A hotspot gathering position prediction method, device, equipment and storage medium

Abstract

The application discloses a hotspot gathering position prediction method, device, equipment and storage medium. After entering a target game, position information of a virtual character in a game map of the target game is obtained, and then the game map is detected according to the position information of the virtual character to obtain a plurality of feasible nodes for movement of the virtual character in the game map, and movement of the virtual character in the game map is started from a position identified by the position information. Then, for each feasible node in the plurality of feasible nodes, a heat influence factor of each feasible node is evaluated to determine a target hotspot gathering position from the plurality of feasible nodes. The target hotspot gathering position can better reflect real player behavior in the target game, so that the target hotspot gathering position can be used to more accurately perform game performance tests such as map balance test and path planning. In addition, the data processing amount is reduced, and the exploration efficiency of the game map is improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, device, and storage medium for predicting hotspot cluster locations. Background Technology

[0002] With the rapid development of science and technology, the gaming industry, as a benchmark product of the internet, has also experienced rapid growth. Battle games, in particular, are increasingly popular among users due to their higher playability and entertainment value.

[0003] Before a battle game is launched, it may be necessary to conduct game map balance analysis, battle path planning, and simulate multiplayer battle behavior based on the exploration of the game map, in order to conduct game performance testing and achieve automation of the battle game. In related technologies, a graph structure of feasible regions can be constructed by diffuse ray detection, then the graph structure of feasible regions can be refined by 3D skeleton lines, most of the movement nodes can be deleted, and finally the movement paths can be generated by path planning.

[0004] However, this method only traverses the game map and fails to reflect real player behavior in competitive games, potentially affecting the accuracy of game performance testing. Furthermore, as the number and complexity of game maps increase, traversing the map significantly reduces exploration efficiency, further impacting the efficiency of game performance testing. Summary of the Invention

[0005] To address the aforementioned technical issues, this application provides a method, apparatus, device, and storage medium for predicting hotspot cluster locations. Target hotspot cluster locations better reflect real player behavior in the target game; therefore, using target hotspot cluster locations allows for more accurate map balance testing, path planning, and other related game performance tests. Furthermore, it reduces data processing volume, improves the efficiency of game map exploration, and consequently enhances the efficiency of game performance testing.

[0006] The embodiments of this application disclose the following technical solutions:

[0007] On one hand, embodiments of this application provide a method for predicting hotspot cluster locations, the method comprising:

[0008] After entering the target game, obtain the location information of the virtual character on the game map of the target game;

[0009] Based on the location information of the virtual character, feasible point detection is performed on the game map to obtain multiple feasible nodes for the virtual character to move in the game map. The movement of the virtual character in the game map starts from the position identified by the location information.

[0010] For each of the plurality of feasible nodes, a heat impact factor is evaluated for each feasible node to determine the target hotspot cluster location from the plurality of feasible nodes. The heat impact factor includes a combination of one or more of the following factors: number of nodes in view, safety factor, task completion factor, and resource utilization factor.

[0011] On one hand, this application provides an embodiment of a hotspot aggregation location prediction device, the device comprising an acquisition unit, a detection unit, and a determination unit:

[0012] The acquisition unit is used to acquire the location information of the virtual character in the game map of the target game after entering the target game;

[0013] The detection unit is used to perform feasible point detection on the game map based on the location information of the virtual character, and obtain multiple feasible nodes for the virtual character to move in the game map. The movement of the virtual character in the game map starts from the position identified by the location information.

[0014] The determining unit is used to evaluate the heat influence factor for each of the plurality of feasible nodes, so as to determine the target hot spot cluster location from the plurality of feasible nodes. The heat influence factor includes a combination of one or more influence factors such as the number of nodes in the field of view, safety factor, task completion factor, and resource utilization factor.

[0015] On one hand, embodiments of this application provide a computer device, the computer device including a processor and a memory:

[0016] The memory is used to store program code and transmit the program code to the processor;

[0017] The processor is configured to execute the method described in any of the foregoing aspects according to the instructions in the program code.

[0018] In one aspect, embodiments of this application provide a computer-readable storage medium for storing program code for performing the methods described in any of the foregoing aspects.

[0019] On one hand, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method described in any of the foregoing aspects.

[0020] As can be seen from the above technical solutions, in competitive games, the playability and appeal are largely reflected in the combat (e.g., gunfights, firefights, etc.), and combat often takes place in advantageous positions (which can be called hotspot clustering locations). Therefore, hotspot clustering locations better reflect the actual player behavior in competitive games. Thus, in this application, to more realistically reflect player behavior for game performance testing, after entering the target game, the location information of the virtual character on the game map can be obtained. Then, based on the virtual character's location information, feasible point detection is performed on the game map to obtain multiple feasible nodes for the virtual character to move within the game map. The virtual character's movement on the game map starts from the location identified by the location information. Then, for each of the multiple feasible nodes, a heat impact factor is evaluated to determine the target hotspot clustering location from among the multiple feasible nodes. The target hotspot clustering location better reflects the actual player behavior in the target game; therefore, using the target hotspot clustering location allows for more accurate map balance testing, path planning, and other related game performance tests. In addition, instead of traversing the game map, the target hotspot cluster location is selected from feasible nodes in the game map when predicting the target hotspot cluster location. This reduces the amount of data processing, improves the exploration efficiency of the game map, and thus improves the efficiency of game performance testing. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A schematic diagram of a game scene provided in an embodiment of this application;

[0023] Figure 2 An application scenario architecture diagram of a method for predicting hotspot cluster locations provided in an embodiment of this application;

[0024] Figure 3 A flowchart illustrating a method for predicting hotspot cluster locations provided in an embodiment of this application;

[0025] Figure 4 A schematic diagram illustrating the principle of multilayer X-ray detection provided in this application embodiment;

[0026] Figure 5 A schematic diagram illustrating the collision between the first detection ray and the surface of an obstacle, provided in an embodiment of this application;

[0027] Figure 6 An example diagram illustrating a method for determining the number of field-of-view nodes provided in an embodiment of this application;

[0028] Figure 7 An example diagram illustrating a sudden change in the number of field-of-view nodes provided in an embodiment of this application;

[0029] Figure 8 A flowchart illustrating another method for predicting hotspot cluster locations provided in an embodiment of this application;

[0030] Figure 9 A structural diagram of a hotspot aggregation location prediction device provided in an embodiment of this application;

[0031] Figure 10 A structural diagram of a terminal provided in an embodiment of this application;

[0032] Figure 11 This is a structural diagram of a server provided in an embodiment of this application. Detailed Implementation

[0033] The embodiments of this application will now be described with reference to the accompanying drawings.

[0034] Fighting games are a type of game with higher playability and fun. The game scenes for fighting games can be seen in... Figure 1 As shown, Figure 1 The game scene shown can be provided by a game map. A game map, also known as a game world or scene map, refers to the specific game scene provided to virtual characters. A game map typically includes scene elements such as roads, buildings, obstacles, rivers, mountains, trees, and bushes. Furthermore, the game map can contain game missions, which are purposefully designed to guide players through game activities, such as defusing bombs or eliminating opponents. The game map can also contain resources, such as items to collect in the game, including offensive tools, ammunition, bandages, and body armor.

[0035] Before a battle game is launched, it may be necessary to conduct game map balance analysis, battle path planning, and simulate multiplayer battle behavior based on the exploration of the game map, so as to conduct game performance testing and realize the automation of the battle game.

[0036] The exploration methods provided by the relevant technologies only involve traversing the game map, which makes it difficult to reflect real player behavior in combat games, and may thus affect the accuracy of game performance testing. Furthermore, as game maps increase in number and complexity, traversing the game map significantly reduces exploration efficiency, thereby impacting the efficiency of game performance testing.

[0037] To address the aforementioned technical problems, this application provides a method for predicting hotspot clustering locations. This method considers that the playability and appeal of combat games lie primarily in combat (e.g., gunfights, firefights, etc.), and combat often takes place in advantageous positions (which can be termed hotspot clustering locations). Therefore, hotspot clustering locations better reflect real player behavior in combat games. Thus, this application can predict hotspot clustering locations and use the predicted locations for game map balance analysis, combat path planning, and simulating multiplayer combat behavior in multiplayer games, thereby facilitating game performance testing.

