Virtual game test method and system, electronic equipment and storage medium

Abstract

The invention discloses a virtual game testing method and system, electronic equipment and a storage medium. The method comprises the steps that a to-be-tested game picture frame is acquired; identifying a virtual object in the to-be-tested game picture frame by using a preset model; analyzing the position information of the joint points of the virtual object to obtain attitude information of the virtual object; obtaining action information of the virtual object according to the attitude information; analyzing the action information of the virtual object to obtain an interaction behavior type of the virtual object; according to the interactive behavior type of the virtual object, generating a simulation operation instruction; controlling the virtual object to operate in a to-be-tested game picture frame based on a simulation operation instruction; and collecting operation data of the virtual object, and performing data analysis on the operation data of the virtual object to obtain a test result. According to the invention, the test efficiency and accuracy can be improved.

Description

Technical Field

[0001] The present application relates to the field of game testing technology, and in particular to a testing method, system, electronic device and storage medium for a virtual game. Background Art

[0002] With the rapid development of science and technology, virtual reality (VR) technology has become an important driving force in the gaming industry, providing players with an unprecedented immersive experience. VR games simulate the three-dimensional environment of the real world, allowing players to participate in the game in an immersive way, greatly enhancing the fun and interactivity of the game. However, the complexity and diversity of virtual games have put forward higher requirements for game testing. Traditional game testing methods mainly rely on manual testing or game log analysis; this method is inefficient, costly, and easily interfered by human factors, making it difficult to ensure the accuracy of the test. Therefore, how to improve the efficiency and accuracy of game testing is an urgent problem to be solved. Summary of the invention

[0003] The main purpose of the present application is to overcome the shortcomings and deficiencies of the prior art and to provide a testing method, system, electronic device and storage medium for a virtual game, which can quickly and accurately obtain simulation operation instructions based on the interactive behavior type of the virtual object, and based on the operation instructions, simulate the operation of the virtual object in the game screen frame, and perform data analysis on the operation data, so as to accurately evaluate the game performance and improve the efficiency and accuracy of the test.

[0004] In order to achieve the above objectives, this application adopts the following technical solutions:

[0005] In a first aspect, the present application provides a method for testing a virtual game, comprising the following steps:

[0006] Acquire a game screen frame to be tested; the game screen frame to be tested includes elements and virtual objects;

[0007] Using a pre-established model to identify a virtual object in the game screen frame to be tested;

[0008] Analyzing the position information of the joint points of the virtual object to obtain the posture information of the virtual object;

[0009] Obtaining action information of the virtual object according to the posture information;

[0010] Analyzing the action information of the virtual object to determine the interactive behavior type of the virtual object;

[0011] generating a simulation operation instruction according to the interactive behavior type of the virtual object;

[0012] Based on the simulation operation instruction, controlling the virtual object to operate in the game screen frame to be tested;

[0013] The operation data of the virtual object is collected, and data analysis is performed on the operation data of the virtual object to obtain a test result.

[0014] As a preferred technical solution, the elements include environmental elements and interactive items in the game screen;

[0015] The virtual objects refer to entities with dynamic behaviors or interactivity, including characters controlled by players.

[0016] As a preferred technical solution, the posture information of the virtual object is obtained by using a posture estimation model to identify the virtual object, including:

[0017] Inputting the identified virtual object into a posture estimation model to extract position information of the joint points of the virtual object;

[0018] Mapping the position information of the joint points to corresponding parts of the virtual object, and connecting the position information of the joint points according to the structure of the virtual object to form a posture skeleton;

[0019] The posture skeleton is analyzed to obtain posture information of the virtual object.

[0020] As a preferred technical solution, analyzing the action information of the virtual object to obtain the interactive behavior type of the virtual object includes:

[0021] Extracting the action information of the virtual object and the time sequence characteristics of the virtual object action information in each frame of the game screen to be tested;

[0022] Encoding the action information and the time sequence features of the virtual object, and arranging the encoded action information and the time sequence features of the virtual object in chronological order to form an action feature sequence;

[0023] Based on the action feature sequence, identifying the action category;

[0024] The continuously recognized action categories are spliced ​​into action sequences in chronological order;

[0025] The action sequence and context information of the virtual environment are analyzed to identify the type of interactive behavior.

[0026] As a preferred technical solution, the context information of the virtual environment refers to element information and scene layout information related to the current action of the virtual object.

[0027] As a preferred technical solution, the operation data includes the time when the simulated operation instruction is issued, the time when the simulated operation instruction ends, and the simulated interactive behavior parameters.

[0028] As a preferred technical solution, the step of performing data analysis on the operation data of the virtual object to obtain a test result includes:

[0029] Acquire the time difference between the start time of issuing the simulation operation instruction and the end time of the virtual object actually executing and completing the simulation operation instruction as the actual response time;

[0030] The actual response time is compared with the preset response time. If the actual response time is less than or equal to the preset response time threshold, the response speed when processing the operation instruction is evaluated to be qualified.

