Page inspection methods, devices and electronic equipment

Abstract

This application discloses a page detection method, apparatus, and electronic device, relating to the field of computer processing technology. The method includes: responding to a dynamic scene detection command for a target page, obtaining a set of target frames corresponding to a dynamic scene from the target page; performing static detection on the set of target frames based on a set of reference frames corresponding to the dynamic scene to obtain a static detection result; performing dynamic detection on the set of target frames based on the reference frame set and the target frame set to obtain a dynamic detection result; and generating a page detection result corresponding to the dynamic scene detection command based on the static and dynamic detection results. This application considers the changing conditions within dynamic scenes and introduces dynamic detection during page detection, detecting dynamic scenes in the target page from both static and dynamic perspectives, thus improving the page detection effect.

Description

Technical Field

[0001] This application relates to the field of computer processing technology, specifically to page detection methods, apparatus, and electronic devices. Background Technology

[0002] Currently, with the development of page display styles, dynamic scenes are appearing more and more frequently on pages.

[0003] In related technologies, when detecting whether a dynamic scene on a test page is displayed correctly, a static image is extracted from the dynamic scene, and the static image is compared with a pre-stored standard image. If the similarity between the static image and the standard image is high, it is determined that the dynamic scene can be displayed correctly on the test page.

[0004] However, in the aforementioned related technologies, determining whether a dynamic scene is displayed correctly on the page based solely on static images results in poor page detection performance. Summary of the Invention

[0005] In view of this, this application provides a page detection method, apparatus, and electronic device to solve the problem of poor page detection results.

[0006] Firstly, this application provides a page detection method, including: In response to a dynamic scene detection command for a target page, a set of target frames corresponding to the dynamic scene is obtained from the target page; Static detection is performed on the target frame set based on the reference frame set corresponding to the dynamic scene to obtain static detection results; Based on the reference frame set and the target frame set, dynamic detection is performed on the target frame set to obtain dynamic detection results; Based on the static detection results and the dynamic detection results, the page detection results corresponding to the dynamic scene detection instructions are generated.

[0007] Secondly, this application provides a page detection device, comprising: The target acquisition module is used to obtain a set of target frames corresponding to the dynamic scene from the target page in response to a dynamic scene detection command for the target page. The static detection module is used to perform static detection on the target frame set based on the reference frame set corresponding to the dynamic scene, and obtain static detection results; The dynamic detection module is used to perform dynamic detection on the target frame set based on the reference frame set and the target frame set, and obtain dynamic detection results; The result acquisition module is used to generate page detection results corresponding to the dynamic scene detection instruction based on the static detection results and the dynamic detection results.

[0008] Thirdly, this application provides an electronic device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the page detection method of the first aspect or any corresponding embodiment described above.

[0009] For example, the electronic device is a server.

[0010] Fourthly, this application provides a computer-readable storage medium storing computer instructions for causing a computer to perform the page detection method of the first aspect or any corresponding embodiment described above.

[0011] Fifthly, this application provides a computer program product, including computer instructions for causing a computer to execute the page detection method of the first aspect or any corresponding embodiment described above.

[0012] The page detection method provided in this application performs static detection on a target frame set using a reference frame set to obtain static detection results. Then, it performs dynamic detection on the target frame set using both the reference frame set and the target frame set to obtain dynamic detection results. Finally, it generates page detection results based on the static and dynamic detection results. This method takes into account the changes that exist in dynamic scenes and introduces dynamic detection during page detection, detecting dynamic scenes in the target page from both static and dynamic perspectives, thereby improving the page detection effect. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the specific embodiments or related technologies of this application, the drawings used in the description of the specific embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0014] Figure 1 This is a schematic diagram illustrating an application scenario according to an embodiment of this application; Figure 2 This is a schematic flowchart of a page detection method according to an embodiment of this application; Figure 3 An example diagram of similarity curves is shown; Figure 4 An exemplary flowchart of a page detection method is shown. Figure 5 This is a structural block diagram of a page detection device according to an embodiment of this application; Figure 6 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0015] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0016] It should be noted that the information (including but not limited to user input information, such as information entered by the user into input boxes), data (including but not limited to data used for analysis, stored data, and displayed data, such as context code, all code of the current project, the service pressure corresponding to operations performed on all code of the current project, and the code development status of the current project), and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with relevant laws, regulations, and standards. For example, the context code, operations performed on all code of the current project, the corresponding service pressure, and the code development status involved in this application were all obtained with full authorization.

[0017] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0018] As one optional application scenario in the embodiments of this application, such as Figure 1 As shown, the system may include at least one terminal device and at least one server. Figure 1 The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.

[0019] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.

[0020] For example, the terminal device includes an application. This application can be one that requires downloading and installation, or it can be an application that is available immediately upon clicking. For example, the application can be any application capable of displaying dynamic scenes.

[0021] For example, the server is the backend server of the application.

[0022] In related technologies, when detecting whether a dynamic scene on a page is displayed correctly, a static image is extracted from the dynamic scene, and the static image is compared with a pre-stored standard image. If the similarity between the static image and the standard image is high, it is determined that the dynamic scene can be displayed correctly on the detection page. However, in the aforementioned related technologies, determining whether a dynamic scene is displayed correctly on the page based solely on a static image cannot dynamically detect dynamic elements within the dynamic scene, resulting in poor page detection performance.

[0023] According to an embodiment of this application, a page detection method embodiment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0024] This embodiment provides a page detection method that can be used with the aforementioned servers, such as standalone physical servers, server clusters, distributed systems, cloud servers, and application backend servers. Figure 2 This is a flowchart of a page detection method according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps: Step S201: In response to the dynamic scene detection instruction for the target page, obtain the set of target frames corresponding to the dynamic scene from the target page.

