Online traffic data analysis method and system

Abstract

The present invention relates to the technical field of traffic analysis, and discloses an online traffic data analysis method and system, including: collecting traffic set data of each zone of the platform within a detection period, and obtaining a first traffic characteristic value of each zone; collecting historical traffic set data of each zone in the detection period and historical target conversion data of each zone, and calculating the historical target conversion value of each zone; obtaining the second traffic characteristic value of each zone, calculating the comprehensive traffic value of the platform, and obtaining the comprehensive conversion results analysis result; comparing with the traffic threshold, and combining the traffic risk characteristics of each zone, generating a traffic anomaly report. The present invention can accurately evaluate the traffic value and conversion efficiency, comprehensively consider the traffic scale, historical conversion capacity and real-time user behavior, accurately evaluate the actual value of each partition traffic and the overall conversion efficiency of the platform, can effectively identify traffic anomalies and risks, can timely discover abnormal traffic fluctuations, and accurately locate the source of risks.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic analysis, and in particular to an online traffic data analysis method and system. Background Art

[0002] With the rapid development of the Internet today, people complete their work and life needs through online behaviors every day. For various online platforms, the analysis of online traffic data has also become an indispensable task in various fields to meet the needs of business development.

[0003] The existing traffic analysis methods have the problem that the sources of platform traffic data are wide and scattered, which makes it difficult to collect and process. Traditional traffic analysis mostly uses traffic scale as the main evaluation basis, and is unable to comprehensively measure traffic quality and value. It does not consider historical traffic, conversion data, and real-time user behavior to build a scientific and reasonable traffic evaluation system. At the same time, it is difficult to quickly discover abnormal traffic fluctuations. Even if they are discovered, it is difficult to deeply analyze the causes of the abnormalities and locate the sources of risks, and it is impossible to ensure the stable operation of the platform. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides an online traffic data analysis method to solve the above problems.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides an online traffic data analysis method, comprising: Collect the flow set data of each area of ​​the platform within the detection period, and process the data to obtain the first flow characteristic value of each area; Collect the historical traffic set data of each zone in the detection period and the historical target conversion data of each zone, calculate the historical target conversion value of each zone, and obtain the key coefficient of each zone of the platform; Based on the first traffic characteristic value and the key coefficient, the second traffic characteristic value of each zone is obtained, and the comprehensive traffic value of the platform is calculated according to the real-time user behavior data of each zone of the platform collected during the detection period, and the comprehensive conversion result analysis result is obtained; Based on the first flow characteristic value of each zone, the value is compared with the flow threshold value, and combined with the flow risk characteristics of each zone, a flow anomaly report is generated.

[0006] As a preferred solution of the online traffic data analysis method described in the present invention, the traffic set data of each area of ​​the platform within the detection period is collected, and the data is processed to obtain the first traffic characteristic value of each area, including: Divide the online platform into several partitions, set a detection cycle, and collect real-time traffic set data of each zone within the cycle, wherein the traffic set data includes the number of visits, number of visitors, and number of page views of each zone; Preprocessing the traffic set data, including data deduplication, outlier filtering, missing value supplementation, and data normalization; Based on the preprocessed traffic set data, the traffic contribution of each visited page in each zone is calculated. The traffic contribution is obtained by multiplying the traffic density of each page by the traffic peak ratio, and weighted calculation is performed by multiplying the total traffic set sum of each page by the traffic contribution to obtain the first traffic characteristic value of each zone.

[0007] As a preferred solution of the online traffic data analysis method of the present invention, the first traffic characteristic value of each zone is expressed as: ; in, Represents a partition The first flow characteristic value, Represents a partition The total number of pages, Display page Number of visitors, Display page The traffic contribution of Display page of visits, Display page of views.

[0008] As a preferred solution of the online traffic data analysis method of the present invention, the historical target conversion value of each zone is calculated to obtain the key coefficients of each zone of the platform, including: Collecting the flow set data of the historical period of each zone in the detection period during the same period, wherein the historical flow set data of the same period is represented by the flow set data of at least one historical period with the same time length and time characteristics as the current detection period; The historical target conversion data of each zone includes the number of users who completed the target behavior and the number of times the target behavior was completed in each zone within at least one historical period of the same period, and the target behavior includes the user behavior of consulting, lead retention, purchase and payment on the platform; According to the historical target conversion data of each zone, the historical target conversion value of each zone is calculated to obtain the key coefficient of each zone of the platform.

