A method and apparatus for predicting future page bounce rate based on RUM performance.

Abstract

This invention provides a method and apparatus for predicting future page bounce rates based on RUM performance. The method includes: S1, obtaining the total number of single-page visits and the total number of page entries, and calculating the page bounce rate; S2, obtaining RUM metric data and calculating the performance score of the metric data; S3, calculating a correlation coefficient based on the page bounce rate and the performance score; S4, predicting future page bounce rates related to future performance based on the correlation coefficient, and issuing a high bounce rate warning. This invention's method places greater emphasis on page performance and error considerations than traditional methods of analyzing page bounce rates, and is more comprehensive, faster, more convenient, and more interpretable.

Description

Technical Field

[0001] This invention belongs to the field of front-end anomaly technology, specifically to a method and apparatus for predicting future page bounce rate based on RUM performance. Background Technology

[0002] Google Analytics defines page bounce rate as: the percentage of visits to a single page or the percentage of visits a visitor leaves a website after entering (the target) page. It refers to the percentage of sessions where the page is the "unique page" in the session, out of all sessions that begin with that page.

[0003] When studying the relationship between User Access Monitoring (RUM) data and bounce rate, while some page bounces are based on subjective user reasons, such as no longer needing the page or having a better page to choose from, RUM data shows that more often, page bounces are due to poor page performance or page errors, directly impacting the bounce rate. In other words, if a page performs poorly or has many errors, users will simply leave.

[0004] Page bounce rate is commonly used in recommendation systems. If a recommended page does not meet the user's needs, the user will choose to leave. The page bounce rate can be used to assess the accuracy of the recommendation algorithm to some extent.

[0005] In RUM data, the bounce rate of key pages directly affects business data. Therefore, studying the relationship between RUM data metrics and page bounce rate is of great value.

[0006] In view of this, the present invention is hereby proposed. Summary of the Invention

[0007] In view of this, the present invention discloses a method and apparatus for predicting future page bounce rate based on RUM performance, which studies the relationship between RUM performance indicators and page bounce rate in a more comprehensive, faster, more convenient and interpretable manner, provides users with predictions of future performance-related page bounce rates, and issues high bounce rate warnings.

[0008] Specifically, the present invention is achieved through the following technical solutions:

[0009] In a first aspect, the present invention discloses a method for predicting future page bounce rate based on RUM performance, comprising the following steps:

[0010] S1. Obtain the total number of single-page visits and the total number of page entries, and calculate the page bounce rate;

[0011] S2. Obtain RUM metric data and calculate the performance score of the metric data;

[0012] S3. Calculate the correlation coefficient based on the page bounce rate and the performance score;

[0013] S4. Based on the correlation coefficient, predict the future page bounce rate related to future performance and issue a high bounce rate warning.

[0014] Furthermore, in step S3, the formula for calculating the correlation coefficient is: correlation coefficient = average performance score / page bounce rate.

[0015] Furthermore, in step S2, the RUM metric data includes: LCP metric, FID metric, CLS metric, and page error rate;

[0016] The LCP (Largest Contentful Paint) metric measures the maximum content rendered and load performance. For a good user experience, LCP should ideally occur within 2.5 seconds of the page initially loading.

[0017] The FID (First Input Delay) metric measures interactivity, indicating the initial input delay. For a good user experience, a page's FID should ideally be 100ms or less.

[0018] The CLS (Cumulative Layout Shift) metric measures cumulative layout shift and visual stability. For a good user experience, a page's CLS should ideally be kept at 0.1 or less.

[0019] Page error rate refers to the percentage of pages that contain errors out of all pages.

[0020] The RUM metrics measure and evaluate loading performance, interaction performance, visual stability, and page error rate. Without any metric or by measuring only a single metric, a comprehensive performance evaluation cannot be obtained. Therefore, the selection of RUM metrics is essential.

[0021] The performance score is calculated as follows: LCP metric × FID metric × CLS metric × Page Error Rate.

[0022] Furthermore, the formula for calculating the future page bounce rate is as follows:

[0023] The future page bounce rate = current average performance score × the correlation coefficient.

[0024] Furthermore, prior to step S1, a performance evaluation of the RUM metric data is performed, dividing the performance metric into three performance levels.

