A CDN network quality evaluation method, device and equipment and a storage medium

Abstract

The application discloses a CDN network quality evaluation method, device and equipment and a storage medium. The method comprises the following steps: acquiring a plurality of node IPs of a target website, a homepage delay of each node IP and a user quantity accessing the target website; calculating a load balancing score of each first node IP according to the distribution quantity of the users accessing the target website in each first node IP; taking a plurality of first node IPs with the load balancing score reaching a first threshold value as effective node IPs, and calculating a performance degradation score of a corresponding node of each effective node IP according to the homepage delay of each effective node IP; calculating a cross-region quality difference determination score of the target website according to the homepage delay of a second node IP and the homepage delay of the first node IP, and performing cross-region optimization adjustment on the target website according to the cross-region quality difference determination score. The application can solve the problem of the monitoring blind area of the existing CDN network quality evaluation method, and can be widely applied in the field of network communication.

Description

Technical Field

[0001] This invention relates to the field of network communication, and in particular to a CDN network quality assessment method, apparatus, device, and storage medium. Background Technology

[0002] A CDN (Content Delivery Network) is a network content service system built on IP networks. It provides content distribution and services based on the efficiency, quality, and order requirements of content access and application. A CDN can represent a high-quality, high-efficiency network application service model built on a network, characterized by a clear network order. However, current network communication systems lack the ability to monitor CDN network quality at a perceptual level. Existing CDN network quality assessment methods rely on routine server maintenance and lack technical means to assess CDN quality aspects such as node performance, load balancing, and cross-province quality differences, thus falling into a monitoring blind spot.

[0003] Therefore, the above problems urgently need to be solved. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a CDN network quality assessment method, apparatus, device, and storage medium to solve the problem of monitoring blind spots in existing CDN network quality assessment methods.

[0005] One aspect of this invention provides a CDN network quality assessment method, comprising:

[0006] Obtain multiple node IPs of the target website, the homepage latency of each node IP, and the number of users accessing the target website; designate the node IPs belonging to the target administrative region as the first node IPs, and the node IPs not belonging to the target administrative region as the second node IPs;

[0007] The load balancing score of each first node IP is calculated based on the number of users accessing the target website across each first node IP.

[0008] The first node IPs that reach the first threshold in the load balancing score are taken as valid node IPs, and the performance degradation score of the node corresponding to each valid node IP is calculated based on the homepage latency of each valid node IP.

[0009] The cross-regional quality assessment score of the target website is calculated based on the homepage latency of the second node IP and the homepage latency of the first node IP, and the target website is optimized and adjusted across regions based on the cross-regional quality assessment score.

[0010] Optionally, the step of obtaining the homepage latency of each of the node IPs includes:

[0011] The sum of the time required for all elements to load on the first non-redirecting page of the target website from each of the node IPs is obtained to obtain the homepage latency corresponding to each of the node IPs. The time required for all elements to load on the first non-redirecting page includes TCP connection latency, download latency, DNS resolution latency, SSL connection latency, and the loading time of the first byte.

[0012] Optionally, obtaining multiple node IPs of the target website includes:

[0013] Using users who access the target website as samples, obtain the sample number of each node IP of the target website;

[0014] Calculate the number of the first node IPs, and based on the number of the first node IPs and the corresponding number of samples, calculate the total number of samples for the first node IPs;

[0015] The average number of samples for the first node IP is calculated based on the total number of samples for the first node IP and the number of first node IPs.

[0016] Optionally, calculating the load balancing score for each first node IP based on the distribution of users accessing the target website across each first node IP includes:

[0017] The difference between the total number of samples and the average number of samples is calculated, and then the result of the difference is divided by the average number of samples to obtain the load balancing jitter rate of each first node IP, which is used as the load balancing score.

[0018] The load balancing score is used to classify the IPs of the first node, and the specific criteria for classification are as follows:

[0019] The first node IP whose load balancing score is within the first preset threshold range is designated as the load balancing node IP; the first node IP whose load exceeds the first preset threshold range is designated as the overloaded node IP; and the first node IP whose load is below the first preset threshold range is designated as the underloaded node IP.

[0020] Optionally, the step of taking multiple first node IPs whose load balancing scores reach a first threshold as valid node IPs, and calculating the performance degradation score of the node corresponding to each valid node IP based on the homepage latency of each valid node IP, includes:

[0021] Obtain the set of average homepage latency for each of the valid node IPs;

[0022] The minimum value in each set of homepage latency averages is used as the homepage jitter benchmark value of the corresponding node. The difference between the homepage jitter benchmark value and each homepage latency average in the set of homepage latency averages is calculated, and the result of each difference is divided with the corresponding homepage latency average to obtain the performance jitter rate of the node corresponding to each effective node IP, which is used as the performance degradation score.

[0023] The performance degradation score is used to identify nodes corresponding to valid node IPs whose performance degradation scores reach a second threshold as performance degradation nodes.

[0024] Optionally, the step of calculating the cross-regional quality assessment score of the target website based on the homepage latency of the second node IP and the homepage latency of the first node IP, and performing cross-regional optimization adjustments on the target website based on the cross-regional quality assessment score, includes:

[0025] The average homepage latency of the first node IP is obtained by dividing the total homepage latency of the first node IP by the total number of nodes corresponding to the first node IP.

[0026] The average homepage latency of the second node IP is obtained by dividing the total homepage latency corresponding to the second node IP by the total number of nodes corresponding to the second node IP.

[0027] The difference between the average latency of the second homepage and the average latency of the first homepage is calculated, and the result of the difference is then divided by the average latency of the first homepage to obtain the cross-regional jitter rate, which is used as the cross-regional quality defect judgment score.

[0028] The nodes corresponding to the second node IP or the first node IP that are outside the second preset threshold range in the cross-regional quality difference judgment score will be optimized and adjusted across regions.