[0009] As a preferred solution of the online traffic data analysis method of the present invention, the calculation of the comprehensive traffic value of the platform includes: The second flow characteristic value of each zone is obtained by multiplying the first flow characteristic value of the zone by the key coefficient; User behavior data collected in each area of ​​the platform during the detection period, including user dwell time, bounce rate, and page scroll depth; Based on the user behavior data, the comprehensive traffic value of the platform is calculated , expressed as: ; in, Represents a partition The second flow characteristic value, Represents a partition Average page dwell time, Represents a partition Average page bounce rate, Represents a partition The average scroll depth of the page, , , represents the weight coefficient, Indicates the total number of partitions.

[0010] As a preferred solution of the online traffic data analysis method of the present invention, obtaining the comprehensive conversion results analysis results includes: Obtain the number of times the platform's comprehensive user target behavior is completed, and combined with the platform's comprehensive traffic value, calculate the platform's conversion achievement score; Using time series as the dimension, plot the change curves of the comprehensive traffic value of the platform and each area and the number of completions of each target behavior to extract the change characteristics; Divide the changing characteristics into different categories, combine with user behavior data, analyze the reasons for low conversion, and formulate optimization strategies.

[0011] As a preferred solution of the online traffic data analysis method of the present invention, generating a traffic anomaly report includes: The flow threshold is determined by the calculated flow lower limit through the average value and standard deviation of the historical flow data of the partition; Compare the first flow characteristic value of each zone and each time period with the flow threshold. If it is greater than the flow threshold, it is judged that there is no flow abnormality. If it is less than the flow threshold, it is judged that there is a flow abnormality. If traffic anomalies occur, the causes of the anomalies are analyzed in combination with the traffic risk characteristics of each zone, and a traffic anomaly report is generated, wherein the traffic risk characteristics include access jams, multiple refreshes in a short period of time, illegal requests, and page errors.

[0012] In a second aspect, the present invention provides an online traffic data analysis system, comprising: The collection module is used to collect the flow set data of each area of ​​the platform within the detection period, and perform data processing to obtain the first flow characteristic value of each area; A calculation module is used to collect the historical traffic set data of each zone in the detection period and the historical target conversion data of each zone, calculate the historical target conversion value of each zone, and obtain the key coefficient of each zone of the platform; An analysis module, configured to obtain the second traffic characteristic value of each zone based on the first traffic characteristic value and the key coefficient, and calculate the comprehensive traffic value of the platform according to the real-time user behavior data of each zone of the platform collected during the detection period, and obtain the comprehensive conversion result analysis result; The anomaly detection module is used to generate a traffic anomaly report based on the first traffic characteristic value of each zone, comparing it with the traffic threshold, and combining the traffic risk characteristics of each zone.

[0013] In a third aspect, the present invention provides an electronic device, comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the online traffic data analysis method are implemented.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the online traffic data analysis method.

