Network analysis service processing method, apparatus, device, medium, and program product

Abstract

The embodiments of the present disclosure disclose a processing method and device for network analysis service, equipment, medium and program product. First, obtain the service data to be analyzed, input the service data to be analyzed into the service level branch in the service quality model, the data specification processed by the service level branch corresponds to the service level of the service data to be analyzed, the service quality model includes a plurality of service level branches, then according to the output data of the service level branch, obtain the model analysis result of the service quality model, the model analysis result is used to evaluate the quality of the service corresponding to the service data. The embodiments of the present disclosure can analyze the related data in the network analysis service process, so as to discover and solve the problems existing in the network analysis service process in time.

Description

Technical Field

[0001] This disclosure relates to network resolution service technology and Internet technology, and in particular to a method, apparatus, device, medium, and program product for processing network resolution services. Background Technology

[0002] Network resolution services are used to help users achieve normal internet functionality. For example, recursive domain name resolution is a crucial component of internet infrastructure, allowing users to access websites or applications via domain names. However, in certain situations, network resolution services, such as recursive domain name resolution, may experience problems, preventing users from accessing the internet normally. Therefore, it is necessary to process relevant information or data related to network resolution services to promptly identify and resolve problems in the process. Summary of the Invention

[0003] Therefore, embodiments of this disclosure provide a method, apparatus, device, medium, and program product for processing network resolution services, which can analyze relevant data during the network resolution service process in order to promptly identify and resolve problems existing in the network resolution service process.

[0004] In a first aspect, embodiments of this disclosure provide a method for processing a network resolution service, including:

[0005] Obtain the business data to be analyzed;

[0006] The business data to be analyzed is input into the service level branch of the business quality model; the data specifications processed by the service level branch correspond to the service level of the business data to be analyzed; the business quality model includes multiple service level branches;

[0007] Based on the output data of the service level branch, the model analysis results of the service quality model are obtained; the model analysis results are used to evaluate the quality of the service corresponding to the service data.

[0008] The business quality model is obtained through the following steps:

[0009] Obtain sample business data for domain name recursive resolution services;

[0010] Cluster the sample business data to obtain the label category to which the sample business data belongs;

[0011] Based on the sample service data of the label categories, model training samples are obtained; the model training samples include multiple label categories, and the model training samples of each label category include sample service data corresponding to multiple evaluation labels; the multiple evaluation labels are pre-defined labels for the quality of network resolution services;

[0012] Based on the training samples of the model, a converged business quality model is obtained;

[0013] The sample business data is updated to obtain updated model training samples;

[0014] The updated model training samples are input into the business quality model to be trained and the converged business quality model. Based on the output results, the converged business quality model is retrained to obtain the fully trained business quality model.

[0015] Secondly, embodiments of this disclosure provide a processing apparatus for a network resolution service, comprising:

[0016] The first acquisition module is used to acquire the business data to be analyzed.

[0017] The first input module is used to input the business data to be analyzed into the service level branch of the business quality model; the data specifications processed by the service level branch correspond to the service level of the business data to be analyzed; the business quality model includes multiple service level branches.

[0018] The first output module is used to obtain the model analysis results of the service quality model based on the output data of the service level branch; the model analysis results are used to evaluate the quality of the service corresponding to the service data.

[0019] The second acquisition module is used to obtain sample business data of the domain name recursive resolution service.

[0020] The clustering module is used to cluster the sample business data to obtain the label category to which the sample business data belongs;

[0021] The third acquisition module is used to obtain model training samples based on the sample service data of the label categories; the model training samples include multiple label categories, and the model training samples of each label category include the sample service data corresponding to multiple evaluation labels; the multiple evaluation labels are pre-set labels for the quality of network resolution services;

[0022] The fourth module is used to obtain a converged business quality model based on the model training samples.

[0023] The update module is used to update the sample business data to obtain updated model training samples;

[0024] The second input module is used to input the updated model training samples into the business quality model to be trained and the converged business quality model, and to retrain the converged business quality model according to the output results to obtain the completed business quality model.

[0025] Thirdly, embodiments of this disclosure provide an electronic device, including:

[0026] Memory, used to store computer program products;

[0027] A processor is configured to execute a computer program product stored in the memory, wherein, when the computer program product is executed, it implements the method provided in any embodiment of the present disclosure.

[0028] Fourthly, embodiments of this disclosure provide a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement the method provided in any embodiment of this disclosure.

[0029] Fifthly, embodiments of this disclosure provide a computer program product, including computer program instructions that, when executed by a processor, implement the method provided in any embodiment of this disclosure.

[0030] The method provided by this disclosure can analyze the business data generated during the network resolution service process to obtain the quality of the service, thereby enabling quality assessment of network services, timely identification of problems and deficiencies in the network service operation process, and targeted improvement of network service quality.