[0031] Analyze the interaction behavior parameters between the virtual object and each element. If the interaction behavior parameters between the virtual object and each element are within the preset interaction behavior parameter range between the virtual object and each element, it is evaluated that the virtual object interaction behavior is qualified; wherein the interaction behavior parameters between the virtual object and each element are used to evaluate the accuracy and interaction fluency of the virtual object interaction behavior;

[0032] The test result of the game screen frame is obtained according to the evaluation results of the response speed and the interactive behavior of the virtual object.

[0033] In a second aspect, the present application provides a virtual game testing system, which is applied to a virtual game testing method, including a picture frame acquisition module, a recognition module, a posture information determination module, an action information determination module, a behavior type determination module, an instruction generation module, a simulation operation module and a testing module;

[0034] The frame acquisition module is used to acquire the game frame to be tested; the game frame to be tested includes elements and virtual objects;

[0035] The recognition module is used to recognize the virtual object in the game screen frame to be tested by using a pre-established model;

[0036] The posture information determination module is used to analyze the position information of the joint points of the virtual object to obtain the posture information of the virtual object;

[0037] The action information determination module is used to obtain the action information of the virtual object according to the posture information;

[0038] The behavior type determination module is used to analyze the action information of the virtual object and determine the interactive behavior type of the virtual object;

[0039] The instruction generation module is used to generate simulation operation instructions according to the interactive behavior type of the virtual object;

[0040] The simulation operation module is used to control the virtual object to operate in the game screen frame to be tested based on the simulation operation instruction;

[0041] The test module is used to collect the operation data of the virtual object and perform data analysis on the operation data of the virtual object to obtain a test result.

[0042] As a preferred technical solution, the elements include environmental elements and interactive items in the game screen; the virtual objects refer to entities with dynamic behaviors or interactivity, including characters controlled by players.

[0043] As a preferred technical solution, the module for determining posture information is specifically used for:

[0044] Inputting the identified virtual object into a posture estimation model to extract position information of the joint points of the virtual object;

[0045] Mapping the position information of the joint points to corresponding parts of the virtual object, and connecting the position information of the joint points according to the structure of the virtual object to form a posture skeleton;

[0046] The posture skeleton is analyzed to obtain posture information of the virtual object.

[0047] As a preferred technical solution, the module for determining the behavior type is specifically used for:

[0048] Extracting the action information of the virtual object and the time sequence characteristics of the virtual object action information in each frame of the game screen to be tested;

[0049] Encoding the action information and the time sequence features of the virtual object, and arranging the encoded action information and the time sequence features of the virtual object in chronological order to form an action feature sequence;

[0050] Based on the action feature sequence, identifying the action category;

[0051] The continuously recognized action categories are spliced ​​into action sequences in chronological order;

[0052] The action sequence and context information of the virtual environment are analyzed to identify the type of interactive behavior.

[0053] As a preferred technical solution, the context information of the virtual environment refers to element information and scene layout information related to the current action of the virtual object.

[0054] As a preferred technical solution, the operation data includes the time when the simulated operation instruction is issued, the time when the simulated operation instruction ends, and the simulated interactive behavior parameters.

[0055] As a preferred technical solution, the test module is specifically used for:

[0056] Acquire the time difference between the start time of issuing the simulation operation instruction and the end time of the virtual object actually executing and completing the simulation operation instruction as the actual response time;

[0057] The actual response time is compared with the preset response time. If the actual response time is less than or equal to the preset response time threshold, the response speed when processing the operation instruction is evaluated to be qualified.

[0058] Analyze the interaction behavior parameters between the virtual object and each element. If the interaction behavior parameters between the virtual object and each element are within the preset interaction behavior parameter range between the virtual object and each element, it is evaluated that the virtual object interaction behavior is qualified; wherein the interaction behavior parameters between the virtual object and each element are used to evaluate the accuracy and interaction fluency of the virtual object interaction behavior;

[0059] The test result of the game screen frame is obtained according to the evaluation results of the response speed and the interactive behavior of the virtual object.

[0060] In a third aspect, the present application provides an electronic device, the electronic device comprising:

[0061] at least one processor; and a memory communicatively coupled to the at least one processor;

[0062] The memory stores computer program instructions that can be executed by the at least one processor, and the computer program instructions are executed by the at least one processor so that the at least one processor can execute the testing method of a virtual game.

[0063] In a fourth aspect, the present application provides a computer-readable storage medium storing a program, which, when executed by a processor, implements the aforementioned method for testing a virtual game.

