Method and device for analyzing buried points of pages

Abstract

The present disclosure relates to a method and device for analyzing buried point of a page, and relates to the field of computer technology. The buried point analysis method includes: taking a screenshot of the page the user is currently on, generating multiple real-time screenshots; calculating the first similarity between the multiple real-time screenshots and each sample buried point image, each sample buried point image is generated by taking a screenshot of the area that has changed in the page in advance; determining the real-time screenshot with a first similarity greater than a first threshold as a target buried point image; and performing buried point analysis on the page according to the target buried point image.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a method for analyzing page embedding points, a device for analyzing page embedding points, and a non-volatile computer-readable storage medium. Background Art

[0002] Site tracking analysis is a data collection method for website analysis. The collected data is used to track the usage of pages in order to further optimize products or provide data support for operations. For example, site tracking analysis includes the number of visits, number of visitors, length of stay, number of page views, bounce rate, etc.

[0003] In related technologies, R&D personnel add tracking code in advance during the page code development process based on product requirements to implement tracking analysis. Summary of the invention

[0004] The inventors of the present disclosure have discovered that the above-mentioned related technologies have the following problems: the business code needs to be invaded to implement the development of the tracking code, and it is difficult for developers to maintain it later, resulting in high development costs for tracking analysis.

[0005] In view of this, the present disclosure proposes a technical solution for page embedding analysis, which can reduce development costs.

[0006] According to some embodiments of the present disclosure, a method for analyzing buried point of a page is provided, including: taking a screenshot of the page where a user is currently located to generate multiple real-time screenshots; calculating a first similarity between the multiple real-time screenshots and each sample buried point image, each sample buried point image being generated by taking a screenshot of a region where changes have occurred in the page in advance; determining a real-time screenshot having a first similarity greater than a first threshold as a target buried point image; and performing buried point analysis on the page according to the target buried point image.

[0007] In some embodiments, calculating the first similarity between multiple real-time screenshots and each sample buried point image includes: calculating the second similarity between the multiple real-time screenshots; determining the real-time screenshots whose second similarity is less than a second threshold as candidate buried point images; and calculating the first similarity between each candidate buried point image and each sample buried point image.

[0008] In some embodiments, calculating the second similarity between the multiple real-time screenshots includes: calculating image features of each real-time screenshot; and calculating the second similarity according to the image features of each real-time screenshot.

[0009] In some embodiments, calculating the image features of each real-time screenshot includes: calculating the pixel mean of each row in each real-time screenshot; and calculating the pixel variance of each real-time screenshot as the image feature based on the pixel mean.

[0010] In some embodiments, taking a screenshot of the page the user is currently on and generating multiple real-time screenshots includes: obtaining the DOM (Document Object Model) of the page; converting the DOM of the page into an SVG (Scalable Vector Graphics) image, and then generating a real-time screenshot in a Canvas.

[0011] In some embodiments, taking a screenshot of the page the user is currently on and generating multiple real-time screenshots includes: in response to the user entering the page, taking a timed screenshot of the page and generating multiple real-time screenshots.

[0012] In some embodiments, multiple real-time screenshots and each sample buried point image are stored in a key-value pair format in the form of form data; calculating the first similarity between the multiple real-time screenshots and each sample buried point image includes: according to the key-value pair format, calling multiple real-time screenshots and each sample buried point image to calculate the first similarity.

[0013] In some embodiments, calculating the first similarity between multiple real-time screenshots and each sample buried point image includes: comparing the sizes of the real-time screenshots and the sample buried point images; when the real-time screenshot is larger than the sample buried point image, shrinking the real-time screenshot so that the size of the real-time screenshot is the same as the size of the sample buried point image; when the sample buried point image is larger than the size of the real-time screenshot, shrinking the sample buried point image so that the size of the sample buried point image is the same as the size of the real-time screenshot; calculating the first similarity between the sample buried point image and the real-time screenshot.

[0014] In some embodiments, the area in the page that has changed includes at least one of an area that has changed due to a pop-up event and an area that has changed due to an operation event.

[0015] In some embodiments, calculating the first similarity between multiple real-time screenshots and each sample buried point image includes: calculating the image features of each real-time screenshot and the image features of each sample buried point image; and calculating the first similarity based on the image features.