[0038] like Figure 2 As shown, Figure 2 An application scenario architecture diagram of a method for predicting hotspot cluster locations is shown. This application scenario may include a terminal 201, on which a target game can run. The target game mentioned in this application embodiment may include a network game, also known as an online game. Generally, it refers to a sustainable, individual, multi-user online game that uses the Internet as a transmission medium, a game server (GameServer) and the user's terminal 201 as game processing devices, and a game client (GameClient) running on the terminal 201 as an information interaction window, aiming to achieve entertainment, leisure, communication, and virtual achievements. The game client refers to a program that provides local game services to users participating in the network game, corresponding to the game server; the game server refers to a service device that provides data calculation, verification, storage, and forwarding functions for the game client. Furthermore, this application does not limit the type of online game in its embodiments; for example, the online game mentioned in this application can be a cloud game or a regular game, that is, the target game can be a cloud game or a regular game; the online game mentioned in this application can be any type of game such as action, adventure, role-playing, shooting, etc., that is, the target game can be any type of combat game such as action, adventure, role-playing, shooting, etc., or other types of games, and this application does not limit this.

[0039] When the target game is a regular game, the application scenario architecture diagram may only include terminal 201, that is, terminal 201 executes the method provided in the embodiments of this application; when the target game is a cloud game, the application scenario architecture diagram may also include a server, which may be a game server that provides cloud games. In this case, the method provided in the embodiments of this application may be executed by the server, or the method provided in the embodiments of this application may be executed by the server and terminal 201 in cooperation.

[0040] After entering the target game, terminal 201 can obtain the location information of the virtual character in the game map of the target game, and then perform feasible point detection on the game map based on the location information of the virtual character to obtain multiple feasible nodes for the virtual character to move in the game map. The movement of the virtual character in the game map starts from the position marked by the location information.

[0041] In this context, a virtual character refers to a virtual game character that a player has in the target game. Players can play the game by controlling the virtual character to move around the game map and perform tasks. This application does not limit the form of the virtual character; the virtual character can be a human character, an animal character, etc.

[0042] The game map includes feasible nodes, which can be nodes that the virtual character can reach. The way to reach them can include walking, jumping, etc. For example, it includes nodes in the game map that will not collide with the virtual character (such as nodes on the road in the game map).

[0043] There may be many feasible nodes in a game map, such as... Figure 2 The circles of different colors shown represent nodes, which are merely examples of some feasible nodes and do not constitute a limitation on the embodiments of this application. The target hotspot gathering location must be a location that virtual characters can reach and that meets the conditions for battle, where virtual characters gather to perform operations such as battles. Therefore, terminal 201 needs to filter target hotspot gathering locations from multiple feasible nodes. Specifically, terminal 201 can evaluate the heat influence factor for each feasible node among the multiple feasible nodes, thereby determining which feasible nodes are suitable for battles (e.g., ...). Figure 2 Nodes with grids are more suitable for battles, in order to determine the target hotspot cluster location from multiple feasible nodes.

[0044] Since target hotspot clusters better reflect real player behavior in the game, using them allows for more accurate testing of game map balance, path planning, and other related game performance metrics. Furthermore, instead of traversing the entire game map, target hotspot clusters are selected from feasible nodes, reducing data processing volume, increasing map exploration efficiency, and consequently improving the efficiency of game performance testing.

[0045] It should be noted that the methods provided in this application's embodiments may involve artificial intelligence (AI). AI is the theory, methods, technology, and application systems that utilize digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results. In other words, AI is a comprehensive technology within computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine capable of reacting in a manner similar to human intelligence. AI also studies the design principles and implementation methods of various intelligent machines, enabling them to possess perception, reasoning, and decision-making capabilities.

[0046] Artificial intelligence (AI) is a comprehensive discipline encompassing a wide range of fields, including both hardware and software technologies. Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies primarily include computer vision, speech processing, natural language processing, as well as machine learning / deep learning, autonomous driving, and intelligent transportation.

[0047] The methods provided in this application may involve computer vision technology, which is a science that studies how to enable machines to "see." More specifically, it refers to machine vision that uses cameras and computers to replace human eyes for target recognition, tracking, and measurement, and further performs image processing to create images more suitable for human observation or transmission to instruments for detection. Computer vision technology typically includes image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content / behavior recognition, 3D object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping (SLAM), autonomous driving, intelligent transportation, and other technologies. It also includes common biometric recognition technologies such as facial recognition and fingerprint recognition. This application primarily uses computer vision technology to identify feasible nodes from a game map, and then filters target hotspot clusters from these feasible nodes.

[0048] Next, with reference to the accompanying drawings, and taking the method provided in the embodiments of this application executed by a terminal as an example, the method for predicting hotspot cluster locations provided in the embodiments of this application will be described in detail. See also Figure 3 , Figure 3 A flowchart of a method for predicting hotspot cluster locations is shown, the method comprising:

[0049] S301. After entering the target game, obtain the location information of the virtual character in the game map of the target game.

[0050] In competitive games, the playability and appeal primarily stem from the combat itself (e.g., gunfights, firefights), which often takes place in advantageous positions (often referred to as hotspots). Therefore, these hotspots more accurately reflect real player behavior within the target game. Consequently, in this application, to more realistically reflect player behavior and facilitate game performance testing, the terminal can obtain the virtual character's location information on the game map after entering the target game. This location information can be obtained through the target game's interface.

[0051] S302. Based on the location information of the virtual character, perform feasible point detection on the game map to obtain multiple feasible nodes for the virtual character to move in the game map. The movement of the virtual character in the game map starts from the position identified by the location information.

[0052] After obtaining the current location information of the virtual character, the terminal can perform feasible point detection on the game map based on the location information to obtain multiple feasible nodes for the virtual character to move on the game map.

[0053] In one possible implementation, feasible point detection can be achieved through raycasting. Raycasting involves emitting a ray from one point (i.e., the ray's origin) towards another point or in one direction. If it collides with an obstacle, it returns the collision point information; otherwise, it continues raycasting downwards.

[0054] By using ray detection, it is possible to predict hotspot cluster locations without building a large-scale database or having external big data support, through the engine's basic functions such as ray detection.

[0055] It should be noted that in this embodiment, ray detection can be performed on the entire game map. However, in some cases, based on the current location information of the virtual character, the virtual character may only move within a certain range. In this case, to improve the efficiency of ray detection, ray detection can be performed only in a feasible area, such as the target feasible area.

[0056] Meanwhile, the key to ray detection lies in the ray origin. Based on this, the way to obtain multiple feasible nodes for the virtual character to move in the game map by detecting feasible points based on the virtual character's position information can be to determine the target feasible area based on the virtual character's position information and determine the first ray origin based on the virtual character's character height. A first detection ray is then emitted from the first ray origin to the target feasible area to detect feasible points and obtain multiple feasible nodes.

[0057] It is understandable that the target feasible area can be an area of ​​various shapes, such as a square, rectangle, circle, etc.; the size of the target feasible area can be set according to the actual game scene, for example, it can be set according to the size of the minimap of the game map in the game scene.

[0058] Furthermore, there are many ways to determine the target feasible area based on location information, and the method may vary depending on the shape of the target feasible area. For example, if the target feasible area is a square, then a square area with a fixed side length (e.g., 200 meters) centered on the location indicated by the location information can be determined as the target feasible area; similarly, if the target feasible area is circular, then a circular area with a fixed diameter (e.g., 200 meters) centered on the location indicated by the location information can be determined as the target feasible area. The above methods for determining the target feasible area are merely examples and do not constitute a limitation of this application.

[0059] The height of a virtual character can be the height it appears to be in the game scene. Since virtual characters may need to hide, attack, move, jump, etc., to adapt to changes in the game scene and task requirements, the virtual character may appear in various postures at the location indicated by the location information, such as lying down, kneeling, or standing. Different postures will result in different perceived heights, meaning the character's height may vary. Therefore, in one possible implementation, the terminal can also obtain the posture type of the virtual character at the location indicated by the location information. Different posture types can correspond to different character heights, thus determining the character height based on the posture type.

[0060] In this way, the height of the virtual character can be determined more accurately, thereby accurately determining the starting point of the first ray and improving the detection accuracy of ray detection.