[0064] In summary, compared with the prior art, the effective effects brought about by the technical solution provided by this application include at least:

[0065] The present application proposes a testing method for virtual games, which automatically identifies virtual objects using a pre-established model, analyzes the posture information of virtual objects, obtains action information based on the posture information and further analyzes it, and obtains the interactive behavior type of each virtual object based on the action information, which can quickly and accurately capture the interactive behavior pattern of virtual objects in the game; and generates simulated operation instructions based on the interactive behavior type of the virtual object, controls the operation of the virtual object in the game screen frame based on the simulated operation instructions, and obtains test results by performing data analysis on the operation data of the virtual object. It can be seen that the present application overcomes the problems of low efficiency and high cost of manual testing, and ensures the efficiency and accuracy of the test; at the same time, by performing data analysis based on the operation data, the response speed when processing the operation instructions and the accuracy and interaction fluency of the interactive behavior of the virtual object can be obtained to accurately evaluate the game performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0067] Figure 1 A flowchart of a virtual game testing method provided by one embodiment of the present application;

[0068] Figure 2 A flowchart of recognizing posture information of a virtual object provided by an embodiment of the present application;

[0069] Figure 3 A flowchart for determining the interactive behavior type of a virtual object provided by an embodiment of the present application;

[0070] Figure 4 A flowchart of performing data analysis on operation data of a virtual object provided by one embodiment of the present application;

[0071] Figure 5 A block diagram of a virtual game testing system provided by one embodiment of the present application;

[0072] Figure 6 A structural diagram of an electronic device provided for one embodiment of the present application. DETAILED DESCRIPTION

[0073] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.

[0074] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0075] With the rapid development of game technology, game content is becoming increasingly rich, especially the widespread application of physics engines, which makes the physical interaction scenes in games extremely complex and changeable. Traditional game testing methods currently rely mainly on manual testing. However, in this case, when dealing with the challenges of modern game development, relying solely on manual testing is not only time-consuming and labor-intensive, but also prone to subjectivity and inconsistency in test results due to human factors. Manual testing may become fatigued after working for a long time, and then ignore some subtle but critical problems, which will cause misjudgment and make it difficult to ensure the accuracy of the test, and thus it is difficult to fully evaluate the quality of the game from the user's perspective.

[0076] In order to solve the above problems, the present application firstly automatically identifies virtual objects using a pre-established model, analyzes the posture information of virtual objects, obtains action information based on the posture information and further analyzes it, and obtains the interactive behavior type of each virtual object based on the action information, so as to quickly and accurately capture the interactive behavior pattern of virtual objects in the game; and generates simulated operation instructions according to the interactive behavior type of virtual objects, controls the operation of virtual objects in the game screen frame based on the simulated operation instructions, and obtains test results by performing data analysis on the operation data of virtual objects. It can be seen that the present application overcomes the problems of low efficiency and high cost of manual testing, and ensures the efficiency and accuracy of the test; at the same time, data analysis is performed based on the operation data to obtain the test results of the response speed when processing the operation instructions and the accuracy and interaction fluency of the interactive behavior of virtual objects, so that game developers can test the results to optimize the game.

[0077] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0078] See also Figure 1In one embodiment of the present application, a method for testing a virtual game is provided, comprising the following steps:

[0079] S1. Acquire a game screen frame to be tested; the game screen frame to be tested includes elements and virtual objects.

[0080] Furthermore, virtual objects refer to entities with dynamic behaviors or interactivity, which play an important role in the game world. These objects include but are not limited to player-controlled characters (such as protagonists, teammates, etc.), non-player-controlled characters, monsters, enemies, pets, etc. Virtual objects can respond to player operations or game logic, perform specific actions or behaviors, and thus affect the game process and results.

[0081] Elements refer to the basic components that make up the game screen frame, which together construct the visual background and functional framework of the game world. Elements include game screen environment elements and interactive items.

[0082] Among them, environmental elements constitute the static visual background of the game world, including terrain (such as mountains, rivers, grasslands), buildings (such as houses, bridges, castles), decorations (such as trees, flowers, statues), etc. Environmental elements provide rich visual scenes for the game, creating different game atmospheres and scene features.

[0083] Interactive items are different from virtual objects. Interactive items mainly refer to objects that players can interact with but usually do not have dynamic behavior. These items have specific functions or properties, and their effects are achieved through player triggers or operations. For example, treasure chests can be opened to obtain rewards, switches can control the opening or closing of doors, and doors can be pushed open or closed to pass through. Interactive items are important interactive elements in games. They provide players with ways to explore the game world, advance the game process, and obtain rewards.

[0084] Furthermore, the game screen frame also includes the scene layout, which specifically refers to the spatial arrangement and combination of various elements and virtual objects in the game screen frame, and defines the environment in which the virtual objects are located in the game, including the distribution and configuration of elements such as terrain, buildings, roads, and vegetation. Specifically, the scene layout includes the layout mode in the scene, the state of the environment, the relationship between objects, etc.

[0085] A game screen frame has multiple different virtual scenes, each of which includes elements and virtual objects. For example, taking a virtual escape room game as an example, the game screen frame may include a starting room virtual scene, a hidden room virtual scene, and a final escape area virtual scene. Each scene contains specific elements and virtual objects to create a unique gaming experience and challenge. Among them, the virtual scene of the starting room includes multiple elements and virtual objects such as password locks (door locks that require the correct password to open), clue items (such as notes, books, pictures, etc., providing clues to solve puzzles), furniture (such as tables, chairs, bookshelves, cabinets, etc., where clues may be hidden), (simulating the behavior of users in the room); the virtual scene of the hidden room includes puzzle devices (such as jigsaw puzzles, mechanisms, password boxes, etc., puzzles that players need to solve), hidden clues (such as hidden buttons, secret doors, password hints, etc.), decorations (such as paintings, statues, lamps, etc., which may contain puzzle clues) elements and virtual objects; the virtual scene of the final escape area includes the ultimate puzzle (the last puzzle), the escape door (the door that can be opened after solving the ultimate puzzle), reward items (such as trophies, treasure chests, etc., as rewards for successful escape) elements and virtual objects.