[0016] In some embodiments, calculating the image features of each real-time screenshot and the image features of each sample buried point image includes: calculating the pixel mean of each row in each real-time screenshot; based on the pixel mean, calculating the pixel variance of each real-time screenshot as its image feature; calculating the pixel mean of each row in each sample buried point image; based on the pixel mean, calculating the pixel variance of each sample buried point image as its image feature.

[0017] According to other embodiments of the present disclosure, a device for analyzing buried point of a page is provided, including: a screenshot unit, used to take a screenshot of the page where a user is currently located, and generate multiple real-time screenshots; a calculation unit, used to calculate a first similarity between the multiple real-time screenshots and each sample buried point image, each sample buried point image is generated by taking a screenshot of a region where changes have occurred in the page in advance; a determination unit, used to determine a real-time screenshot with a first similarity greater than a first threshold as a target buried point image; and an analysis unit, used to perform buried point analysis on the page according to the target buried point image.

[0018] In some embodiments, the calculation unit calculates the second similarity between multiple real-time screenshots; the determination unit determines the real-time screenshots whose second similarity is less than a second threshold as candidate buried point images; and the calculation unit calculates the first similarity between each candidate buried point image and each sample buried point image.

[0019] In some embodiments, the calculation unit calculates image features of each real-time screenshot; and calculates the second similarity based on the image features of each real-time screenshot.

[0020] In some embodiments, the calculation unit calculates the pixel mean of each row in each real-time screenshot; based on the pixel mean, the pixel variance of each real-time screenshot is calculated as the image feature.

[0021] In some embodiments, the screenshot unit obtains the DOM of the page, converts the DOM of the page into an SVG image, and then generates a real-time screenshot in Canvas.

[0022] In some embodiments, the screenshot unit takes a timed screenshot of the page in response to the user entering the page, generating multiple real-time screenshots.

[0023] In some embodiments, multiple real-time screenshots and each sample buried point image are stored in a key-value pair format in the form of form data; the calculation unit calls multiple real-time screenshots and each sample buried point image to calculate the first similarity according to the key-value pair format.

[0024] In some embodiments, the computing unit compares the sizes of the real-time screenshot and the sample buried point image; if the real-time screenshot is larger than the sample buried point image, the real-time screenshot is scaled down so that the size of the real-time screenshot is the same as the size of the sample buried point image; if the sample buried point image is larger than the size of the real-time screenshot, the sample buried point image is scaled down so that the size of the sample buried point image is the same as the size of the real-time screenshot; and a first similarity between the sample buried point image and the real-time screenshot is calculated.

[0025] In some embodiments, the area in the page that has changed includes at least one of an area that has changed due to a pop-up event and an area that has changed due to an operation event.

[0026] In some embodiments, the computing unit calculates the image features of each real-time screenshot and the image features of each sample buried point image; and calculates the first similarity based on the image features.

[0027] In some embodiments, the computing unit calculates the pixel mean of each row in each real-time screenshot; based on the pixel mean, calculates the pixel variance of each real-time screenshot as its image feature; calculates the pixel mean of each row in each sample buried point image; based on the pixel mean, calculates the pixel variance of each sample buried point image as its image feature.

[0028] According to some other embodiments of the present disclosure, a device for analyzing page embedding points is provided, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute the method for analyzing page embedding points in any one of the above embodiments based on instructions stored in the memory device.

[0029] According to some further embodiments of the present disclosure, a non-volatile computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method for analyzing the buried points of a page in any of the above embodiments is implemented.

[0030] In the above embodiment, the image used for the buried point analysis is determined by comparing the similarity between the real-time screenshot and the sample buried point image. In this way, the buried point analysis can be implemented without intrusion into the business code and participation of professional R&D personnel, thereby reducing the development cost of the buried point analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings, which constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0032] The present disclosure may be more clearly understood from the following detailed description with reference to the accompanying drawings:

[0033] Figure 1 A flowchart showing some embodiments of the method for analyzing page embedding points disclosed in the present invention;

[0034] Figure 2 Show Figure 1 Flowcharts of some embodiments of step 120;

[0035] Figure 3 Flowcharts showing other embodiments of the method for analyzing page embedding points disclosed in the present invention;

[0036] Figure 4 A block diagram showing some embodiments of the apparatus for analyzing page embedding points disclosed in the present invention;

[0037] Figure 5 A block diagram showing some other embodiments of the apparatus for analyzing page embedding points disclosed in the present invention;

[0038] Figure 6 A block diagram showing some further embodiments of the apparatus for analyzing page embedding points of the present disclosure. DETAILED DESCRIPTION

[0039] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure unless otherwise specifically stated.