[0031] The technical solutions of this disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0032] The accompanying drawings, which form part of this specification, illustrate embodiments of this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0033] This disclosure will become clearer with reference to the accompanying drawings and the following detailed description, wherein:

[0034] Figure 1 A flowchart of one embodiment of the method of this disclosure;

[0035] Figure 2 This is a schematic diagram of a method according to another embodiment of the present disclosure;

[0036] Figure 3 This is a service level diagram for one example of this disclosure;

[0037] Figure 4 This is a schematic diagram of intelligent parsing in one example of this disclosure;

[0038] Figure 5 This is a schematic diagram illustrating a forwarding dependency in one example of this disclosure;

[0039] Figure 6 This is a flowchart of a method in one example of the present disclosure;

[0040] Figure 7 This is a schematic diagram of a business quality model as an example of this disclosure;

[0041] Figure 8 This is a schematic diagram illustrating the implementation framework of a method in one example of this disclosure;

[0042] Figure 9 for Figure 8 The schematic diagram of the detection terminal layer shown in the figure;

[0043] Figure 10 for Figure 8 The diagram shows the architectural topology.

[0044] Figure 11 This is a schematic diagram of the method flow in another example of this disclosure;

[0045] Figure 12 This is a schematic diagram of a detection management center in one example of this disclosure;

[0046] Figure 13 This is a schematic diagram of an electronic device in one example of the present disclosure. Detailed Implementation

[0047] To make the technical problems, technical solutions, and beneficial effects to be solved by this disclosure clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this disclosure and are not intended to limit it.

[0048] In the following description, specific details such as particular system architectures and techniques are set forth in order to provide a thorough understanding of the embodiments of this disclosure. However, those skilled in the art will understand that this disclosure may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this disclosure with unnecessary detail.

[0049] It should be understood that, when used in this disclosure and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0050] It should also be understood that the term “and / or” as used in this disclosure and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0051] As used in this disclosure and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be interpreted, depending on the context, as "once determined," "in response to determination," "once [the described condition or event] is detected," or "in response to detection of [the described condition or event]."

[0052] Furthermore, in the description of this disclosure and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0053] References to "one embodiment" or "some embodiments" as described in this disclosure mean that one or more embodiments of this disclosure include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including, but not limited to," unless otherwise specifically emphasized.

[0054] Figure 1 A flowchart illustrating a method for processing a network resolution service according to an embodiment of the present disclosure is shown, including the following steps S11 to S13.

[0055] Step S11: Obtain the business data to be analyzed.

[0056] In this embodiment of the disclosure, the business data to be analyzed can be the raw data generated during the implementation of the network resolution service. Alternatively, it can be obtained from the raw data generated during the implementation of the network resolution service. For example, the raw data generated during the implementation of the network resolution service can be filtered and cleaned to obtain the business data to be analyzed.

[0057] Correspondingly, the business data to be analyzed includes information about the network resolution service that needs to be processed. For example, when a user uses the network resolution service, business data is generated. This business data is used as the business data to be analyzed. The business data to be analyzed is used to process the network resolution service in order to obtain an evaluation result of the network resolution service. Furthermore, based on the evaluation result, it is possible to find, analyze, and issue early warnings about problems with the network resolution service.

[0058] In this embodiment of the disclosure, business data can refer to data generated during the course of a business process. The business data to be analyzed can be data generated during a single business process, or data generated during multiple business processes within a set time period.

[0059] In this embodiment of the disclosure, the business data to be analyzed can also be referred to as business data. During the training phase of the business quality model, the business data is also sample business data. After the business quality model has been trained, the sample business data is also the business data to be analyzed (or, in other words, business data).

[0060] Step S12: Input the business data to be analyzed into the service level branch in the business quality model; the data specifications processed by the service level branch correspond to the service level of the business data to be analyzed; the business quality model includes multiple service level branches.

[0061] In one possible implementation, inputting the business data to be analyzed into the service level branch in the business quality model may include: dividing the business data to be analyzed according to service level, determining the target service level to which the business data to be analyzed belongs; and inputting the business data to be analyzed into the service level branch corresponding to the target service level.

[0062] In another possible implementation, inputting the business data to be analyzed into the service level branch in the business quality model may include: inputting the business data to be analyzed into the input module of the business quality model, and the input module of the business quality model inputting the business data to be analyzed into the corresponding branch.

[0063] The Service Level (SLR) branch in the business quality model can be used to process business data of a corresponding scale. The data specifications processed by the SLR branch, and the service level of the business data to be analyzed, can be used to describe the scale of the business corresponding to the business data.

[0064] The business quality model is used to analyze the business data to be analyzed, and based on the business data, to analyze the business completion effect and predict (or evaluate) the quality of the business.

[0065] Step S13: Based on the output data of the service level branch, obtain the model analysis results of the service quality model; the model analysis results are used to evaluate the quality of the service corresponding to the service data.

[0066] In this embodiment of the disclosure, step S13 may include: obtaining the output data of the service level branch, and outputting the output data of the service level branch as the model analysis result of the business quality model. Alternatively, step S13 may also include: further processing the output data of the service level branch to obtain the model analysis result of the business quality model.