[0061] The key to X-ray detection lies in the ray initiation point. The detection ray emitted for feasibility point detection can be called the first detection ray, and therefore the ray initiation point corresponding to the first detection ray can be called the first ray initiation point. The method for determining the first ray initiation point will be introduced next.

[0062] In one possible implementation, the character height of the virtual character can be determined as the height of the first ray starting point, that is, the first ray starting point is set at a height equal to the height of the first ray starting point.

[0063] In another possible implementation, the target game's scene also includes obstacles, which are any virtual models other than the virtual characters. These virtual models can be items, buildings, environments, etc., that constitute the virtual world. Obstacles can include walls, boxes, plants, vehicles, ships, containers, and buildings. Not all obstacles are infeasible for the virtual characters; for example, buildings can be considered. In this case, to ensure more feasible nodes can be detected, the virtual character's height plus a preset height value can be used to determine the first ray starting point height. This preset height value exceeds the height of the tallest obstacle on the game map; that is, the first ray starting point is set at a height equal to the first ray starting point height. The preset height value can be set based on the actual height of the tallest obstacle on the game map. For example, based on the height of the tallest obstacle in a certain battle game, the preset height value could be set to 200 meters.

[0064] Because the preset height value exceeds the height of the tallest obstacle in the game map, the first detection ray emitted from the first ray point can perform ray detection on every obstacle, especially on each floor of a building. This allows for the detection of possible feasible nodes within obstacles, avoiding omissions of feasible nodes, improving the accuracy of ray detection, and better reflecting real player behavior.

[0065] Setting the first ray origin at a height equal to the height of the first ray origin can also be done in several ways. One method is to set multiple first ray origins on a plane at the same height as the first ray origin, thereby emitting dense detection rays. For example, the distance between each first ray origin is preset, and the plane is guaranteed to cover the feasible area of ​​the target. In this way, the first detection rays emitted from the multiple first ray origins can be parallel to each other and enter the feasible area of ​​the target from a vertical direction.

[0066] The preset interval can affect the efficiency of X-ray detection and the accuracy of subsequently determining the location of target hotspot clusters. Generally, a smaller preset interval results in lower X-ray detection efficiency but potentially higher accuracy in determining the location of target hotspot clusters; conversely, a smaller preset interval results in higher X-ray detection efficiency but potentially lower accuracy in determining the location of target hotspot clusters. Therefore, the preset interval should be set to achieve a balance between X-ray detection efficiency and the accuracy of determining the location of target hotspot clusters, or it can be adjusted according to actual needs, prioritizing either X-ray detection efficiency or the accuracy of determining the location of target hotspot clusters. Based on experience, in this embodiment, the preset interval can be set to, for example, 1 meter.

[0067] The second approach is to set the first ray starting point above the location indicated by the above location information, at a height equal to the height of the first ray starting point, and then emit the first detection ray from the first ray starting point in different directions so that the first detection ray covers the feasible area of ​​the target as much as possible.

[0068] It should be noted that, in order to ensure that the first detection ray can detect the lowest plane in the game map, the length of the first detection ray needs to be long enough so that the end of the first detection ray emanating from its starting point can touch the lowest plane in the game map. If the target feasible area is a square area with a side length of 200 meters centered on or with the location indicated by the location information as its vertex, and the starting height of the first ray is determined based on a preset height value of 200 meters, then the length of the first detection ray can be set to 400 meters to ensure that the end of the first detection ray can touch the lowest plane in the game map, thereby avoiding missing feasible nodes and improving the accuracy of feasible point detection.

[0069] Since the purpose of ray detection in this application embodiment is to detect feasible nodes, rather than simply detecting the existence of obstacles, the ray detection used in this application embodiment differs from conventional ray detection in order to ensure that each detection ray can detect all feasible nodes in the direction of its emission at once. This application embodiment employs multi-layer ray detection. That is, a first detection ray is emitted from the first ray starting point towards the target feasible area to detect feasible points. The method to obtain multiple feasible nodes is as follows: after the first detection ray is emitted downwards from the first ray starting point in the target feasible area, after the first detection ray first collides with an obstacle, it moves downwards a preset distance from the point of first collision, and uses the moved position as the new starting point of the first ray, continuing to emit the first detection ray downwards until the first detection ray finally collides with an obstacle. Then, the collision point information obtained during the emission of the first detection ray is returned all at once. This collision point information includes relevant information about all collision points hit by the first detection ray, and multiple feasible nodes can be determined based on this collision point information. The preset distance can be determined based on the thickness of the building. Typically, the preset distance needs to exceed the thickness of the building to ensure that the detected collision point is located on the feasible surface of the building as much as possible, thereby increasing the probability that the collision point is a feasible node.

[0070] See Figure 4 As shown, Figure 4This diagram illustrates the principle of a multi-layer ray detection system. The principle is that after the first detection ray initially collides with an obstacle, it does not return directly. Instead, it moves downwards by a preset distance of 0.5 meters (since the thickness of a building is generally no more than 0.5 meters, this preset distance can be set to 0.5 meters), and uses this new position as the new starting point for the first detection ray to continue firing downwards. If an obstacle is encountered a second time, the same method is used to continue detecting obstacles downwards, finally returning all detected collision point information. Figure 4 In the diagram, the white dot represents the point of collision. Figure 4 Taking three collision points as an example, from top to bottom they are the collision points of the first collision, the second collision, and the third collision.

[0071] By using multi-layer ray detection, each detection ray can detect all feasible nodes in the direction of its emission at once, reducing the possibility of missing feasible nodes and improving the efficiency and accuracy of feasible point detection.

[0072] Normally, since collision point information is used to determine feasible nodes, obtaining feasible nodes is actually obtaining the location of feasible nodes. Therefore, collision point information must include at least the location of the collision points.

[0073] In some cases, the obstacles encountered by the first detection ray can be of various types. For some types of obstacles, the virtual character cannot move on them, such as walls or rivers; while some obstacles, although movable from a type perspective, may have excessively steep slopes, making them impossible for the virtual character to climb. Considering the impact of these factors on the determination of feasible nodes, the collision point information can include an obstacle marker and the normal to the obstacle surface hit by the first detection ray. The obstacle marker indicates the type of obstacle, and the normal to the obstacle surface measures the slope of the obstacle surface. In this case, determining multiple feasible nodes based on the collision point information can be done by, for each collision point, if the obstacle marker indicates the obstacle is ground and the angle between the normal and the vertical direction is less than an angle threshold, then the collision point is determined as a feasible node.

[0074] See Figure 5 As shown, Figure 5 A schematic diagram showing the collision between the first detection ray and the surface of the obstacle is shown. Figure 5 If the obstacle indicated by the obstacle in the collision point information corresponding to the collision point is the ground, it means that the virtual character is very likely to move on the obstacle. If the angle between the normal of the obstacle surface and the vertical direction is less than the angle threshold, it can be considered that the slope of the obstacle surface where the collision point is located is small, and the virtual character can climb up. At this time, the collision point can be identified as a feasible node.

[0075] The obstacle markers can be numbers, symbols, names, etc., and the angle threshold can be set according to actual needs, such as 45 degrees.

[0076] Since most of the collision points on the ground are reachable by the virtual character, while many collision points on other obstacles are not reachable by the virtual character, in this embodiment of the application, only feasible nodes on the ground can be detected, and some feasible nodes on obstacles can be removed, thereby filtering out more feasible nodes that conform to the behavior of real players.

[0077] S303. For each of the plurality of feasible nodes, evaluate the heat influence factor for each feasible node to determine the target hotspot cluster location from the plurality of feasible nodes.

[0078] The terminal can evaluate the heat impact factor for each feasible node separately, and then determine the target hotspot cluster location from multiple feasible nodes based on the evaluation results. The heat impact factor can be an indicator to measure whether a feasible node is a hotspot cluster location.