[0040] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0041] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0042] Technologies, methods and equipment known to ordinary technicians in the relevant field may not be discussed in detail, but where appropriate, the technologies, methods and equipment should be considered part of the authorization specification.

[0043] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0044] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0045] As mentioned above, in order to solve the technical problem that R&D personnel need to invade the business code to report tracking points, and tracking point processing can only be completed by R&D personnel, resulting in high development costs, the following embodiments can be used to implement tracking point analysis.

[0046] Figure 1 A flowchart showing some embodiments of the method for analyzing page embedding points of the present disclosure.

[0047] like Figure 1 As shown, in step 110, a screenshot is taken of the page the user is currently on, and multiple real-time screenshots are generated. For example, in response to the user entering the page, a screenshot is taken of the page at a fixed time, and multiple real-time screenshots are generated.

[0048] In some embodiments, HTML2canvas technology can be used to perform real-time screenshots. For example, the DOM of the acquired page can be converted into an SVG image, and then a real-time screenshot is generated in Canvas.

[0049] In this way, since the SVG image uses XML (Extensible Markup Language), its structure is consistent with DOM, thereby improving the accuracy of the tracking point analysis.

[0050] In some embodiments, rasterizeHTML.js technology can also be used to perform real-time screenshots.

[0051] In step 120, a first similarity between the multiple real-time screenshots and each sample buried point image is calculated.

[0052] In some embodiments, each sample buried point image is generated by pre-screening the area of ​​the page that has changed. For example, the area of ​​the page that has changed includes at least one of an area that has changed due to a pop-up event and an area that has changed due to an operation event.

[0053] In some embodiments, a screenshot of the area of ​​the page that needs to be analyzed can be taken in advance and stored as a sample buried point image. The sample buried point image is used to compare with multiple real-time screenshots to filter out the target buried point image corresponding to the user.

[0054] For example, the area that needs to be analyzed may be the pop-up window exposure point-embedding area. Before and after the pop-up window appears, a screenshot of the area on the page where the pop-up window will appear can be taken as a sample point-embedding image.

[0055] For example, the area that needs to be analyzed can be the operation event tracking area. The operation event can be a click event, a sliding event, etc. You can take a screenshot of the area on the page where the change effect occurs before and after the click operation.

[0056] In some embodiments, the real-time screenshots may be pre-processed to improve the effect and efficiency of the tracking point analysis. For example, the real-time screenshots may be compressed.

[0057] For example, the front-end JS (Java Script) compression of real-time screenshots can be achieved through file API (file Application Programming Interface) and Canvas technology in HTML5 (HyperText Markup Language).

[0058] This saves bandwidth for users who submit tracking points and saves storage space.

[0059] In some embodiments, the multiple real-time screenshots and each sample embedded point image are stored in a key-value pair format in the form of Formdata (form data). According to the key-value pair format, the multiple real-time screenshots and each sample embedded point image are called to calculate the first similarity.

[0060] In this way, using the key-value pair format of FormData to submit and store images can realize the serialization of form data, thereby reducing the splicing of form elements and improving work efficiency.

[0061] For example, the real-time screenshots can be assembled into a set of key-value pairs sent using XML Http Request (XML HyperText Transfer Protocol Request, Extensible Markup Language Hypertext Transfer Protocol Request) through the FormData object.

[0062] You can set the encoding type of the form to multipart / form-data. The data format of the form transmitted through FormData is the same as the data format of the form transmitted through the submit() method.

[0063] In this way, FormData can be used independently of the form, so form data can be sent more flexibly.