[0067] In this embodiment of the disclosure, the business quality model is obtained through the following steps S14 to S19.

[0068] Step S14: Obtain sample business data for the domain name recursive resolution service.

[0069] In this embodiment of the disclosure, the sample service data may belong to multiple target service levels, and these multiple target service levels may correspond to all service level branches of the service quality model. That is to say, the amount of sample service data is greater than the amount of service data to be processed.

[0070] Domain name recursive resolution refers to the process where, during domain name resolution, DNS (Domain Name System) servers recursively query multiple DNS servers until the IP address of the target domain name is found. This process involves the collaborative work of multiple DNS servers, with the local DNS server (also known as the domain name recursive resolution server) acting as an intermediary, responsible for communicating and querying with other DNS servers.

[0071] The method for obtaining sample business data can be similar to that for the business data to be analyzed mentioned above.

[0072] Step S15: Cluster the sample business data to obtain the label category to which the sample business data belongs.

[0073] Clustering the sample business data can be performed using a specific clustering method, according to pre-defined label categories. For example, KMeans (k-means clustering algorithm) and / or DBSCAN (Density-Based Spatial Clustering of Applications with Noise) can be used to cluster the sample business data. The label categories can be pre-selected evaluation labels with a moderate number of categories and minimal data differences within each category. Each label category can be scored based on empirical information, and the score serves as a sample reference answer, which is then included as part of the first round of supervised data.

[0074] The tag category to which sample business data belongs can refer to an aspect (or dimension) of the business quality involved in the sample business data (or business data). For example, if a sample business data contains information related to cybersecurity, reflecting the quality of business related to cybersecurity, then the tag category to which the sample business data belongs can be cybersecurity.

[0075] In step S15, given the large amount of data in the sample business data, each piece of data can be classified according to the label category to determine the sample business data included in each label category.

[0076] Step S16: Obtain model training samples based on the sample business data of the label categories; the model training samples include multiple label categories, and the model training samples of each label category include the sample business data corresponding to multiple evaluation labels; the multiple evaluation labels are pre-set labels for recursive domain name resolution business record data.

[0077] When initially training the quality analysis model to be trained, the model training samples can be equivalent to the first round of supervision data mentioned above. Using the training data and the first round of supervision data, the business quality model to be trained is trained. When the model's loss function converges, the obtained model is the converged business quality model. In this embodiment of the disclosure, the business quality model can also be called a domain name recursive resolution service quality model or a rating analysis model. In one possible implementation, the business quality model can use a linear regression method to process the input data, and therefore can also be called a linear regression model.

[0078] After determining the label category to which the sample business data belongs, evaluation labels can be determined for each sample business data, and evaluation labels can be added to the sample business data. The model training samples can then include sample business data with determined label categories and added evaluation labels. In other words, the model training samples can include label categories and sample business data. Furthermore, during multiple rounds of optimization of the business quality model to be trained, the internal parameters of the business quality model are adjusted based on the sample reference answers.

[0079] In possible implementations, each label category includes multiple evaluation labels, and each evaluation label is a sub-dimension of the business quality involved in the sample business data (or business data) under the evaluation category. For example, under the dimension of network security, there are multiple sub-dimensions that evaluate the security of different aspects of the network.

[0080] Step S17: Obtain a converged business quality model based on the model training samples.

[0081] After obtaining the model training samples, these samples can be input into the business quality model to be trained. The model then outputs its training results based on the training samples. The loss value is calculated using the training output, sample reference answers, and the loss function. The parameters of the business quality model are then adjusted based on this loss value. Through multiple rounds of parameter adjustments, the loss value calculated by the loss function is minimized.

[0082] In this embodiment of the disclosure, the converged business quality model can refer to the business quality model obtained when the loss function converges. The business quality model to be trained can refer to the business quality model at any model training stage before the loss function converges, or in other words, the business quality model to be trained can refer to the business quality model when the loss function has not converged. Alternatively, the business quality model to be trained can refer to the business quality model that has not been trained.

[0083] Step S18: Update the sample business data to obtain updated model training samples.

[0084] In one possible implementation, updating the sample business data to obtain updated model training samples may include: adding new sample business data to the original sample business data to obtain updated model training samples; and performing clustering processing on the updated model training samples to obtain updated model training samples. The method of clustering the updated model training samples can be similar to the method of processing the sample business data in steps S15 and S16.

[0085] Step S19: Input the updated model training samples into the business quality model to be trained and the converged business quality model, and retrain the converged business quality model according to the output results to obtain the completed business quality model.

