Game anomaly detection method and device, computer equipment and storage medium

Abstract

The invention provides a game anomaly detection method and device, computer equipment and a storage medium, and is applied to a game client, the method comprises the following steps: obtaining a game loading page in response to detection of entering any game loading scene; performing anomaly detection on the game loading page by utilizing a pre-trained anomaly detection model to obtain a detection result of the game loading page; the detection result comprises at least one abnormal element detected in the game loading page; and in response to the detection result, indicating that loading is abnormal, sending the game loading page and the detection result to a game server connected with the game client.

Description

Technical Field

[0001] The present disclosure relates to the field of game technology, and in particular to a game anomaly detection method, device, computer equipment and storage medium. Background Art

[0002] When playing a game, the game may fail to run properly due to errors in parsing the game data packet or loading the game. In this case, if the game server is to discover and resolve this abnormal loading situation, it needs to rely on the user to obtain abnormal game data in the game and upload the abnormal game data through a specially set feedback portal. This method is complicated and inefficient. Summary of the invention

[0003] The embodiments of the present disclosure at least provide a game anomaly detection method, device, computer equipment and storage medium.

[0004] In a first aspect, an embodiment of the present disclosure provides a game anomaly detection method, which is applied to a game client, and the method includes: in response to detecting entry into any game loading scene, obtaining a game loading page; using a pre-trained anomaly detection model to perform anomaly detection on the game loading page to obtain a detection result of the game loading page; the detection result includes at least one abnormal element detected in the game loading page; in response to the detection result indicating a loading abnormality, sending the game loading page and the detection result to a game server connected to the game client.

[0005] In an optional implementation, the game loading scene includes at least one of the following: a game startup loading scene, a game scene switching loading scene, and a game level switching loading scene.

[0006] In an optional embodiment, in response to detecting entry into any game loading scenario, obtaining a game loading page includes: in response to detecting entry into any game loading scenario, determining an acquisition condition corresponding to the game loading page under the game loading scenario; the acquisition condition is used to indicate a timing for obtaining the game loading page under the game loading scenario; in response to satisfying the corresponding acquisition condition under the game loading scenario, obtaining the game loading page.

[0007] In an optional implementation, the method of performing anomaly detection on the game loading page using a pre-trained anomaly detection model to obtain a detection result of the game loading page includes: using the pre-trained anomaly detection model to identify and determine at least one target element in the game loading page, and a display state corresponding to each target element; the target element is determined based on the game loading scene; and based on the display state corresponding to each target element, the detection result of the game loading page is determined.

[0008] In an optional embodiment, the target element includes a game background element, and the display state of the target element includes a normal display state or an abnormal display state; the use of the pre-trained anomaly detection model to identify and determine at least one target element in the game loading page, and the display state corresponding to each target element, includes: using the pre-trained anomaly detection model to identify the target element in the game loading page to obtain an identification result of the target element; the identification result indicates the detection position of the target element in the game loading page, the confidence corresponding to the detection position, and a first probability value that the display state of the target element is an abnormal display state; based on the confidence and the first probability value determined for the target element, determine a second probability value that the display state of the target element is an abnormal display state, so as to determine the display state corresponding to the target element based on the comparison of the second probability value with a preset probability threshold determined for the abnormal display state.

[0009] In an optional implementation, in response to the detection result indicating a loading abnormality, the method further includes: determining a game node of the game loading scene under the game, and reloading the game node.

[0010] In an optional embodiment, before reloading the game node, the method further includes: receiving game data fed back by the game server based on a detection result indicating a loading abnormality; the game data is used to correct the game abnormality information indicated by the loading abnormality in the game; and reloading the game node includes: reloading the game node using the game data.

[0011] In an optional implementation, the anomaly detection model is trained in the following manner: sample data for training the anomaly detection model is determined; and the anomaly detection model to be trained is trained using the sample data to obtain the anomaly detection model.

[0012] In a second aspect, an embodiment of the present disclosure further provides a game abnormality detection device, characterized in that, when applied to a game client, the device comprises: an acquisition module, for acquiring a game loading page in response to detecting entry into any game loading scene; a detection module, for performing abnormality detection on the game loading page using a pre-trained abnormality detection model, and obtaining a detection result of the game loading page; the detection result comprises at least one abnormal element detected in the game loading page; and a sending module, for sending the game loading page and the detection result to a game server connected to the game client in response to the detection result indicating a loading abnormality.