[0064] In some embodiments, the real-time screenshot and the sample embedded point image may be preprocessed before calculating the first similarity. For example, the preprocessing may include image reduction processing, grayscale processing, etc.

[0065] For example, real-time screenshots and sample buried point images are grayed out and converted into grayscale images, thereby reducing the complexity of subsequent calculations.

[0066] For example, the size of the real-time screenshot is compared with that of the sample embedded point image. If the real-time screenshot is larger than the sample embedded point image, the real-time screenshot is reduced so that the size of the real-time screenshot is the same as that of the sample embedded point image; if the sample embedded point image is larger than the real-time screenshot, the sample embedded point image is reduced so that the size of the sample embedded point image is the same as that of the real-time screenshot; the first similarity between the sample embedded point image and the real-time screenshot is calculated.

[0067] In this way, the sizes of real-time screenshots and sample embedded point images can be kept consistent, which can improve the accuracy of similarity calculation and thus improve the accuracy of embedded point analysis.

[0068] In some embodiments, the image features of each real-time screenshot and the image features of each sample buried point image are calculated; and based on the image features, a first similarity is calculated.

[0069] For example, the pixel mean of each row in each real-time screenshot is calculated; based on the pixel mean, the pixel variance of each real-time screenshot is calculated as its image feature; the pixel mean of each row in each sample buried point image is calculated; based on the pixel mean, the pixel variance of each sample buried point image is calculated as its image feature.

[0070] For example, the first similarity may also be calculated using image template matching or SSIM (Structural SIMilarity).

[0071] In some embodiments, before calculating the first similarity, the real-time screenshots may be screened to eliminate the influence of similar real-time screenshots on the tracking point analysis. Figure 2 The embodiments in the present invention implement screening.

[0072] Figure 2 Show Figure 1 Flowchart of some embodiments of step 120 in FIG.

[0073] like Figure 2 As shown, in step 1210, a second similarity between the multiple real-time screenshots is calculated.

[0074] In some embodiments, the image features of each real-time screenshot are calculated; and the second similarity is calculated based on the image features of each real-time screenshot. For example, the pixel mean of each row in each real-time screenshot is calculated; and the pixel variance of each real-time screenshot is calculated as the image feature based on the pixel mean.

[0075] In some embodiments, the first similarity may also be calculated using image template matching or SSIM.

[0076] In step 1220, the real-time screenshot with a second similarity less than the second threshold is determined as a candidate buried point image.

[0077] In step 1230, a first similarity between each candidate buried point image and each sample buried point image is calculated.

[0078] In this way, the real-time screenshots with high similarity can be filtered out, and only the real-time screenshots with large differences can be retained as candidate embedded point images, thereby improving the efficiency and effect of embedded point analysis. Figure 1 Perform the remaining steps in the analysis.

[0079] In step 130, the real-time screenshot with the first similarity greater than the first threshold is determined as the target buried point image. In this way, the target buried point image corresponding to the user can be determined for buried point analysis based on the pre-stored sample buried point images without the need for professional participation and redevelopment of code.

[0080] In step 140, a buried point analysis is performed on the page according to the target buried point image.

[0081] Figure 3 Flowcharts showing other embodiments of the method for analyzing page embedding points of the present disclosure.

[0082] like Figure 3 As shown, in step 301, the user enters the current page and prepares to perform corresponding operations. For example, a screenshot of the area in the page that needs buried point analysis can be taken in advance and stored as a sample buried point image for later comparison to determine the user's target buried point image.

[0083] In some embodiments, after the user enters the current page, the buried point analysis can be implemented through several steps such as reporting user-related information, obtaining user behavior paths, and obtaining buried point images.

[0084] In some embodiments, the step of reporting user-related information may include step 302 and step 303 .

[0085] In step 302, the DOM of the page is loaded, and in response to the user entering the page, real-time screenshots are started.

[0086] In some embodiments, HTML2canvas technology can be used to take screenshots. The DOM of the page is converted into an SVG image, and then the SVG image is generated into Canvas. In this way, since the SVG image uses the XML representation form, it can be ensured that the structure of the screenshot is consistent with the DOM of the page.

[0087] In step 303, the real-time screenshot and the corresponding user information are stored and reported for use in burying point analysis of the user. For example, FormData can be used to implement image storage and reporting.