[0029] Optionally, the method further includes:

[0030] Let the step of calculating the load balancing score of each first node IP based on the number of users accessing the target website on each first node IP be encapsulated as a sample layer;

[0031] The steps of taking multiple first node IPs whose load balancing scores reach a first threshold as valid node IPs and calculating the performance degradation score of the node corresponding to each valid node IP based on the homepage latency of each valid node IP are encapsulated as a first performance layer.

[0032] Let the steps of calculating the cross-regional quality defect judgment score of the target website based on the homepage latency of the second node IP and the homepage latency of the first node IP, and performing cross-regional optimization and adjustment of the target website based on the cross-regional quality defect judgment score be encapsulated as a second performance layer;

[0033] The sample layer, the first performance layer, and the second performance layer are executed sequentially, and the input parameters of the next layer are determined based on the output results of the previous layer.

[0034] Another aspect of the present invention provides a CDN network quality assessment device, comprising:

[0035] The first unit is used to obtain multiple node IPs of the target website, the homepage latency of each node IP, and the number of users accessing the target website; the node IPs belonging to the target administrative region are designated as the first node IPs, and the node IPs not belonging to the target administrative region are designated as the second node IPs;

[0036] The second unit is used to calculate the load balancing score of each first node IP based on the number of users accessing the target website across each first node IP.

[0037] The third unit is used to take multiple first node IPs that have reached the first threshold as valid node IPs, and to calculate the performance degradation score of the node corresponding to each valid node IP based on the homepage latency of each valid node IP.

[0038] The fourth unit is used to calculate the cross-regional quality defect judgment score of the target website based on the homepage latency of the second node IP and the homepage latency of the first node IP, and to perform cross-regional optimization and adjustment of the target website based on the cross-regional quality defect judgment score.

[0039] Another aspect of the present invention provides an electronic device, including a processor and a memory;

[0040] The memory is used to store programs;

[0041] The processor executes the program to implement the CDN network quality assessment method.

[0042] Another aspect of this invention provides a computer-readable storage medium storing a program that is executed by a processor to implement the CDN network quality assessment method described above.

[0043] This invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the aforementioned method.

[0044] Compared with the prior art, the present invention has at least the following beneficial effects:

[0045] This invention acquires key performance data for application-layer perception, namely node IP, homepage latency, and the number of users distributed across the network. Based on this key performance data, it performs CDN node load balancing scoring, CDN node performance degradation scoring, and CDN website cross-province quality assessment scoring. This fills the gap in the existing technology for CDN network quality analysis regarding the evaluation and monitoring of these three indicators, enabling precise location of CDN network quality issues. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used 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 those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 A flowchart illustrating a CDN network quality assessment method provided in an embodiment of the present invention;

[0048] Figure 2 This is a schematic diagram illustrating a process for obtaining multiple node IPs of a target website, provided as an embodiment of the present invention.

[0049] Figure 3 This is a schematic diagram of a process for scoring the performance degradation of nodes according to an embodiment of the present invention;

[0050] Figure 4 A schematic diagram of a cross-provincial quality difference determination process provided by an embodiment of the present invention;

[0051] Figure 5 This is a schematic diagram of a layered encapsulation and sequential parameter input process provided in an embodiment of the present invention;

[0052] Figure 6 An example flowchart of a CDN network quality assessment method provided in an embodiment of the present invention;

[0053] Figure 7 This is an example diagram of a balanced evaluation of nodes within a province provided in an embodiment of the present invention;

[0054] Figure 8 This is a schematic diagram of the cross-provincial quality difference algorithm results for CDN websites provided in an embodiment of the present invention;

[0055] Figure 9 A structural block diagram of a CDN network quality assessment device provided in an embodiment of the present invention;

[0056] Figure 10 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0058] It should be noted that although functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart.

[0059] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to limit the invention.

[0061] To achieve CDN network quality assessment, this invention proposes a CDN network quality assessment method. When assessing CDN network quality, it obtains multiple node IPs of the target website, the homepage latency of each node IP, and the number of users accessing the target website. It also implements node load balancing assessment, performance degradation assessment, and cross-provincial quality judgment of the target website, solving the problem of the lack of corresponding assessment methods in existing technologies. This CDN network quality assessment method can be applied to user terminals, servers, or an implementation environment composed of user terminals and servers. Furthermore, this CDN network quality assessment method can also be software running on user terminals or servers, such as applications with CDN network quality assessment functions. User terminals can be smartphones, tablets, laptops, desktop computers, smart speakers, smartwatches, etc., but are not limited to these. Servers can be independent physical servers, server clusters or distributed systems composed of multiple physical servers, or cloud servers providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0062] Reference Figure 1 This invention provides a CDN network quality assessment method, including steps S100 to S130, as follows:

[0063] S100: Obtain multiple node IPs of the target website, the homepage latency of each node IP, and the number of users accessing the target website; designate the node IPs belonging to the target administrative region as the first node IPs, and the node IPs not belonging to the target administrative region as the second node IPs.

[0064] It should be noted that the administrative regions in the embodiments of the present invention may include provinces, municipalities directly under the central government, autonomous regions, special administrative regions, prefecture-level administrative regions, county-level administrative regions, and township-level administrative regions. For ease of description, the embodiments of the present invention will be described using one type of administrative region as an example. Optionally, the embodiments of the present invention will be described using a province as an example, and the embodiments for other administrative regions will not be listed one by one. For details, please refer to the description using a province as an example. Therefore, the above-mentioned target administrative region can be a target province, the first node IP can be a node IP within the province, and the second node IP can be a node IP outside the province.

[0065] Specifically, in this embodiment of the invention, multiple websites can be selected as target websites. These target websites can be top-ranking websites in terms of traffic (e.g., the top 75 or top 100) or multiple websites requiring evaluation. For ease of description, this embodiment uses one target website as an example to illustrate the CDN network quality evaluation steps. Other target websites can refer to this example for CDN network quality evaluation. Furthermore, the target province can be a user-specified province or a province where CDN network quality evaluation is required. Specifying the target province is used to evaluate the CDN network quality of the target website within that province.