[0025] Furthermore, the performance profiles include: GOOD, NEEDSIMPOVEMENT, and POOR;

[0026] The criteria for determining the RUM indicator data are as follows:

[0027] The LCP index is GOOD in [0, 2.5 sec), NEEDSIMPO VEMENT in [2.5 sec, 4.0 sec), and POOR in [4.0 sec, +∞).

[0028] The FID index is GOOD in [0, 100ms), NEEDSIMPO VEMENT in [100ms, 300ms), and POOR in [300ms, +∞).

[0029] The CLS index is GOOD in [0, 0.1), NEEDSIMPOVEMENT in [0.1, 0.25), and POOR in [0.25, +∞).

[0030] Therefore, it is evident that for the LCP, FID, and CLS metrics, higher values ​​generally indicate worse performance, higher page error rates, and overall poorer performance. Based on the principle of mathematical multiplication, we can derive the evaluation criteria for these metrics.

[0031] The criteria for determining the performance indicators are as follows:

[0032] The performance metric is GOOD in [0, 25) and NEEDSIMPROVEMENT in [25, 300).

[0033] In [300, +∞).

[0034] Furthermore, in step S2, the method for calculating the page bounce rate is as follows:

[0035] The page bounce rate = total number of page entries / total number of page entries.

[0036] Secondly, the present invention discloses an apparatus for predicting future page bounce rate based on RUM performance, comprising:

[0037] Page bounce rate calculation module: Get the total number of single-page visits and the total number of page entries, and calculate the page bounce rate;

[0038] Performance score calculation module: acquires RUM metric data and calculates the performance score of the metric data;

[0039] Correlation coefficient calculation module: Calculates the correlation coefficient based on the page bounce rate and the performance score;

[0040] Future page bounce rate prediction module: Predicts the future page bounce rate related to future performance based on the correlation coefficient, and issues a high bounce rate warning.

[0041] Thirdly, the present invention discloses a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method for predicting future page bounce rates based on RUM performance as described in the first aspect.

[0042] Fourthly, the present invention discloses a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method for predicting future page bounce rate based on RUM performance as described in the first aspect.

[0043] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0044] The present invention proposes a method and apparatus for predicting future page bounce rates based on RUM performance. It determines the correlation between RUM performance score and page bounce rate, and focuses more on page performance and error considerations than traditional methods of analyzing page bounce rate. It provides users with predictions of future performance-related page bounce rates, and issues high bounce rate warnings. It is more comprehensive, faster, more convenient, and more interpretable. Attached Figure Description

[0045] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0046] Figure 1 A flowchart of a method for predicting future page bounce rate based on RUM performance provided in an embodiment of the present invention;

[0047] Figure 2 A schematic diagram of a device for predicting future page bounce rate based on RUM performance provided in an embodiment of the present invention;

[0048] Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0049] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings and specific embodiments. However, those skilled in the art will understand that the embodiments described below are some embodiments of the present invention, but not all embodiments, and are only used to illustrate the present invention, and should not be regarded as limiting the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] To more clearly illustrate the technical solutions in this invention, specific embodiments are described below.

[0051] Example

[0052] Reference Figure 1 As shown, this invention discloses a method for predicting future page bounce rate based on RUM performance, comprising the following steps:

[0053] S1. Obtain the total number of single-page visits and the total number of page entries, and calculate the page bounce rate;

[0054] S2. Obtain RUM metric data and calculate the performance score of the metric data;

[0055] S3. Calculate the correlation coefficient based on the page bounce rate and the performance score;

[0056] S4. Based on the correlation coefficient, predict the future page bounce rate related to future performance and issue a high bounce rate warning.

[0057] Furthermore, in step S3 above, the formula for calculating the correlation coefficient is: Correlation coefficient = Average performance score / Page bounce rate.

[0058] Furthermore, in step S2 above, the RUM metric data includes: LCP metric, FID metric, CLS metric, and page error rate;

[0059] The LCP (Largest Contentful Paint) metric measures the maximum content rendered and load performance. For a good user experience, LCP should ideally occur within 2.5 seconds of the page initially loading.

[0060] The FID (First Input Delay) metric measures interactivity, indicating the initial input delay. For a good user experience, a page's FID should ideally be 100ms or less.

[0061] The CLS (Cumulative Layout Shift) metric measures cumulative layout shift and visual stability. For a good user experience, a page's CLS should ideally be kept at 0.1 or less.

[0062] Page error rate refers to the percentage of pages that contain errors out of all pages.