[0088] In some embodiments, the real-time screenshot is assembled into a set of key-value pairs for sending a request using XML Http Request through a FormData object. The encoding type of the form can be set to multipart / form-data, and the data format transmitted through FormData is consistent with the data format transmitted through the submit() method.

[0089] In this way, since FormData can be used independently of the form, form data can be sent more flexibly and conveniently.

[0090] In some embodiments, before storage and reporting, the file API and Canvas technology in HTML5 can be used to implement front-end JS compression of real-time screenshots and sample buried point images.

[0091] In some embodiments, the step of obtaining the user behavior path may include step 304 and step 305 .

[0092] In step 304, the real-time screenshot and the sample buried point image may be preprocessed. For example, the preprocessing may include image compression processing and grayscale processing.

[0093] For example, image compression processing can save transmission bandwidth and storage space; grayscale processing converts the image into a grayscale image to reduce the complexity of subsequent calculations.

[0094] In step 305, a second similarity between the real-time screenshots is calculated, and a second score of each real-time screenshot is determined.

[0095] In some embodiments, the average value υ of each row of pixels in each real-time screenshot is calculated respectively, and each υ corresponds to the characteristics of a row of images; according to the υ of each row of pixels in each real-time screenshot, the variance σ of each real-time screenshot is calculated as the image feature, which is used to show the fluctuation of each row of pixels; according to the difference between the variances of each real-time screenshot, the second score of each real-time screenshot is calculated. For example, the second score can be calculated according to C=1 / σ to characterize the similarity between images.

[0096] For example, the greater the difference between the image variances, the lower the second similarity and the higher the second score. The real-time screenshot with a higher second score is determined as a candidate buried point image.

[0097] Second, low similarity means that the user's operation on the page has caused the area on the page to change. In this way, real-time screenshots with high similarity can be filtered out to improve the efficiency and effect of embedded point analysis.

[0098] In some embodiments, the step of acquiring the buried point image may include steps 306 to 308.

[0099] In step 306, the real-time screenshot and the sample embedded point image may be preprocessed. For example, the preprocessing may include image reduction processing so that the size of the real-time screenshot and the sample embedded point image remain consistent.

[0100] In step 307, the first similarity between the filtered real-time screenshot (candidate buried point image) and the sample buried point image prepared in advance is calculated, and the first score of each candidate buried point image is determined.

[0101] In some embodiments, the first similarity can be calculated by the variance of the image. The smaller the difference between the image variances, the higher the first similarity and the higher the first score. A high first score indicates that the candidate buried point image is similar to the sample buried point image.

[0102] In step 308, the first image with the highest score is determined as the target buried point image.

[0103] In step 309, the buried point is reported according to the target buried point image, and buried point analysis is performed by analyzing the user's operation information, user identity information and other user-related information corresponding to the reported screenshot.

[0104] Figure 4 A block diagram showing some embodiments of the device for analyzing page embedding points of the present disclosure.

[0105] like Figure 4 As shown, the page embedding point analysis device 4 includes a screenshot unit 41, a calculation unit 42, a determination unit 43 and an analysis unit 44.

[0106] The screenshot unit 41 takes a screenshot of the page the user is currently on, generating a plurality of real-time screenshots.

[0107] In some embodiments, the area in the page that has changed includes at least one of an area that has changed due to a pop-up event and an area that has changed due to an operation event.

[0108] In some embodiments, the screenshot unit 41 obtains the DOM of the page, converts the DOM of the page into an SVG image, and then generates a real-time screenshot in Canvas.

[0109] In some embodiments, the screenshot unit 41 takes a timed screenshot of the page in response to the user entering the page, generating multiple real-time screenshots.

[0110] The calculation unit 42 calculates the first similarity between the multiple real-time screenshots and each sample embedded point image. Each sample embedded point image is generated by pre-screening the area of ​​the page that has changed.

[0111] In some embodiments, the calculation unit 42 calculates the image features of each real-time screenshot; and calculates the second similarity based on the image features of each real-time screenshot.

[0112] In some embodiments, the calculation unit 42 calculates the pixel mean of each row in each real-time screenshot; based on the pixel mean, the pixel variance of each real-time screenshot is calculated as the image feature.

