target time; based on game data at multiple times and the exclusion conditions, determining a target time period that does not satisfy the exclusion conditions from the initial time period.

[0129] Optionally, the aforementioned computer-readable storage medium is further configured to store program code for performing the following steps: determining multiple aiming targets based on game data at multiple times, and a first aiming degree of a first virtual character toward a second virtual character, wherein the aiming target is used to characterize the virtual character being aimed at by the first virtual character, and the first aiming degree is used to characterize the angle between the orientation of the first virtual character and the second virtual character; determining an effective attention period from a first preset time period based on the aiming targets at multiple times, wherein the aiming target during the effective attention period is the second virtual character; and determining an initial time period from the effective attention period based at least on the first aiming degree, wherein the first aiming degree during the initial time period satisfies a preset condition.

[0130] Optionally, the aforementioned computer-readable storage medium is further configured to store program code for performing the following steps: determining the time interval between the start time and the target time of the effective attention period, and the average value of the first targeting degree within the effective attention period; determining an initial time period from within the effective attention period based on the average value and the time interval, wherein the average value within the initial time period is greater than a preset value, and the time interval is greater than a preset interval.

[0131] Optionally, the aforementioned computer-readable storage medium is further configured to store program code for performing the following steps: determining a first length of an effective attention period, an average value of the cosine of a first aiming degree within the effective attention period, and a change in the cosine of the first aiming degree within the effective attention period; determining an initial time period from within the effective attention period based on the first length, the average value, and the change, wherein the first length of the initial time period is greater than a preset length, the average value is greater than a preset value, and the change is greater than a preset change.

[0132] Optionally, the aforementioned computer-readable storage medium is further configured to store program code for performing the following steps: determining a first length of an effective attention period, an average value of the cosine of a first aiming degree within the effective attention period, and a change in the cosine of the first aiming degree within the effective attention period; determining an initial time period from within the effective attention period based on the first length, the average value, and the change, wherein the first length of the initial time period is greater than a preset length, the average value is greater than a preset value, and the change is greater than a preset change.

[0133] Optionally, the aforementioned computer-readable storage medium is further configured to store program code for performing the following steps: determining the average value of the cosine of a first aiming degree within an effective attention period; determining an effective aiming period based on the average value within the effective attention period, wherein the average value within the effective aiming period is greater than a preset value; obtaining the ratio of a second length of the effective aiming period to a preset length of a first preset period to obtain an aiming rate of the effective aiming period; and determining an initial period based on the aiming rate within the effective aiming period, wherein the aiming rate within the initial period is greater than a preset aiming rate.

[0134] Optionally, the aforementioned computer-readable storage medium is further configured to store program code for performing the following steps: based on game data at multiple times, determining the shooting time within a first preset time period and the second aiming degree of the first virtual character towards the second virtual character within a second preset time period prior to the shooting time, wherein the shooting time is used to characterize the moment when the first virtual character performs a shooting operation towards the second virtual character within the first preset time period, and the second aiming degree is used to characterize the angle between the orientation of the first virtual character and the second virtual character; based on the second aiming degree, determining an initial time period from within the second preset time period, wherein the cosine value of the second aiming degree within the initial time period is greater than the cosine value of the first preset degree.

[0135] Optionally, the aforementioned computer-readable storage medium is further configured to store program code for performing the following steps: determining a third aiming degree of the first virtual character toward the second virtual character and the movement distance of the second virtual character based on game data within a first preset time period, wherein the third aiming degree is used to characterize the angle between the orientation of the first virtual character and the second virtual character; determining an initial time period from the first preset time period based on the third aiming degree and the movement distance, wherein the third aiming degree in the initial time period is greater than the second preset degree and the movement distance is less than the preset distance.

[0136] Optionally, the aforementioned computer-readable storage medium is further configured to store program code for performing the following steps: obtaining a preset frequency corresponding to the abnormal behavior; if the detection frequency is greater than or equal to the preset frequency, determining that the detection result is that the first virtual character is the target virtual character; if the detection frequency is less than the preset frequency, determining that the detection result is that the first virtual character is not the target virtual character.