[0086] Specifically, each virtual scene in the game screen frame of this embodiment can use Blender's rich modeling tools to create a detailed 3D model. For example, in the virtual escape room game mentioned above, the starting room virtual scene includes a password lock, clue items, furniture elements and virtual objects; Blender's modeling tools are used to build the detailed structure of the password lock model, including a numeric keypad, a lock body, a rotating handle and other parts; 3D models of various clue items are created, such as old paper slips, yellowed books, blurred pictures, etc.; 3D models of furniture such as tables, chairs, bookshelves, and cabinets are constructed; and a player character model is created.

[0087] After completing the creation of the 3D model, place the furniture, password locks and clue items in the Unity scene editor to ensure that their location and layout are consistent with the logic and atmosphere of the escape room; and configure physical properties such as mass, density, and friction for models such as password locks and furniture; at the same time, write the interaction logic, for example: in the virtual scene of the starting room, write a script to listen to the password entered by the player and compare it with the preset correct password. If the password is correct, the animation or event of the door lock opening is triggered; write a script for each clue item to realize the functions of picking up, viewing and operating, such as displaying the description of the item or clue information when the virtual object clicks or approaches the item.

[0088] Among them, Blender is an open source 3D modeling and animation software that supports a variety of 3D graphics applications, including visual effects, 3D visualization, 3D animation production, etc. It has a built-in game engine and can also be used to create real-time 3D interactive content. Unity is a powerful game engine with a built-in advanced physics engine that can accurately simulate physical phenomena in the real world, such as collisions and friction.

[0089] In this embodiment, the virtual scene may be rendered to obtain a more realistic virtual game environment, and the steps include:

[0090] (1) Obtain the elements, virtual objects and scene layout feature information in the virtual scene.

[0091] (2) Determine the visual style of the virtual scene and configure rendering parameters according to the visual style.

[0092] Furthermore, rendering parameters include: resolution, anti-aliasing and ray tracing parameters, etc.

[0093] (3) Based on the rendering parameters, material assignment and texture mapping are performed on the elements, virtual objects and scene layout.

[0094] Furthermore, you can edit the material properties; material properties include color, reflectivity, roughness, etc. to simulate real-world material characteristics.

[0095] Specifically, for example, when creating the virtual escape room game mentioned above, the detailed design of materials and textures is the key to creating an immersive experience. Each virtual object and the scene layout in which it is located can greatly enhance the player's sense of immersion and the fun of solving puzzles through carefully selected and blended materials and textures.

[0096] For example, for the virtual scene of the starting room, the password lock is the core interactive element, and its material can be made of metal texture. High reflectivity and high-gloss details are used to simulate the gloss of stainless steel or brass, while the roughness is adjusted to show subtle scratches or wear on the lock surface to add realism. Clue items such as notes, books, and pictures are made of paper or cloth, and soft texture maps are used to show the wrinkles and yellowing of the paper or the texture of the picture, so that players can touch these items. Furniture parts, such as tables, chairs, bookshelves, and cabinets, are given corresponding colors, reflectivity, and roughness according to their different materials such as wood, metal, or plastic, to ensure that they present natural light and shadow effects and tactile feedback under light.

[0097] S2. Using a pre-established model to identify virtual objects in the game screen frame to be tested.

[0098] Furthermore, an object detection model is used to identify virtual objects in the virtual environment. The object detection model uses a YOLO model to identify virtual objects in the virtual environment and mark the category, position and bounding box of the virtual object; specifically including:

[0099] (1) Each image frame in the game screen frame is input into the object detection model, which first extracts features in the virtual scene image through a series of convolutional layers and pooling layers;

[0100] Furthermore, in the initial stage of the YOLO model, continuous image frames in the game screen frames are input into the object detection model frame by frame; these image frames first pass through a series of designed convolutional layers, which use different convolutional kernels to slide on the image to extract rich feature information; then, the feature map is reduced in dimension through the pooling layer to reduce the amount of calculation while retaining important features, and this process is repeated many times to construct a deep feature representation.

[0101] (2) After feature extraction, use the pre-defined anchor boxes to predict the virtual object bounding box, confidence, and category probability of the virtual object that may exist in each grid;

[0102] Furthermore, after feature extraction, the YOLO model uses predefined anchor boxes as initial estimates of bounding boxes, which are designed based on the size and proportion of virtual objects predefined in the training data set. Each grid in the object detection model is responsible for predicting the bounding boxes of objects whose centers fall within the grid, the confidence that objects exist in these bounding boxes (i.e., the probability that an object actually exists in the bounding box multiplied by the probability that the object is accurately predicted), and the probability of the virtual object category that may exist in each grid. Through this step, the YOLO model can simultaneously complete the task of locating and classifying objects in a single forward propagation, greatly improving the detection speed.