[0025] The target page refers to any page capable of displaying dynamic scenes. Dynamic scenes refer to changing scenes within the target page. Optionally, the target page can be either a static page or a dynamic page.

[0026] In one possible implementation, the target page is a static page, and the dynamic scene is the changing scene displayed after the target function on the target page is triggered. For example, the target function includes, but is not limited to, at least one of the following: page jump function, pop-up call function, icon display style switching function, etc.

[0027] In another possible implementation, the target page is a dynamic page, and the dynamic scene is the changing scene displayed after the target page is rendered. For example, the dynamic scene includes, but is not limited to, at least one of the following: dynamic icons, scrolling text, changing images, etc.

[0028] A dynamic scene detection command is used to trigger page detection for dynamic scenes. In one possible implementation, the target page is a static page, and the dynamic scene detection command is the dynamic scene trigger command; upon detecting the dynamic scene detection command, the target page displays the dynamic scene; correspondingly, upon detecting the dynamic scene detection command, the server determines to perform page detection on the target page. In another possible implementation, the target page is a dynamic page; upon detecting the dynamic scene detection command, the target page continues to be displayed; correspondingly, upon detecting the dynamic scene detection command, the server determines to perform page detection on the target page.

[0029] In this embodiment of the application, during page detection, the server responds to a dynamic scene detection command for the target page and obtains a set of target frames corresponding to the dynamic scene from the target page. The set of target frames includes more than one target frame.

[0030] Optionally, the target frame set is used to characterize the real-time display process of a dynamic scene. For example, upon detecting a dynamic scene detection command, the server captures the real-time display process of the dynamic scene from the target page to obtain the target video; further, the target video is sampled based on a sampling frequency to obtain the target frame set. For example, the sampling frequency is determined based on a reference video, as described below.

[0031] Optionally, the dynamic scene corresponds to a start marker element and an end marker element. The start marker element indicates the start of the dynamic scene, and the end marker element indicates the end of the dynamic scene. For example, when the server detects a start marker element from the target page, it determines that dynamic scene capture has begun; subsequently, when the server detects an end marker element from the target page, it determines that dynamic scene capture is complete, and the target video is obtained.

[0032] For example, after acquiring the target video, a start target frame is obtained from the beginning of the target video, an end target frame is obtained from the end of the target video, and intermediate target frames are obtained between the beginning and the end based on the sampling frequency. Optionally, the start target frame includes a start marker element, and the end target frame includes an end marker element.

[0033] Step S202: Perform static detection on the target frame set based on the reference frame set corresponding to the dynamic scene to obtain the static detection result.

[0034] Optionally, when the server detects the aforementioned dynamic scene detection instruction, it acquires a set of reference frames corresponding to the dynamic scene while acquiring the aforementioned target frame set. The set of reference frames includes more than one reference frame.

[0035] Optionally, the reference frame set is used to characterize the standard display process of a dynamic scene. Optionally, the reference frame set is pre-stored information. Exemplarily, the target page and the dynamic scene are displayed on a reference device. The server captures the standard display process based on the content displayed on the reference device to obtain a reference video. Further, the reference video is sampled based on the sampling frequency to obtain a reference frame set. Exemplarily, after obtaining the reference video, the server samples the reference video based on the sampling interval to obtain a sampled frame set. If the number of similar frames in the sampled frame set is less than the target value, the reference video is determined to be a fast-motion video, and the pre-set sampling frequency corresponding to the fast-motion video is obtained. If the number of similar frames in the sampled frame set is greater than or equal to the target frame, the reference video is determined to be a slow-motion video, and the pre-set sampling frequency corresponding to the slow-motion video is obtained. Optionally, the reference device is a device with a stable operating environment and network environment. Optionally, the target value is any value, and can be flexibly set and adjusted according to the actual situation; this application embodiment does not limit this.

[0036] Optionally, in accordance with the target frame type described above, the start reference frame in the reference frame includes the start marker element described above, and the end reference frame includes the end marker element described above.

[0037] In this embodiment, after obtaining the target frame set, the server performs static detection on the target frame set based on the reference frame set corresponding to the dynamic scene, and obtains the static detection result. The static detection result indicates whether the static display of the dynamic scene in the target frame set is normal.

[0038] Optionally, the server retrieves a set of reference frames corresponding to the dynamic scene from pre-stored information based on the aforementioned dynamic scene detection instructions, and then performs static detection on the target frame set based on the set of reference frames to obtain static detection results.

[0039] Step S203: Based on the reference frame set and the target frame set, perform dynamic detection on the target frame set to obtain dynamic detection results.

[0040] In this embodiment, after obtaining the target frame set, the server performs dynamic detection on the target frame set based on the reference frame set and the target frame set to obtain a dynamic detection result. The dynamic detection result is used to indicate whether the dynamic display of the dynamic scene in the target frame set is normal.

[0041] Step S204: Based on the static detection results and dynamic detection results, generate the page detection results corresponding to the dynamic scene detection instructions.

[0042] In this embodiment, after obtaining the static detection results and the dynamic detection results, the server generates page detection results corresponding to the dynamic scene detection command based on the static and dynamic detection results. The page detection results are used to characterize whether the display of the dynamic scene in the target frame set is normal.

[0043] In one possible implementation, the page detection result includes both static and dynamic detection results. The server directly packages the static and dynamic detection results to generate the page detection result.

[0044] In another possible implementation, the page detection results include a visual report. The server converts the static and dynamic detection results into a visual report to obtain the page detection results.