[0013] In an optional implementation, the game loading scene includes at least one of the following: a game startup loading scene, a game scene switching loading scene, and a game level switching loading scene.

[0014] In an optional embodiment, when the acquisition module acquires the game loading page in response to detecting the entry into any game loading scenario, it is used to: determine the acquisition condition corresponding to the game loading page under the game loading scenario in response to detecting the entry into any game loading scenario; the acquisition condition is used to indicate the timing of acquiring the game loading page under the game loading scenario; in response to satisfying the corresponding acquisition condition under the game loading scenario, acquire the game loading page.

[0015] In an optional embodiment, when the detection module uses a pre-trained anomaly detection model to perform anomaly detection on the game loading page and obtains the detection result of the game loading page, it is used to: use the pre-trained anomaly detection model to identify and determine at least one target element in the game loading page, and the display status corresponding to each target element; the target element is determined based on the game loading scene; based on the display status corresponding to each target element, determine the detection result of the game loading page.

[0016] In an optional implementation, the target element includes a game background element, and the display state of the target element includes a normal display state or an abnormal display state;

[0017] When the detection module uses the pre-trained anomaly detection model to identify and determine at least one target element and the display state corresponding to each target element in the game loading page, it is used to: use the pre-trained anomaly detection model to identify the target element in the game loading page to obtain the recognition result of the target element; the recognition result indicates the detection position of the target element in the game loading page, the confidence corresponding to the detection position, and a first probability value that the display state of the target element is an abnormal display state; based on the confidence and the first probability value determined for the target element, determine the second probability value that the display state of the target element is an abnormal display state, so as to determine the display state corresponding to the target element based on the comparison of the second probability value with a preset probability threshold determined for the abnormal display state.

[0018] In an optional embodiment, the device further includes a processing module, and in response to the detection result indicating a loading abnormality, the processing module is used to: determine a game node of the game loading scene under the game, and reload the game node.

[0019] In an optional embodiment, before reloading the game node, the processing module is also used to: receive game data fed back by the game server based on a detection result indicating a loading abnormality; the game data is used to correct the game abnormality information indicated by the loading abnormality in the game; when reloading the game node, the processing module is used to: reload the game node using the game data.

[0020] In an optional implementation, the anomaly detection model is trained in the following manner: sample data for training the anomaly detection model is determined; and the anomaly detection model to be trained is trained using the sample data to obtain the anomaly detection model.

[0021] In a third aspect, an optional implementation of the present disclosure further provides a computer device, a processor, and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the processor is used to execute the machine-readable instructions stored in the memory, and when the machine-readable instructions are executed by the processor, the machine-readable instructions perform the steps of the above-mentioned first aspect, or any possible implementation of the first aspect.

[0022] In a fourth aspect, an optional implementation of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed, the steps of the above-mentioned first aspect, or any possible implementation of the first aspect are executed.

[0023] The disclosed embodiments provide a method, device, computer equipment, and storage medium for detecting game anomalies. In a game loading scenario where a game anomaly may occur in the game, the game loading page can be actively obtained on the game client and anomaly detection can be performed to determine whether there is a loading anomaly, and feedback can be sent to the game server when there is a loading anomaly. In this way, there is no need to rely on the user to manually determine whether there is a loading anomaly; in addition, by performing anomaly detection on the game loading page in the switched game loading scenario, it can be determined whether there is a loading error in the game, and the detection efficiency is higher.

[0024] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following is a brief introduction to the drawings required for use in the embodiments. The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can also be obtained based on these drawings without creative work.

[0026] Figure 1 A flowchart of a game anomaly detection method provided by an embodiment of the present disclosure is shown;

[0027] Figure 2 A schematic diagram of a game loading page in various game loading scenarios provided by an embodiment of the present disclosure is shown;

[0028] Figure 3 An example diagram of a game loading page actually obtained in a game startup loading scenario provided by an embodiment of the present disclosure is shown;

[0029] Figure 4 A situation in which a white screen loading exception occurs provided by an embodiment of the present disclosure is shown;

[0030] Figure 5 A specific schematic diagram of the game anomaly detection device provided by an embodiment of the present disclosure is shown;

[0031] Figure 6 A schematic diagram of a computer device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical scheme and advantages of the embodiments of the present disclosure clearer, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the embodiments of the present disclosure generally described and shown here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure is not intended to limit the scope of the present disclosure claimed for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present disclosure.