[0066] Next, the steps for obtaining the homepage latency of each node IP will be explained as follows:

[0067] The sum of the time required for all elements to load on the first non-redirecting page of the target website from each of the node IPs is obtained to obtain the homepage latency corresponding to each of the node IPs. The time required for all elements to load on the first non-redirecting page includes TCP connection latency, download latency, DNS resolution latency, SSL connection latency, and the loading time of the first byte.

[0068] Specifically, the homepage latency metric is defined as the sum of the time required to load all elements of the first non-redirecting page of a website. The calculation method for this metric includes: adding up the [TotalTime] of all sub-items of the first non-redirecting page of the website (where TotalTime = TCP connection latency + download latency + DNS resolution latency + SSL connection latency + first byte time).

[0069] In one alternative implementation, the homepage latency can be the HTTP homepage latency.

[0070] Reference Figure 2 This invention provides a flowchart for obtaining multiple node IPs of a target website, specifically including the following steps:

[0071] S200: Using users who access the target website as samples, obtain the sample number of each node IP of the target website.

[0072] Specifically, different users access the target website through different node IPs, so each node IP corresponds to a number of accessing users, and this number of users is used as the sample size for the corresponding node IP.

[0073] There can be multiple node IPs to access the target website. Each node IP corresponds to a node, which can be a network communication device, terminal, or base station.

[0074] For example, in embodiments of the present invention, the number of users of the target website can be more than 100,000, and the number of test samples (i.e., the number of users) per day can be more than 100 million.

[0075] S210: Calculate the number of the first node IPs, and calculate the total number of samples of the first node IPs based on the number of the first node IPs and the corresponding number of samples.

[0076] S220: Calculate the average number of samples for the first node IP based on the total number of samples for the first node IP and the number of samples for the first node IP.

[0077] S110: Calculate the load balancing score of each first node IP based on the number of users accessing the target website across each first node IP.

[0078] Based on the total number of samples obtained in step S210 and the average number of samples obtained in step S220, step S110 may further include: subtracting the total number of samples from the average number of samples, and then dividing the result of the difference by the average number of samples to obtain the load balancing jitter rate of each first node IP, which is used as the load balancing score.

[0079] The load balancing score is used to classify the IPs of the first node, and the specific criteria for classification are as follows:

[0080] The first node IP whose load balancing score is within the first preset threshold range is designated as the load balancing node IP; the first node IP whose load exceeds the first preset threshold range is designated as the overloaded node IP; and the first node IP whose load is below the first preset threshold range is designated as the underloaded node IP.

[0081] Optionally, the first preset threshold range can be selected or set according to actual needs. This embodiment of the invention does not specifically limit the first preset threshold range.

[0082] For example, the first preset threshold range can be (-0.5, 0.5), that is, node IPs with a load balancing score greater than or equal to 0.5 are considered as node IPs with excessive load, node IPs with a load balancing score less than or equal to -0.5 are considered as node IPs with excessive load, and node IPs with a load balancing score in (-0.5, 0.5) are considered as node IPs for load balancing.

[0083] S120: Select multiple first node IPs whose load balancing scores reach the first threshold as valid node IPs, and calculate the performance degradation score of the node corresponding to each valid node IP based on the homepage latency of each valid node IP.

[0084] Specifically, the load-balanced node IPs and the overloaded node IPs determined in step S110 above can be used as valid node IPs.

[0085] Furthermore, taking the first preset threshold range of (-0.5, 0.5) in step S110 above as an example, the first threshold in this embodiment of the invention can be the minimum value of the first preset threshold range, i.e., -0.5, that is, multiple local node IPs with a load balancing score of -0.5 are regarded as valid node IPs.

[0086] Reference Figure 3 This invention provides a flowchart for scoring the performance degradation of nodes, specifically including the following steps:

[0087] S300: Obtain the set of average homepage latency for each of the valid node IPs.

[0088] Specifically, each valid node IP corresponds to multiple accessing users (i.e., samples), and each user of that valid node IP generates a homepage latency when accessing the target website. The average homepage latency of each user of that valid node IP is the mean homepage latency of that valid node IP. The mean homepage latency of all valid node IPs forms a set of mean homepage latency.

[0089] S310: Take the minimum value in each set of homepage latency averages as the homepage jitter benchmark value of the corresponding node, subtract the homepage jitter benchmark value from each homepage latency average value in the set of homepage latency averages, and then divide each subtraction result by the corresponding homepage latency average value to obtain the performance jitter rate of the node corresponding to each effective node IP, which is used as the performance degradation score.

[0090] The performance degradation score is used to identify nodes corresponding to valid node IPs whose performance degradation scores reach a second threshold as performance degradation nodes.

[0091] Optionally, taking the first preset threshold range of (-0.5, 0.5) in step S110 as an example, the second threshold of this embodiment can be the maximum value of the first preset threshold range, i.e., 0.5, and the node corresponding to the valid node IP with a performance degradation score greater than or equal to 0.5 is regarded as the performance degradation node.

[0092] S130: Calculate the cross-regional quality assessment score of the target website based on the homepage latency of the second node IP and the homepage latency of the first node IP, and perform cross-regional optimization and adjustment on the target website based on the cross-regional quality assessment score.

[0093] Specifically, the cross-provincial quality assessment score of the target website can be calculated based on the homepage latency of the IP addresses of nodes outside the province to determine whether the target website is degraded when accessed from outside the province. Similarly, the cross-provincial quality assessment score of the target website can be calculated based on the homepage latency of the IP addresses of nodes within the province to determine whether the target website is degraded when accessed from within the province. Furthermore, if the cross-provincial quality assessment of the target website is deemed degraded, corresponding cross-provincial optimization adjustments will be made.

[0094] Furthermore, referring to Figure 4 This invention provides a flowchart for cross-provincial quality assessment.

[0095] S400: Divide the total homepage latency corresponding to the first node IP by the total number of nodes corresponding to the first node IP to obtain the average homepage latency of the first node IP.