[0045] The page detection method provided in this embodiment performs static detection on the target frame set using a reference frame set to obtain static detection results. Then, it performs dynamic detection on the target frame set using both the reference frame set and the target frame set to obtain dynamic detection results. Finally, it generates page detection results based on the static and dynamic detection results. By taking into account the changes that exist in dynamic scenes, dynamic detection is introduced during page detection, detecting dynamic scenes in the target page from both static and dynamic perspectives, thereby improving the page detection effect.

[0046] In an exemplary embodiment, step S202 includes: Step S2021: Compare the reference frame set and the target frame set frame by frame to obtain the image similarity of each comparison group.

[0047] In this embodiment, after obtaining the target frame set, the server performs frame-by-frame image comparison between the reference frame set and the target frame set to obtain the image similarity of each comparison group. Each comparison group includes one reference frame and one target frame, and the reference frame set and the target frame set have the same sampling frequency.

[0048] Optionally, the target frame corresponds to a timestamp, and the reference frame also corresponds to a timestamp. The server aligns the target frame and the reference frame one by one based on the order of the timestamps to obtain comparison groups. Further, using the comparison groups as the reference unit, image comparison is performed on the target frame and the reference frame to obtain the image similarity of each comparison group. For example, the start target frame and the start reference frame form one comparison group, and the end target frame and the end reference frame form another comparison group.

[0049] Step S2022: The target frame in the comparison group whose image similarity is less than the first threshold is identified as the first abnormal frame.

[0050] In this embodiment of the application, when the image similarity of each of the above comparison groups is obtained, the server determines the target frame in the comparison group whose image similarity is less than the first threshold as the first abnormal frame.

[0051] For example, the image similarity can be any value, and the image similarity can be flexibly set and adjusted according to the actual situation. This application embodiment does not limit this.

[0052] Step S2023: Based on the timestamp of the first abnormal frame, obtain the abnormal parameters corresponding to the first abnormal frame.

[0053] In this embodiment, after obtaining the first abnormal frame, the server obtains the abnormal parameters corresponding to the first abnormal frame based on the timestamp of the first abnormal frame. The abnormal parameters include the stage to which the first abnormal frame belongs and the cause of the abnormality. The stage to which the first abnormal frame belongs refers to the stage of the first abnormal frame in the dynamic scene, and the cause of the abnormality refers to the device-related cause that led to the first abnormal frame.

[0054] Specifically, step S2023 above includes: Step S2023a: Obtain the stage parameters of the reference frame set.

[0055] In this embodiment, after acquiring the first abnormal frame, the server acquires stage parameters of the reference frame set. These stage parameters include at least two stages contained in the reference frame set and the display time of each stage. For example, after acquiring the reference frame set based on the sampling frequency, the server divides the reference frame set into stages based on the display characteristics of each reference frame, obtaining at least two stages contained in the reference frame set, and determines the display time of each stage based on the timestamp of the reference frame corresponding to each stage.

[0056] For example, a stage refers to the phases contained in a dynamic scene. For instance, if the dynamic scene is a pop-up display scene, the set of reference frames includes three stages: the appearance stage, the stable stage, and the disappearance stage. The appearance stage refers to the stage from when the pop-up starts to be displayed until it is fully displayed; the stable stage refers to the stage from when the pop-up is fully displayed until it is completely disappeared; and the disappearance stage refers to the stage from when the pop-up starts to disappear until it is completely disappeared. If the dynamic scene is a text scrolling scene, the set of reference frames includes three stages: the start display stage, the scrolling stage, and the end display stage. The start display stage refers to the stage where the information is statically displayed at the beginning; the scrolling stage refers to the stage where the text is dynamically displayed; and the end display stage refers to the stage where the information is statically displayed at the end.

[0057] For example, the display time can be either the display duration or a display period. In one possible implementation, the display time is the display duration. For example, in a dynamic scene that is a pop-up display, the display time during the appearance phase is 1.2 seconds, the display time during the stable phase is 1.5 seconds, and the display time during the disappearance phase is 1 second. In another possible implementation, the display time is a display period. For example, in a dynamic scene that is a pop-up display, the display time during the appearance phase is 0~1.2 seconds, the display time during the stable phase is 1.3~2.7 seconds, and the display time during the disappearance phase is 2.8~3.7 seconds.

[0058] Step S2023b: Based on the timestamp of the first abnormal frame, locate the display period of the first abnormal frame in the target frame set.

[0059] In this embodiment of the application, after obtaining the first abnormal frame, the server locates the display period of the first abnormal frame in the target frame set based on the timestamp of the first abnormal frame.

[0060] Step S2023c: Determine the stage to which the first abnormal frame belongs based on the display time period and stage parameters.

[0061] In this embodiment of the application, after obtaining the above-mentioned display period, the server determines the stage to which the first abnormal frame belongs based on the display period and the above-mentioned stage parameters.

[0062] Step S2023d: Obtain the metadata of the first abnormal frame.

[0063] In this embodiment, after acquiring the first abnormal frame, the server acquires the metadata of the first abnormal frame. The metadata is used to characterize the operating parameters of the target page's display device at the time the first abnormal frame was captured.

[0064] In one possible implementation, when acquiring the aforementioned set of target frames, the server synchronously acquires the metadata of each target frame, and then, after determining the first abnormal frame, directly acquires the metadata of the first abnormal frame.

[0065] In another possible implementation, in order to reduce cache pressure, after the first abnormal frame is identified, the server obtains the metadata of the first abnormal frame from the operation log of the display device based on the timestamp of the first abnormal frame.

[0066] Step S2023e: Determine the cause of the anomaly of the first abnormal frame based on the metadata of the first abnormal frame.

[0067] In this embodiment of the application, after obtaining the metadata of the first abnormal frame, the server determines the cause of the abnormality of the first abnormal frame based on the metadata of the first abnormal frame.