[0033] According to research, when playing games, users may encounter game loading anomalies due to parsing anomalies or incorrect loading, etc. Since these game loading anomalies occur during the game, in order for the game server to discover and resolve these anomalies, it usually relies on users to discover and obtain abnormal game data during the actual game process, and then feedback the abnormal game data through a specially set feedback entrance. This method is complex and inefficient.

[0034] Based on the above research, the present disclosure provides a game anomaly detection method. In a game loading scenario where a game anomaly may occur in the game, the game loading page can be actively obtained on the game client and anomaly detection can be performed to determine whether there is a loading anomaly, and feedback can be sent to the game server when there is a loading anomaly. In this way, there is no need to rely on the user to manually determine whether there is a loading anomaly, nor is there a need for the user to obtain and submit abnormal data; in addition, by performing anomaly detection on the game loading page in the switched game loading scenario, it can be determined whether there is a loading error in the game, and the detection efficiency is higher.

[0035] The defects existing in the above solutions are the results obtained by the inventor after practice and careful research. Therefore, the discovery process of the above problems and the solutions proposed by the present disclosure for the above problems below should be the contributions made by the inventor to the present disclosure during the disclosure process.

[0036] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0037] To facilitate understanding of this embodiment, a game anomaly detection method disclosed in the embodiment of the present disclosure is first introduced in detail. The execution subject of the game anomaly detection method provided in the embodiment of the present disclosure is generally a computer device with certain computing capabilities, and the computer device includes, for example: a terminal device or a server or other processing device, and the terminal device can be a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the game anomaly detection method can be implemented by a processor calling a computer-readable instruction stored in a memory.

[0038] The following is an example of the game anomaly detection method provided by the embodiment of the present disclosure, taking the execution subject as a game client. The game anomaly detection method provided by the embodiment of the present disclosure can be specifically applied to a game client equipped with a game. The game client is specifically a client corresponding to the user operating the game. Corresponding to the game client, a game server is also involved in the embodiment of the present disclosure. The game server is connected to the game client by signal, and can specifically send game data to the game client, and can also receive information fed back by the game client.

[0039] See also Figure 1 FIG. 1 is a flowchart of a method for detecting game anomalies provided by an embodiment of the present disclosure, wherein the method comprises steps S101 to S103, wherein:

[0040] S101: In response to detecting that any game loading scene is entered, obtaining a game loading page;

[0041] S102: Performing anomaly detection on the game loading page using a pre-trained anomaly detection model to obtain a detection result of the game loading page; the detection result includes at least one abnormal element detected in the game loading page;

[0042] S103: In response to the detection result indicating a loading abnormality, sending the game loading page and the detection result to a game server connected to the game client.

[0043] With respect to the above S101, first, the game loading scene is described. In the disclosed embodiment, the loading anomaly in the game is specifically detected. In the game, there are multiple game nodes with game loading scenes, which are called game loading scenes in the disclosed embodiment.

[0044] Specifically, see Figure 2The following is a schematic diagram of a game loading page under various game loading scenarios provided by the embodiment of the present disclosure. From the time the game is triggered to start, there is a game loading process before entering the game, that is, the game startup loading scenario, specifically, Figure 2 As shown in (a), in order to indicate the current loading progress and game content, multiple elements may be displayed in the game loading page in the game startup loading scenario, such as a game cover image serving as the game background, and a loading progress bar. The game cover image displayed here is referred to as a game background element in the disclosed embodiment, and the displayed progress bar is referred to as a progress bar element in the disclosed embodiment.