[0015] Compared with the prior art, the present invention has the following beneficial effects: the present invention collects traffic data of each zone of the platform from multiple dimensions, including real-time traffic, historical traffic in the same period, and user behavior data, etc., so that operators can fully understand the distribution, scale, and change trend of platform traffic, as well as the interaction between users and the platform, and form a panoramic understanding of platform traffic; it can accurately evaluate the value of traffic and conversion efficiency, by calculating the key coefficient, the second traffic characteristic value, and the comprehensive traffic value, combined with the conversion results analysis, comprehensively considering the traffic scale, historical conversion capacity, and real-time user behavior, accurately evaluating the actual value of each partition traffic and the overall conversion efficiency of the platform, and providing a scientific basis for measuring business performance; it can effectively identify traffic anomalies and risks, compare the traffic value with the threshold and combine it with risk characteristics, so as to timely discover abnormal fluctuations in traffic and accurately locate the source of risk, providing strong support for ensuring stable operation of the platform and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0017] Figure 1 A schematic diagram of the overall process of an online traffic data analysis method according to an embodiment of the present invention; Figure 2 The figure is a schematic diagram of the overall structure of an online traffic data analysis system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0019] Reference Figure 1-Figure 2 , is an embodiment of the present invention, and provides an online traffic data analysis method, comprising: S101, collecting flow set data of each area of ​​the platform within a detection period, and performing data processing to obtain a first flow characteristic value of each area; S102, collect historical traffic set data of each zone in the detection period, combine the historical target conversion value of each zone, calculate the historical target conversion value of each zone, and obtain the key coefficient of each zone of the platform; S103, based on the first traffic characteristic value and the key coefficient, obtain the second traffic characteristic value of each zone, and calculate the comprehensive traffic value of the platform according to the user behavior data of each zone of the platform collected during the detection period, and obtain the comprehensive conversion result analysis result; S104: Based on the first flow characteristic value of each zone, the flow characteristic value is compared with the flow threshold value, and combined with the flow risk characteristics of each zone, a flow anomaly report is generated.

[0020] In a preferred embodiment, collecting the flow set data of each zone of the platform within the detection period, and performing data processing to obtain the first flow characteristic value of each zone includes: Divide the online platform into several zones, set a detection cycle, and collect real-time traffic data of each zone within the cycle. The traffic data includes the number of visits, visitors, and page views of each zone. Preprocess the traffic set data, including data deduplication, outlier filtering, missing value supplementation, and data normalization; Based on the preprocessed traffic set data, the traffic contribution of each visited page in each zone is calculated. The traffic contribution is obtained by multiplying the traffic density of each page by the traffic peak ratio, and then weightedly calculated by multiplying the total traffic set of each page by the traffic contribution to obtain the first traffic characteristic value of each zone.

[0021] Specifically, dividing the online platform into several partitions can provide a more objective understanding of the overall traffic situation of the platform, and the data is more accurate. The partition division rules can be divided according to the functionality or the user guidance behavior path designed by the platform. For example, according to the functionality, it can be divided into industry information area, knowledge popularization area, consulting service area, user case area, etc. The multi-page site of the platform is divided into different areas, each area contains at least one page, and its content includes but is not limited to content display (including text, video or live broadcast, etc.), interactive communication, business conversion (user information retention, service purchase, online consultation, etc.). Furthermore, a detection cycle is set, which can be set according to actual detection needs. It can be a time period (several hours) before the current moment or a period (year / month / week / day). According to the detection cycle, the actual traffic set data of the platform in the current period is collected to obtain the first traffic characteristic value of each area.

[0022] Furthermore, the traffic set data of each zone includes the number of visits, number of visitors, and page views of each zone. The number of visits refers to the number of times each page of the platform partition is visited during the detection period, reflecting the overall popularity of the page. The number of visitors refers to the number of different users who visit each page of the platform partition during the detection period. A user is counted as only one no matter how many times he visits, which is used to measure the user coverage of the platform. The page views refer to the total number of pages that users browse for more than 3 seconds in each platform partition during the detection period, which can understand the user's browsing depth of the platform content.

[0023] Furthermore, data preprocessing includes data deduplication, outlier filtering, missing value supplementation and data normalization. Data deduplication is to remove duplicate access record data, such as multiple identical records of the same user (multiple page refreshes); outlier filtering is to delete obviously unreasonable data, and upper and lower thresholds can be set to exclude data out of the range; missing value supplementation is for some missing data, which can be filled by the mean, median or interpolation method. For a large number of missing values, the reasons need to be further analyzed to decide whether to discard the relevant data; data normalization is to standardize data of different magnitudes and units. The data is converted to the same numerical range through normalization or standardization methods to facilitate subsequent data analysis and comparison.

[0024] In an optional implementation, the traffic density of the page The calculation is based on the page visits and page views to evaluate the traffic intensity of a partition per unit time, expressed as: ; in, Display page of visits, Display page Number of views, Indicates the number of hours of the detection cycle.