[0068] In one possible implementation, the server determines the cause of the first abnormal frame's abnormality based on its metadata.

[0069] In another possible implementation, the server performs anomaly analysis on the metadata of the first abnormal frame based on a first pre-analysis rule to determine the cause of the anomaly. For example, the first pre-analysis rule can be a pre-written algorithm or a pre-trained machine learning model.

[0070] Step S2024: Generate the first static detection result based on the first abnormal frame and abnormal parameters.

[0071] In this embodiment of the application, after obtaining the abnormal parameters corresponding to the first abnormal frame, the server generates a first static detection result based on the first abnormal frame and the abnormal parameters. The first static detection result is used to characterize the static display abnormality of the dynamic scene in the target frame set.

[0072] For example, the first static detection result includes a first abnormal frame and abnormal parameters.

[0073] Step S2025: If there is no first abnormal frame in the target frame set, generate a second static detection result.

[0074] In this embodiment, after obtaining the image similarity of each comparison group, the server generates a second static detection result if no first abnormal frame exists in the target frame set. The second static detection result is used to characterize the normal static display of the dynamic scene in the target frame set.

[0075] In the embodiments of this application, the above static detection results include a first static detection result or a second static detection result, and the static detection results also include the image similarity of each comparison group.

[0076] This embodiment provides a page detection method. By comparing frame-by-frame images between a reference frame set and a target frame set, the image similarity of each comparison group is obtained. Then, based on the image similarity of each comparison group, it is determined whether the static display of the dynamic scene in the target frame set is normal. Each comparison group includes a reference frame and a target frame. The reference frame set and the target frame set have the same sampling frequency. The reference frame and target frame are obtained based on the same sampling frequency, so that the reference frame and target frame can correspond one-to-one. The high-precision alignment between the reference frame and the target frame improves the accuracy of static detection of the target page. Moreover, in the case of abnormal static display of the dynamic scene in the target frame set, the stage to which the first abnormal frame belongs and the cause of the abnormality are obtained based on the timestamp of the first abnormal frame. The stage to which the abnormality belongs can be quickly located in the target frame set, and the cause of the abnormality can be quickly determined. While improving the accuracy of static detection, the static detection results can intuitively reflect the stage to which the first abnormal frame belongs and the cause of the abnormality, which is conducive to improving the efficiency of subsequent abnormality handling.

[0077] In addition, by using the stage parameters of the reference frame set and the timestamp of the first abnormal frame, the stage to which the first abnormal frame belongs can be located. By using the metadata of the first abnormal frame, the cause of the abnormality of the first abnormal frame can be determined. The metadata is used to characterize the operating parameters of the target page's display device when the first abnormal frame is captured. That is, while acquiring the first abnormal frame, the cause of the abnormality is analyzed based on the operating parameters of the display device. This is beneficial to eliminating abnormal situations caused by external devices, to quickly locate the cause of the abnormality, and to improve the efficiency of subsequent abnormality handling.

[0078] In an exemplary embodiment, step S203 includes: Step S2031: Perform adjacent frame detection on the target frame set to obtain the image difference between each adjacent group.

[0079] In this embodiment, after obtaining the target frame set, the server performs adjacent frame detection on the target frame set to obtain the image difference between each adjacent group. An adjacent group includes two adjacent target frames, and there are identical frames between adjacent adjacent groups. That is, two adjacent adjacent groups include three target frames.

[0080] Step S2032: Based on the image difference between each adjacent group, the first dynamic detection result is obtained.

[0081] In this embodiment of the application, after obtaining the image difference degree between each of the above-mentioned adjacent groups, the server obtains the first dynamic detection result based on the image difference degree between each of the adjacent groups.

[0082] Specifically, step S2032 above includes at least one of the following: Step S2032a: The three target frames contained in two adjacent groups whose image difference is less than the second threshold are identified as the second abnormal frames; the cause of the abnormality of the second abnormal frames is determined based on the metadata of the second abnormal frames; wherein, the first dynamic detection result includes the second abnormal frames and the cause of the abnormality of the second abnormal frames. Step S2032b: Identify two target frames in adjacent groups whose image difference is greater than the third threshold as the third abnormal frame; determine the cause of the abnormality of the third abnormal frame based on the metadata of the third abnormal frame; wherein, the first dynamic detection result includes the third abnormal frame and the cause of the abnormality of the third abnormal frame.

[0083] For example, the second abnormal frame can be called a stuttering frame. If the second abnormal frame exists in the target frame set, the dynamic display of the dynamic scene in the target frame set will stutter. The third abnormal frame can be called a screen tearing frame (or a missing frame). If the third abnormal frame exists in the target frame set, the dynamic display of the dynamic scene in the target frame set will tear (or a missing frame).

[0084] For example, the second and third thresholds are related to the type of the dynamic element. Optionally, in this embodiment, when obtaining the second and third thresholds, the server obtains the type of the dynamic element in the target page; further, the second and third thresholds are determined based on a preset relationship and the type of the dynamic element. The preset relationship includes the correspondence between the type and the second threshold, and the correspondence between the type and the third threshold.

[0085] For example, similar to the first abnormal frame described above, in one possible implementation, the server determines the cause of the abnormality of the second abnormal frame from its metadata. In another possible implementation, the server performs anomaly analysis on the metadata of the second abnormal frame based on a second pre-analysis rule to obtain the cause of the abnormality of the second abnormal frame. For example, the second pre-analysis rule can be a pre-written algorithm or a pre-trained machine learning model.

[0086] For example, similar to the first abnormal frame described above, in one possible implementation, the server determines the cause of the abnormality of the third abnormal frame from its metadata. In another possible implementation, the server performs anomaly analysis on the metadata of the third abnormal frame based on a third pre-analysis rule to obtain the cause of the abnormality of the third abnormal frame. For example, the third pre-analysis rule can be a pre-written algorithm or a pre-trained machine learning model.