[0103] (3) Process the prediction results obtained in step (2); first, use the non-maximum suppression algorithm to remove redundant bounding boxes, that is, retain the bounding box with the highest confidence while suppressing its adjacent bounding boxes, thereby ensuring that each object is detected only once; then, according to the preset confidence threshold, further screen out those bounding boxes with sufficiently high confidence as valid detection results; finally, based on the category probability distribution within each bounding box, determine the specific category of the virtual object within the bounding box by selecting the category with the highest probability.

[0104] S3. Analyze the position information of the joint points of the virtual object to obtain the posture information of the virtual object.

[0105] Furthermore, the posture information of the virtual object is obtained by using a posture estimation model. The posture estimation model in this embodiment may be an OpenPose model. The OpenPose model is based on deep learning and computer vision technology, especially convolutional neural network (CNN), and is used to detect key points of the human body, face and hands in an image or video, thereby achieving accurate estimation of the dynamic posture of different parts of the human body. In this embodiment, the posture information of the virtual object is identified by the OpenPose model, please refer to Figure 2 , the steps include:

[0106] S31, inputting the identified virtual object into a posture estimation model, and extracting position information of the joint points of the virtual object;

[0107] Furthermore, deep learning algorithms are used to identify the joints of the player's body in each frame of the image, such as wrists, elbows, shoulders, knees, etc. These joints are key information that constitutes the human body posture, and the precise position of the joints is crucial for subsequent analysis.

[0108] S32, mapping the position information of the joint points to the corresponding parts of the virtual object, and connecting the position information of the joint points according to the structure of the virtual object to form a posture skeleton;

[0109] S33: Analyze the posture skeleton to obtain posture information of the virtual object.

[0110] After constructing the posture skeleton, the posture estimation model will further analyze the posture skeleton to obtain richer posture information, including the angles of each joint, the extension degree of the limbs, the tilt direction of the body, etc.

[0111] S4. Obtaining action information of the virtual object according to the posture information.

[0112] Furthermore, based on the posture information of the virtual object, the action information of the virtual object can be determined; for example, in a virtual escape room game, this information is important for determining whether the virtual object is operating a puzzle device, the strength and method of the operation, etc. For example, by analyzing the posture of the virtual object's arm, it can be determined whether it is trying to rotate a handle; and by observing the posture of the fingers, it can be identified whether the virtual object is pressing a button to determine the action of the virtual object.

[0113] S5. Analyze the action information of the virtual object to determine the interactive behavior type of the virtual object.

[0114] Furthermore, a behavior recognition model is used to analyze the action information of continuous image frames of the virtual object to identify the type of virtual object interaction behavior; wherein the virtual object interaction behavior type includes but is not limited to moving, attacking, defending, picking up items, using skills, and talking to NPCs (non-player characters).

[0115] Specifically, in this embodiment, the behavior recognition model can be a long short-term memory network (LSTM) or a three-dimensional convolutional neural network (3DCNN); the behavior recognition model is used to analyze the action information of the continuous image frames of the virtual object to identify the type of virtual object interaction behavior, please refer to Figure 3 , the steps include:

[0116] S51, extracting the action information of the virtual object and the time sequence characteristics of the virtual object action information in each frame of the game screen to be tested;

[0117] Specifically, the behavior recognition model extracts key features from image frames continuously captured in the virtual environment, including using convolutional neural networks (CNN) or more advanced image feature extractors to capture action information in each frame. At the same time, in order to understand the evolution of action in the time dimension, the behavior recognition model analyzes the changes in pixel or action information between consecutive frames and extracts temporal features.

[0118] S52, encoding the action information and the time sequence features of the virtual object, and arranging the encoded action information and the time sequence features of the virtual object in chronological order to form an action feature sequence;

[0119] Among them, the encoded action information and temporal features of the virtual object are arranged in chronological order to form a series of feature sequences. This serialized representation enables the model to capture the temporal dependency and dynamic changes of the action. Each sequence corresponds to a potential action process experienced by the virtual object.

[0120] S53, identifying the action category based on the action feature sequence;

[0121] S54, splicing the continuously recognized action categories into an action sequence in chronological order;

[0122] S55: Analyze the action sequence and the context information of the virtual environment to identify the type of interactive behavior.

[0123] Furthermore, the context information of the virtual environment refers to the elements and their scene layout related to the current action of the virtual object, such as the position and state of the elements, the scene layout and structure, etc.

[0124] Specifically, the interactive behavior in this embodiment involves a series of actions that occur in chronological order, so the time dependency, sequence, and posture information of virtual object actions are captured through the behavior recognition model and the posture estimation model to distinguish different interactive behaviors. For example, the action sequence of "reaching out - grabbing an item - moving an item" may represent the "pick up" behavior, while "reaching out - entering a password - clicking to confirm" may represent the "unlock" behavior.

[0125] S6. Generate a simulation operation instruction according to the interactive behavior type of the virtual object.