[0096] S410: Divide the total homepage latency corresponding to the second node IP by the total number of nodes corresponding to the second node IP to obtain the average homepage latency of the second node IP.

[0097] S420: Subtract the average latency of the second homepage from the average latency of the first homepage, and then divide the result of the difference with the average latency of the first homepage to obtain the cross-region jitter rate, which is used as the cross-region quality defect judgment score.

[0098] S430: Perform cross-regional optimization adjustment on the nodes corresponding to the second node IP or the nodes corresponding to the first node IP that are outside the second preset threshold range for cross-regional quality difference judgment scores.

[0099] Considering that not all cross-provincial access requires optimization, cross-provincial optimization adjustments for websites within the judgment range may exceed the carrying capacity of nodes outside or within the province, causing node congestion and resulting in perceived degradation. Therefore, in an optional implementation, the second preset threshold range of this embodiment of the invention can be (-0.3, 0.5). If the cross-provincial quality assessment score is less than or equal to -0.3, it is determined that the target website is degraded within the province; if the cross-provincial quality assessment score is greater than or equal to 0.5, it is determined that the target website is degraded outside the province; if the cross-provincial quality assessment score of the target website is within the second preset threshold range, then no cross-provincial optimization adjustment is required.

[0100] Furthermore, embodiments of the present invention may also include a process of encapsulating steps S100 to S130, for details please refer to Figure 5 The present invention provides a flowchart illustrating layered encapsulation and sequential parameter input, as detailed below:

[0101] S500: Let the step of calculating the load balancing score of each first node IP based on the distribution number of users accessing the target website on each first node IP be encapsulated as a sample layer.

[0102] S510: The step of taking the multiple first node IPs whose load balancing scores reach the first threshold as valid node IPs and calculating the performance degradation score of the node corresponding to each valid node IP based on the homepage latency of each valid node IP is encapsulated as a first performance layer.

[0103] S520: Let the step of calculating the cross-regional quality defect judgment score of the target website based on the homepage latency of the second node IP and the homepage latency of the first node IP, and performing cross-regional optimization and adjustment of the target website based on the cross-regional quality defect judgment score be encapsulated as a second performance layer.

[0104] S530: The sample layer, the first performance layer, and the second performance layer are executed sequentially, and the input parameters of the next layer are determined based on the output results of the previous layer.

[0105] The embodiments of the present invention can implement the steps of layered encapsulation and sequential parameter input, which can improve the scalability of CDN network quality assessment method analysis; at the same time, the data processing method of bottom-level data connection and multi-level result output makes the CDN network quality assessment method simple and efficient to execute.

[0106] The application process of this invention will be illustrated with specific examples below.

[0107] The CDN network quality assessment method of this invention includes the following three types of algorithms:

[0108] 1. CDN Node Performance Degradation Algorithm: Performs numerical simulation analysis on the degradation of homepage latency of nodes within the province to accurately locate poor-quality CDN nodes within the province. The purpose is to discover degraded nodes within the province that have no obvious server alarms or have long-term performance risks.

[0109] 2. CDN website cross-province quality deterioration algorithm: Perform cross-province digital model analysis on the homepage latency and out-of-province access rate of the website's internal and external nodes to accurately locate cross-province quality deterioration websites. The purpose is to discover websites with deterioration in access from outside the province or within the province.

[0110] 3. CDN Node Load Balancing Algorithm: Performs balanced analysis on the number of access samples of nodes within the province to evaluate the load status of each node within the province. The purpose is to screen out nodes with excessively low or high loads and achieve precise optimization.

[0111] Reference Figure 6 This invention provides an example flowchart of a CDN network quality assessment method, including the following steps:

[0112] 1. Probe data interface.

[0113] Provincial probe system: Utilizes provincial optical broadband gateway probes to collect HTTP access data from the top 75 mainstream websites, obtaining application-layer data such as website node IPs and homepage latency for HTTP testing. This data serves as the basis for the analysis of CDN network quality perception evaluation algorithms. It can sample more than 100,000 users and test more than 100 million samples per day.

[0114] 2. CDN database processing.

[0115] Based on the following ideas, after determining the three objectives of CDN load balancing, node performance, and cross-province quality degradation, this invention simplifies the formulas for big data analysis based on TCP principles and linear algebra principles without affecting accuracy, resulting in three final machine algorithms: CDN node load balancing algorithm, CDN node performance degradation algorithm, and CDN website cross-province quality degradation algorithm.

[0116] 3. Data compression and data cleaning.

[0117] 3.1 This invention abandons the traditional weighted quality evaluation method. After big data and simplification processing, it retains only the homepage latency as a key input parameter, so that the final algorithm does not need to consider correlation factors and interference factors.

[0118] For certain specific objectives, traditional network-weighted quality assessment has the following shortcomings:

[0119] The weighted values ​​will change over time, making them difficult to assess accurately;

[0120] Weighted quality metrics are not very maintainable;

[0121] The reason why the accuracy of this embodiment of the invention is improved compared to the traditional weighted analysis method is that it only retains the HTTP homepage latency.

[0122] Big data analysis shows that the sources of poor homepage latency are concentrated at both ends of the network (near-end gateway side and far-end CDN node side). Most of the poor latency along the path (including DNS latency, Layer 3 network latency, etc.) can be filtered out through preset thresholds or correlation calculations.

[0123] HTTP relies on TCP for reliable transmission. If the path latency exceeds the preset threshold, it will first trigger UDP packet latency anomalies. UDP-based business or management channels will issue alarms in advance. As long as the algorithm cycle is appropriate, the path latency issues can be filtered out.

[0124] Homepage latency is a comprehensive CDN evaluation parameter that includes many factors such as SSL, website size, and server performance. It can be effectively used to evaluate remote target CDN nodes.

[0125] 4. CDN digital-mode architecture.