[0113] In some embodiments, multiple real-time screenshots and each sample buried point image are stored in a key-value pair format in the form of form data; the calculation unit 42 calls multiple real-time screenshots and each sample buried point image to calculate the first similarity according to the key-value pair format.

[0114] In some embodiments, the computing unit 42 compares the sizes of the real-time screenshot and the sample buried-point image; if the real-time screenshot is larger than the sample buried-point image, the real-time screenshot is scaled down so that the size of the real-time screenshot is the same as that of the sample buried-point image; if the sample buried-point image is larger than the real-time screenshot, the sample buried-point image is scaled down so that the size of the sample buried-point image is the same as that of the real-time screenshot; and a first similarity between the sample buried-point image and the real-time screenshot is calculated.

[0115] In some embodiments, the calculation unit 42 calculates the image features of each real-time screenshot and the image features of each sample buried point image; and calculates the first similarity based on the image features.

[0116] In some embodiments, the calculation unit 42 calculates the pixel mean of each row in each real-time screenshot; based on the pixel mean, calculates the pixel variance of each real-time screenshot as its image feature; calculates the pixel mean of each row in each sample buried point image; based on the pixel mean, calculates the pixel variance of each sample buried point image as its image feature.

[0117] The determination unit 43 determines the real-time screenshot with a first similarity greater than a first threshold as a target buried point image.

[0118] In some embodiments, the calculation unit 42 calculates the second similarity between multiple real-time screenshots; the determination unit 43 determines the real-time screenshots whose second similarity is less than the second threshold as candidate buried point images; the calculation unit 42 calculates the first similarity between each candidate buried point image and each sample buried point image.

[0119] The analysis unit 44 performs a buried point analysis on the page according to the target buried point image.

[0120] Figure 5 A block diagram showing some other embodiments of the device for analyzing page embedding points of the present disclosure.

[0121] like Figure 5 As shown, the page embedding analysis device 5 of this embodiment includes: a memory 51 and a processor 52 coupled to the memory 51, and the processor 52 is configured to execute the page embedding analysis method in any one of the embodiments of the present disclosure based on the instructions stored in the memory 51.

[0122] The memory 51 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, a database, and other programs.

[0123] Figure 6 A block diagram showing some further embodiments of the apparatus for analyzing page embedding points of the present disclosure.

[0124] like Figure 6 As shown, the page embedding analysis device 6 of this embodiment includes: a memory 610 and a processor 620 coupled to the memory 610, and the processor 620 is configured to execute the page embedding analysis method in any one of the aforementioned embodiments based on the instructions stored in the memory 610.

[0125] The memory 610 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, and other programs.

[0126] The page embedding analysis device 6 may also include an input / output interface 630, a network interface 640, a storage interface 650, etc. These interfaces 630, 640, 650 and the memory 610 and the processor 620 may be connected, for example, via a bus 660. Among them, the input / output interface 630 provides a connection interface for input / output devices such as a display, a mouse, a keyboard, a touch screen, a microphone, and a speaker. The network interface 640 provides a connection interface for various networked devices. The storage interface 650 provides a connection interface for external storage devices such as SD cards and USB flash drives.

[0127] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transient storage media including but not limited to disk storage, CD-ROM, optical storage, etc., which contain computer-usable program code.

[0128] So far, the page embedding analysis method, page embedding analysis device and non-volatile computer-readable storage medium according to the present disclosure have been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed here.

[0129] The method and system of the present disclosure may be implemented in many ways. For example, the method and system of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present disclosure may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present disclosure. Therefore, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

[0130] Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A method for analyzing page embedding points. include: Take a screenshot of the page the user is currently on and generate multiple real-time screenshots; Calculating a first similarity between the multiple real-time screenshots and each sample embedded point image, wherein each sample embedded point image is generated by pre-screening a region of the page that has changed; Determine the real-time screenshot with a first similarity greater than a first threshold as the target buried point image; According to the target buried point image, the page is subjected to buried point analysis, The calculating of the first similarity between the plurality of real-time screenshots and each sample buried point image comprises: Calculating a second similarity between the plurality of real-time screenshots; Determine the real-time screenshots whose second similarity is less than the second threshold as candidate buried point images; Calculate the first similarity between each candidate buried point image and each sample buried point image.