[0079] The popularity influencing factor can include a combination of one or more of the following: number of visible nodes, safety factor, task completion factor, and resource utilization factor. The number of visible nodes refers to the number of nodes appearing within the virtual character's field of vision at a given feasible node, reflecting the ease with which the virtual character can observe the situation. The safety factor reflects the virtual character's safety at a given feasible node, such as the availability of support from friendly characters or attacks from enemy characters if a battle occurs at that node. The task completion factor indicates the ease with which a feasible node facilitates task completion, for example, through the distance from the feasible node to the task location. The resource utilization factor refers to the available resources at a feasible node, including resource type, quantity, and importance. The evaluation of different influencing factors will be discussed in detail later; it will not be elaborated upon here.

[0080] As can be seen from the above technical solutions, in competitive games, the playability and appeal are primarily reflected in the combat (e.g., gunfights, firefights, etc.), and combat often takes place in advantageous positions (which can be called hotspot clustering locations). Therefore, hotspot clustering locations better reflect real player behavior in competitive games. Thus, in this application, to more realistically reflect player behavior for game performance testing, after entering the target game, the location information of the virtual character on the game map can be obtained. Then, based on the virtual character's location information, feasible point detection is performed on the game map to obtain multiple feasible nodes for the virtual character to move from the location identified by the location information. Next, for each of these feasible nodes, a heat impact factor is evaluated to determine the target hotspot clustering location. Since the target hotspot clustering location better reflects real player behavior in competitive games, using it allows for more accurate map balance testing, path planning, and other related game performance tests. In addition, instead of traversing the game map, the target hotspot cluster location is selected from feasible nodes in the game map when predicting the target hotspot cluster location. This reduces the amount of data processing, improves the exploration efficiency of the game map, and thus improves the efficiency of game performance testing.

[0081] In one possible implementation, the popularity influencing factors include a combination of one or more of the following: number of visible nodes, safety factor, task completion factor, and resource utilization factor. In other words, in this embodiment, the evaluation of one or more popularity influencing factors can be used to measure which feasible nodes among multiple feasible nodes better meet the combat requirements of the target game, thereby selecting target hotspot locations for combat.

[0082] If the factors influencing popularity include multiple factors, then multiple feasible nodes can be comprehensively evaluated based on these factors to select the target hotspot cluster location. There are several ways to comprehensively evaluate multiple feasible nodes based on multiple factors to select the target hotspot cluster location. One method is for the terminal to evaluate each feasible node separately using different factors, obtaining multiple evaluation results for each feasible node. Then, for each feasible node, the multiple evaluation results are weighted according to the weights corresponding to different influence factors to obtain a comprehensive evaluation result for each feasible node. Finally, based on the comprehensive evaluation result of each feasible node, the terminal determines the target hotspot cluster location from the multiple feasible nodes.

[0083] For example, if multiple influencing factors include a first influencing factor (e.g., the number of nodes in the field of view) and a second influencing factor (e.g., a safety coefficient), then the first influencing factor can be evaluated separately for each feasible node to obtain a first evaluation result (i.e., a field of view score obtained by determining the number of nodes in the field of view), and the second influencing factor can be evaluated separately for each feasible node to obtain a second evaluation result (e.g., a safety score obtained by determining the safety coefficient, which can be the safety coefficient itself or other scoring methods). Then, based on the first weight of the first influencing factor and the second weight of the second influencing factor, the first evaluation result and the second evaluation result are weighted to obtain a comprehensive evaluation result for each feasible node. For example, the comprehensive evaluation result can be obtained by multiplying the first weight by the field of view score and then multiplying the second weight by the safety score. Then, feasible nodes with comprehensive evaluation results greater than a certain score threshold are selected from multiple feasible nodes as target hotspot clustering locations, or the comprehensive evaluation results are sorted in descending order, and the feasible nodes with the top N comprehensive evaluation results are selected as target hotspot clustering locations.

[0084] The second approach involves first evaluating each of the multiple feasible nodes using one impact factor, identifying multiple candidate hotspot clusters from these nodes. Then, evaluating each of these candidate hotspot clusters using another impact factor, and continuing this process to reduce the number of candidate hotspot clusters, until the final impact factor is evaluated. The target hotspot cluster is then determined from the latest candidate hotspot clusters. The order in which impact factors are evaluated can be based on a pre-set evaluation order or a pre-set priority, with evaluations performed in descending order of priority. The priority of impact factors can be set according to actual needs. For example, in a target game, the typical evaluation order for the aforementioned multiple impact factors is: first, evaluate the number of nodes in sight; then, evaluate the safety factor; then, evaluate the task completion factor; and finally, evaluate the resource utilization factor.

[0085] Of course, other evaluation orders can also be adopted. This application does not limit this. For example, the number of vision nodes can be evaluated first, then the security coefficient can be evaluated, and finally the task completion coefficient and resource utilization coefficient can be evaluated. Or, the number of vision nodes can be evaluated first, then the security coefficient, task completion coefficient and resource utilization coefficient can be evaluated, and so on.

[0086] When the heat index influencing factors include multiple factors, this embodiment uses a combination of a first influencing factor and a second influencing factor as an example to facilitate the description of the method for determining the target hotspot cluster location. The first influencing factor is one of the following: number of visible nodes, safety factor, task completion factor, and resource utilization factor. The second influencing factor is an influencing factor that differs from the first influencing factor among the following: number of visible nodes, safety factor, task completion factor, and resource utilization factor. In this case, the method for evaluating the heat index influencing factors for each feasible node to determine the target hotspot cluster location from multiple feasible nodes can be as follows: evaluate the first influencing factor for each feasible node to determine multiple candidate hotspot cluster locations. Then, evaluate the second influencing factor for each of the multiple candidate hotspot cluster locations to determine the target hotspot cluster location.

[0087] In this way, not all assessments are based on multiple feasible nodes. The objects to be assessed change from multiple feasible nodes to the candidate hotspot cluster locations obtained through screening. As a result, the number of objects to be assessed is continuously reduced, which greatly reduces the amount of data processing, improves assessment efficiency, and thus improves the efficiency of determining the target hotspot cluster locations.

[0088] When multiple influencing factors include a first influencing factor and a second influencing factor, the first influencing factor and the second influencing factor can be combinations of the aforementioned different influencing factors. The process of determining the target hotspot cluster location under different combinations will be described in detail below. It should be noted that since there may be many possible combinations, this embodiment will use several combinations as examples. The specific implementation methods for other combinations are similar to those described below, and therefore will not be described in detail.

[0089] The first combination could be the number of nodes in the field of view and the safety factor. Taking the number of nodes in the field of view as the first influencing factor and the safety factor as the second influencing factor as an example:

[0090] If the first influencing factor is the number of visible nodes, the method of evaluating the first influencing factor for each feasible node to determine multiple candidate hotspot cluster locations from multiple feasible nodes can be that the terminal determines the number of visible nodes for each feasible node. The number of visible nodes reflects the number of nodes appearing within the field of view at that feasible node. In target games, players usually control virtual characters to reach a position where they can both attack and defend, where the virtual character can hide and engage in combat with enemy characters at any time, such as a corner. The number of visible nodes at such positions is usually much different from other positions. Therefore, in this embodiment, the terminal can determine feasible nodes with a sudden change in the number of visible nodes as multiple candidate hotspot cluster locations.

[0091] It should be noted that, in this embodiment, ray detection can be used to determine the number of visual nodes for each feasible node. Specifically, for each feasible node, the terminal can determine the starting point of the second ray based on the location identified by the location information and the character height of the virtual character. Then, a second detection ray is emitted from the starting point of the second ray to other feasible nodes. The number of visual nodes for each feasible node is then determined based on the obstacle distribution detected by the second detection ray. The obstacle distribution indicates whether there are obstacles during the emission of the second detection ray to other feasible nodes. The character height in this embodiment is similar to the method for determining character height described above, and will not be elaborated further here.

[0092] Understandably, determining the starting point of the second ray based on the location identified by the location information and the virtual character's height could involve moving the location identified by the location information up by the character's height, thus using this as the starting point of the second ray. This simulates the player's perspective by assuming the virtual character has arrived at this feasible node and moving the character's height upwards. A second detection ray is then emitted from the second ray starting point to other feasible nodes (or the position at the moved character's height) to determine if there are obstacles between these two nodes. If no obstacles are found, it means that the feasible node is within the player's field of vision at that location. For example... Figure 6 As shown, the feasible nodes with grids are the feasible nodes for which the number of nodes in the field of view needs to be determined. Figure 6 If there are no obstacles between a white feasible node and another feasible node, then the white node is within the field of view. If there are obstacles between a black feasible node and another feasible node, then the black node is outside the field of view. This determines the number of nodes within the field of view of a feasible node with a grid, i.e., the number of nodes in the field of view.