[0126] The embodiments of this invention consider the scalability and efficiency of machine algorithms, and adopt a layered structure for software algorithm design. See details below. Figure 6 .

[0127] Only the lowest-level "base class" connects to the database, while the "sample class" and "performance class" are encapsulated, with hierarchical sequential input parameters (the calculation results of the lower-level part are used as the input parameters of the next layer), and the output results of each encapsulation layer complete various CDN analysis objectives.

[0128] The layered encapsulation and sequential parameter input architecture makes the CDN network quality assessment method highly scalable; the data processing method of low-level data connection and multi-level result output makes the CDN network quality assessment method simple and efficient to execute.

[0129] 5. CDN Layer 1: Basic Classes.

[0130] Specifically, the basic class connects to the database to obtain data such as multiple node IPs of the target website, the homepage latency of each node IP, and the number of users accessing the target website, as well as other optional data.

[0131] 6. CDN Layer 2: Sample Class.

[0132] CDN Node Load Balancing Algorithm: This algorithm uses the number of samples distributed across each node to evaluate the actual load balancing of the website. It belongs to the sample layer in the hierarchical design of this algorithm, and its calculation results serve as the input parameters for the next performance layer algorithm.

[0133] Reference Figure 7 This invention provides a sample diagram for the balanced evaluation of nodes within a province. Figure 7 In the example of load balancing evaluation of intra-provincial nodes shown, the eight nodes of website a are load-balanced, the first, fourth and fifth nodes of website b are unbalanced, and the second, third and sixth nodes of website b are load-balanced.

[0134] The machine algorithm is as follows:

[0135] The website's node IPs are assigned to provinces, and a set of node IPs from the same province is selected: {website[IP='this province']} for load balancing algorithm.

[0136] 1) Calculation of various basic data:

[0137] Obtain the number of IP samples for a single node of the website Samples: Samples = {number of IP samples for website nodes}.

[0138] Calculate the number of IPs of nodes in the province: NodesInProv = COUNT(website[IP = 'province']).

[0139] Calculate the total number of samples of IPs of nodes in the province, and sum the number of samples of IPs of nodes in the province: SamplesInProv = ∑(Samples[IP = 'province']).

[0140] Average number of samples of IPs of nodes in the province: AverageInProv = SamplesInProv / NodesInProv.

[0141] 2) Calculate the load balancing jitter rate of a single node IP:

[0142] EqualizeJit, the equalization jitter rate of a single node IP, calculation formula:

[0143] EqualizeJit = (Samples - AverageInProv) / AverageInProv.

[0144] 3) Load balancing determination:

[0145] If EqualizeJit >= 0.5, it is determined that the load of the node IP is too high; if EqualizeJit <= -0.5, it is determined that the load of the node IP is too low; if -0.5 < EqualizeJit < 0.5, it is determined that the load of the node IP is normal.

[0146] The evaluation target of this algorithm is the website, which can effectively evaluate the load balancing situation of the website among nodes in the province and be used as the input parameter of the next-level performance algorithm. The algorithm effectiveness is shown in the following table:

[0147]

[0148]

[0149] 7. CDN Layer Three: Performance Category.

[0150] 7.1 CDN Node Performance Deterioration Algorithm.

[0151] This algorithm belongs to the performance layer in the hierarchical design, and needs to use the output result EqualizeJit equalization jitter rate of the sample layer as the input parameter. The machine algorithm is as follows:

[0152] 1) For a certain website, select the set of IPs of nodes in the province where EqualizeJit > -0.5 as the calculation basis for this algorithm:

[0153] The effective IP address of the website's nodes in this province is calculated as follows: {nodes in this province[EqualizeJit>-0.5]}.

[0154] 2) Within the effective node range of this province, obtain the set of average homepage latency values ​​for a single node IP, AveHDelay{}:

[0155] AveHDelay = {Average homepage latency of a single valid local node IP}.

[0156] 3) Calculate the homepage jitter baseline value, selecting the minimum value among the average homepage latency values ​​of each node, i.e.:

[0157] HDelayBasic=MIN(AveHomeDelay).

[0158] 4) Calculate the node performance jitter rate, PerformanceJit, using the formula:

[0159] PerformanceJit=(AveHDelay-HDelayBasic) / HDelayBasic.

[0160] 5) Node performance degradation assessment:

[0161] If PerformanceJit >= 0.5, it is determined that the node performance is degraded.

[0162] The algorithm evaluates nodes with high accuracy. In the first real-world analysis in a certain province, it accurately identified two nodes within the province with potential performance degradation, affecting five websites, achieving 100% accuracy. See the table below for details:

[0163]

[0164] 7.2 CDN website cross-province quality algorithm.

[0165] This algorithm belongs to the performance layer in the hierarchical design. The machine algorithm is as follows:

[0166] 1) Calculate the average homepage latency HDelayOutProv for nodes outside the province, using the formula:

[0167] HDelayOutProv = Total homepage latency of nodes outside the province / Total number of nodes outside the province.

[0168] 2) Calculate the average homepage latency HDelayInProv for this province's nodes, using the formula:

[0169] HDelayInProv = Total homepage latency of nodes in this province / Total number of nodes in this province.

[0170] 3) Calculate the cross-province jitter rate HDelayProvJit, formula:

[0171] HDelayProvJit=(HDelayOutProv-HDelayInProv) / HDelayInProv.

[0172] 4) Cross-provincial quality assessment:

[0173] HDelayProvJit>=0.5 indicates website degradation when accessed from outside the province;

[0174] HDelayProvJit <= -0.3, indicating that the website is experiencing local access degradation.

[0175] The algorithm evaluates websites, and its significance lies in its ability to not only pinpoint website degradation issues affecting access from outside the province and within the province, but also in the simplified judgment range (-0.3, 0.5) indicating that not all cross-provincial access requires optimization. Optimizing websites within this range might exceed the capacity of nodes outside or within the province, causing node congestion and resulting in perceived degradation. The algorithm effectively mitigates this issue within its judgment range, as detailed in the table below:

[0176]

[0177] 8. CDN report output.