[0086] In a possible implementation, after obtaining the updated model training samples, in step S19, the updated model training samples can be input into the business quality model to be trained, i.e., the business quality model to be trained before step S17, to obtain the first output result; and the updated model training samples can be input into the converged business quality model to obtain the second output result. Then, based on the first and second output results, it is determined whether the converged business quality model meets the expected conditions. If the determination is not correct, the converged business quality model is optimized again based on the first and second output results, and then the process returns to step S18, re-executes step S18, and re-determines whether the new first and second output results meet the expected conditions, until the expected conditions are finally met, thus obtaining the fully trained business quality model.

[0087] In a possible implementation, step S19 may further include steps S191 to S193 as described below.

[0088] Step S191: Input the updated model training samples into the business quality model to be trained to obtain the first output result.

[0089] Step S192: Input the updated model training samples into the converged business quality model to obtain the second output result.

[0090] Step S193: Based on the difference between the first output result and the second output result, determine whether the difference between the converged business quality model and the business quality model to be trained meets expectations. If yes, the business quality model that has been trained is obtained; otherwise, return to step S18.

[0091] In step S19, the converged service quality model is used to evaluate the quality of the updated model training samples, obtaining the second output result. Based on the second output result, second-round supervision data is obtained for retraining, and this process is repeated to obtain the final service quality evaluation model. During this process, a quality adjustment instruction can be sent to the converged service quality model at any time. This instruction can be generated by adjusting the quality of the first and / or second output results. The final trained service quality model, as a usable evaluation model for network resolution services, is then deployed on the target server or distributed to the client, executing steps S11 to S13.

[0092] In the model training phase, a business quality model capable of accurately analyzing business quality is formed by designing rating indicators and an iterative convergence process. This involves designing and modeling the corresponding service scope indicators within the network resolution service quality indicator system. In the evaluation phase, the evaluation model obtained during training is used. By inputting the data item to be evaluated, a quality score for that data item is obtained. The business quality model used in this embodiment can be obtained through weakly supervised learning. In weakly supervised learning, the role of sample reference answers may be weakened. Therefore, the training process of the business quality model is less dependent on sample reference answers, thus avoiding the impact of inaccurate sample reference answers on the business quality model.

[0093] The method provided by this disclosure can analyze the business data generated during the network resolution service process to obtain the quality of the service, thereby enabling quality assessment of network services, timely identification of problems and deficiencies in the network service operation process, and targeted improvement of network service quality.

[0094] In one implementation, obtaining a converged service quality model based on model training samples includes: determining the number of sample service data corresponding to each evaluation label among the multiple label categories for the target label category; determining the initial weight of each evaluation label in each service level branch of the service quality model to be trained based on the number of sample service data corresponding to each evaluation label; outputting the model analysis results of the training phase for the sample service data of the target label category; adjusting the initial weights based on the model analysis results and sample analysis results to obtain adjusted weights; and obtaining a converged service quality model based on the adjusted weights.

[0095] In this embodiment of the disclosure, the target label category can be one of multiple label categories. Determining the number of sample business data corresponding to each evaluation label for the target label category among the multiple label categories can include: for each label category among the multiple label categories, determining the number of sample business data corresponding to the evaluation labels under each label category.

[0096] By adjusting the initial weights of the evaluation labels in each service level branch of the business quality model to be trained, the model parameters used to process the input data can be changed, thereby optimizing the model.

[0097] In one implementation, determining the initial weight of each evaluation label in each service level branch of the converged service quality model based on the number of sample service data corresponding to each evaluation label includes: for a single evaluation label, if the number of sample service data corresponding to the evaluation label meets a set quantity threshold requirement, setting the initial weight of the evaluation label according to the default weight value pre-set for the evaluation label.

[0098] In this embodiment, the initial weights of the evaluation labels can serve as internal parameters of the business quality model before training. For each label type, a default weight value is set for the evaluation label. The default weight value represents the ideal initial internal parameter of the business quality model to be trained. Ideally, the evaluation labels for each label type have sufficient sample business data. In this case, setting the initial weights of the evaluation labels according to the default weight values ​​can save the initialization time of the business quality model to be trained and improve model optimization efficiency.

[0099] In one implementation, determining the initial weight of each evaluation label in each service level branch of the converged service quality model based on the quantity of sample service data corresponding to each evaluation label includes: for a single evaluation label, if the quantity of sample service data corresponding to the evaluation label does not meet a set quantity threshold requirement, obtaining a first evaluation label that meets the set quantity threshold requirement and a second evaluation label that does not meet the set quantity threshold requirement among the plurality of evaluation labels; determining the sum of the default weight values ​​pre-set for the first evaluation label and the proportion of the default weight values ​​pre-set for the second evaluation label; determining the allocation ratio of the sum on the sample service data corresponding to the second evaluation label according to the proportion; adjusting the default weight values ​​pre-set for each evaluation label according to the allocation ratio to obtain the updated weight values ​​corresponding to each evaluation label; and determining the initial weight of each evaluation label according to the updated weight values.

[0100] If the number of sample business data corresponding to the evaluation label does not meet the set threshold requirement, it can be considered that there is a lack of sample business data corresponding to the evaluation label.