[0045] After the game is loaded, the game is officially entered. However, in the game, there may be scene switching. For example, in a large map game, when controlling the movement of the game character, the scene switching is accompanied by entering a new game map area. Therefore, the game loading scene can also include the game scene switching loading scene. For example Figure 2 As shown in (b), the game loading page in the game scene switching loading scene is shown. Generally, when the game scene is switched in a single task, link or level in the game, there is no progress bar displayed to the user, but the game data is directly loaded and switched. Therefore, the elements in the game loading page only show the game scene elements and game prop elements in the form of examples. The game scene elements indicate the game scene screen in the game, and the game prop elements indicate the props that the user can choose to use when completing the game (such as the characters to be filled in the crossword puzzle) and / or the game props that constitute the game content itself in the game (such as the reserved character filling space in the crossword puzzle).

[0046] According to the above description, there may be different links, tasks or levels in the game. When the links, tasks or levels are switched, the game content will actually be updated, so there is a synchronous game loading process, which is called the game level switching loading scene in the disclosed embodiment. In this case, for example, since the game is still in progress, there are also game scene elements and game prop elements displayed in the game scene switching loading scene, and also a progress bar element displayed due to the loading of new game data when the level is switched. The progress bar element here is specifically used to detect whether there is a loading anomaly, for example Figure 2 As shown in (c).

[0047] That is, in the embodiments of the present disclosure, the game loading scene includes but is not limited to at least one of the following: a game startup loading scene, a game scene switching loading scene, and a game level switching loading scene; and, in different game loading scenes, the elements to be loaded and displayed are different.

[0048] In the above example, the game loading page that can be obtained in the game loading scenario when the loading is normal is shown in the form of an example diagram, and each element on the game loading page can be displayed normally at first. In the actual game process, due to data loading or parsing exceptions, the elements may not be displayed normally, or the game may not be loaded normally. For example, for the game scene elements described above, it can be judged whether there is a loading abnormality by whether a "white screen" appears; and for the progress bar element described above, if after waiting for the time required for normal loading, the progress bar element still shows that the loading progress has not reached 100%, it can also be judged that there is a loading abnormality.

[0049] Through the above example of determining whether there is a loading anomaly based on the progress bar element, we can know that there are certain acquisition conditions when obtaining the game loading page. For example, if the game loading page is obtained right after entering the game, the game is still in the normal loading process. It is normal for the progress bar to not reach 100% in the obtained game loading page, and it should not be judged as a loading anomaly.

[0050] Therefore, in response to detecting the entry into any game loading scenario and obtaining the game loading page, it can be specifically possible to determine the acquisition condition corresponding to the game loading page under the game loading scenario in response to detecting the entry into any game loading scenario; the acquisition condition is used to indicate the timing of obtaining the game loading page under the game loading scenario; in response to satisfying the corresponding acquisition condition under the game loading scenario, the game loading page is obtained.

[0051] Taking the game startup loading scenario described above as an example, when obtaining the game loading page, the specific acquisition conditions may include at least the following two: In one possible case, the acquisition condition may include a waiting time. For example, based on the size of the game data packet that actually needs to be received and / or parsed when loading the game, or based on the data obtained during the game test, it is determined that a maximum of 30 seconds are required to load the game, and then the waiting time can be determined to be 30 seconds, that is, when the game startup loading scenario is detected, it is selected to wait for 30 seconds before obtaining the game loading page. In this way, if the presence of a loading anomaly can still be determined through the game loading page under the maximum loading time, the fact that a loading anomaly exists in the game can be determined with a higher degree of confidence.

[0052] In another possible case, the acquisition condition may also include reaching a set loading progress. When the game is started and loaded, different game data required in the game, such as game character data, scene data, etc., are usually received and / or downloaded in sequence. Therefore, when the game is started and loaded, it can be determined at which progress the loading anomaly may occur. For example, when the loading progress reaches 20%, the game server will receive an update data packet to send, then the data reception anomaly may occur, resulting in a loading anomaly in the game startup loading scene, or when the loading progress reaches 50%, the received data packet will be parsed, then the data parsing anomaly may also occur, which will also cause the loading anomaly in the game startup loading scene. Therefore, the loading progress nodes that may be abnormal can be predetermined, and the game loading page can be selected under these loading progress nodes to determine whether there is a loading anomaly by anomaly detection.

[0053] In this way, according to the above method, when entering any game loading scene, the game loading page for detection can be obtained.

[0054] In S102 above, for the obtained game loading page, a pre-trained anomaly detection model may be used to perform anomaly detection on the game loading page to obtain a detection result of the game loading page. Here, the pre-trained anomaly detection model is specifically installed in the game client.