[0063] The RUM metrics measure and evaluate loading performance, interaction performance, visual stability, and page error rate. Without any metric or by measuring only a single metric, a comprehensive performance evaluation cannot be obtained. Therefore, the selection of RUM metrics is essential.

[0064] Performance score = LCP metric × FID metric × CLS metric × Page error rate.

[0065] Furthermore, the formula for calculating the future page bounce rate is:

[0066] Future page bounce rate = current average performance score × correlation coefficient.

[0067] Furthermore, prior to step S1, a performance evaluation of the RUM metric data is performed, dividing the performance metric into three performance levels.

[0068] Furthermore, the performance profiles include: GOOD, NEEDSIMPOVEMENT, and POOR;

[0069] The criteria for determining RUM indicator data are:

[0070] The LCP indicator is GOOD in [0, 2.5 sec), NEEDSIMPOVEMENT in [2.5 sec, 4.0 sec), and POOR in [4.0 sec, +∞).

[0071] The FID metric is GOOD in [0, 100ms), NEEDSIMPOVEMENT in [100ms, 300ms), and POOR in [300ms, +∞).

[0072] The CLS index is GOOD in [0, 0.1), NEEDSIMPOVEMENT in [0.1, 0.25), and POOR in [0.25, +∞).

[0073] Therefore, it is evident that for the LCP, FID, and CLS metrics, higher values ​​generally indicate worse performance, higher page error rates, and overall poorer performance. Based on the principle of mathematical multiplication, we can derive the evaluation criteria for these metrics.

[0074] The criteria for judging performance indicators are as follows:

[0075] Performance metrics are GOOD in [0, 25), NEEDSIMPROVEMENT in [25, 300), and NEEDSIMPROVEMENT in [0, 25).

[0076] [300, +∞).

[0077] Furthermore, in step S2, the page bounce rate is calculated as follows:

[0078] Bounce rate = Total number of page entries / Total number of page entries.

[0079] In actual operation, this invention follows the following process, specifically as follows:

[0080] Taking data from a certain site on the cloud as an example, the total number of single-page visits and the total number of page entries were obtained from the previous day. Based on the obtained RUM (Recovery Management Unit) metric data, the specific performance level of each page was determined, and the page bounce rate for each performance level was calculated. Specifically, 574 pages were classified as GOOD, with 102 pages bouncing, resulting in a GOOD page bounce rate of approximately 102 / 574 ≈ 17.8%; 107 pages were classified as NEEDS IMPROVEMENT, with 21 pages bouncing, resulting in a NEEDS IMPROVEMENT page bounce rate of approximately 21 / 107 ≈ 19.6%; and 60 pages were classified as POOR, with 37 pages bouncing, resulting in a POOR page bounce rate of approximately 37 / 60 ≈ 61.7%.

[0081] Obtain the site's performance score from the previous day and directly obtain the average performance score through the cloud monitoring system. Based on the calculated page bounce rate and average performance score for each performance tier, specifically, the average performance score for the GOOD tier is 12.5, the average performance score for the NEEDS IMPROVEMENT tier is 162.5, and the average performance score for the POOR tier is 300.

[0082] Calculate the correlation coefficient, which is calculated as: Correlation Coefficient = Average Performance Score / Page Bounce Rate. Specifically, among the 574 GOOD pages, the correlation coefficient for the GOOD page is 12.5 / 17.8% = 0.014, the correlation coefficient for the NEEDS IMPROVEM ENT page is 162.5 / 19.6% = 0.001, and the correlation coefficient for the POOR page is 300 / 61.7% = 0.002.

[0083] Obtain the performance score for the current period and calculate the current average performance score. Then, calculate the future bounce rate based on the previously obtained correlation coefficient. Future bounce rate = Current average performance score × Correlation coefficient. Specifically, take the current average performance score for one hour. The current average performance score for the GOOD category is 15.2, for the NEEDS IMPROVEMENT category it is 171.3, and for the POOR category it is 327.5. Calculate the future bounce rate for each category: the future bounce rate for GOOD is 15.2 × 0.014 ≈ 21%, for NEEDS IMPROVEMENT it is 171.3 × 0.001 ≈ 17%, and for POOR it is 327.5 × 0.002 = 65.5%. This is how to predict the bounce rate for the next day based on the previous day's data, given only performance data for location pageviews.