[0093] It is understood that, in the embodiments of this application, there are many ways to determine whether the number of view nodes of a feasible node has changed abruptly. In one possible implementation, for each feasible node, the number of view nodes of that feasible node can be compared with the minimum number of view nodes among its neighboring feasible nodes. If the difference is greater than a certain threshold, it can be determined that the number of view nodes of that feasible node has changed abruptly. The certain threshold can be set according to actual needs or experience; for example, the certain threshold can be 5.

[0094] One method for determining adjacent feasible nodes is to identify other feasible nodes within the node range corresponding to the feasible node as adjacent feasible nodes. The methods for determining the node range can include various approaches. For example, other feasible nodes within a cube centered on the feasible node with a side length of a certain length (this certain length can be set according to actual needs or experience; for example, a certain length could be 1 meter) can be identified as adjacent feasible nodes. Another example is other feasible nodes within a sphere centered on the feasible node with a diameter of a certain length (this certain length can be set according to actual needs or experience; for example, a certain length could be 1 meter).

[0095] See Figure 7 As shown, Figure 7 An example diagram showing a sudden change in the number of nodes in the field of view is shown. In the diagram marked (b), the feasible node with a grid is the adjacent feasible node of the feasible node with a grid in the diagram marked (a). In the diagram marked (b), the number of nodes in the field of view of the feasible node with a grid is significantly more than that of its adjacent feasible nodes, that is, there are more black nodes. In other words, the number of nodes in the field of view of the feasible node with a grid has changed abruptly, so this feasible node is a candidate hotspot clustering location.

[0096] After identifying multiple candidate hotspot cluster locations, a second influencing factor can be further evaluated to determine the final target hotspot cluster location. If the second influencing factor includes a safety coefficient, in the target game, which is typically a multiplayer game, the game scene may include not only virtual characters but also friendly and enemy characters. Friendly characters can help the virtual characters in combat and protect their safety, while enemy characters pose a threat. In this case, evaluating the second influencing factor for each candidate hotspot cluster location to determine the target hotspot cluster location can be achieved by obtaining the first spawn location of the virtual character's friendly characters and the second spawn location of the virtual character's enemy characters. Generally, the closer a candidate hotspot cluster location is to friendly characters, the safer it is; the closer it is to enemy characters, the more dangerous it is, and the more likely it is to be surrounded and attacked by multiple enemy characters. Therefore, for each candidate hotspot cluster location, the terminal can determine a first distance between the candidate hotspot cluster location and the first birth location, and a second distance between the candidate hotspot cluster location and the second birth location, and then determine a safety factor for the candidate hotspot cluster location based on the first and second distances. Next, based on the safety factor of each candidate hotspot cluster location, the target hotspot cluster location is determined from the multiple candidate hotspot cluster locations.

[0097] The methods for determining the safety factor of candidate hotspot cluster locations based on the first distance and the second distance can include various approaches, such as subtracting the first distance from the second distance to obtain the safety factor, or dividing the second distance by the first distance to obtain the safety factor, and so on.

[0098] It is understandable that, based on the safety coefficient of each candidate hotspot cluster location, there can be multiple ways to determine the target hotspot cluster location from multiple candidate hotspot cluster locations. One way is to determine the candidate hotspot cluster location with a safety coefficient higher than a certain threshold as the target hotspot cluster location.

[0099] Another approach is to sort the candidate hotspot cluster locations in descending order of their safety coefficient, and then select the top N candidate hotspot cluster locations as the target hotspot cluster locations.

[0100] The second combination could be the number of visible nodes and the task completion coefficient. Taking the number of visible nodes as the first influencing factor and the task completion coefficient as the second influencing factor as an example, the method for determining multiple candidate hotspot cluster locations based on the number of visible nodes can be found in the aforementioned embodiments and will not be repeated here. If the second influencing factor includes the task completion coefficient, the method for evaluating each candidate hotspot cluster location using the second influencing factor to determine the target hotspot cluster location from multiple candidate hotspot cluster locations could be that the terminal determines the distance between each candidate hotspot cluster location and the task location, and then determines the task completion coefficient of the corresponding candidate hotspot cluster location based on the distance.

[0101] In the target game, it may not only involve combat but also the completion of various tasks, such as bomb disposal and rescue missions. Different tasks have corresponding mission locations. Since the mission completion coefficient reflects the ease with which a candidate hotspot cluster location facilitates mission completion, the closer the candidate hotspot cluster location is to the mission location, the higher the ease of completion and the larger the mission completion coefficient. Therefore, the target hotspot cluster location can be determined from multiple candidate hotspot cluster locations based on the mission completion coefficient of each candidate hotspot cluster location. The method of determining the target hotspot cluster location from multiple candidate hotspot cluster locations based on the mission completion coefficient is similar to the method described above for determining the target hotspot cluster location from multiple candidate hotspot cluster locations based on the safety coefficient, and will not be repeated here.

[0102] In objective-based games where tasks need to be completed, it is necessary to consider not only whether it is convenient to engage in combat, but also whether it is convenient to complete the task. By using the methods described above, we can identify target hotspots that meet the task requirements, thereby better simulating player behavior.

[0103] The third combination could be the number of visible nodes and the resource utilization coefficient. Taking the number of visible nodes as the first influencing factor and the resource utilization coefficient as the second influencing factor as an example, the method for determining multiple candidate hotspot cluster locations based on the number of visible nodes can be found in the aforementioned embodiments and will not be repeated here. If the second influencing factor includes the resource utilization coefficient, the method for evaluating each candidate hotspot cluster location using the second influencing factor to determine the target hotspot cluster location can be based on the resource situation of each candidate hotspot cluster location, determining the corresponding resource utilization coefficient. The resource situation can include resource type, resource quantity, resource importance, etc. Resource types can include, for example, ammunition, handheld attack tools, bandages, hemostatic agents, bulletproof vests, etc.

[0104] In the target game, virtual characters rely on virtual resources whether they are attacking or defending. For example, attacking may require ammunition and handheld attack tools, while defending may require bandages, hemostatic agents, and bulletproof vests. The more complete the types of resources, the greater the quantity, and the higher the importance of the resources in a candidate hotspot cluster location, the higher the resource utilization coefficient, which is more beneficial for the virtual characters in combat. Based on this, the terminal can determine the target hotspot cluster location from multiple candidate hotspot cluster locations according to the resource utilization coefficient of each candidate hotspot cluster location.

[0105] The above methods can identify target hotspots that meet resource usage needs, thereby better simulating player behavior.

[0106] It should be noted that the foregoing embodiments only illustrate the three combinations described above. Other combinations are also possible, but will not be described in detail in this application. However, when other combinations occur, the evaluation method for each influencing factor is similar to that described above, with only slight changes in the execution order and the selected objects.

[0107] Hotspot cluster location prediction is a crucial part of automation in combat games. Once the target hotspot cluster locations are obtained, they can be used for game map balance testing, path planning, and other related game performance tests. For example, in path planning, after obtaining the target hotspot cluster locations, it's necessary to determine the current target location for each virtual character. To cover as many target hotspot cluster locations as possible, after each virtual character spawns, the terminal can randomly select a target hotspot cluster location as the virtual character's target location and generate a movement path by calling the target game's navigation interface.

[0108] Compared to automated solutions based on path key points in related technologies, which require manual annotation of key points on the game map and manual maintenance of the data whenever the game map data changes, this solution eliminates the need for human intervention and automatically predicts the locations of target hotspots on the game map.

[0109] Compared to automated solutions based on recording and playback in related technologies, which require manual recording of game matches, this solution requires no human intervention and can automatically analyze target hotspot clusters in the game map, thereby controlling virtual characters to attack the target hotspot clusters.

[0110] For example, in game map balance testing, after obtaining the target hotspot cluster locations, the balance of the game map can be analyzed based on the number of target hotspot cluster locations and their distribution on the game map.