[0087] Step S2033: Obtain target visual features from the target frame set.

[0088] In this embodiment, after obtaining the aforementioned target frame set, the server retrieves target visual features from the target frame set. These target visual features characterize the changes in dynamic elements within the target frame set, such as the trajectory of dynamic elements and patterns of display style changes.

[0089] In one possible implementation, the server extracts visual features from the target frame set to obtain target visual features.

[0090] In another possible implementation, in order to reduce static feature interference and improve the accuracy of target visual features, the server extracts visual features from the dynamic regions in the target frame set to obtain target visual features.

[0091] In one exemplary embodiment, after acquiring the target frame set, the server compares the pixel values ​​of adjacent frames in the target frame set to obtain target comparison results. Further, regions where the pixel value change indicated by the target comparison results is greater than a fifth threshold are designated as dynamic regions, thus obtaining dynamic regions in each target frame. Then, visual detection is performed on the dynamic regions in the target frame set to obtain target visual features. The dynamic regions in the target frame set include the dynamic regions in each target frame. Correspondingly, the server designates regions where the pixel value change indicated by the target comparison results is less than or equal to the fifth threshold as static regions, thus obtaining static regions in each target frame. Exemplarily, the fifth threshold can be any value, and can be flexibly set and adjusted according to actual conditions; this embodiment does not limit this.

[0092] In another exemplary embodiment, since the second dynamic detection result below requires the use of reference visual features, and the reference visual frames are pre-stored information, to save time, after obtaining the aforementioned set of reference frames, the server performs pixel value comparison on adjacent frames in the set of reference frames to obtain a reference comparison result; further, the region where the pixel value change indicated by the reference comparison result is greater than a fifth threshold is taken as a dynamic region, and the dynamic region and region coordinates in each reference frame are obtained; then, visual detection is performed on the dynamic region in the set of reference frames to obtain reference visual features. The dynamic region in the set of reference frames includes the dynamic region in each reference frame. Correspondingly, the server takes the region where the pixel value change indicated by the reference comparison result is less than or equal to the fifth threshold as a static region, and obtains the static region in each reference frame. After obtaining the set of target frames, the server determines the pixel coordinate mapping relationship between the reference frame and the target frame based on the marker frame of the reference frame and the marker frame of the target frame; further, based on this pixel coordinate mapping relationship and the region coordinates in each reference frame, the dynamic region in each target frame is obtained; then, visual detection is performed on the dynamic region in the set of target frames to obtain target visual features. For example, the marker frame of the reference frame is the aforementioned start reference frame, and the marker frame of the target frame is the aforementioned start target frame; or, the marker frame of the quasi-frame is the aforementioned end reference frame, and the marker frame of the target frame is the aforementioned end target frame. Of course, in practical applications, since both the target frame and the reference frame are obtained from the target page, the server can directly obtain the pixel coordinate mapping relationship based on the display size of the target frame and the display size of the reference frame.

[0093] Step S2034: Based on the difference between the target visual features and the reference visual features corresponding to the reference frame set, a second dynamic detection result is obtained.

[0094] In this embodiment, after acquiring the aforementioned target visual features, the server obtains a second dynamic detection result based on the difference between the target visual features and the baseline visual features corresponding to the baseline frame set. The baseline visual features are used to characterize the changes in dynamic elements within the baseline frame set.

[0095] Specifically, step S2034 above includes: Step S2034a: If the difference between the target visual features and the reference visual features is less than the fourth threshold, a first dynamic result is generated; wherein, the first dynamic result is used to characterize the normal dynamic display of the dynamic scene in the target frame set. Step S2034b: If the difference between the target visual features and the reference visual features is greater than or equal to the fourth threshold, a second dynamic result is generated; wherein, the second dynamic result is used to characterize the dynamic display anomaly of the dynamic scene in the target frame set.

[0096] For example, the fourth threshold can be any value, and the fourth threshold can be flexibly set and adjusted according to the actual situation. This application embodiment does not limit this.

[0097] In the embodiments of this application, the second dynamic detection result includes either the first dynamic result or the second dynamic result, and the dynamic detection result includes both the first dynamic detection result and the second dynamic detection result.

[0098] The page detection method provided in this embodiment obtains a first dynamic detection result by using adjacent frames in the target frame set, and obtains a second dynamic detection result by using target visual features and reference visual features. That is, it performs dynamic detection on the dynamic scene from both its own and reference perspectives, which improves the accuracy of the dynamic detection result and thus improves the page detection effect.

[0099] Furthermore, three target frames in two adjacent groups with image differences less than a second threshold are identified as second abnormal frames, and the cause of the abnormality is determined based on the metadata of the second abnormal frames. Similarly, two target frames in adjacent groups with image differences greater than a third threshold are identified as third abnormal frames, and the cause of the abnormality is determined based on the metadata of the third abnormal frames. Dynamic detection from the perspective of the target frames themselves is used to determine whether stuttering or frame skipping occurs, improving the detection effect for dynamic scenes and thus improving the page detection effect. In addition, different second and third thresholds are set for different types of dynamic elements, taking into account the diversity of dynamic scenes. Flexibly setting different thresholds for different types of dynamic elements helps reduce false positives for abnormal frames during dynamic detection and improves the accuracy of page detection.

[0100] In addition, the changes in dynamic elements in dynamic scenes are detected separately based on target visual features and baseline visual features, which further improves the page detection effect.

[0101] In an exemplary embodiment, step S204 includes: Step S2041: Generate similarity curves based on the image similarity of each comparison group.