[0084] This invention also provides a device for predicting future page bounce rate based on RUM performance, such as... Figure 2 As shown, it specifically includes:

[0085] Page bounce rate calculation module: Get the total number of single-page visits and the total number of page entries, and calculate the page bounce rate;

[0086] Performance score calculation module: acquires RUM metric data and calculates the performance score of the metric data;

[0087] Correlation coefficient calculation module: Calculates correlation coefficients based on page bounce rate and performance score;

[0088] Future page bounce rate prediction module: Predicts future page bounce rates related to future performance based on correlation coefficients and issues high bounce rate warnings.

[0089] The system mainly consists of the four modules mentioned above. By building this system, the goal of parallel operation can be achieved by mounting the same file system at the same time.

[0090] In practice, the above modules can be implemented as independent entities or combined in any way to be implemented as the same or several entities. For the specific implementation of each unit, please refer to the previous method implementation examples, which will not be repeated here.

[0091] Figure 3 This is a schematic diagram of the structure of a computer device disclosed in this invention. (Reference) Figure 3As shown, the computer device 400 includes at least a memory 402 and a processor 401. The memory 402 is connected to the processor via a communication bus 403 and is used to store computer instructions executable by the processor 401. The processor 401 is used to read computer instructions from the memory 402 to implement the steps of the method for predicting future page bounce rate based on RUM performance in the above embodiments.

[0092] For the above-described apparatus embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The apparatus embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0093] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal disks or removable disks), magneto-optical disks, and CD-ROMs and DVD-ROMs. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0094] Finally, it should be noted that although this specification contains many specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but are primarily used to describe the features of specific embodiments of a particular invention. Certain features described in the various embodiments of this specification may also be implemented in combination in a single embodiment. On the other hand, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation of a sub-combination.

[0095] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0096] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0097] The above are merely preferred embodiments disclosed in this invention and are not intended to limit this disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for predicting future page bounce rate based on RUM performance, characterized in that, Includes the following steps: S1. Obtain the total number of single-page visits and the total number of page entries, and calculate the page bounce rate; S2. Obtain RUM metric data and calculate the performance score of the metric data; S3. Calculate the correlation coefficient based on the page bounce rate and the performance score; S4. Based on the correlation coefficient, predict the future page bounce rate related to future performance and issue a high bounce rate warning. In step S3, the formula for calculating the correlation coefficient is: correlation coefficient = average performance score / page bounce rate; In step S2, the RUM metric data includes: LCP metric, FID metric, CLS metric, and page error rate; The performance score = LCP metric × FID metric × CLS metric × Page Error Rate; The formula for calculating the future page bounce rate is: The future page bounce rate = current average performance score × the correlation coefficient; Before step S1, a performance evaluation of the RUM metric data is performed, and the performance metric is divided into three performance levels. The performance profiles include: GOOD, NEEDSIMPOVEMENT, and POOR. The criteria for determining the RUM indicator data are as follows: The LCP index is GOOD in [0, 2.5 sec), NEEDSIMPOVEMENT in [2.5 sec, 4.0 sec), and POOR in [4.0 sec, +∞). The FID index is GOOD in [0, 100ms), NEEDSIMPOVEMENT in [100ms, 300ms), and POOR in [300ms, +∞). The CLS index is GOOD in [0, 0.1), NEEDSIMPOVEMENT in [0.1, 0.25), and POOR in [0.25, +∞). The criteria for determining the performance indicators are as follows: The performance metrics are GOOD in [0, 25), NEEDSIMPROVEMENT in [25, 300), and NEEDSIMPROVEMENT in [300, +∞).

2. The method for predicting future page bounce rate based on RUM performance according to claim 1, characterized in that, In step S2, the page bounce rate is calculated as follows: The page bounce rate = total number of page entries / total number of page entries.

3. An apparatus for predicting future page bounce rate based on RUM performance, using the method as described in claim 1 or 2, characterized in that, include: Page bounce rate calculation module: Get the total number of single-page visits and the total number of page entries, and calculate the page bounce rate; Performance score calculation module: acquires RUM metric data and calculates the performance score of the metric data; Correlation coefficient calculation module: Calculates the correlation coefficient based on the page bounce rate and the performance score; Future page bounce rate prediction module: Predicts the future page bounce rate related to future performance based on the correlation coefficient, and issues a high bounce rate warning.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed, it implements the steps of the method for predicting future page bounce rate based on RUM performance as described in claim 1 or 2.

5. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method for predicting future page bounce rate based on RUM performance as described in claim 1 or 2.

Images