[0178] 9. CDN implementation, node performance, cross-province quality issues, load balancing, and website content.

[0179] This invention utilizes big data analysis at the application layer to accurately pinpoint CDN network quality degradation, offering the following advantages:

[0180] 1. High objectivity: Existing technologies rely on routine server maintenance and maintenance-related alarms below the network layer; the CDN network quality assessment method of this invention is based on HTTP application layer test data obtained by the user gateway, which more realistically reflects user-perceived anomalies than existing maintenance-related alarms below the network layer, and the maintenance value is more obvious.

[0181] 2. High Accuracy: Existing technologies lack monitoring methods for CDN node load balancing, performance degradation, and cross-province quality issues. The CDN network quality assessment method of this invention, based on HTTP big data analysis, undergoes a highly simplified process, masking performance data such as DNS latency, SSL connection time, and first packet latency, retaining only the homepage latency as a key data point. This eliminates the need for the algorithm to consider correlation factors and interference factors. Furthermore, because homepage latency is the sum of multiple key indicators and TCP reliability characteristics, it can accurately affect CDN node quality assessment. For specific targets such as perceived poor CDN quality, the accuracy is extremely high, approaching 100% after effective tracking and evaluation.

[0182] 3. Low cost: Existing network monitoring systems need to be deployed on each CDN node and rely on the server's own detection and reporting; CDN awareness monitoring relies on the probe data collected by the existing network's built-in optical modem gateway version, which can realize multi-dimensional quality monitoring of CDN network node performance, cross-province quality difference, load balancing and other aspects. The algorithm is simple and effective, and the related maintenance system construction cost is low, the cycle is short and the results are quick.

[0183] 4. High sensitivity: Existing maintenance alarms are difficult to track and analyze the quality problems of the fourth to seventh layers of the network, and are not sensitive enough to the degradation caused by load, scheduling and other factors. The periodic network seven-layer evaluation algorithm of this invention is more sensitive to intermittent hidden dangers and can discover medium and long-term hidden dangers caused by no maintenance alarms or ignored alarms.

[0184] Next, another specific embodiment will be provided for illustration, as follows:

[0185] 1. CDN node load balancing algorithm.

[0186] In a certain province, 251 nodes of 13 websites experienced uneven access load. After assessing the traffic management and construction situation, the client performed a full load balancing adjustment on 3 of these websites. After the adjustment, there were no nodes with abnormal load (too high or too low), and the access performance improved by more than 40%.

[0187]

[0188] 2. CDN node performance degradation algorithm.

[0189] A CDN quality analysis model in a certain province identified two nodes across five websites with performance degradation, resulting in a poor user experience. These nodes were located in city 1 (xxx.xxx.x.xxx) and city 2 (yy.yyy.yyy.yy). After optimization, the node performance improved by more than 50%.

[0190]

[0191]

[0192] City 1 (xxx.xxx.x.xxx) has a total bandwidth of 400G. The latency within the City 1 IDC network was checked and found to be normal with no abnormal alarms. The customer is Customer A. It was found that there were about 95% peak traffic on the user port for about 10 days within the past month. After traffic diversion and optimization, the node performance returned to normal level.

[0193] The network yy.yyy.yyy.yy in City 2 has a total bandwidth of 100G. The latency within the City 2 IDC network was checked and found to be normal with no abnormal alarms. The customer is Customer B. It was found that there were about 20 days in the past month when the peak traffic of the user port reached 90%. After traffic diversion and optimization, the node performance returned to normal level.

[0194] 3. CDN website cross-province quality algorithm.

[0195] According to the cross-provincial CDN quality analysis results of a certain province in May, among the 35 websites that had been deployed in the province, 21 websites had cross-provincial access issues. Among them, 7 websites had degraded access from outside the province, and 1 website had degraded access within the province. The client carried out cross-provincial optimization adjustments in May. The optimization results in June showed that there were no websites with poor access quality from outside the province, a decrease of 7 compared to the previous month; the latency of the homepage of the website with poor access quality within the province decreased from 5406ms to 1326ms.

[0196] Meanwhile, the June CDN cross-provincial assessment results showed that five new abnormal websites were added within the province. Investigations revealed that while these five websites' outbound access rates exceeded 10% in the second quarter, they were not within the degradation assessment range. The client still implemented outbound access adjustments for these websites. Although the outbound access rate decreased significantly in June, insufficient capacity of the provincial nodes led to a substantial increase in latency for websites within the province, negatively impacting user experience. For details, please refer to [link / reference]. Figure 8 .

[0197] Reference Figure 9 This invention provides a CDN network quality assessment device, comprising:

[0198] The first unit is used to obtain multiple node IPs of the target website, the homepage latency of each node IP, and the number of users accessing the target website; the node IPs belonging to the target province are designated as local node IPs, and the node IPs not belonging to the target province are designated as out-of-province node IPs;

[0199] The second unit is used to use the user as a sample and calculate the load balancing score of each of the provincial node IPs based on the distribution number of the sample in each of the provincial node IPs.

[0200] The third unit is used to take multiple local node IPs that have reached the first threshold as valid node IPs, and to calculate the performance degradation score of the node corresponding to each valid node IP based on the homepage latency of each valid node IP.

[0201] The fourth unit is used to calculate the cross-provincial quality assessment score of the target website based on the homepage latency of the out-of-province node IP and the homepage latency of the local node IP, and to perform cross-provincial optimization and adjustment on the target website based on the cross-provincial quality assessment score.

[0202] The specific implementation of this CDN network quality assessment device is basically the same as the specific implementation of the CDN network quality assessment method described above, and will not be repeated here.

[0203] This invention also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned CDN network quality assessment method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0204] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned CDN network quality assessment method.

[0205] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0206] This application also provides a computer device, including a memory and a processor. The memory stores a computer program, which, when executed by the processor, causes the processor to perform the methods described in the foregoing embodiments.