[0101] In cases where sample business data corresponding to some evaluation labels is missing, by recalculating the default weight values ​​according to the missing information, the business quality model to be trained can be trained normally even when the sample business data does not meet the quantity requirements, thereby improving the utilization rate of sample business data.

[0102] In one implementation, determining the allocation ratio of the sum on the sample business data corresponding to the second evaluation label according to the ratio includes: determining the allocation ratio of each second evaluation label on each first evaluation label by multiplying the ratio of each second evaluation label by the sum.

[0103] By calculating the allocation ratio of evaluation labels for missing sample business data, it is possible to train the business quality model to be trained using existing sample business data even when some evaluation labels lack sample business data.

[0104] In one implementation, adjusting the default weight values ​​pre-set for each evaluation label according to the allocation ratio to obtain the updated weight values ​​corresponding to each evaluation label includes: adjusting the default weight values ​​pre-set for each second evaluation label to zero to obtain the updated weight values ​​corresponding to each second evaluation label; and for a single first evaluation label, adding the allocation ratio of each second evaluation label on the first evaluation label to the default weight values ​​pre-set for the first evaluation label to obtain the updated weight values ​​corresponding to the first evaluation label.

[0105] By setting the evaluation label of the missing sample business data to 0 and increasing the weight value of the evaluation label of the remaining non-missing sample business data, the weight values ​​corresponding to each evaluation label can be adjusted to a reasonable range, so that the initial weight values ​​are adapted to the sample business data, thereby making fuller use of the sample business data during the model training process.

[0106] In one implementation, before obtaining the model analysis result of the business quality model based on the output data of the service level branch, the process includes: obtaining the submodule processing result obtained by at least one submodule in the service level branch processing the business data; each submodule in the at least one submodule is used to process the business data in a dimension of at least one of the plurality of tag types; and obtaining the output data based on the submodule processing result.

[0107] In possible implementations, different calculation methods can be used within different submodules to obtain the submodule processing results.

[0108] For example, in one implementation, a decision tree algorithm can be used to obtain the output results of a subset of sub-modules. Obtaining the sub-module processing result obtained by processing the business data by at least one sub-module in the service level branch includes: calculating the score corresponding to each evaluation label in the sub-module based on the weight value corresponding to each evaluation label in the service level branch and the score corresponding to the business data value of each evaluation label; and calculating the total score corresponding to all evaluation labels in the sub-module based on the scores corresponding to each evaluation label in the sub-module, thereby obtaining the sub-module processing result.

[0109] By calculating the total score corresponding to each evaluation label, the quality level of the sample business data under multiple evaluation labels can be obtained, thus enabling the quality assessment of the sample business data.

[0110] In one implementation, obtaining sample business data for domain name recursive resolution services includes: sending a sample business data collection task to a business data probe; the collection task is generated based on an evaluation tag indicating missing sample business data; receiving probe data returned by the probe for the collection task; determining the consistency of the probe data based on a unified identifier in the probe data; and filtering the probe data based on the consistency to obtain the sample business data.

[0111] The probe can efficiently obtain business data generated during the network resolution service process. At the same time, by filtering the probe data based on its consistency, sample business data can be obtained, which can effectively reduce data noise in the probe data and improve data quality.

[0112] Because the quality requirements and focuses of domain name recursive resolution services differ across service levels—for example, nationwide domain name recursive resolution services have high requirements for service quality, hierarchical dependency, and security indicators; provincial domain name recursive resolution services have high requirements for service quality and hierarchical dependency; and enterprise-level domain name recursive resolution services need to have basic protocol completeness and service availability—in one implementation, the service level is determined based on the scope of the business service recipients; the service levels include: nationwide, provincial, and enterprise.

[0113] The aforementioned "national level" refers to the network resolution service's business impact being nationwide, with the domain name recursive resolution service defined as nationwide recursive, abbreviated as DG3 level. The aforementioned "provincial level" refers to the network resolution service's business impact being provincial, with the domain name recursive resolution service defined as provincial recursive, abbreviated as DG2 level. The aforementioned "enterprise level" refers to the network resolution service's business impact being enterprise-level. In one example disclosed in this disclosure, the domain name recursive resolution service without compliance filing is defined as enterprise-level recursive, abbreviated as DG1 level. The higher the level number for each service level, the greater the domain name recursive resolution service's influence and the higher its evaluation weight score. Figure 3 As shown, in one example, the evaluation weight of DG3 is [80%-100%], the evaluation weight of DG2 is [60%-80%], and the evaluation weight of DG1 is [40%-60%].

[0114] The evaluation weight scores of national, provincial and enterprise-level indicators for domain name recursive resolution services were designed in a hierarchical manner. Different branches were used to process business data or sample business data of different service levels within the business quality model, so that different weight values ​​could be assigned to data of different service levels and different important information could be assigned to sample business data of different service levels.