[0126] Furthermore, it is necessary to generate simulation operation instructions according to the interaction behavior type, and the simulation operation instructions are used to simulate the user's operation on the virtual object in the game screen frame to be tested.

[0127] S7. Based on the simulation operation instruction, control the virtual object to operate in the game screen frame to be tested.

[0128] Furthermore, the simulation operation instructions are a direct reflection of the player's intentions, guiding virtual objects (such as player characters) on how to interact with elements in the virtual world; based on the type or parameters of the simulation operation instructions, the specific actions or interactive behaviors that the virtual objects need to perform are determined, such as rotating handles, pushing boxes, jumping, etc.

[0129] S8. Collecting the operation data of the virtual object, and performing data analysis on the operation data of the virtual object to obtain a test result.

[0130] Furthermore, the operation data includes the time when the simulated operation instruction is issued, the time when the simulated operation instruction ends, and the simulated interaction behavior parameters.

[0131] Specifically, the operation data of the virtual object is analyzed to obtain the test results. Figure 4 , the steps include:

[0132] S81, obtaining the time difference between the start time of issuing the simulation operation instruction and the end time of the virtual object actually executing and completing the simulation operation instruction as the actual response time;

[0133] S82, comparing the actual response time with a preset response time, if the actual response time is less than or equal to a preset response time threshold, evaluating that the response speed when processing the operation instruction is qualified;

[0134] S83, analyzing the interaction behavior parameters between the virtual object and each element, and if the interaction behavior parameters between the virtual object and each element are within the preset interaction behavior parameter range between the virtual object and each element, then evaluating that the virtual object interaction behavior is qualified; wherein the interaction behavior parameters between the virtual object and each element are used to evaluate the accuracy and interaction fluency of the virtual object interaction behavior;

[0135] Furthermore, the interaction behavior parameters between the virtual object and each element are within the preset interaction behavior parameters between the virtual object and each element to evaluate the accuracy and interaction fluency of the virtual object interaction behavior; wherein the interaction behavior parameters include interaction duration and interaction position. Furthermore, if the interaction duration is not within the preset interaction duration range, the interaction fluency is considered unqualified; if the interaction position is not within the preset interaction position range, the interaction behavior is considered inaccurate.

[0136] S84. Obtain a test result of the game screen frame according to the evaluation results of the response speed and the virtual object interaction behavior.

[0137] Furthermore, based on the evaluation results of the response speed of the virtual game system when processing operating instructions and the evaluation results of the accuracy and interaction fluency of the interactive behavior, test results of the response speed of the virtual game when processing operating instructions and the accuracy and interaction fluency of the virtual object interactive behavior are obtained; based on the test results, game developers can optimize the game.

[0138] Specifically, it also includes: if the test result is unqualified (i.e., there is an exception), then obtain the simulated operation instruction with the exception, and determine to which type of interactive behavior (moving, jumping, or picking up items, etc.) the operation instruction belongs, analyze the distribution and frequency of the abnormal interactive behavior to determine the cause of the exception (the cause of the exception includes interaction failure, unreasonable interaction path, etc.), make improvement suggestions based on the cause of the exception, and form a test report; the development team can modify the game based on the improvement suggestions to improve the game performance and user experience.

[0139] It should be noted that, for the sake of convenience of description, the aforementioned method embodiments are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously.

[0140] Based on the same idea as the test method of a virtual game in the above embodiment, the present application also provides a test system for a virtual game, which can be used to execute the test method of a virtual game. For ease of explanation, the structural diagram of an embodiment of a test system for a virtual game only shows the parts related to the embodiment of the present application. Those skilled in the art can understand that the illustrated structure does not constitute a limitation on the system, and may include more or fewer components than shown in the diagram, or combine certain components, or arrange the components differently.

[0141] See also Figure 5 In another embodiment of the present application, a virtual game testing system is provided, the system comprising a picture frame acquisition module 101, a recognition module 102, a posture information determination module 103, an action information determination module 104, a behavior type determination module 105, an instruction generation module 106, a simulation operation module 107 and a testing module 108;

[0142] The frame acquisition module 101 is used to acquire a game frame to be tested; the game frame to be tested includes elements and virtual objects;

[0143] The recognition module 102 is used to recognize the virtual object in the game screen frame to be tested by using a pre-established model;

[0144] The posture information determination module 103 is used to analyze the position information of the virtual object joints to obtain the posture information of the virtual object;

[0145] The action information determination module 104 is used to obtain the action information of the virtual object according to the posture information;

[0146] The behavior type determination module 105 is used to analyze the action information of the virtual object and determine the interactive behavior type of the virtual object;

[0147] The instruction generating module 106 is used to generate a simulation operation instruction according to the interactive behavior type of the virtual object;

[0148] The simulation operation module 107 is used to control the virtual object to operate in the game screen frame to be tested based on the simulation operation instruction;

[0149] The test module 108 is used to collect the operation data of the virtual object and perform data analysis on the operation data of the virtual object to obtain a test result.

[0150] As a preferred technical solution, the elements include environmental elements and interactive items in the game screen;

[0151] The virtual objects refer to entities with dynamic behaviors or interactivity, including characters controlled by players.