[0207] Specifically, computer equipment can be either a user terminal or a server.

[0208] This invention takes a computer device as a user terminal as an example, as detailed below:

[0209] like Figure 10As shown, the computer device 1000 may include an RF (Radio Frequency) circuit 1010, a memory 1020 including one or more computer-readable storage media, an input unit 1030, a display unit 1040, a sensor 1050, an audio circuit 1060, a short-range wireless transmission module 1070, a processor 1080 including one or more processing cores, and a power supply 1090, among other components. Those skilled in the art will understand that... Figure 10 The device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0210] The RF circuit 1010 can be used for receiving and transmitting signals during information transmission or calls. Specifically, it receives downlink information from the base station and hands it over to one or more processors 1080 for processing; additionally, it transmits uplink data to the base station. Typically, the RF circuit 1010 includes, but is not limited to, an antenna, at least one amplifier, a tuner, one or more oscillators, a Subscriber Identity Module (SIM) card, a transceiver, a coupler, an LNA (Low Noise Amplifier), a duplexer, etc. Furthermore, the RF circuit 1010 can also communicate wirelessly with networks and other devices. Wireless communication can use any communication standard or protocol, including but not limited to GSM (Global System for Mobile communication), GPRS (General Packet Radio Service), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), LTE (Long Term Evolution), email, SMS (Short Messaging Service), etc.

[0211] The memory 1020 can be used to store software programs and modules. The processor 1080 executes various functional applications and data processing by running the software programs and modules stored in the memory 1020. The memory 1020 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the device 1000 (such as audio data, telephone book, etc.). In addition, the memory 1020 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 1020 may also include a memory controller to provide access to the memory 1020 by the processor 1080 and the input unit 1030. Although Figure 10 The RF circuit 1010 is shown, but it is understood that it is not a necessary component of the device 1000 and can be omitted as needed without changing the nature of the invention.

[0212] The input unit 1030 can be used to receive input numerical or character information, and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control. Specifically, the input unit 1030 may include a touch-sensitive surface 1031 and other input devices 1032. The touch-sensitive surface 1031, also known as a touch display screen or touchpad, can collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch-sensitive surface 1031), and drive the corresponding connection device according to a pre-set program. Optionally, the touch-sensitive surface 1031 may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch position and the signal generated by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, converts it into touch point coordinates, sends it to the processor 1080, and can receive and execute commands from the processor 1080. In addition, the touch-sensitive surface 1031 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. Besides the touch-sensitive surface 1031, the input unit 1030 may also include other input devices 1032. Specifically, other input devices 1032 may include, but are not limited to, one or more of the following: a physical keyboard, function keys (such as volume control buttons, power buttons, etc.), a trackball, a mouse, and a joystick.

[0213] The display unit 1040 can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces for controlling the 1000. These graphical user interfaces can be composed of graphics, text, icons, video, and any combination thereof. The display unit 1040 may include a display panel 1041, which may optionally be configured as an LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), or similar display. Furthermore, a touch-sensitive surface 1031 may cover the display panel 1041. When the touch-sensitive surface 1031 detects a touch operation on or near it, it transmits the information to the processor 1080 to determine the type of touch event. Subsequently, the processor 1080 provides corresponding visual output on the display panel 1041 according to the type of touch event. Although in Figure 10 In this embodiment, the touch-sensitive surface 1031 and the display panel 1041 are implemented as two separate components to realize input and output functions. However, in some embodiments, the touch-sensitive surface 1031 and the display panel 1041 can be integrated to realize input and output functions.

[0214] The computer device 1000 may also include at least one sensor 1050, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor. The ambient light sensor can adjust the brightness of the display panel 1041 according to the ambient light level, and the proximity sensor can turn off the display panel 1041 and / or backlight when the device 1000 is moved to the ear. As a type of motion sensor, a gravity acceleration sensor can detect the magnitude of acceleration in various directions (generally three axes). When stationary, it can detect the magnitude and direction of gravity and can be used for applications that recognize the phone's posture (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition-related functions (such as pedometers, taps), etc. Other sensors that the device 1000 may be equipped with, such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, will not be described in detail here.

[0215] Audio circuitry 1060, speaker 1061, and microphone 1062 provide an audio interface between the user and device 1000. Audio circuitry 1060 converts received audio data into electrical signals and transmits them to speaker 1061, where speaker 1061 converts them into sound signals for output. Conversely, microphone 1062 converts collected sound signals into electrical signals, which are then received by audio circuitry 1060, converted back into audio data, and processed by processor 1080 before being transmitted via RF circuitry 1010 to another control device, or output to memory 1020 for further processing. Audio circuitry 1060 may also include an earphone jack to facilitate communication between peripheral headphones and device 1000.

[0216] The short-range wireless transmission module 1070 can be a WIFI (wireless fidelity) module, Bluetooth module, or infrared module, etc. Device 1000 can transmit information with the wireless transmission module installed on the battle equipment via the short-range wireless transmission module 1070.

[0217] Processor 1080 is the control center of device 1000. It connects various parts of the control device via various interfaces and lines. By running or executing software programs and / or modules stored in memory 1020, and by calling data stored in memory 1020, it performs various functions of device 1000 and processes data, thereby providing overall monitoring of the control device. Optionally, processor 1080 may include one or more processing cores; optionally, processor 1080 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the aforementioned modem processor may not be integrated into processor 1050.

[0218] The device 1000 also includes a power supply 1090 (such as a battery) to power various components. Preferably, the power supply can be logically connected to the processor 1080 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 1090 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0219] Although not shown, device 1000 may also include a camera, Bluetooth module, etc., which will not be described in detail here.

[0220] This invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, causing the computer device to perform... Figure 1 The method shown.

[0221] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is altered and sub-operations described as part of a larger operation are executed independently.

[0222] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the described functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0223] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0224] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0225] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0226] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0227] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0228] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0229] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of the present invention.