[0055] According to the above description, for the obtained game loading page, which includes a progress bar element or a game background element, the display status corresponding to these elements can be used to indirectly determine whether there is a loading abnormality in the game loading page. For example, if the progress bar element indication has not reached 100% or the game background element appears a white screen, it can be determined that there is a loading abnormality in the game loading page.

[0056] Therefore, in a specific implementation, when using a pre-trained anomaly detection model to perform anomaly detection on the game loading page and obtaining a detection result of the game loading page, the following method can be specifically adopted:

[0057] Utilizing the pre-trained anomaly detection model, at least one target element and the display status corresponding to each target element are identified and determined in the game loading page; the target element is determined based on the game loading scenario; based on the display status corresponding to each target element and the normal display status corresponding to each element in the game loading scenario, the detection result of the game loading page is compared and determined.

[0058] Still taking the game loading page obtained in the game startup loading scenario as an example, for example, see Figure 3As shown in FIG. 1 , an example diagram of a game loading page actually obtained in a game startup loading scenario provided by an embodiment of the present disclosure is shown. Using a pre-trained anomaly detection model, at least one target element can be identified in the game loading page, such as Figure 3 In the example, the target elements are identified, including the progress bar elements and the game background elements that can be identified in the game startup loading scene, which are specifically marked with a dotted frame. Here, the target elements can specifically include text and images. For example, the progress bar element usually has an image displayed in a bar shape and a specific progress indicated by text such as "70%".

[0059] Here, before using the pre-trained anomaly detection model to detect and identify the game loading page, the image format, size, etc. of the game loading page can be adjusted and modified according to the specific requirements of the anomaly detection model for identifying the detection image to adapt to the anomaly detection model's detection requirements for the image.

[0060] For the identified target element, the display state corresponding to the target element can also be identified. Since different target elements have different display characteristics, different target elements have different display states. For example, for a progress bar element, the display state can be represented as completed progress or uncompleted progress, or refined into progress completion status, such as 70% or 80%.

[0061] By using the determined display status of each target element and the corresponding normal display status of each element in the game loading scene, the detection result of the game loading page can be compared and determined. Figure 3 The game loading page is identified, and the target elements include a progress bar element and a game background element, wherein the display state corresponding to the progress bar element is a state of incomplete progress, and the display state corresponding to the game background element is a normal display state of complete display.

[0062] By using the display status corresponding to each target element, the detection result of the game loading page can be determined by comparing it with the normal display status corresponding to each element in the game loading scene.

[0063] Here, since there are multiple target elements, each element is compared with the corresponding normal display state to determine the above detection result. Specifically, when it is determined that there is a target element display abnormality, it can be determined that the detection result of the game loading page indicates a loading abnormality; when it is determined that the display states of multiple target elements are all normal display states, it is determined that the detection result of the game loading page indicates a loading abnormality.

[0064] The normal display state is specifically related to the target element. For example, for a progress bar element, the normal display state includes both the icon part and the text part of the progress bar indicating that the progress is 100%, while for a game background element, the normal display state includes that the image is completely loaded.

[0065] Since the game background elements are loaded in the form of images, a "white screen" exception may occur during loading. The white screen exception here indicates that the image of the game background element cannot be displayed in a normal display mode after loading. For example, it should be displayed in full screen, but the image is stretched and displayed in half screen. For example, see Figure 4 As shown, a white screen loading exception occurs in an embodiment of the present disclosure. Figure 4 (a) shows the game background elements displayed under normal loading conditions. Figure 4 (b) shows a white screen abnormality due to image stretching caused by abnormal loading. In this case, only detecting whether there are game background elements or whether the image indicated by the game background elements is fully displayed cannot effectively indicate whether a loading abnormality has occurred.

[0066] Therefore, for the case where the target element includes a game background element, the pre-trained anomaly detection model can be used to identify the target element in the game loading page to obtain an identification result of the target element; the identification result indicates the detection position of the target element in the game loading page, the confidence corresponding to the detection position, and a first probability value that the display state of the target element is an abnormal display state; based on the confidence and the first probability value determined for the target element, a second probability value that the display state of the target element is an abnormal display state is determined, so as to determine the display state corresponding to the target element based on the comparison of the second probability value with a preset probability threshold determined for the abnormal display state.