[0111] The above provides a detailed description of the hotspot clustering location prediction method provided in the embodiments of this application. Based on the above description, the embodiments of this application also provide a hotspot clustering location prediction method. This method uses a multi-layer ray detection method to detect the ground in the game map. It emits dense first detection rays from top to bottom. After colliding with an obstacle, the detection rays do not immediately return collision point information but continue to be emitted downwards, finally returning all collision point information. The ground in the game map can be located based on the collision information. For each feasible node on the ground, a second detection ray is emitted in all directions. The number of visible nodes is calculated based on the second detection ray. Simultaneously, a safety factor for different feasible nodes is calculated based on the first spawn position of friendly characters and the second spawn position of enemy characters. Finally, the target hotspot clustering location is determined based on the number of visible nodes and the safety factor. After generating the target hotspot clustering location, the navigation interface of the target game is called to control the virtual character to reach the target hotspot clustering location and start the battle, which can better simulate player behavior. See also Figure 8 , Figure 8 A flowchart of a method for predicting hotspot cluster locations is shown, the method comprising:

[0112] S801: The terminal determines multiple feasible nodes on the ground through multi-layer ray detection.

[0113] S802. For each feasible node, the terminal evaluates the number of nodes in the field of view and identifies feasible nodes where the number of nodes in the field of view changes abruptly as candidate hotspot clustering locations.

[0114] S803: The terminal assesses the security level for each candidate hotspot cluster location.

[0115] S804: The terminal selects the target hotspot cluster location from the candidate hotspot cluster locations based on the security factor.

[0116] S805: The terminal generates a movement path based on the target hotspot cluster location.

[0117] The specific implementation of S801-S805 can be based on Figure 3 As described in the corresponding embodiments, this application will not repeat the details.

[0118] It should be noted that, based on the implementation methods provided in the above aspects, this application can be further combined to provide more implementation methods.

[0119] based on Figure 3 Corresponding to the hotspot clustering location prediction method provided in the embodiments, this application also provides a hotspot clustering location prediction device 900. See also Figure 9 The hotspot cluster location prediction device 900 includes an acquisition unit 901, a detection unit 902, and a determination unit 903.

[0120] The acquisition unit 901 is used to acquire the location information of the virtual character in the game map of the target game after entering the target game;

[0121] The detection unit 902 is used to perform feasible point detection on the game map based on the location information of the virtual character, and obtain multiple feasible nodes for the virtual character to move in the game map. The movement of the virtual character in the game map starts from the position identified by the location information.

[0122] The determining unit 903 is used to evaluate the heat influence factor for each of the plurality of feasible nodes, so as to determine the target hot spot cluster location from the plurality of feasible nodes. The heat influence factor includes a combination of one or more influence factors such as the number of nodes in the field of view, safety factor, task completion factor, and resource utilization factor.

[0123] In one possible implementation, the detection unit 902 is specifically used for:

[0124] The feasible target area is determined based on the location information of the virtual character, and the starting point of the first ray is determined based on the character height of the virtual character;

[0125] After the first detection ray is emitted downward from the first ray starting point in the feasible area of ​​the target, after the first detection ray first collides with the obstacle, it moves downward by a preset distance from the point of first collision, and takes the moved position as the new starting point of the first ray, and continues to emit the first detection ray downward until the first detection ray finally collides with the obstacle.

[0126] Return the collision point information obtained during the emission of the first detection ray;

[0127] The plurality of feasible nodes are determined based on the collision point information.

[0128] In one possible implementation, the collision point information includes an obstacle marker and the normal to the surface of the obstacle where the first detection ray hits. The detection unit 902 is specifically used for:

[0129] For each collision point, if the obstacle marker indicates that the obstacle is the ground and the angle between the normal and the vertical direction is less than an angle threshold, the collision point is determined to be a feasible node.

[0130] In one possible implementation, the detection unit 902 is specifically used for:

[0131] The character height is added to a preset height value to determine the first ray starting point height, where the preset height value exceeds the height of the tallest obstacle in the game map.

[0132] Multiple first ray initiators are set at preset intervals at the height of the first ray initiator.

[0133] In one possible implementation, the acquisition unit 902 is further configured to:

[0134] Obtain the pose type of the virtual character at the location indicated by the location information;

[0135] The determining unit 903 is also used to determine the character height based on the posture type.

[0136] In one possible implementation, if the heat index influencing factor includes multiple influencing factors, and the multiple influencing factors include a first influencing factor and a second influencing factor, wherein the first influencing factor is one of the following: number of visible nodes, safety factor, task completion factor, and resource utilization factor, and the second influencing factor is an influencing factor that is different from the first influencing factor among the following: number of visible nodes, safety factor, task completion factor, and resource utilization factor, the determining unit 903 is specifically used for:

[0137] For each feasible node, a first influence factor is evaluated to determine multiple candidate hotspot cluster locations from the multiple feasible nodes;

[0138] The second influence factor is evaluated for each of the multiple candidate hotspot cluster locations to determine the target hotspot cluster location from the multiple candidate hotspot cluster locations.

[0139] In one possible implementation, the first influencing factor is the number of nodes in the field of view, and the determining unit 903 is specifically used for:

[0140] For each feasible node, determine the number of nodes in the field of view of that feasible node;

[0141] The feasible nodes where the number of nodes in the field of view changes abruptly are identified as the locations where the multiple candidate hotspots cluster.

[0142] In one possible implementation, the determining unit 903 is specifically used for:

[0143] For each feasible node, the starting point of the second ray is determined based on the location identified by the location information and the character height of the virtual character;

[0144] A second detection ray is emitted from the origin of the second ray to other feasible nodes;

[0145] Based on the obstacle distribution detected by the second detection ray, the number of visual nodes of the feasible node is determined, and the obstacle distribution indicates whether there are obstacles during the process of the second detection ray being emitted to the other feasible nodes.

[0146] In one possible implementation, the second influence factor includes a safety factor, and the determining unit 903 is specifically used for:

[0147] Obtain the first spawn position of the virtual character's friendly characters and the second spawn position of the virtual character's enemy characters;

[0148] For each candidate hotspot cluster location, a first distance is determined between the candidate hotspot cluster location and the first birth location, and a second distance is determined between the candidate hotspot cluster location and the second birth location;

[0149] The safety factor of the candidate hotspot cluster location is determined based on the first distance and the second distance;

[0150] The target hotspot cluster location is determined from the plurality of candidate hotspot cluster locations based on the safety factor of each candidate hotspot cluster location.

[0151] In one possible implementation, the second influencing factor includes a task completion coefficient, and the determining unit 903 is specifically used for:

[0152] Determine the distance between each candidate hotspot cluster location and the task location;

[0153] The task completion coefficient of the corresponding candidate hotspot cluster location is determined based on the distance.

[0154] The target hotspot cluster location is determined from the plurality of candidate hotspot cluster locations based on the task completion coefficient of each candidate hotspot cluster location.

[0155] In one possible implementation, the second influencing factor includes a resource utilization coefficient, and the determining unit 903 is specifically used for:

[0156] Based on the resource situation of each candidate hotspot cluster location, determine the resource utilization coefficient of the corresponding candidate hotspot cluster location;

[0157] The target hotspot cluster location is determined from the plurality of candidate hotspot cluster locations based on the resource utilization coefficient of each candidate hotspot cluster location.

[0158] In one possible implementation, if the heat index influencing factors include multiple influencing factors, the determining unit 903 is specifically used for:

[0159] For each feasible node, different influencing factors are evaluated to obtain multiple evaluation results for each feasible node;

[0160] For each feasible node, the multiple evaluation results of the feasible node are weighted according to the weights corresponding to different influencing factors to obtain the comprehensive evaluation result of the feasible node;

[0161] Based on the comprehensive evaluation results of each feasible node, the target hotspot cluster location is determined from the plurality of feasible nodes.