[0025] In an optional implementation, the peak traffic ratio of a page is calculated by comparing the peak traffic ratio of the page with the peak traffic ratio of the partition to compare the performance of different pages during peak periods. The detection cycle is counted every hour or multiple hours (set according to the actual scenario), and the data with the highest number of visits per hour or multiple hours is selected as the peak traffic ratio. Peak flow ratio Respectively expressed as: ; ; in, Indicates the total number of visits per hour or multiple hours. Display page The peak flow ratio, Display page The peak flow rate, Display page The partition The peak flow rate.

[0026] In an optional implementation, the traffic contribution of each accessed page in each zone is calculated by multiplying the traffic density of each page by the traffic peak ratio, which is expressed as: ; in, Display page Traffic contribution.

[0027] In an optional implementation, the first flow characteristic value of each zone is calculated as: ; in, Represents a partition The first flow characteristic value, Represents a partition The total number of pages, Display page The number of visitors.

[0028] It should be noted that this step can clearly understand the traffic conditions in different areas by collecting traffic set data from each area of ​​the platform, which helps to have an intuitive and comprehensive understanding of the overall traffic pattern of the platform and provide basic data for subsequent analysis. Accurately obtaining the traffic value of each area is the basis for all subsequent analysis. Making the basic data accurate and complete ensures the reliability and effectiveness of subsequent work such as traffic characteristics, conversion analysis, and anomaly detection. The traffic value reflects the business activity and user attention of each partition to a certain extent. Based on this, a preliminary assessment of the development trend of the business in each partition can be made, providing a reference for business decision-making.

[0029] In a preferred embodiment, the historical target conversion value of each zone is calculated to obtain the key coefficients of each zone of the platform, including: Collect the historical flow set data of each zone in the detection period, the historical flow set data of the same period is represented by the flow set data of at least one historical period with the same time length and time characteristics as the current detection period; The historical target conversion data of each zone includes the number of users who completed the target behavior and the number of times the target behavior was completed in each zone during the same historical period. The target behavior includes the platform's consultation, lead, purchase and payment user behavior; According to the historical target conversion data of each zone, the historical target conversion value of each zone is calculated to obtain the key coefficient of each zone of the platform.

[0030] Specifically, the historical periods of the same period in each zone of the current detection period are represented as at least one historical period that satisfies the same time length and the same time characteristics as the current detection period. For example, if the duration of the current detection period is 24 hours or 7 days, the period length of the selected historical period is also 24 hours or 7 days. The same time characteristics may be historical periods with the same dates as the current detection period in previous years. For example, if the current detection period is from August 1 to August 15, 2024, the historical period may be from August 1 to August 15 in previous years (2023, 2022). It may also be divided according to the time type, and the recent historical period with the same time type is selected. The time type is set according to the actual scenario, and may be a peak period, a peaceful period, or a slow period divided according to the business heat. If multiple historical periods of the same period are selected, the data of all periods are weighted averaged to obtain the calculated data, and the traffic set data of the historical period that meets the above two conditions is collected, wherein the traffic set data also includes the number of visits, the number of visitors, and the number of page views of each zone.

[0031] Furthermore, the historical target conversion data of each zone includes the number of users who completed the target behavior in each zone within at least one historical period and the number of times the target behavior was completed. The target behavior represents the operational behavior that the platform defines as the expected user. It is used as a factor to measure the platform's conversion results and to represent the platform's performance output. The target behavior includes but is not limited to the platform's consulting behavior, effective lead retention behavior, purchasing behavior, and paid user behavior.

[0032] In an optional implementation, the historical target conversion value of each zone is calculated to obtain the key coefficient of each zone of the platform, including: According to the user's consulting behavior, effective lead retention behavior, purchasing behavior and payment behavior, the number of users who completed the target behavior in each partition and the number of times the target behavior was completed are obtained, and the historical target conversion value of each partition is calculated. The historical target conversion value includes the user conversion rate of the partition And traffic conversion rate , respectively expressed as: ; ; in, Indicates the number of users who completed the target behavior in the partition, Indicates the total number of visitors entering the partition, Indicates the total number of times the partition completes the target behavior, Indicates the total number of accesses to the partition; By multiplying the user conversion rate of the partition by the traffic conversion rate, we can calculate the historical target conversion value of the partition, that is, the key coefficient of each zone on the platform.