[0067] Specifically, after obtaining the game loading page, the pre-trained anomaly detection model performs recognition processing on the game loading page, for example, obtaining multiple detection boxes, and the detection boxes specifically mark the detection position of the target element in the game loading page, such as the coordinate value in the game loading page. In addition, the recognition result also includes the confidence corresponding to the detection position, that is, the confidence corresponding to the corresponding detection box; and the first probability value that the display state of the target element is an abnormal display state, which is specifically used to characterize the probability of a "white screen" anomaly occurring in the area where the detection box is located.

[0068] Exemplarily, the recognition result may specifically include a vector of length 6, wherein the first four digits represent the detection position, that is, the coordinate information of the detection box, the fifth digit represents the confidence corresponding to the detection box, and the sixth digit represents the probability value of a "white screen" abnormality occurring in the detection box.

[0069] When determining the display state corresponding to the target element, the second probability value that the display state of the target element is an abnormal display state can be calculated by multiplying the confidence value under the fifth position and the first probability value under the sixth position determined above.

[0070] When checking whether there is a "white screen" anomaly under the target element, a preset probability threshold that can be considered to be an anomaly can be determined based on experience, and the second probability value determined above is compared with the preset probability threshold to determine the display state corresponding to the target element. For example, if the determined second probability value is less than the preset probability threshold, the display state corresponding to the target element is determined to be a normal display state; if the determined second probability value is greater than or equal to the preset probability threshold, the display state corresponding to the target element is determined to be an abnormal display state.

[0071] In another embodiment of the present disclosure, the anomaly detection model may be obtained based on a known method of training anomaly detection models.

[0072] In another embodiment of the present disclosure, any of the sample data includes a game loading sample page, and abnormal elements marked in the game loading sample page; the sample data includes: a first game loading page indicating abnormal loading, and / or a second game loading page obtained by constructing abnormal elements in a game loading page under normal loading. The abnormal elements include, for example, a game background element with a white screen area, or a progress bar element that has not reached 100% progress.

[0073] Regarding the above S103, for the above detection results, if it indicates that the loading is normal, the game client can play the game normally; if it indicates that the loading is abnormal, the game loading page and the detection results can be sent to the game server connected to the game client, so that the game server can adjust the game according to the feedback of the abnormal results.

[0074] For the game client, if there is a loading anomaly, the game may not be able to continue. For example, when the game background elements are displayed abnormally, there may be a situation where they cannot be aligned with the game props, resulting in the user being unable to play the game normally. Therefore, for a game loading scene that detects an indication of a loading anomaly, the game node of the game loading scene under the game can be determined, and the game node can be reloaded. For example, if a loading anomaly detection result is obtained in the game startup loading scene, it is determined that the game node includes a game loading node, and the game loading is restarted; or, when a loading anomaly detection result is obtained when switching levels, the loading of the switched level is restarted.

[0075] Furthermore, if the game itself has a situation such as loss of loading data, directly selecting to reload the game node may cause similar loading abnormality problems. Therefore, before reloading the game node, the game data fed back by the game server based on the detection result indicating the loading abnormality can also be received; the game data is used to correct the game abnormality information indicated by the loading abnormality in the game, and when reloading the game node, the game data is selected to reload the game node.

[0076] Specifically, after receiving the feedback of the loading exception detection result, the game server can determine the error type of the loading error based on the detection result, and provide a solution based on the error type of the loading error, such as issuing data patches, updating resource packs, and other game data. These game data can specifically correct the game exception information indicated under the loading exception, such as recalibrating the display position of the game background elements, etc.

[0077] Therefore, for the game client, after receiving the game data fed back by the game server, it can use the game data to reload the game node, so as to solve the original loading abnormality after reloading the game node with a greater probability.