[0137] This embodiment of the computer-readable storage medium provides a technical solution. By acquiring game data of a first virtual character at multiple moments in a single game, matching the game data at multiple moments with detection conditions corresponding to abnormal behavior, a target time period in the single game is determined. Then, statistics can be performed on the target time period to determine the detection frequency of abnormal behavior. Based on the detection frequency of abnormal behavior, the detection result of the first virtual character can be obtained, confirming that the first virtual character is using cheats to cheat during the game. This achieves the technical effect of identifying cheaters in the game, thereby solving the technical problem of the large number of cheaters in FPS games affecting the gaming experience of honest players.

[0138] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0139] In exemplary embodiments of this disclosure, a computer-readable storage medium stores a program product capable of implementing the methods described above in this embodiment. In some possible implementations, various aspects of the embodiments of this disclosure may also be implemented as a program product including program code, which, when the program product is run on a terminal device, causes the terminal device to perform the steps according to various exemplary embodiments of this disclosure described in the "Exemplary Methods" section above.

[0140] The program product for implementing the above-described method according to embodiments of the present disclosure may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the embodiments of the present disclosure is not limited thereto. In the embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0141] The aforementioned program product may take the form of any combination of one or more computer-readable media. Such computer-readable storage media may be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples (not exhaustive) of computer-readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0142] It should be noted that the program code contained on the computer-readable storage medium can be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0143] Embodiments of this disclosure also provide an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0144] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0145] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0146] S1, retrieves game data of the first virtual character at multiple moments in a single game;

[0147] S2, match game data from multiple moments with the detection conditions corresponding to abnormal behavior to determine the target time period in a single game, where the game data within the target time period successfully matches the detection conditions;

[0148] S3, perform statistics on the target time period to determine the detection frequency of abnormal behavior, where the detection frequency is used to characterize the number of times abnormal behavior is detected in a single game.

[0149] S4. Based on the detection frequency of abnormal behavior, the detection result of the first virtual character is obtained, wherein the detection result is used to characterize whether the first virtual character is the target virtual character.

[0150] Optionally, the processor may also be configured to perform the following steps via a computer program: the detection conditions include: judgment conditions and exclusion conditions; based on game data from multiple times, a target time is determined among the multiple times, wherein the target time is used to characterize the moment when the second virtual character first becomes visible relative to the first virtual character, or when the first virtual character successfully performs a shooting operation on the second virtual character; based on game data from multiple times, an initial time period that meets the judgment conditions is determined from a first preset time period before the target time; based on game data from multiple times and the exclusion conditions, a target time period that does not meet the exclusion conditions is determined from the initial time period.

[0151] Optionally, the processor may also be configured to perform the following steps via a computer program: determining multiple aiming targets and a first aiming degree of the first virtual character towards the second virtual character based on game data at multiple times, wherein the aiming target is used to characterize the virtual character being aimed at by the first virtual character, and the first aiming degree is used to characterize the angle between the orientation of the first virtual character and the second virtual character; determining an effective attention period from a first preset time period based on the aiming targets at multiple times, wherein the aiming target during the effective attention period is the second virtual character; and determining an initial time period from the effective attention period based at least on the first aiming degree, wherein the first aiming degree during the initial time period satisfies a preset condition.

[0152] Optionally, the processor may also be configured to perform the following steps via a computer program: determining the time interval between the start time and the target time of the effective attention period, and the average value of the first targeting degree within the effective attention period; determining an initial time period from within the effective attention period based on the average value and the time interval, wherein the average value within the initial time period is greater than a preset value, and the time interval is greater than a preset interval.