[0033] It should be noted that by analyzing the historical traffic set data and historical target conversion data, it is possible to discover the relationship between traffic and conversion in different periods, find the rules and trends of traffic conversion, and provide a basis for optimizing current business. Using the historical data for the same period as a comparison benchmark will help to judge the conversion capacity of the partition to the platform, and facilitate objective statistics of the platform's comprehensive traffic data. The key coefficients comprehensively consider the historical traffic and conversion conditions, and can more comprehensively and objectively reflect the inherent characteristics and potential of each district in traffic conversion, providing important quantitative indicators for the subsequent further evaluation and analysis of the traffic in each district.

[0034] In a preferred embodiment, calculating the comprehensive flow value of the platform includes: The second flow characteristic value of each zone is obtained by multiplying the first flow characteristic value of the zone by the key coefficient; User behavior data collected in each area of ​​the platform during the detection period, including user dwell time, bounce rate, and page scroll depth; Based on user behavior data, calculate the comprehensive traffic value of the platform , expressed as: ; in, Represents a partition The second flow characteristic value, Represents a partition Average page dwell time, Represents a partition Average page bounce rate, Represents a partition The average scroll depth of the page, , , represents the weight coefficient, Indicates the total number of partitions.

[0035] Specifically, the user behavior data of each area of ​​the platform during the detection period includes user dwell time, bounce rate, and page scroll depth, which are used to reflect the impact of users' real-time behavior on traffic. User dwell time indicates the length of time a user stays on a page, reflecting the user's interest in the content of the page. The longer the dwell time, the more interested the user is in the page content, which can increase the number of views. The timestamps of users entering and leaving the page can be recorded through the embedding technology, and the difference between the two can be calculated. The bounce rate indicates the proportion of users who leave after visiting only one page, reflecting the page's attractiveness to users. A high bounce rate means that the page content is not attractive, the page loads slowly, or users do not find the information they want. It is an important indicator for measuring page quality and user experience. It can reduce the number of page views by analyzing the user behavior path, counting the number of users who only visit a single page, and then dividing it by the total number of people who visit the page; page scrolling depth refers to the distance or proportion that users scroll on the page, reflecting the user's browsing depth and participation in the page content. It is used to measure whether the user has viewed all or most of the content of the page. A higher scrolling depth may indicate that the user is more concerned about the page content and is willing to spend time browsing more information, which can increase the number of page views. It can be calculated by monitoring the user's scrolling operation on the page and recording the change in the position of the scroll bar, by calculating the pixel distance of the scroll or the percentage of the page that is scrolled.

[0036] Furthermore, based on the user dwell time, bounce rate, and page scroll depth of each page, the average data of the partition is calculated, the data is normalized, and then the comprehensive user behavior value of the partition is calculated. Finally, the comprehensive traffic value of the platform is calculated using the above formula.

[0037] In a preferred embodiment, obtaining the comprehensive transformation results analysis results includes: Obtain the number of times the platform's comprehensive user target behavior is completed, and combined with the platform's comprehensive traffic value, calculate the platform's conversion results score; Using time series as the dimension, plot the change curves of the comprehensive traffic value of the platform and each area and the number of completions of each target behavior to extract the change characteristics; Divide the changing characteristics into different categories, combine them with user behavior data, analyze the reasons for low conversion, and formulate optimization strategies.

[0038] In an optional embodiment, the conversion achievement score of the calculation platform is It is expressed as: ; in, Indicates the total number of times all platform users complete the target behavior within the detection period. Indicates the comprehensive traffic value of the platform.