[0115] In one implementation, the network resolution service includes a domain name recursive resolution service; the business data includes business log data of the domain name recursive resolution service; the tag categories include: the geographical scope of the domain name recursive resolution service, the quality of the domain name recursive resolution service, recursion level dependency related, and recursive resolution security related.

[0116] Currently, the domain name recursive resolution service providers are complex and difficult to govern, with rampant illegal recursive calls. In the traditional tiered process of domain name recursive resolution services, whether certain network indicators are met plays a crucial role in evaluating the quality of the service. These indicators include request response time, request response success rate, resolution result accuracy, and TTL (time to live) configuration. Current evaluation and tiering standards and specifications generally rely on these data indicators for analysis, resulting in a relatively singular analytical dimension.

[0117] As a public internet service, recursive DNS resolution is difficult to manage and evaluate through a single resource control approach. It requires multi-faceted and comprehensive measurement of factors such as recursive DNS dependency, the scope of recursive DNS service, service quality, and security measures. Traditional analytical methods have limited dimensions and cannot provide a comprehensive evaluation of recursive DNS services within the network environment. Therefore, the evaluation and grading methods need to be redefined to adapt to long-term usage needs.

[0118] This disclosure provides an embodiment that summarizes the evaluation content of network service data classification and service indicator requirements, analyzes and summarizes the general principles, processes, and methods of data classification in the Internet industry, constructs the aforementioned tag types, and implements a network resolution method using the PDCA (plan, do, check, act) cycle to evaluate and analyze the quality of network services. Through the network resolution service processing method provided in this disclosure, the processing method of a single closed-loop network resolution service is transformed into a long-term continuous model optimization and business data processing. It combines the security risks of recursive resolution services requiring long-term monitoring with the effectiveness of security protection measures for recursive resolution services and recursive analysis and evaluation, forming a graded evaluation system for domain name recursive resolution services, ultimately achieving the long-term maintenance of the security status of domain name recursive resolution services.

[0119] Because this embodiment employs a weakly supervised approach for training the service quality model, the sample service data is clustered according to label categories and evaluation labels to obtain more valuable model training data. The service quality indicators for network resolution services involve numerous metrics, which contain both discrete and continuous data.

[0120] In one example, during the training phase of the service quality model, training data is first obtained by selecting service quality-related evaluation labels from batch recursive data acquired by the domain name recursive resolution service detection system to label sample service data. Before labeling the sample service data, such as... Figure 2As shown, during the training phase, KMeans and DBSCAN algorithms can be used to cluster the sample business data. Clustering results with a moderate number of categories and minimal data differences within each category are selected. For each label type, a sample reference answer is annotated. The sample business data, evaluation labels, label types, and sample reference answers constitute the first round of supervision data. Using the first round of supervision data and other relevant training data, a domain name recursive resolution service quality model (linear regression model) is trained. After the model converges, as shown... Figure 2 As shown, in the evaluation phase, the model is used to assess the quality of the training data, and the quality assessment results are used as the second round of supervised data for retraining to obtain the final service quality assessment model. Throughout this process, manual verification and adjustments are required at all times to ensure the quality of the model-generated data, ultimately resulting in a usable evaluation model.

[0121] The evaluation process uses the evaluation model obtained during the training phase. By inputting the data item to be evaluated, the quality score of that data item can be obtained.

[0122] Among multiple indicator types, different types of evaluation indicators are independent of each other; evaluation indicators of the same type are not repeated; and a reasonable hierarchical structure is established among dependent evaluation indicator items. As an analysis and rating of basic internet public services, combined with the service model of the domain name recursive resolution service itself, in one example, the label types include the scope of the domain name recursive resolution service (also known as the geographical scope of the domain name recursive resolution service), the quality of the domain name recursive resolution service, recursive hierarchy dependency (also known as recursive hierarchy dependency related), and recursive resolution security (also known as recursive resolution security related). The effective evaluation labels under each indicator dimension (label type) are as follows.

[0123] Evaluation tags under the domain name recursive resolution service scope may include: node IP (Internet Protocol) whitelist settings, node geographical location, and daily active user count.

[0124] Evaluation tags for domain recursive resolution service quality can include: response time for user recursive requests, service level ability (SLA), user request response success rate, no TTL hijacking, no hijacking / pruning of domain name resolution results, support for intelligent resolution of domain recursive resolution services at the level of the three major telecom operators, DNS protocol support completeness, support for IDN (Internationalized Domain Names) domain name queries, support for multiple record rotation and sorting, activation of domain name service privacy leakage protection, and access to DRSS (Domain Name Resolution Supervision Service System).

[0125] Evaluation tags under recursive hierarchical dependencies can include: whether there is a replica root access, and whether there is forwarding to other recursive DNS services.