[0153] Optionally, the processor may also be configured to perform the following steps via a computer program: determining a first length of an effective attention period, the average value of the cosine of the first aiming degree within the effective attention period, and the amount of change of the cosine of the first aiming degree within the effective attention period; and determining an initial time period from within the effective attention period based on the first length, the average value, and the amount of change, wherein the first length of the initial time period is greater than a preset length, the average value is greater than a preset value, and the amount of change is greater than a preset amount of change.

[0154] Optionally, the processor may also be configured to perform the following steps via a computer program: determining the average value of the cosine of the first aiming degree within the effective attention period; determining an effective aiming period based on the average value, wherein the average value within the effective aiming period is greater than a preset value; obtaining the ratio of the second length of the effective aiming period to the preset length of the first preset period to obtain the aiming rate of the effective aiming period; and determining an initial period based on the aiming rate within the effective aiming period, wherein the aiming rate within the initial period is greater than a preset aiming rate.

[0155] Optionally, the processor may also be configured to perform the following steps via a computer program: obtain a preset frequency corresponding to the abnormal behavior; if the detection frequency is greater than or equal to the preset frequency, determine that the detection result is that the first virtual character is the target virtual character; if the detection frequency is less than the preset frequency, determine that the detection result is that the first virtual character is not the target virtual character.

[0156] In the electronic device of this embodiment, game data of the first virtual character at multiple moments in a single game is acquired, and the game data at multiple moments is matched with the detection conditions corresponding to abnormal behavior to determine the target time period in the single game. Then, the target time period can be statistically analyzed to determine the detection frequency of abnormal behavior. Based on the detection frequency of abnormal behavior, the detection result of the first virtual character can be obtained, confirming that the first virtual character is using cheats to cheat in the game. This achieves the technical effect of identifying cheaters in the game, thereby solving the technical problem of the large number of cheats in FPS games affecting the gaming experience of honest players.

[0157] Figure 24 This is a schematic diagram of an electronic device according to an embodiment of the present disclosure. Figure 24 As shown, the electronic device 2400 is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0158] like Figure 24 As shown, the electronic device 2400 is presented in the form of a general-purpose computing device. The components of the electronic device 2400 may include, but are not limited to: at least one processor 2410, at least one memory 2420, a bus 2430 connecting different system components (including memory 2420 and processor 2410), and a display 2440.

[0159] The memory 2420 stores program code that can be executed by the processor 2410, causing the processor 2410 to perform the steps described in the method section of the embodiments of this disclosure according to various exemplary implementations of this disclosure.

[0160] The memory 2420 may include a readable medium in the form of volatile memory cells, such as random access memory (RAM) 24201 and / or cache memory 24202, and may further include read-only memory (ROM) 24203, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.

[0161] In some instances, memory 2420 may also include programs / utilities 24204 having a set (at least one) of program modules 24205, including but not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Memory 2420 may further include memory remotely located relative to processor 2410, which can be connected to electronic device 2400 via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0162] Bus 2430 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, peripheral bus, graphics acceleration port, processor 2410, or a local bus using any of the various bus structures.

[0163] The display 2440 may be, for example, a touch screen liquid crystal display (LCD) that allows a user to interact with the user interface of the electronic device 2400.

[0164] Optionally, the electronic device 2400 can also communicate with one or more external devices 2500 (e.g., keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 2400, and / or any device that enables the electronic device 2400 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via the input / output (I / O) interface 2450. Furthermore, the electronic device 2400 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via the network adapter 2460. Figure 24 As shown, network adapter 2460 communicates with other modules of electronic device 2400 via bus 2430. It should be understood that, although... Figure 24 As not shown, other hardware and / or software modules may be used in conjunction with electronic device 2400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0165] The aforementioned electronic device 2400 may further include: a keyboard, a cursor control device (such as a mouse), an input / output interface (I / O interface), a network interface, a power supply, and / or a camera.