[0039] Specifically, using time series as the dimension, draw a curve of the traffic value of each partition and the platform as a whole and the number of completions of each target behavior, and observe how the target behavior changes when the traffic rises or falls. For example, if the traffic of a partition continues to grow during a specific time period, but the target behavior gradually decreases, it may mean that the quality of the newly introduced traffic is not high, or that there is a problem in the conversion link when the partition is dealing with traffic growth. Perform a correlation analysis and calculate the correlation coefficient between the traffic value and the completion of the target behavior. If the correlation coefficient is positive and close to 1, it indicates that the traffic and conversion rate are strongly positively correlated, that is, traffic growth is often accompanied by an increase in conversion rate. If the correlation coefficient is negative or close to 0, it is necessary to deeply analyze the complex relationship between the two, and there may be other factors interfering with the conversion. Divide the changing characteristics into different categories, which can be high traffic and high conversion, high traffic and low conversion, low traffic and high conversion, and low traffic and low conversion. Analyze the content characteristics, user group characteristics or user behavior patterns of the analysis results of high traffic and high conversion and low traffic and high conversion. Learn from successful experiences and apply them to other partitions. For high traffic and low conversion and low traffic and low conversion, analyze the reasons in combination with user behavior data, evaluate their existence value, and consider whether to adjust the content, optimize functions or directly integrate them into other related partitions.

[0040] It should be noted that the second traffic characteristic value is obtained by multiplying the traffic value of each zone by the key coefficient. It takes into account the current traffic scale and combines the historical conversion capacity, and more comprehensively evaluates the quality and value of the traffic in each zone, avoiding the one-sidedness of judging solely by the traffic scale. It combines real-time user behavior data to calculate the comprehensive traffic value of the platform, which can comprehensively consider the interaction between users and the platform from multiple dimensions (such as user page dwell time, bounce rate, scrolling depth, etc.), and more accurately measure the actual value and effect of the overall traffic of the platform, rather than just focusing on the amount of traffic. Through comprehensive conversion results analysis based on comprehensive traffic values ​​and related data, we can deeply understand the overall conversion situation of the platform during the current detection cycle, such as which partitions have good conversion effects and which need to be improved, and the impact of user behavior performance in each link on conversion, so as to provide detailed guidance for optimizing platform functions and adjusting operation strategies.

[0041] In a preferred implementation, generating a traffic anomaly report includes: The flow threshold is determined by the calculated flow lower limit through the mean and standard deviation of the historical flow data of the partition; Compare the first flow characteristic value of each zone and each time period with the flow threshold. If it is greater than the flow threshold, it is judged that there is no flow abnormality. If it is less than the flow threshold, it is judged that there is a flow abnormality. If traffic anomalies occur, the cause of the anomaly is analyzed based on the traffic risk characteristics of each zone, and a traffic anomaly report is generated. The traffic risk characteristics include access freeze rate, short-term multiple refresh frequency, illegal requests, and page error rate.

[0042] Specifically, the historical traffic data of a partition can be the traffic data of the partition over a period of time (such as the past month or a quarter). It is expressed as: ; in, Represents the average value of historical traffic data, represents the standard deviation of historical traffic data, is the coefficient, and its value is 2-3.

[0043] Furthermore, the detection cycle is divided into multiple time periods, and the first traffic characteristic value of each zone and time period is calculated, and then compared with the traffic threshold to determine the traffic abnormality. The abnormal traffic risk characteristics can be analyzed through access freeze rate, short-term multiple refresh frequency, illegal request rate and page error rate. According to the data of abnormal traffic risk in the time period when the traffic abnormality occurs, the cause of the abnormality is analyzed and a traffic abnormality report is generated. For example, the abnormal traffic in a certain partition may be caused by a malicious attacker taking advantage of the traffic peak to attack; multiple refreshes in a certain partition in a short period of time may be because the partition page has been recently revised, and the new page layout and content display method make the user experience poor, causing users to repeatedly refresh and try to obtain information.

[0044] It should be noted that by comparing the traffic value of each zone with the traffic threshold, it is possible to quickly identify which time periods and areas have experienced abnormal traffic fluctuations, and issue early warning signals in a timely manner, so that operators can quickly pay attention to possible problems; combined with traffic risk characteristics, such as access freezes, multiple refreshes in a short period of time and other factors, the causes of traffic anomalies can be further analyzed to determine whether they are caused by technical problems, abnormal user behavior or changes in the business itself, which helps to take targeted measures to solve the problem. Traffic anomaly reports provide important decision-making basis for platform operations and management. Management can adjust resource allocation, optimize platform performance, and improve business strategies in a timely manner based on the report content to ensure the stable operation of the platform and user experience, reduce potential risks, and improve the overall operational efficiency and benefits of the platform.