[0102] In this embodiment, after obtaining the static detection results, the server generates a similarity curve based on the image similarity of each comparison group. The horizontal axis of the similarity curve represents the target frame, and the vertical axis represents the image similarity.

[0103] Step S2042: If the static detection results include the first static detection results, the first abnormal frame is labeled on the similarity curve with the first display style and abnormal parameters based on the first static detection results.

[0104] In this embodiment of the application, after obtaining the above similarity curve, if the static detection result includes the first static detection result, the server marks the first abnormal frame on the similarity curve with a first display style and abnormal parameters based on the first static detection result.

[0105] Step S2043: If the first dynamic detection result includes the second abnormal frame and the cause of the second abnormal frame, the second abnormal frame is labeled on the similarity curve with the second display style and the cause of the second abnormal frame.

[0106] In this embodiment of the application, after obtaining the above similarity curve, if the first dynamic detection result includes the second abnormal frame and the cause of the second abnormal frame, the server marks the second abnormal frame on the similarity curve with the second display style and the cause of the second abnormal frame.

[0107] Step S2044: If the first dynamic detection result includes the third abnormal frame and the cause of the third abnormal frame, the third abnormal frame is labeled on the similarity curve with the third display style and the cause of the third abnormal frame.

[0108] In the embodiments of this application, after obtaining the above similarity curve, if the first dynamic detection result includes the third abnormal frame and the cause of the third abnormal frame, the server marks the third abnormal frame on the similarity curve with the third display style and the cause of the third abnormal frame.

[0109] In this embodiment of the application, the page detection results include the labeled similarity curve and the second dynamic detection results.

[0110] Optionally, the labeled similarity curve and the second dynamic detection result constitute the aforementioned visualization report. For example, as shown... Figure 3 As shown, in the specific display, in the similarity curve 30, the first abnormal frame is directly displayed in the first display style, the second abnormal frame is directly displayed in the second display style, and the third abnormal frame is directly displayed in the third display style. The second dynamic detection result (not shown in the figure) is also directly displayed. Then, if an operation targeting the first abnormal frame is detected, the abnormal parameters are displayed; if an operation targeting the second abnormal frame is detected, the abnormal reason for the second abnormal frame is displayed; if an operation targeting the third abnormal frame is detected, the abnormal reason for the third abnormal frame is displayed. For example, the operation is a click operation.

[0111] The page detection method provided in this embodiment generates a similarity curve through image similarity and marks abnormal frames on the similarity curve, so that the page detection results can be displayed intuitively. The intuitive display of the similarity curve and abnormal frames is conducive to improving the efficiency of subsequent anomaly processing.

[0112] In addition, combined Figure 4 This application provides a complete description of the page detection method, specifically including: Step S401: Obtain the set of reference frames.

[0113] Step S402: Obtain the stage parameters and reference visual features of the reference frame set from the reference frame set.

[0114] Step S403: In response to the dynamic scene detection instruction for the target page, obtain the set of target frames corresponding to the dynamic scene from the target page.

[0115] Static testing includes: Step S404: Compare the reference frame set and the target frame set frame by frame to obtain the image similarity of each comparison group; Step S405: Based on the image similarity of each comparison group, determine whether there is a first abnormal frame in the target frame set; if there is a first abnormal frame in the target frame set, execute steps S406 and S408; if there is no first abnormal frame in the target frame set, execute steps S407 and S408. Step S406: Based on the timestamp of the first abnormal frame and the stage parameters of the reference frame set, obtain the abnormal parameters corresponding to the first abnormal frame and generate the first static detection result. Step S407: Generate the second static detection result; Step S408: Generate static detection results; the static detection results include either the first static detection result or the second static detection result.

[0116] Dynamic detection includes: Step S409: Perform adjacent frame detection on the target frame set to obtain the image difference between each adjacent group; Step S410: Based on the image difference between each adjacent group, the first dynamic detection result is obtained; Step S411: Obtain target visual features from the target frame set, and obtain the second dynamic detection result based on the difference between the target visual features and the reference visual features; Step S412: Generate dynamic detection results; the dynamic detection results include the first dynamic detection result and the second dynamic detection result.

[0117] Step S412: Based on the static detection results and dynamic detection results, generate the page detection results corresponding to the dynamic scene detection instructions.

[0118] As one or more specific application embodiments of this application, the optimal implementation scheme or the scheme that the inventors most want to embody is described in combination with the specific application scenario.

[0119] This embodiment also provides a page detection device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0120] This embodiment provides a page detection device, such as... Figure 5 As shown, it includes: The target acquisition module 501 is used to obtain the set of target frames corresponding to the dynamic scene from the target page in response to the dynamic scene detection command for the target page.

[0121] The static detection module 502 is used to perform static detection on the target frame set based on the reference frame set corresponding to the dynamic scene, and obtain the static detection result.

[0122] The dynamic detection module 503 is used to perform dynamic detection on the target frame set based on the reference frame set and the target frame set, and obtain the dynamic detection result.

[0123] The result acquisition module 504 is used to generate page detection results corresponding to dynamic scene detection instructions based on static detection results and dynamic detection results.

[0124] In some alternative implementations, the static detection module 502 includes: The image comparison unit is used to compare the reference frame set and the target frame set frame by frame to obtain the image similarity of each comparison group; wherein, a comparison group includes a reference frame and a target frame, and the reference frame set and the target frame set have the same sampling frequency; The first determining unit is used to determine the target frame in the comparison group whose image similarity is less than a first threshold as the first abnormal frame; The parameter determination unit is used to obtain the abnormal parameters corresponding to the first abnormal frame based on the timestamp of the first abnormal frame; wherein, the abnormal parameters include the stage to which the first abnormal frame belongs and the cause of the abnormality; The first generation unit is used to generate a first static detection result based on the first abnormal frame and abnormal parameters. The first static detection result is used to characterize the static display abnormality of the dynamic scene in the target frame set. The second generation unit is used to generate a second static detection result when there is no first abnormal frame in the target frame set; wherein the second static detection result is used to characterize the static display of the dynamic scene in the target frame set as normal; wherein the static detection result includes either the first static detection result or the second static detection result; the static detection result also includes the image similarity of each comparison group.