[0162] As can be seen from the above technical solutions, in competitive games, the playability and appeal are largely reflected in the combat (e.g., gunfights, firefights, etc.), and combat often takes place in advantageous positions (which can be called hotspot clustering locations). Therefore, hotspot clustering locations better reflect the actual player behavior in competitive games. Thus, in this application, to more realistically reflect player behavior for game performance testing, after entering the target game, the location information of the virtual character on the game map can be obtained. Then, based on the virtual character's location information, feasible point detection is performed on the game map to obtain multiple feasible nodes for the virtual character to move within the game map. The virtual character's movement on the game map starts from the location identified by the location information. Then, for each of the multiple feasible nodes, a heat impact factor is evaluated to determine the target hotspot clustering location from among the multiple feasible nodes. The target hotspot clustering location better reflects the actual player behavior in the target game; therefore, using the target hotspot clustering location allows for more accurate map balance testing, path planning, and other related game performance tests. In addition, instead of traversing the game map, the target hotspot cluster location is selected from feasible nodes in the game map when predicting the target hotspot cluster location. This reduces the amount of data processing, improves the exploration efficiency of the game map, and thus improves the efficiency of game performance testing.

[0163] This application also provides a computer device capable of executing a method for predicting hotspot cluster locations. This computer device can be, for example, a terminal, such as a smartphone.

[0164] Figure 10 The diagram shown is a block diagram of a portion of the structure of a smartphone provided in an embodiment of this application. (Reference) Figure 10 The smartphone includes components such as: a radio frequency (RF) circuit 1010, a memory 1020, an input unit 1030, a display unit 1040, a sensor 1050, an audio circuit 1060, a Wi-Fi module 1070, a processor 1080, and a power supply 1090. The input unit 1030 may include a touch panel 1031 and other input devices 1032; the display unit 1040 may include a display panel 1041; and the audio circuit 1060 may include a speaker 1061 and a microphone 1062. It is understood that... Figure 10 The smartphone structure shown does not constitute a limitation on smartphones and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0165] The memory 1020 can be used to store software programs and modules. The processor 1080 executes various functions and data processing of the smartphone by running the software programs and modules stored in the memory 1020. The memory 1020 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, applications required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the smartphone (such as audio data, phonebook, etc.). In addition, the memory 1020 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0166] The processor 1080 is the control center of the smartphone, connecting various parts of the smartphone via various interfaces and lines. It performs various functions and processes data by running or executing software programs and / or modules stored in the memory 1020 and by accessing data stored in the memory 1020. Optionally, the processor 1080 may include one or more processing units; preferably, the processor 1080 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 1080.

[0167] In this embodiment, the processor 1080 in the smartphone can perform the following steps:

[0168] After entering the target game, obtain the location information of the virtual character on the game map of the target game;

[0169] Based on the location information of the virtual character, feasible point detection is performed on the game map to obtain multiple feasible nodes for the virtual character to move in the game map. The movement of the virtual character in the game map starts from the position identified by the location information.

[0170] For each of the plurality of feasible nodes, a heat impact factor is evaluated for each feasible node to determine the target hotspot cluster location from the plurality of feasible nodes. The heat impact factor includes a combination of one or more of the following factors: number of nodes in view, safety factor, task completion factor, and resource utilization factor.

[0171] The computer device provided in this application embodiment can also be a server; please refer to [link to relevant documentation]. Figure 11 As shown, Figure 11The diagram illustrates the structure of a server 1100 provided in this embodiment. The server 1100 can vary significantly due to different configurations or performance characteristics. It may include one or more central processing units (CPUs) 1122 (e.g., one or more processors) and a memory 1132, and one or more storage media 1130 (e.g., one or more mass storage devices) for storing application programs 1142 or data 1144. The memory 1132 and storage media 1130 may be temporary or persistent storage. The program stored in the storage media 1130 may include one or more modules (not shown in the diagram), each module including a series of instruction operations on the server. Furthermore, the CPU 1122 may be configured to communicate with the storage media 1130 and execute the series of instruction operations stored in the storage media 1130 on the server 1100.

[0172] Server 1100 may also include one or more power supplies 1126, one or more wired or wireless network interfaces 1150, one or more input / output interfaces 1158, and / or one or more operating systems 1141, such as Windows Server. TM Mac OS X TM Unix TM Linux TM FreeBSD TM etc.

[0173] In this embodiment, the central processing unit 1122 in server 1100 can perform the following steps:

[0174] After entering the target game, obtain the location information of the virtual character on the game map of the target game;

[0175] Based on the location information of the virtual character, feasible point detection is performed on the game map to obtain multiple feasible nodes for the virtual character to move in the game map. The movement of the virtual character in the game map starts from the position identified by the location information.

[0176] For each of the plurality of feasible nodes, a heat impact factor is evaluated for each feasible node to determine the target hotspot cluster location from the plurality of feasible nodes. The heat impact factor includes a combination of one or more of the following factors: number of nodes in view, safety factor, task completion factor, and resource utilization factor.

[0177] According to one aspect of this application, a computer-readable storage medium is provided for storing program code for executing the hotspot clustering location prediction method described in the foregoing embodiments.

[0178] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in various optional implementations of the above embodiments.

[0179] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0180] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application 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 application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a 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.

[0181] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0182] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0183] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0184] 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 application, 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 computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0185] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for predicting hotspot cluster locations, characterized in that, The method includes: After entering the target game, obtain the location information of the virtual character on the game map of the target game; Based on the location information of the virtual character, feasible point detection is performed on the game map to obtain multiple feasible nodes for the virtual character to move in the game map. The movement of the virtual character in the game map starts from the position identified by the location information. For each of the multiple feasible nodes, a heat index influence factor is evaluated for each feasible node to determine the target hotspot cluster location from the multiple feasible nodes. The heat index influence factor includes a combination of one or more influence factors such as the number of visible nodes, safety factor, task completion factor, and resource utilization factor. The target hotspot cluster location is a location that is advantageous in battle and is used to reflect the real player behavior in the battle game. The number of field-of-view nodes refers to the number of nodes appearing within the field of view of a feasible node, which is used to characterize the convenience of the virtual character to observe the situation at the feasible node; the safety coefficient is used to characterize the safety level of the virtual character when a battle occurs at a feasible node; the task completion coefficient is used to characterize the convenience of a feasible node for completing a task; and the resource utilization coefficient is used to characterize the available resources at a feasible node.

2. The method according to claim 1, characterized in that, The step of performing feasible point detection on the game map based on the virtual character's position information to obtain multiple feasible nodes for the virtual character to move on the game map includes: The feasible target area is determined based on the location information of the virtual character, and the starting point of the first ray is determined based on the character height of the virtual character; After the first detection ray is emitted downward from the first ray starting point in the feasible area of ​​the target, after the first detection ray first collides with the obstacle, it moves downward by a preset distance from the point of first collision, and takes the moved position as the new starting point of the first ray, and continues to emit the first detection ray downward until the first detection ray finally collides with the obstacle. Return the collision point information obtained during the emission of the first detection ray; The plurality of feasible nodes are determined based on the collision point information.

3. The method according to claim 2, characterized in that, The collision point information includes obstacle markers and the normal to the surface of the obstacle hit by the first detection ray. Determining the plurality of feasible nodes based on the collision point information includes: For each collision point, if the obstacle marker indicates that the obstacle is the ground and the angle between the normal and the vertical direction is less than an angle threshold, the collision point is determined to be a feasible node.

4. The method according to claim 2, characterized in that, Determining the starting point of the first ray based on the character height of the virtual character includes: The character height is added to a preset height value to determine the first ray starting point height, where the preset height value exceeds the height of the tallest obstacle in the game map. Multiple first ray initiation points are set at preset intervals at the height of the first ray initiation point.

5. The method according to any one of claims 2-4, characterized in that, The method further includes: Obtain the pose type of the virtual character at the location indicated by the location information; The character height is determined based on the posture type.

6. The method according to claim 1, characterized in that, If the heat index influencing factors include multiple influencing factors, and the multiple influencing factors include a first influencing factor and a second influencing factor, wherein the first influencing factor is one of the following: number of visible nodes, safety factor, task completion factor, and resource utilization factor, and the second influencing factor is an influencing factor that is different from the first influencing factor among the following: the step of evaluating the heat index influencing factors for each feasible node to determine the target hotspot cluster location from the multiple feasible nodes includes: For each feasible node, a first influence factor is evaluated to determine multiple candidate hotspot cluster locations from the multiple feasible nodes; The second influence factor is evaluated for each of the multiple candidate hotspot cluster locations to determine the target hotspot cluster location from the multiple candidate hotspot cluster locations.