[0045] The present invention collects traffic data of each zone of the platform from multiple dimensions, including real-time traffic, historical traffic in the same period, and user behavior data, etc., so that operators can fully understand the distribution, scale, and change trend of platform traffic, as well as the interaction between users and the platform, and form a panoramic understanding of platform traffic; it can accurately evaluate the value of traffic and conversion efficiency, by calculating the key coefficient, the second traffic characteristic value, and the comprehensive traffic value, combined with the conversion results analysis, comprehensively considering the traffic scale, historical conversion capacity, and real-time user behavior, accurately evaluating the actual value of each partition traffic and the overall conversion efficiency of the platform, and providing a scientific basis for measuring business performance; it can effectively identify traffic anomalies and risks, compare the traffic value with the threshold and combine it with the risk characteristics, so as to timely discover abnormal fluctuations in traffic and accurately locate the source of risk, providing strong support for ensuring the stable operation of the platform and user experience.

[0046] The above is a schematic scheme of an online traffic data analysis method of this embodiment. It should be noted that the technical scheme of the online traffic data analysis system and the technical scheme of the above-mentioned online traffic data analysis method belong to the same concept. For details not described in detail in the technical scheme of the online traffic data analysis system in this embodiment, please refer to the description of the technical scheme of the above-mentioned online traffic data analysis method.

[0047] The online traffic data analysis system in this embodiment includes: The collection module is used to collect the flow set data of each area of ​​the platform within the detection period, and perform data processing to obtain the first flow characteristic value of each area; The calculation module is used to collect the historical traffic set data of each zone in the detection period, as well as the historical target conversion data of each zone, calculate the historical target conversion value of each zone, and obtain the key coefficient of each zone of the platform; The analysis module is used to obtain the second traffic characteristic value of each zone based on the first traffic characteristic value and the key coefficient, and calculate the comprehensive traffic value of the platform according to the real-time user behavior data of each zone of the platform collected during the detection period, and obtain the comprehensive conversion result analysis result; The anomaly detection module is used to generate a traffic anomaly report based on the first traffic characteristic value of each zone, comparing it with the traffic threshold, and combining the traffic risk characteristics of each zone.

[0048] This embodiment further provides an electronic device suitable for online traffic data analysis, including: Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the online traffic data analysis method proposed in the above embodiment.

[0049] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the online traffic data analysis method proposed in the above embodiment is implemented.

[0050] The storage medium proposed in this embodiment and the method for implementing online traffic data analysis proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0051] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0052] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An online traffic data analysis method, characterized in that: include: Collect the flow set data of each area of ​​the platform within the detection period, and process the data to obtain the first flow characteristic value of each area; Collect the historical traffic set data of each zone in the detection period and the historical target conversion data of each zone, calculate the historical target conversion value of each zone, and obtain the key coefficient of each zone of the platform; Based on the first traffic characteristic value and the key coefficient, the second traffic characteristic value of each zone is obtained, and the comprehensive traffic value of the platform is calculated according to the real-time user behavior data of each zone of the platform collected during the detection period, and the comprehensive conversion result analysis result is obtained; Based on the first flow characteristic value of each zone, the value is compared with the flow threshold value, and combined with the flow risk characteristics of each zone, a flow anomaly report is generated.

2. The online traffic data analysis method according to claim 1, characterized in that: Collect the flow data of each area of ​​the platform within the detection period, and process the data to obtain the first flow characteristic value of each area, including: Divide the online platform into several partitions, set a detection cycle, and collect real-time traffic set data of each zone within the cycle, wherein the traffic set data includes the number of visits, number of visitors, and number of page views of each zone; Preprocessing the traffic set data, including data deduplication, outlier filtering, missing value supplementation, and data normalization; Based on the preprocessed traffic set data, the traffic contribution of each visited page in each zone is calculated. The traffic contribution is obtained by multiplying the traffic density of each page by the traffic peak ratio, and weighted calculation is performed by multiplying the total traffic set sum of each page by the traffic contribution to obtain the first traffic characteristic value of each zone.