[0125] In some alternative implementations, the parameter determination unit is used for: Obtain the stage parameters of the reference frame set; wherein, the stage parameters include at least two stages contained in the reference frame set, and the display time of each stage; Based on the timestamp of the first abnormal frame, locate the display period of the first abnormal frame in the target frame set; Based on the display time period and stage parameters, determine the stage to which the first abnormal frame belongs; Obtain the metadata of the first abnormal frame. The metadata is used to characterize the operating parameters of the target page's display device when the first abnormal frame is captured. Based on the metadata of the first abnormal frame, determine the cause of the abnormality of the first abnormal frame.

[0126] In some alternative implementations, the dynamic detection module 503 includes: The difference comparison unit is used to perform adjacent frame detection on the target frame set to obtain the image difference between each adjacent group; wherein, an adjacent group includes two adjacent target frames, and there are identical frames between adjacent adjacent groups; The first acquisition unit is used to obtain the first dynamic detection result based on the image difference between each adjacent group; The feature acquisition unit is used to acquire target visual features from the target frame set. The target visual features are used to characterize the changes of dynamic elements in the target frame set. The feature comparison unit is used to obtain a second dynamic detection result based on the difference between the target visual features and the reference visual features corresponding to the reference frame set; wherein the reference visual features are used to characterize the changes of dynamic elements in the reference frame set; wherein the dynamic detection result includes a first dynamic detection result and a second dynamic detection result.

[0127] In some optional implementations, the first acquisition unit is used for at least one of the following: The three target frames contained in two adjacent groups whose image difference is less than the second threshold are identified as the second abnormal frames; the cause of the abnormality of the second abnormal frames is determined based on the metadata of the second abnormal frames; wherein, the first dynamic detection result includes the second abnormal frames and the cause of the abnormality of the second abnormal frames. Two target frames in adjacent groups whose image difference is greater than a third threshold are identified as the third abnormal frame; the cause of the abnormality of the third abnormal frame is determined based on the metadata of the third abnormal frame; wherein, the first dynamic detection result includes the third abnormal frame and the cause of the abnormality of the third abnormal frame.

[0128] In some alternative embodiments, the apparatus further includes: The type retrieval module is used to retrieve the type of dynamic elements on the target page; The threshold acquisition module is used to determine the second threshold and the third threshold based on the preset relationship and the type of the dynamic element; wherein, the preset relationship includes the correspondence between the type and the second threshold, and the correspondence between the type and the third threshold.

[0129] In some alternative implementations, the feature comparison unit is used for: If the difference between the target visual features and the reference visual features is less than a fourth threshold, a first dynamic result is generated; wherein, the first state result is used to characterize the normal dynamic display of the dynamic scene in the target frame set; If the difference between the target visual features and the baseline visual features is greater than a fourth threshold, a second dynamic result is generated; wherein, the second dynamic result is used to characterize the dynamic display anomalies of the dynamic scene in the target frame set; The second dynamic detection result includes either the first dynamic result or the second dynamic result.

[0130] In some alternative embodiments, the apparatus further includes: The curve generation module is used to generate similarity curves based on the image similarity of each comparison group; where the horizontal axis of the similarity curve is the target frame and the vertical axis is the image similarity. The first annotation module is used to annotate the first abnormal frame on the similarity curve with a first display style and abnormal parameters based on the first static detection result when the static detection result includes the first static detection result. The second annotation module is used to annotate the second abnormal frame on the similarity curve with a second display style and the cause of the second abnormal frame when the first dynamic detection result includes the second abnormal frame and the cause of the second abnormal frame. The third annotation module is used to annotate the third abnormal frame on the similarity curve with the third display style and the abnormal reason of the third abnormal frame when the first dynamic detection result includes the third abnormal frame and the abnormal reason of the third abnormal frame; wherein, the page detection result includes the annotated similarity curve and the second dynamic detection result.

[0131] The page detection apparatus provided in this application can execute the page detection method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the various modules and units described above are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0132] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0133] The following is a detailed reference. Figure 6 This diagram illustrates a suitable structural schematic for implementing the electronic device described in the embodiments of this application. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 601, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 602 or a program loaded from memory 608 into random access memory (RAM) 603. The RAM 603 also stores various programs and data required for the operation of the electronic device. The processor 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0134] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0135] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a memory 608, or installed from a ROM 602. When the computer program is executed by the processor 601, it performs the functions defined in the page detection method of embodiments of this application.

[0136] Figure 6The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0137] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded over a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the page detection method shown in the above embodiments is implemented.

[0138] A portion of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0139] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A page detection method, characterized in that, The method includes: In response to a dynamic scene detection command for a target page, a set of target frames corresponding to the dynamic scene is obtained from the target page; Static detection is performed on the target frame set based on the reference frame set corresponding to the dynamic scene to obtain static detection results; Based on the reference frame set and the target frame set, dynamic detection is performed on the target frame set to obtain dynamic detection results; Based on the static detection results and the dynamic detection results, the page detection results corresponding to the dynamic scene detection instructions are generated.