7. The method according to claim 6, characterized in that, The first influence factor is the number of nodes in the field of view. The step of evaluating the first influence factor for each feasible node to determine multiple candidate hotspot cluster locations from the multiple feasible nodes includes: For each feasible node, determine the number of nodes in the field of view of that feasible node; The feasible nodes where the number of nodes in the field of view changes abruptly are identified as the locations where the multiple candidate hotspots cluster.

8. The method according to claim 7, characterized in that, Determining the number of visible nodes for each feasible node includes: For each feasible node, the starting point of the second ray is determined based on the location identified by the location information and the character height of the virtual character; A second detection ray is emitted from the origin of the second ray to other feasible nodes; Based on the obstacle distribution detected by the second detection ray, the number of visual nodes of the feasible node is determined, and the obstacle distribution indicates whether there are obstacles during the process of the second detection ray being emitted to the other feasible nodes.

9. The method according to claim 6, characterized in that, The second influence factor includes a safety factor. The evaluation of the second influence factor for each of the plurality of candidate hotspot cluster locations to determine the target hotspot cluster location from the plurality of candidate hotspot cluster locations includes: Obtain the first spawn position of the virtual character's friendly characters and the second spawn position of the virtual character's enemy characters; For each candidate hotspot cluster location, a first distance is determined between the candidate hotspot cluster location and the first birth location, and a second distance is determined between the candidate hotspot cluster location and the second birth location; The safety factor of the candidate hotspot cluster location is determined based on the first distance and the second distance; The target hotspot cluster location is determined from the plurality of candidate hotspot cluster locations based on the safety factor of each candidate hotspot cluster location.

10. The method according to claim 6, characterized in that, The second influence factor includes a task completion coefficient. The evaluation of the second influence factor for each of the plurality of candidate hotspot cluster locations to determine the target hotspot cluster location from the plurality of candidate hotspot cluster locations includes: Determine the distance between each candidate hotspot cluster location and the task location; The task completion coefficient of the corresponding candidate hotspot cluster location is determined based on the distance. The target hotspot cluster location is determined from the plurality of candidate hotspot cluster locations based on the task completion coefficient of each candidate hotspot cluster location.

11. The method according to claim 6, characterized in that, The second influencing factor includes a resource utilization coefficient. The evaluation of the second influencing factor for each of the plurality of candidate hotspot cluster locations to determine the target hotspot cluster location from the plurality of candidate hotspot cluster locations includes: Based on the resource situation of each candidate hotspot cluster location, determine the resource utilization coefficient of the corresponding candidate hotspot cluster location; The target hotspot cluster location is determined from the plurality of candidate hotspot cluster locations based on the resource utilization coefficient of each candidate hotspot cluster location.

12. The method according to claim 1, characterized in that, If the heat index influencing factors include multiple influencing factors, the step of evaluating the heat index influencing factors for each feasible node to determine the target hotspot cluster location from the multiple feasible nodes includes: For each feasible node, different influencing factors are evaluated to obtain multiple evaluation results for each feasible node; For each feasible node, the multiple evaluation results of the feasible node are weighted according to the weights corresponding to different influencing factors to obtain the comprehensive evaluation result of the feasible node; Based on the comprehensive evaluation results of each feasible node, the target hotspot cluster location is determined from the plurality of feasible nodes.

13. A device for predicting hotspot cluster locations, characterized in that, The device includes an acquisition unit, a detection unit, and a determination unit: The acquisition unit is used to acquire the location information of the virtual character in the game map of the target game after entering the target game; The detection unit is used to perform feasible point detection on the game map based on the location information of the virtual character, and obtain multiple feasible nodes for the virtual character to move in the game map. The movement of the virtual character in the game map starts from the position identified by the location information. The determining unit is used to evaluate the heat influence factors for each of the plurality of feasible nodes, so as to determine the target hot spot clustering location from the plurality of feasible nodes. The heat influence factors include a combination of one or more of the following factors: number of visible nodes, safety coefficient, task completion coefficient, and resource utilization coefficient. The target hot spot clustering location is a location that is advantageous in battle and is used to reflect the real player behavior in the battle game. The number of field-of-view nodes refers to the number of nodes appearing within the field of view of a feasible node, which is used to characterize the convenience of the virtual character to observe the situation at the feasible node; the safety coefficient is used to characterize the safety level of the virtual character when a battle occurs at a feasible node; the task completion coefficient is used to characterize the convenience of a feasible node for completing a task; and the resource utilization coefficient is used to characterize the available resources at a feasible node.

14. The prediction device according to claim 13, characterized in that, If the heat index influencing factor includes multiple influencing factors, and the multiple influencing factors include a first influencing factor and a second influencing factor, wherein the first influencing factor is one of the following: number of visible nodes, safety factor, task completion factor, and resource utilization factor, and the second influencing factor is an influencing factor that is different from the first influencing factor among the following: number of visible nodes, safety factor, task completion factor, and resource utilization factor, the determining unit is specifically used for: For each feasible node, a first influence factor is evaluated to determine multiple candidate hotspot cluster locations from the multiple feasible nodes; The second influence factor is evaluated for each of the multiple candidate hotspot cluster locations to determine the target hotspot cluster location from the multiple candidate hotspot cluster locations.

15. The prediction device according to claim 14, characterized in that, The first influencing factor is the number of nodes in the field of view, and the determining unit is specifically used for: For each feasible node, determine the number of nodes in the field of view of that feasible node; The feasible nodes where the number of nodes in the field of view changes abruptly are identified as the locations where the multiple candidate hotspots cluster.

16. The prediction device according to claim 15, characterized in that, The determining unit is specifically used for: For each feasible node, the starting point of the second ray is determined based on the location identified by the location information and the character height of the virtual character; A second detection ray is emitted from the origin of the second ray to other feasible nodes; Based on the obstacle distribution detected by the second detection ray, the number of visual nodes of the feasible node is determined, and the obstacle distribution indicates whether there are obstacles during the process of the second detection ray being emitted to the other feasible nodes.

17. The prediction device according to claim 14, characterized in that, The second influencing factor includes a safety factor, and the determining unit is specifically used for: Obtain the first spawn position of the virtual character's friendly characters and the second spawn position of the virtual character's enemy characters; For each candidate hotspot cluster location, a first distance is determined between the candidate hotspot cluster location and the first birth location, and a second distance is determined between the candidate hotspot cluster location and the second birth location; The safety factor of the candidate hotspot cluster location is determined based on the first distance and the second distance; The target hotspot cluster location is determined from the plurality of candidate hotspot cluster locations based on the safety factor of each candidate hotspot cluster location.

18. The prediction device according to claim 14, characterized in that, The second influencing factor includes the task completion coefficient, and the determining unit is specifically used for: Determine the distance between each candidate hotspot cluster location and the task location; The task completion coefficient of the corresponding candidate hotspot cluster location is determined based on the distance. The target hotspot cluster location is determined from the plurality of candidate hotspot cluster locations based on the task completion coefficient of each candidate hotspot cluster location.

19. The prediction device according to claim 14, characterized in that, The second influencing factor includes the resource utilization coefficient, and the determining unit is specifically used for: Based on the resource situation of each candidate hotspot cluster location, determine the resource utilization coefficient of the corresponding candidate hotspot cluster location; The target hotspot cluster location is determined from the plurality of candidate hotspot cluster locations based on the resource utilization coefficient of each candidate hotspot cluster location.

20. The prediction device according to claim 13, characterized in that, If the heat index influencing factors include multiple influencing factors, the determining unit is specifically used for: For each feasible node, different influencing factors are evaluated to obtain multiple evaluation results for each feasible node; For each feasible node, the multiple evaluation results of the feasible node are weighted according to the weights corresponding to different influencing factors to obtain the comprehensive evaluation result of the feasible node; Based on the comprehensive evaluation results of each feasible node, the target hotspot cluster location is determined from the plurality of feasible nodes.

21. A computer device, characterized in that, The computer device includes a processor and memory: The memory is used to store program code and transmit the program code to the processor; The processor is configured to execute the method according to any one of claims 1-12 according to the instructions in the program code.

22. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program code that, when executed by a processor, causes the processor to perform the method according to any one of claims 1-12.

23. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1-12.

Images