3. The online traffic data analysis method according to claim 2, characterized in that: The first flow characteristic value of each zone is expressed as: ； in, Represents a partition The first flow characteristic value, Represents a partition The total number of pages, Display page Number of visitors, Display page The traffic contribution of Display page of visits, Display page of views.

4. The online traffic data analysis method according to claim 2, characterized in that: Calculate the historical target conversion value of each area, and get the key coefficients of each area of ​​the platform, including: Collecting historical traffic set data of each zone in the detection period during the same period, wherein the historical traffic set data of the same period is represented by traffic set data of at least one historical period with the same time length and time characteristics as the current detection period; The historical target conversion data of each zone includes the number of users who completed the target behavior and the number of times the target behavior was completed in each zone within at least one historical period of the same period, and the target behavior includes the platform's consultation, lead retention, purchase and payment user behavior; According to the historical target conversion data of each zone, the historical target conversion value of each zone is calculated to obtain the key coefficient of each zone of the platform.

5. The online traffic data analysis method according to claim 1, characterized in that: The calculated comprehensive traffic value of the platform includes: The second flow characteristic value of each zone is obtained by multiplying the first flow characteristic value of the zone by the key coefficient; User behavior data collected in each area of ​​the platform during the detection period, including user dwell time, bounce rate, and page scroll depth; Based on the user behavior data, the comprehensive traffic value of the platform is calculated , expressed as: ； in, Represents a partition The second flow characteristic value, Represents a partition Average page dwell time, Represents a partition Average page bounce rate, Represents a partition The average scroll depth of the page, , , represents the weight coefficient, Indicates the total number of partitions.

6. The online traffic data analysis method according to claim 5, characterized in that: Obtaining comprehensive transformation results analysis results includes: Obtain the number of times the platform's comprehensive user target behavior is completed, and combined with the platform's comprehensive traffic value, calculate the platform's conversion achievement score; Using time series as the dimension, plot the change curves of the comprehensive traffic value of the platform and each area and the number of completions of each target behavior to extract the change characteristics; Divide the changing characteristics into different categories, combine with user behavior data, analyze the reasons for low conversion, and formulate optimization strategies.

7. The online traffic data analysis method according to claim 1, characterized in that: Generate traffic anomaly reports including: The flow threshold is determined by the calculated flow lower limit through the average value and standard deviation of the historical flow data of the partition; Compare the first flow characteristic value of each zone and each time period with the flow threshold. If it is greater than the flow threshold, it is judged that there is no flow abnormality. If it is less than the flow threshold, it is judged that there is a flow abnormality. If traffic anomalies occur, the causes of the anomalies are analyzed in combination with the traffic risk characteristics of each zone, and a traffic anomaly report is generated, wherein the traffic risk characteristics include access jams, multiple refreshes in a short period of time, illegal requests, and page errors.

8. An online traffic data analysis system, using the online traffic data analysis method according to any one of claims 1 to 7, characterized in that: include, The collection module is used to collect the flow set data of each area of ​​the platform within the detection period, and perform data processing to obtain the first flow characteristic value of each area; A calculation module is used to collect the historical traffic set data of each zone in the detection period and the historical target conversion data of each zone, calculate the historical target conversion value of each zone, and obtain the key coefficient of each zone of the platform; An analysis module, configured to obtain the second traffic characteristic value of each zone based on the first traffic characteristic value and the key coefficient, and calculate the comprehensive traffic value of the platform according to the real-time user behavior data of each zone of the platform collected during the detection period, and obtain the comprehensive conversion result analysis result; The anomaly detection module is used to generate a traffic anomaly report based on the first traffic characteristic value of each zone, comparing it with the traffic threshold, and combining the traffic risk characteristics of each zone.

9. An electronic device, characterized in that: include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the online traffic data analysis method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: It stores computer executable instructions, which, when executed by a processor, can implement the steps of the online traffic data analysis method described in any one of claims 1 to 7.

Images