[0166] Those skilled in the art will understand that Figure 24 The structure shown is for illustrative purposes only and does not limit the structure of the electronic device described above. For example, the electronic device 2400 may also include components that are more... Figure 24 The more or fewer components shown, or having the same Figure 1 Different configurations are shown. The memory 2420 can be used to store computer programs and corresponding data, such as the computer program and corresponding data corresponding to the virtual character detection method in this embodiment. The processor 2410 executes various functional applications and data processing by running the computer program stored in the memory 2420, thereby implementing the aforementioned virtual character detection method.

[0167] The sequence numbers of the embodiments disclosed above are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0168] In the above embodiments of this disclosure, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0169] In the several embodiments provided in this disclosure, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0170] 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 units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0171] Furthermore, the functional units in the various embodiments of this disclosure 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 as a software functional unit.

[0172] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0173] The above description is only a preferred embodiment of this disclosure. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principles of this disclosure, and these improvements and modifications should also be considered within the scope of protection of this disclosure.

Claims

1. A method for detecting virtual characters, characterized in that, include: Acquire game data of the first virtual character at multiple points in a single game; The game data from the multiple time points are matched with the detection conditions corresponding to the abnormal behavior to determine the target time period in the single game, wherein the game data within the target time period successfully matches the detection conditions. The target time period is statistically analyzed to determine the detection frequency of the abnormal behavior, wherein the detection frequency is used to characterize the number of times the abnormal behavior is detected in a single game. Based on the detection frequency of the abnormal behavior, the detection result of the first virtual character is obtained, wherein the detection result is used to characterize whether the first virtual character is the target virtual character; The detection conditions include: judgment conditions and exclusion conditions. Matching the game data from the multiple time points with the detection conditions corresponding to the abnormal behavior determines the target time period within a single game session, including: Based on the game data at the multiple moments, a target moment is determined among the multiple moments. The target moment is used to characterize the moment when the second virtual character first becomes visible relative to the first virtual character, or when the first virtual character successfully performs a shooting operation on the second virtual character. The visible state is determined by rendering detection. Based on the game data at the multiple times, an initial time period that meets the judgment condition is determined from a first preset time period before the target time, wherein the first preset time period is the time period from the initial time to the time period between the first virtual character and the second virtual character becoming visible; Based on the game data at the multiple times and the exclusion criteria, the target time period that does not meet the exclusion criteria is determined from the initial time period, wherein the exclusion criteria are used to exclude the normal behavior of the first virtual character.

2. The method of claim 1, wherein, Based on the game data from the multiple moments, the initial time period that satisfies the determination condition is determined from the first preset time period before the target time, including: Based on the game data at the multiple moments, the aiming targets at the multiple moments are determined, and the first aiming degree of the first virtual character towards the second virtual character is determined, wherein the aiming target is used to represent the virtual character being aimed at by the first virtual character, and the first aiming degree is used to represent the angle between the orientation of the first virtual character and the second virtual character. Based on the multiple targeting moments, an effective attention period is determined from the first preset time period, wherein the targeting moment within the effective attention period is the second virtual character; Based at least on the first aiming degree, the initial time period is determined from the effective attention time period, wherein the first aiming degree within the initial time period satisfies a preset condition.

3. The method of claim 2, wherein, Determining the initial time period from the effective attention period, at least based on the first targeting level, includes: Determine the time interval between the start time of the effective attention period and the target time, and the average value of the first aiming degree within the effective attention period; Based on the average value and the time interval, the initial time period is determined from the effective attention period, wherein the average value within the initial time period is greater than a preset value, and the time interval is greater than a preset interval.

4. The method of claim 2, wherein, Determining the initial time period from the effective attention period, at least based on the first targeting level, includes: Determine the first length of the effective attention period, the average value of the cosine of the first aiming degree within the effective attention period, and the amount of change of the cosine of the first aiming degree within the effective attention period. Based on the first length, the average value, and the amount of change, the initial time period is determined from the effective attention time period, wherein the first length in the initial time period is greater than a preset length, the average value is greater than a preset value, and the amount of change is greater than a preset amount of change.