[0078] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0079] Based on the same inventive concept, a game abnormality detection device corresponding to the game abnormality detection method is also provided in the embodiment of the present disclosure. Since the principle of solving the problem by the device in the embodiment of the present disclosure is similar to the above-mentioned game abnormality detection method in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0080] Reference Figure 5 FIG. 1 is a schematic diagram of a game abnormality detection device provided by an embodiment of the present disclosure, wherein the device comprises: an acquisition module 51, a detection module 52, and a sending module 53; wherein:

[0081] An acquisition module 51 is used to acquire a game loading page in response to detecting that any game loading scene is entered;

[0082] A detection module 52, configured to perform anomaly detection on the game loading page using a pre-trained anomaly detection model to obtain a detection result of the game loading page; the detection result includes at least one abnormal element detected in the game loading page;

[0083] The sending module 53 is used to send the game loading page and the detection result to the game server connected to the game client in response to the detection result indicating that the loading is abnormal.

[0084] In an optional implementation, the game loading scene includes at least one of the following: a game startup loading scene, a game scene switching loading scene, and a game level switching loading scene.

[0085] In an optional embodiment, when the acquisition module 51 acquires the game loading page in response to detecting the entry into any game loading scenario, it is used to: determine the acquisition condition corresponding to the game loading page in the game loading scenario in response to detecting the entry into any game loading scenario; the acquisition condition is used to indicate the timing of acquiring the game loading page in the game loading scenario; in response to satisfying the corresponding acquisition condition in the game loading scenario, acquire the game loading page.

[0086] In an optional embodiment, when the detection module 52 performs anomaly detection on the game loading page using a pre-trained anomaly detection model and obtains the detection result of the game loading page, it is used to: use the pre-trained anomaly detection model to identify and determine at least one target element in the game loading page, and the display status corresponding to each target element; the target element is determined based on the game loading scene; and the detection result of the game loading page is determined based on the display status corresponding to each target element.

[0087] In an optional implementation, the target element includes a game background element, and the display state of the target element includes a normal display state or an abnormal display state;

[0088] When the detection module 52 uses the pre-trained anomaly detection model to identify and determine at least one target element in the game loading page, and the display state corresponding to each target element, it is used to: use the pre-trained anomaly detection model to identify the target element in the game loading page to obtain the recognition result of the target element; the recognition result indicates the detection position of the target element in the game loading page, the confidence corresponding to the detection position, and a first probability value that the display state of the target element is an abnormal display state; based on the confidence and the first probability value determined for the target element, determine the second probability value that the display state of the target element is an abnormal display state, so as to determine the display state corresponding to the target element based on the comparison of the second probability value with a preset probability threshold determined for the abnormal display state.

[0089] In an optional implementation, the device further includes a processing module 54. In response to the detection result indicating a loading abnormality, the processing module 54 is used to: determine a game node of the game loading scene under the game, and reload the game node.

[0090] In an optional embodiment, before reloading the game node, the processing module 54 is also used to: receive game data fed back by the game server based on the detection result indicating the loading abnormality; the game data is used to correct the game abnormality information indicated by the loading abnormality in the game; when reloading the game node, the processing module 54 is used to: reload the game node using the game data.

[0091] In an optional implementation, the anomaly detection model is trained in the following manner: sample data for training the anomaly detection model is determined; and the anomaly detection model to be trained is trained using the sample data to obtain the anomaly detection model.

[0092] For descriptions of the processing flow of each module in the device and the interaction flow between each module, reference may be made to the relevant descriptions in the above method embodiment, which will not be described in detail here.

[0093] The present disclosure also provides a computer device, such as Figure 6 FIG. 1 is a schematic diagram of a computer device structure provided in an embodiment of the present disclosure, including:

[0094] A processor 10 and a memory 20; the memory 20 stores machine-readable instructions executable by the processor 10, and the processor 10 is used to execute the machine-readable instructions stored in the memory 20. When the machine-readable instructions are executed by the processor 10, the processor 10 performs the following steps:

[0095] In response to detecting entry into any game loading scene, obtaining a game loading page; performing anomaly detection on the game loading page using a pre-trained anomaly detection model to obtain a detection result of the game loading page; the detection result includes at least one abnormal element detected in the game loading page; in response to the detection result indicating a loading abnormality, sending the game loading page and the detection result to a game server connected to the game client.

[0096] The above-mentioned memory 20 includes an internal memory 210 and an external memory 220; the internal memory 210 here is also called an internal memory, which is used to temporarily store the calculation data in the processor 10, as well as the data exchanged with the external memory 220 such as a hard disk. The processor 10 exchanges data with the external memory 220 through the internal memory 210.