Claims

1. A CDN network quality assessment method, characterized in that, include: Obtain multiple node IPs of the target website, the homepage latency of each node IP, and the number of users accessing the target website; The node IPs belonging to the target administrative region are designated as the first node IPs, and the node IPs not belonging to the target administrative region are designated as the second node IPs. The load balancing score of each first node IP is calculated based on the number of users accessing the target website across each first node IP. The first node IPs that reach the first threshold in the load balancing score are taken as valid node IPs, and the performance degradation score of the node corresponding to each valid node IP is calculated based on the homepage latency of each valid node IP. The cross-regional quality assessment score of the target website is calculated based on the homepage latency of the second node IP and the homepage latency of the first node IP, and the target website is optimized and adjusted across regions based on the cross-regional quality assessment score. The steps for obtaining the homepage latency of each node IP include: The sum of the time required for all elements to load on the first non-redirecting page of the target website by each node IP is obtained to obtain the homepage latency corresponding to each node IP. The time required for loading all elements on the first non-redirecting page includes TCP connection latency, download latency, DNS resolution latency, SSL connection latency, and the loading time of the first byte. The acquisition of multiple node IPs of the target website includes: Using users who access the target website as samples, obtain the sample number of each node IP of the target website; Calculate the number of the first node IPs, and based on the number of the first node IPs and the corresponding number of samples, calculate the total number of samples for the first node IPs; The average number of samples for the first node IP is calculated based on the total number of samples for the first node IP and the number of first node IPs.

2. The CDN network quality assessment method according to claim 1, characterized in that, The calculation of the load balancing score for each first node IP based on the distribution of users accessing the target website across each first node IP includes: The difference between the total number of samples and the average number of samples is calculated, and then the result of the difference is divided by the average number of samples to obtain the load balancing jitter rate of each first node IP, which is used as the load balancing score. The load balancing score is used to classify the IPs of the first node, and the specific criteria for classification are as follows: The first node IP whose load balancing score is within the first preset threshold range is designated as the load balancing node IP; the first node IP whose load balancing score exceeds the first preset threshold range is designated as the overloaded node IP; and the first node IP whose load balancing score is below the first preset threshold range is designated as the underloaded node IP.

3. The CDN network quality assessment method according to claim 1, characterized in that, The step of selecting multiple first node IPs whose load balancing scores reach a first threshold as valid node IPs, and calculating the performance degradation score of the node corresponding to each valid node IP based on the homepage latency of each valid node IP, includes: Obtain the set of average homepage latency for each of the valid node IPs; The minimum value in each set of homepage latency averages is used as the homepage jitter benchmark value of the corresponding node. The difference between the homepage jitter benchmark value and each homepage latency average in the set of homepage latency averages is calculated, and the result of each difference is divided with the corresponding homepage latency average to obtain the performance jitter rate of the node corresponding to each effective node IP, which is used as the performance degradation score. The performance degradation score is used to identify nodes corresponding to valid node IPs whose performance degradation scores reach a second threshold as performance degradation nodes.

4. The CDN network quality assessment method according to claim 1, characterized in that, The step of calculating the cross-regional quality assessment score of the target website based on the homepage latency of the second node IP and the homepage latency of the first node IP, and then performing cross-regional optimization adjustments on the target website based on the cross-regional quality assessment score, includes: The average homepage latency of the first node IP is obtained by dividing the total homepage latency of the first node IP by the total number of nodes corresponding to the first node IP. The average homepage latency of the second node IP is obtained by dividing the total homepage latency corresponding to the second node IP by the total number of nodes corresponding to the second node IP. The difference between the average latency of the second homepage and the average latency of the first homepage is calculated, and the result of the difference is then divided by the average latency of the first homepage to obtain the cross-regional jitter rate, which is used as the cross-regional quality defect judgment score. The nodes corresponding to the second node IP or the first node IP that are outside the second preset threshold range in the cross-regional quality difference judgment score will be optimized and adjusted across regions.

5. A CDN network quality assessment method according to any one of claims 1 to 4, characterized in that, The method further includes: Let the step of calculating the load balancing score of each first node IP based on the number of users accessing the target website on each first node IP be encapsulated as a sample layer; The steps of taking multiple first node IPs whose load balancing scores reach a first threshold as valid node IPs and calculating the performance degradation score of the node corresponding to each valid node IP based on the homepage latency of each valid node IP are encapsulated as a first performance layer. Let the steps of calculating the cross-regional quality defect judgment score of the target website based on the homepage latency of the second node IP and the homepage latency of the first node IP, and performing cross-regional optimization and adjustment of the target website based on the cross-regional quality defect judgment score be encapsulated as a second performance layer; The sample layer, the first performance layer, and the second performance layer are executed sequentially, and the input parameters of the next layer are determined based on the output results of the previous layer.

6. A CDN network quality assessment device, characterized in that, The apparatus is used to implement the CDN network quality assessment method as described in claim 1, and the apparatus includes: The first unit is used to obtain multiple node IPs of the target website, the homepage latency of each node IP, and the number of users accessing the target website; the node IPs belonging to the target administrative region are designated as the first node IPs, and the node IPs not belonging to the target administrative region are designated as the second node IPs; The second unit is used to calculate the load balancing score of each first node IP based on the number of users accessing the target website across each first node IP. The third unit is used to take multiple first node IPs that have reached the first threshold as valid node IPs, and to calculate the performance degradation score of the node corresponding to each valid node IP based on the homepage latency of each valid node IP. The fourth unit is used to calculate the cross-regional quality defect judgment score of the target website based on the homepage latency of the second node IP and the homepage latency of the first node IP, and to perform cross-regional optimization and adjustment of the target website based on the cross-regional quality defect judgment score.

7. An electronic device, characterized in that, Including the processor and memory; The memory is used to store programs; The processor executes the program to implement a CDN network quality assessment method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The storage medium stores a program that is executed by a processor to implement a CDN network quality assessment method as described in any one of claims 1 to 5.

Images