[0126] The assessment tags for recursive DNS resolution security include: whether DNSSEC (Domain Name System Security Extensions) and DLV (DNSSEC Lookaside Validation) are configured and deployed; whether the independent public IP address only provides port 53 of TCP (Transmission Control Protocol) and UDP (User Datagram Protocol); whether there are technical means to clear cached data on the recursive DNS resolution server; security configuration for any resolution type; security configuration for TXT (Text) resolution type; whether the resolution entry and exit points are separated; whether CNAME (Canonical Name) loops exist; monitoring of domain name abuse; whether file tunnel detection is enabled; support for iterative query Qname mini (queryname mini); and the ability to switch replicas. Among these, monitoring of domain name abuse further includes: monitoring of domains associated with pornography, gambling, and drugs; DGA (Domain Name Generation Algorithm) domains; and other malicious domains.

[0127] Finally, the following is a brief explanation of some of the evaluation labels.

[0128] Intelligent DNS resolution service: Traditional DNS resolution, upon receiving a domain name resolution request, does not determine the visitor's origin but instead returns a fixed IP address or a randomly selected IP address. Intelligent resolution can intelligently determine the visitor's origin (e.g., the ISP to which the visitor's IP belongs) and match it with an IP address, reducing cross-network access and improving resolution efficiency. The intelligent resolution process is as follows: Figure 4 As shown.

[0129] Domain name recursive resolution service forwarding dependency: When a domain name recursive resolution server receives a DNS resolution request, if the server does not have the mapping information for that domain name, it will forward the query request to another name server. This process is called forwarding dependency. However, in some cases, this forwarding process may loop indefinitely, so circular dependencies need to be avoided in DNS configuration. The forwarding dependency process is illustrated below:

[0130] DNSSEC adds digital signature information to DNS data, allowing clients to verify the authenticity and legitimacy of responses by checking the signature. This provides source verification and integrity checks for DNS data, preventing attacks against DNS.

[0131] In one example, for each evaluation tag among the four tag types mentioned above, the horizontal and vertical span characteristics of the four dimensions can be analyzed using the information content weighting method. Combined with known domain name recursive resolution service information, a reasonable range of values ​​and initial weight values ​​are assigned to the business data corresponding to the evaluation tag. If the business data values ​​are continuous, one range of values ​​corresponds to one default weight value. If the range of values ​​for the business data corresponding to the evaluation tag is discrete, each discrete value corresponds to one default weight value. The default weight value can be directly used as the initial weight value or obtained after dynamic adjustment through amortization. The score corresponding to each evaluation tag can be a pre-set score. Thus, when the business data values ​​for the evaluation tag are continuous, one range of values ​​corresponds to one pre-set score. When the business data values ​​for the evaluation tag are discrete, each discrete value corresponds to one pre-set score.

[0132] When evaluating the recursive DNS resolution services at all levels using the series of evaluation tags provided in this disclosure, it may be impossible to obtain sample business data for some evaluation tags. To more reasonably evaluate the quality of these recursive DNS resolution network services, it is necessary to first dynamically adjust the default weight values ​​for some evaluation tags when sample business data is missing, and then use the adjusted default weight values ​​to evaluate the remaining sample business data. This makes the process of analyzing input data for the business quality model more reasonable and accurate.

[0133] In one example, the dynamic adjustment of the model's internal parameters is an iterative process. When determining the initial weights for the business quality analysis model to be trained, precise statistics are needed for all metrics related to each label type. The dynamic adjustment process for metric weights is as follows: Figure 5 As shown, it includes the following steps S51 to S56.

[0134] Step S51: Count the set A of evaluation labels for which no value can be obtained under the label type.

[0135] The default weight values ​​of the evaluation labels in set A are denoted as a1, a2, ..., am.

[0136] Step S52: Calculate the set B of indicator items that can obtain values ​​within this indicator dimension.

[0137] The default weight values ​​of the evaluation labels in set B are denoted as b1, b2, ..., bn.

[0138] Step S53: Calculate the sum of the default weight values ​​sa for all evaluation labels in set A.

[0139] sa = a1 + a2 + ... + am.

[0140] Step S54: Calculate the proportion brn of the default weight values ​​for all evaluation labels in set B.

[0141] The calculation process is as follows (using the formula below).

[0142] br1=b1 / (b1+b2+...+bn); br2=b2 / (b1+b2+...+bn);...brn=bn / (b1+b2+...+bn).

[0143] Step S55: Multiply the total sa and each proportion brn to obtain the apportionment weight bsn of each indicator item in set B.

[0144] The calculation process is as follows: bs1 = sa × br1; bs2 = sa × br2; bsn = sa × brn.

[0145] Step S56: Set the weights of each indicator item in set A to zero, and sum the original weights of each indicator item in set B with the allocated weights to obtain the latest weight values.

[0146] For example, the calculation results are as follows: a1 = 0; a2 = 0; ...; am = 0; b1 = b1 + bs1; b2 = b2 + bs2; bn = bn + bsn.