5. The method of claim 2, wherein, Determining the initial time period from the effective attention period, at least based on the first targeting level, includes: Determine the average value of the cosine of the first aiming degree within the effective attention period; Based on the average value, an effective targeting time period is determined from the effective attention time period, wherein the average value within the effective targeting time period is greater than a preset value; The ratio of the second length of the effective aiming time period to the preset length of the first preset time period is obtained to obtain the aiming rate of the effective aiming time period; Based on the aiming rate, the initial time period is determined from the effective aiming time period, wherein the aiming rate within the initial time period is greater than the preset aiming rate.

6. The method of claim 1, wherein, Based on the game data from the multiple moments, the initial time period that satisfies the determination condition is determined from the first preset time period before the target time, including: Based on the game data at the multiple moments, the shooting moment within the first preset time period and the second aiming degree of the first virtual character towards the second virtual character within the second preset time period before the shooting moment are determined. The shooting moment is used to characterize the moment when the first virtual character performs a shooting operation on the second virtual character within the first preset time period, and the second aiming degree is used to characterize the angle between the orientation of the first virtual character and the second virtual character. Based on the second aiming degree, the initial time period is determined from the second preset time period, wherein the cosine value of the second aiming degree in the initial time period is greater than the cosine value of the first preset degree.

7. The method of claim 1, wherein, Based on the game data from the multiple moments, the initial time period that satisfies the determination condition is determined from the first preset time period before the target time, including: Based on game data within the first preset time period, the third aiming degree of the first virtual character toward the second virtual character and the movement distance of the second virtual character are determined, wherein the third aiming degree is used to characterize the angle between the orientation of the first virtual character and the second virtual character; Based on the third aiming degree and the movement distance, the initial time period is determined from the first preset time period, wherein the third aiming degree in the initial time period is greater than the second preset degree, and the movement distance is less than the preset distance.

8. The method of claim 1, wherein, Based on the detection frequency of the abnormal behavior, the detection result of the first virtual character is obtained, including: Obtain the preset frequency corresponding to the abnormal behavior; If the detection frequency is greater than or equal to the preset frequency, the detection result is determined to be that the first virtual character is the target virtual character; If the detection frequency is less than the preset frequency, the detection result is determined to be that the first virtual character is not the target virtual character.

9. A virtual character detection apparatus characterized by comprising: include: The acquisition module is used to acquire game data of the first virtual character at multiple moments in a single game. The matching module is used to match the game data at the multiple times with the detection conditions corresponding to the abnormal behavior to determine the target time period in the single game. The game data within the target time period is successfully matched with the detection conditions, which include: judgment conditions and exclusion conditions. The statistics module is used to perform statistics on the target time period and determine the detection frequency of the abnormal behavior, wherein the detection frequency is used to characterize the number of times the abnormal behavior is detected in a single game. The determination module is used to obtain the detection result of the first virtual character based on the detection frequency of the abnormal behavior, wherein the detection result is used to characterize whether the first virtual character is the target virtual character; The matching module is further configured to determine a target time among the multiple time points based on the game data at the multiple time points, wherein the target time point is used to characterize the moment when the second virtual character first becomes visible relative to the first virtual character, or when the first virtual character successfully performs a shooting operation on the second virtual character, and the visible state is determined by rendering detection; based on the game data at the multiple time points, an initial time period that meets the judgment condition is determined from a first preset time period before the target time point, wherein the first preset time period is the time period from the initial time point to when the first virtual character and the second virtual character become visible; based on the game data at the multiple time points and the exclusion condition, a target time period that does not meet the exclusion condition is determined from the initial time period, wherein the exclusion condition is used to exclude normal behavior of the first virtual character.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the virtual character detection method according to any one of claims 1 to 8 when run by a processor. 11.An electronic device comprising a memory and a processor, the electronic device characterized by, The memory stores a computer program, and the processor is configured to run the computer program to perform the virtual character detection method according to any one of claims 1 to 8.

Images