2. The method for analyzing buried points according to claim 1, in, The calculating the second similarity between the plurality of real-time screenshots comprises: Calculate the image features of each real-time screenshot; The second similarity is calculated according to the image features of each of the real-time screenshots.

3. The method for analyzing buried points according to claim 2, in, The calculation of the image features of each real-time screenshot comprises: Calculate the pixel mean of each row in each real-time screenshot; According to the pixel mean, the pixel variance of each real-time screenshot is calculated as the image feature.

4. The method for analyzing buried points according to claim 1, in, The taking a screenshot of the page the user is currently on and generating multiple real-time screenshots includes: Get the document object model DOM of the page; After converting the DOM of the page into a scalable vector graphics (SVG) image, a real-time screenshot is generated in a canvas.

5. The method for analyzing buried points according to claim 1, in, The taking a screenshot of the page the user is currently on and generating multiple real-time screenshots includes: In response to the user entering the page, taking a regular screenshot of the page to generate the multiple real-time screenshots.

6. The method for analyzing buried points according to claim 1, in, The multiple real-time screenshots and the sample buried point images are stored in a key-value pair format in the form of form data; The calculating the first similarity between the multiple real-time screenshots and each sample buried point image comprises: According to the key-value pair format, the multiple real-time screenshots and the sample buried point images are called to calculate the first similarity.

7. The method for analyzing buried points according to claim 1, in, The calculating the first similarity between the multiple real-time screenshots and each sample buried point image comprises: Compare the sizes of the real-time screenshot and the sample buried point image; If the real-time screenshot is larger than the size of the sample embedded point image, the real-time screenshot is reduced so that the size of the real-time screenshot is the same as the size of the sample embedded point image; When the sample buried point image is larger than the size of the real-time screenshot, the sample buried point image is reduced so that the size of the sample buried point image is the same as the size of the real-time screenshot; Calculate the first similarity between the sample buried point image and the real-time screenshot.

8. The method for analyzing buried points according to any one of claims 1 to 7, in, The area that changes in the page includes at least one of an area that changes due to a pop-up event and an area that changes due to an operation event.

9. The method for analyzing buried points according to any one of claims 1 to 7, in, The calculating the first similarity between the multiple real-time screenshots and each sample buried point image comprises: Calculate the image features of each real-time screenshot and the image features of each sample buried point image; The first similarity is calculated according to the image features.

10. The method for analyzing buried points according to claim 9, in, The calculating of the image features of each real-time screenshot and the image features of each sample buried point image comprises: Calculate the pixel mean of each row in each real-time screenshot; Calculate the pixel variance of each real-time screenshot as its image feature according to the pixel mean; Calculate the pixel mean of each row in each sample buried point image; According to the pixel mean, the pixel variance of each sample buried point image is calculated as its image feature.

11. A device for analyzing page embedding points, include: A screenshot unit is used to take a screenshot of the page the user is currently on and generate multiple real-time screenshots; A calculation unit, used for calculating a first similarity between the plurality of real-time screenshots and each sample embedded point image, wherein each sample embedded point image is generated by pre-screening a region of the page that has changed; A determination unit, configured to determine the real-time screenshot having a first similarity greater than a first threshold as a target buried point image; An analysis unit is used to perform a buried point analysis on the page according to the target buried point image. in, The calculation unit calculates a second similarity between the plurality of real-time screenshots; The determination unit determines the real-time screenshot whose second similarity is less than the second threshold as a candidate buried point image; The calculation unit calculates the first similarity between each candidate buried point image and each sample buried point image.

12. The buried point analysis device according to claim 11, in, The screenshot unit obtains the document object model DOM of the page, converts the DOM of the page into a scalable vector graphic SVG image, and then generates a real-time screenshot in a canvas Canvas.

13. A device for analyzing page embedding points, include: Memory; and A processor coupled to the memory, the processor being configured to execute the page embedding analysis method described in any one of claims 1-10 based on instructions stored in the memory.

14. A non-volatile computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for analyzing page embedding points as described in any one of claims 1-10.

Images