[0152] As a preferred technical solution, the module 103 for determining posture information is specifically used for:

[0153] Inputting the identified virtual object into a posture estimation model to extract position information of the joint points of the virtual object;

[0154] Mapping the position information of the joint points to corresponding parts of the virtual object, and connecting the position information of the joint points according to the structure of the virtual object to form a posture skeleton;

[0155] The posture skeleton is analyzed to obtain posture information of the virtual object.

[0156] As a preferred technical solution, the module for determining the behavior type 105 is specifically used for:

[0157] Extracting the action information of the virtual object and the time sequence characteristics of the virtual object action information in each frame of the game screen to be tested;

[0158] Encoding the action information and the time sequence features of the virtual object, and arranging the encoded action information and the time sequence features of the virtual object in chronological order to form an action feature sequence;

[0159] Based on the action feature sequence, identifying the action category;

[0160] The continuously recognized action categories are spliced ​​into action sequences in chronological order;

[0161] The action sequence and context information of the virtual environment are analyzed to identify the type of interactive behavior.

[0162] As a preferred technical solution, the context information of the virtual environment refers to element information and scene layout information related to the current action of the virtual object.

[0163] As a preferred technical solution, the operation data includes the time when the simulated operation instruction is issued, the time when the simulated operation instruction ends, and the simulated interactive behavior parameters.

[0164] As a preferred technical solution, the test module 108 is specifically used for:

[0165] Acquire the time difference between the start time of issuing the simulation operation instruction and the end time of the virtual object actually executing and completing the simulation operation instruction as the actual response time;

[0166] The actual response time is compared with the preset response time. If the actual response time is less than or equal to the preset response time threshold, the response speed when processing the operation instruction is evaluated to be qualified.

[0167] Analyze the interaction behavior parameters between the virtual object and each element. If the interaction behavior parameters between the virtual object and each element are within the preset interaction behavior parameter range between the virtual object and each element, it is evaluated that the virtual object interaction behavior is qualified; wherein the interaction behavior parameters between the virtual object and each element are used to evaluate the accuracy and interaction fluency of the virtual object interaction behavior;

[0168] The test result of the game screen frame is obtained according to the evaluation results of the response speed and the interactive behavior of the virtual object.

[0169] It should be noted that a testing system for a virtual game of the present application corresponds one-to-one to a testing method for a virtual game of the present application. The technical features and beneficial effects described in the embodiment of the testing method for a virtual game mentioned above are applicable to the embodiment of a testing system for a virtual game. For specific contents, please refer to the description in the embodiment of the method of the present application. It will not be repeated here. This is hereby declared.

[0170] In addition, in the implementation of a virtual game testing system in the above-mentioned embodiment, the logical division of each program module is only an example. In actual application, the above-mentioned functions can be assigned to different program modules as needed, for example, for the configuration requirements of the corresponding hardware or the convenience of software implementation. That is, the internal structure of the virtual game testing system is divided into different program modules to complete all or part of the functions described above.

[0171] See also Figure 6 In another embodiment, an electronic device for implementing a method for testing a virtual game is provided. The electronic device may include a processor, a memory, and a bus, and may also include a computer program stored in the memory and executable on the processor, such as a test program for the virtual game.

[0172] Exemplarily, in this embodiment, the computer program may be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present application. The one or more module elements may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the device.

[0173] The electronic device may be a computing device such as a desktop computer, a notebook, a palm computer, a cloud server, etc. The device may include, but is not limited to, a processor and a memory.

[0174] In some embodiments, the processor may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center (Control Unit) of the device, and uses various interfaces and lines to connect the various components of the entire device; by running or executing the program or module stored in the memory, and calling the data stored in the memory, the various functions of the electronic device and the processing data are executed.

[0175] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; in addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0176] Wherein, the memory may be an internal storage unit of an electronic device in some embodiments, such as a mobile hard disk of the electronic device. The memory may also be an external storage device of an electronic device in other embodiments, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the memory may also include both an internal storage unit of the electronic device and an external storage device. The memory may be used not only to store application software and various types of data installed in the electronic device, such as the code of a test program of a virtual game, but also to temporarily store data that has been output or is to be output.

[0177] Figure 6 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 6 The structure shown does not constitute a limitation on the electronic device, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0178] The test program of a virtual game stored in the memory of the electronic device is a combination of multiple instructions, and when running in the processor, it can achieve:

[0179] Acquire a game screen frame to be tested; the game screen frame to be tested includes elements and virtual objects;

[0180] Using a pre-established model to identify a virtual object in the game screen frame to be tested;

[0181] Analyzing the position information of the joint points of the virtual object to obtain the posture information of the virtual object;

[0182] Obtaining action information of the virtual object according to the posture information;

[0183] Analyzing the action information of the virtual object to determine the interactive behavior type of the virtual object;

[0184] generating a simulation operation instruction according to the interactive behavior type of the virtual object;

[0185] Based on the simulation operation instruction, controlling the virtual object to operate in the game screen frame to be tested;

[0186] The operation data of the virtual object is collected, and data analysis is performed on the operation data of the virtual object to obtain a test result.