2. The method according to claim 1, characterized in that, The static detection of the target frame set based on the reference frame set corresponding to the dynamic scene, to obtain the static detection result, includes: The reference frame set and the target frame set are compared frame by frame to obtain the image similarity of each comparison group; wherein, a comparison group includes a reference frame and a target frame, and the reference frame set and the target frame set have the same sampling frequency; The target frame in the comparison group whose image similarity is less than the first threshold is identified as the first abnormal frame; Based on the timestamp of the first abnormal frame, obtain the abnormal parameters corresponding to the first abnormal frame; wherein, the abnormal parameters include the stage to which the first abnormal frame belongs and the cause of the abnormality; Based on the first abnormal frame and the abnormal parameters, a first static detection result is generated. The first static detection result is used to characterize the static display abnormality of the dynamic scene in the target frame set. If the first abnormal frame is not present in the target frame set, a second static detection result is generated; wherein, the second static detection result is used to characterize that the static display of the dynamic scene in the target frame set is normal; The static detection results include either the first static detection result or the second static detection result; the static detection results also include the image similarity of each of the comparison groups.

3. The method according to claim 2, characterized in that, The step of obtaining the abnormal parameters corresponding to the first abnormal frame based on the timestamp of the first abnormal frame includes: Obtain the stage parameters of the reference frame set; wherein the stage parameters include at least two stages contained in the reference frame set, and the display time of each stage; Based on the timestamp of the first abnormal frame, locate the display period of the first abnormal frame in the target frame set; Based on the display period and the stage parameters, determine the stage to which the first abnormal frame belongs; Obtain the metadata of the first abnormal frame, wherein the metadata is used to characterize the operating parameters of the display device of the target page when the first abnormal frame is captured; Based on the metadata of the first abnormal frame, determine the cause of the abnormality of the first abnormal frame.

4. The method according to claim 1, characterized in that, The step of dynamically detecting the target frame set based on the reference frame set and the target frame set to obtain dynamic detection results includes: Adjacent frame detection is performed on the target frame set to obtain the image difference between each adjacent group; wherein, an adjacent group includes two adjacent target frames, and there are identical frames between adjacent adjacent groups; The first dynamic detection result is obtained based on the image difference between each adjacent group; Target visual features are obtained from the target frame set, and the target visual features are used to characterize the changes of dynamic elements in the target frame set; A second dynamic detection result is obtained based on the difference between the target visual features and the baseline visual features corresponding to the baseline frame set; wherein, the baseline visual features are used to characterize the changes of dynamic elements in the baseline frame set. The dynamic detection results include the first dynamic detection result and the second dynamic detection result.

5. The method according to claim 4, characterized in that, The first dynamic detection result obtained based on the image difference between each adjacent group includes at least one of the following: The three target frames contained in two adjacent groups whose image difference is less than the second threshold are identified as the second abnormal frames; Based on the metadata of the second abnormal frame, the cause of the abnormality of the second abnormal frame is determined; wherein, the first dynamic detection result includes the second abnormal frame and the cause of the abnormality of the second abnormal frame; Two target frames in adjacent groups whose image difference is greater than a third threshold are identified as third abnormal frames; the cause of the abnormality of the third abnormal frame is determined based on the metadata of the third abnormal frame; wherein, the first dynamic detection result includes the third abnormal frame and the cause of the abnormality of the third abnormal frame.

6. The method according to claim 5, characterized in that, The method further includes: Obtain the type of the dynamic element from the target page; Based on a preset relationship and the type of the dynamic element, the second threshold and the third threshold are determined; wherein the preset relationship includes the correspondence between the type and the second threshold, and the correspondence between the type and the third threshold.

7. The method according to claim 4, characterized in that, The second dynamic detection result is obtained based on the difference between the target visual features and the reference visual features corresponding to the reference frame set, including: If the difference between the target visual features and the reference visual features is less than a fourth threshold, a first dynamic result is generated; wherein, the first dynamic result is used to characterize the normal dynamic display of the dynamic scene in the target frame set; If the difference between the target visual features and the reference visual features is greater than the fourth threshold, a second dynamic result is generated; wherein the second dynamic result is used to characterize the dynamic display anomaly of the dynamic scene in the target frame set; The second dynamic detection result includes either the first dynamic result or the second dynamic result.

8. The method according to claim 2 or 4, characterized in that, The step of generating page detection results corresponding to the dynamic scene detection instruction based on the static detection results and the dynamic detection results includes: A similarity curve is generated based on the image similarity of each comparison group; wherein, the horizontal axis of the similarity curve is the target frame, and the vertical axis is the image similarity; If the static detection results include the first static detection result, the first abnormal frame is marked on the similarity curve with a first display style and abnormal parameters based on the first static detection result; If the first dynamic detection result includes a second abnormal frame and the cause of the abnormality of the second abnormal frame, the second abnormal frame is marked on the similarity curve with a second display style and the cause of the abnormality of the second abnormal frame. If the first dynamic detection result includes a third abnormal frame and the cause of the abnormality of the third abnormal frame, the third abnormal frame is marked on the similarity curve with a third display style and the cause of the abnormality of the third abnormal frame. The page detection results include the labeled similarity curve and the second dynamic detection results.

9. A page detection device, characterized in that, The device includes: The target acquisition module is used to obtain a set of target frames corresponding to the dynamic scene from the target page in response to a dynamic scene detection command for the target page. The static detection module is used to perform static detection on the target frame set based on the reference frame set corresponding to the dynamic scene, and obtain static detection results; The dynamic detection module is used to perform dynamic detection on the target frame set based on the reference frame set and the target frame set, and obtain dynamic detection results; The result acquisition module is used to generate page detection results corresponding to the dynamic scene detection instruction based on the static detection results and the dynamic detection results.

10. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory stores computer instructions, and the processor executes the page detection method according to any one of claims 1 to 8 by executing the computer instructions.

Images