[0097] The specific execution process of the above instructions can refer to the steps of the game anomaly detection method described in the embodiment of the present disclosure, which will not be repeated here.

[0098] The present disclosure also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the game abnormality detection method described in the above method embodiment are executed. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0099] The present disclosure also provides a computer program product that carries a program code. The program code includes instructions that can be used to execute the steps of the game anomaly detection method described in the above method embodiment. For details, please refer to the above method embodiment, which will not be repeated here.

[0100] The computer program product may be implemented in hardware, software or a combination thereof. In one optional embodiment, the computer program product is implemented as a computer storage medium. In another optional embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0101] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0102] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0103] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0104] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0105] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present disclosure, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for detecting game anomalies, characterized in that: Applied to a game client, the method includes: In response to detecting that any game loading scene is entered, obtaining a game loading page; Performing anomaly detection on the game loading page using a pre-trained anomaly detection model to obtain a detection result of the game loading page; the detection result includes at least one abnormal element detected in the game loading page; In response to the detection result indicating a loading abnormality, the game loading page and the detection result are sent to a game server connected to the game client.

2. The method according to claim 1, characterized in that The game loading scene includes at least one of the following: a game startup loading scene, a game scene switching loading scene, and a game level switching loading scene.

3. The method according to claim 1 or 2, characterized in that: In response to detecting that any game loading scene is entered, obtaining a game loading page includes: In response to detecting that any game loading scene has been entered, determining an acquisition condition corresponding to the game loading page in the game loading scene; the acquisition condition is used to indicate a timing for acquiring the game loading page in the game loading scene; In response to satisfying the corresponding acquisition condition in the game loading scenario, the game loading page is acquired.

4. The method according to claim 1, characterized in that: The using of the pre-trained anomaly detection model to perform anomaly detection on the game loading page to obtain a detection result of the game loading page includes: Using the pre-trained anomaly detection model, identifying and determining at least one target element and a display state corresponding to each target element in the game loading page; the target element is determined based on the game loading scene; Based on the display status corresponding to each of the target elements, the detection result of the game loading page is determined.

5. The method according to claim 4, characterized in that The target element includes a game background element, and the display state of the target element includes a normal display state or an abnormal display state; The using the pre-trained anomaly detection model to identify and determine at least one target element in the game loading page, and a display state corresponding to each of the target elements, includes: Using the pre-trained anomaly detection model to identify a target element in the game loading page, obtaining an identification result of the target element; the identification result indicates a detection position of the target element in the game loading page, a confidence level corresponding to the detection position, and a first probability value that a display state of the target element is an abnormal display state; Based on the confidence determined for the target element and the first probability value, a second probability value that the display state of the target element is an abnormal display state is determined, so as to determine the display state corresponding to the target element based on comparison between the second probability value and a preset probability threshold determined for the abnormal display state.

6. The method according to claim 1, characterized in that In response to the detection result indicating a loading abnormality, the method further includes: Determine the game node of the game loading scene under the game, and reload the game node.

7. The method according to claim 6, characterized in that Before reloading the game node, the method further includes: Receiving game data fed back by the game server based on a detection result indicating a loading anomaly; the game data is used to correct the game anomaly information indicating the loading anomaly in the game; The reloading of the game node comprises: The game node is reloaded using the game data.

8. The method according to claim 1, characterized in that The anomaly detection model is trained in the following manner: Determining sample data for training the anomaly detection model; The sample data is used to train the anomaly detection model to be trained to obtain an anomaly detection model.

9. A game anomaly detection device, characterized in that: Applied to a game client, the device comprises: An acquisition module, configured to acquire a game loading page in response to detecting that any game loading scene is entered; A detection module, configured to perform anomaly detection on the game loading page using a pre-trained anomaly detection model to obtain a detection result of the game loading page; the detection result includes at least one abnormal element detected in the game loading page; A sending module is used to send the game loading page and the detection result to a game server connected to the game client in response to the detection result indicating a loading abnormality.

10. A computer device, characterized in that: include: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the processor is used to execute the machine-readable instructions stored in the memory. When the machine-readable instructions are executed by the processor, the processor executes the steps of the game abnormality detection method as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program. When the computer program is executed by a computer device, the computer device executes the steps of the game anomaly detection method according to any one of claims 1 to 8.

Images