[0187] Accordingly, the present application also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute a virtual game testing method as described in any one of the above embodiments.

[0188] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0189] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0190] The above embodiments are preferred implementation modes of the present application, but the implementation modes of the present application are not limited to the above embodiments. Any other changes, modifications, substitutions, combinations, and simplifications that do not deviate from the spirit and principles of the present application should be equivalent replacement methods and are included in the protection scope of the present application.

Claims

1. A virtual game testing method, characterized in that: The steps include: Acquire a game screen frame to be tested; the game screen frame to be tested includes elements and virtual objects; Using a pre-established model to identify a virtual object in the game screen frame to be tested; Analyzing the position information of the joint points of the virtual object to obtain the posture information of the virtual object; Obtaining action information of the virtual object according to the posture information; Analyzing the action information of the virtual object to determine the interactive behavior type of the virtual object; generating a simulation operation instruction according to the interactive behavior type of the virtual object; Based on the simulation operation instruction, controlling the virtual object to operate in the game screen frame to be tested; The operation data of the virtual object is collected, and data analysis is performed on the operation data of the virtual object to obtain a test result.

2. A virtual game testing method according to claim 1, characterized in that: The elements include environmental elements and interactive items in the game screen; The virtual objects refer to entities with dynamic behaviors or interactivity, including characters controlled by players.

3. A virtual game testing method according to claim 1, characterized in that: The posture information of the virtual object is obtained by using a posture estimation model to identify the virtual object, including: Inputting the identified virtual object into a posture estimation model to extract position information of the joint points of the virtual object; Mapping the position information of the joint points to corresponding parts of the virtual object, and connecting the position information of the joint points according to the structure of the virtual object to form a posture skeleton; The posture skeleton is analyzed to obtain posture information of the virtual object.

4. A virtual game testing method according to claim 1, characterized in that: The analyzing the action information of the virtual object to obtain the interactive behavior type of the virtual object includes: Extracting the action information of the virtual object and the time sequence characteristics of the virtual object action information in each frame of the game screen to be tested; Encoding the action information and the time sequence features of the virtual object, and arranging the encoded action information and the time sequence features of the virtual object in chronological order to form an action feature sequence; Based on the action feature sequence, identifying the action category; The continuously recognized action categories are spliced ​​into action sequences in chronological order; The action sequence and context information of the virtual environment are analyzed to identify the type of interactive behavior.

5. A virtual game testing method according to claim 4, characterized in that: The context information of the virtual environment refers to element information and scene layout information related to the current action of the virtual object.

6. A virtual game testing method according to claim 1, characterized in that: The operation data includes the time when the simulation operation instruction is issued, the time when the simulation operation instruction is ended, and the simulated interaction behavior parameters.

7. A virtual game testing method according to claim 6, characterized in that: The performing data analysis on the operation data of the virtual object to obtain a test result includes: Acquire the time difference between the start time of issuing the simulation operation instruction and the end time of the virtual object actually executing and completing the simulation operation instruction as the actual response time; The actual response time is compared with the preset response time. If the actual response time is less than or equal to the preset response time threshold, the response speed when processing the operation instruction is evaluated to be qualified. Analyze the interaction behavior parameters between the virtual object and each element. If the interaction behavior parameters between the virtual object and each element are within the preset interaction behavior parameter range between the virtual object and each element, it is evaluated that the virtual object interaction behavior is qualified; wherein the interaction behavior parameters between the virtual object and each element are used to evaluate the accuracy and interaction fluency of the virtual object interaction behavior; The test result of the game screen frame is obtained according to the evaluation results of the response speed and the interactive behavior of the virtual object.

8. A virtual game testing system, characterized in that: A virtual game testing method applied to any one of claims 1-7, comprising a picture frame acquisition module, a recognition module, a posture information determination module, an action information determination module, a behavior type determination module, an instruction generation module, a simulation operation module and a testing module; The frame acquisition module is used to acquire the game frame to be tested; the game frame to be tested includes elements and virtual objects; The recognition module is used to recognize the virtual object in the game screen frame to be tested by using a pre-established model; The posture information determination module is used to analyze the position information of the joint points of the virtual object to obtain the posture information of the virtual object; The action information determination module is used to obtain the action information of the virtual object according to the posture information; The behavior type determination module is used to analyze the action information of the virtual object and determine the interactive behavior type of the virtual object; The instruction generation module is used to generate simulation operation instructions according to the interactive behavior type of the virtual object; The simulation operation module is used to control the virtual object to operate in the game screen frame to be tested based on the simulation operation instruction; The test module is used to collect the operation data of the virtual object and perform data analysis on the operation data of the virtual object to obtain a test result.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; Wherein, the memory stores computer program instructions that can be executed by the at least one processor, and the computer program instructions are executed by the at least one processor so that the at least one processor can execute a virtual game testing method as described in any one of claims 1-7.

10. A computer-readable storage medium storing a program, characterized in that: When the program is executed by a processor, a virtual game testing method as described in any one of claims 1 to 7 is implemented.

Images