[0147] After completing the initial design of the evaluation tag system, the actual domain name recursive resolution service is evaluated in conjunction with the business quality model. When the evaluation results do not match the actual domain name recursive resolution service, the business quality model needs to undergo multiple rounds of iterative evaluation, monitoring, and evolution until the evaluation tag system and business quality model are gradually converged to align with the actual domain name recursive resolution service. The process of establishing the service level classification and quality evaluation index system for domain name recursive resolution service is as follows: Figure 6 As shown, it includes steps S61 to S66.

[0148] Step S61: Obtain service grading requirements information and quality assessment requirements dimension information.

[0149] Based on the received instructions, the service level and dimensional information can be determined, and based on the dimensional information, each evaluation label can be determined.

[0150] Step S62: Determine the indicator type and evaluation indicators based on the dimensional information of the quality assessment requirements.

[0151] In step S62, by identifying, sorting and evaluating the evaluation indicators of the domain name recursive resolution service, the indicator types corresponding to each dimension of information are obtained, as well as the evaluation indicators under each indicator type in different service levels.

[0152] Step S63: Determine the service level and the corresponding evaluation indicators based on the service level demand information.

[0153] Step S64: Determine the evaluation indicators corresponding to each service level, and the default weight values ​​of the evaluation indicators corresponding to each service level.

[0154] Step S65: Determine the score corresponding to the evaluation indicator.

[0155] Step S66: Evaluate the business data based on the service level, indicator type, evaluation indicator, default weight value, and the score corresponding to the evaluation indicator.

[0156] In step S66, the indicator type, service level, evaluation indicator, default weight value and the score corresponding to the evaluation indicator can be integrated into the model parameters of the business quality model to be trained. The business quality model to be trained is trained by the method provided in any embodiment of this disclosure, and the business quality model is used to evaluate the business data.

[0157] Step S67: Adjust at least one of the following: service level, indicator type, evaluation indicator, default weight value, and score corresponding to the evaluation indicator.

[0158] The quality assessment indicator system consists of service level, indicator type, evaluation indicator, default weight value, and corresponding score for each evaluation indicator. During the operation of this system, at least one of these parameters can be adjusted based on changes in actual circumstances, allowing the quality assessment indicator system to evolve with the displayed conditions.

[0159] During the evolution and maintenance of the quality assessment indicator system, the following events will trigger the iterative establishment process of the indicator system.

[0160] Event 1: The value range of the domain recursive resolution service quality assessment indicators has changed, requiring adjustments to the score range of the indicator values. For example, new members have been added to the protocol families supported by recursion.

[0161] Event 2: The dimensions of the domain recursive resolution service quality assessment indicators have not changed, but the indicator items or their weights within those dimensions need to be adjusted. For example, if a new assessment indicator is added, the weight values ​​of all indicator items within that assessment indicator dimension need to be recalculated and adjusted.

[0162] Event 3: The evaluation metrics for the domain name recursive resolution service have changed, such as the addition of new evaluation metrics, which requires adjusting the weights of all evaluation metrics.

[0163] Event 4: When the existing domain name recursive resolution service classification and quality assessment model is not applicable, it is necessary to reimplement the processes of quality assessment indicator identification and sorting, domain name recursive resolution service classification, establishment of domain name recursive resolution service quality assessment indicator system, quality assessment algorithm model design, model convergence monitoring, and algorithm optimization.

[0164] In possible implementations, the quality assessment of domain name recursive resolution services comprehensively evaluates four dimensions: service scope, service quality, recursion hierarchy dependency, and security capabilities. Since these four dimensions differ in the number of indicators and assessment difficulty, different evaluation methods will be used for each dimension. Furthermore, because the service scope (i.e., service level) significantly impacts various business indicators within the domain name recursive resolution service, it is proposed to first categorize recursion based on the service scope indicator, and then set corresponding algorithm models for evaluation according to different categories, in order to better reflect real-world conditions.

[0165] In one example, within the business quality model, at least three different branches are set up, corresponding to three different service levels: DG3, DG2, and DG1.

[0166] For example, in the business data generated during the domain name recursive resolution service process, the business data related to service level is discrete data, and the decision tree algorithm can be directly used to classify the service level of the obtained business data. Given the high feasibility of manual service level rating, manually labeled service level reference answers can be appropriately used as supervision data in the early stages of training the business quality model. In other words, during the training phase of the business quality model, the service level corresponding to the model training data can be determined through manually labeled information.

[0167] After the service level is confirmed, model branches with different focuses are designed according to the service level, such as the national level model branch corresponding to the national level. Each service level model branch is evaluated based on evaluation labels of multiple dimensions (indicator types).

[0168] Figure 7An example of a domain name recursive resolution service rating model based on service hierarchy (i.e., the service quality model in the aforementioned embodiments) is shown.

[0169] according to Figure 7 As shown, the input data of the business quality model consists of business data in three tag categories (namely, domain name recursive resolution service quality, recursive hierarchy dependency, and recursive resolution security assurance capability), and the output data is the recursive evaluation result (equivalent to the model analysis result in the aforementioned embodiment).

[0170] To reduce the coupling between modules in the business quality model, the model can be divided into several sub-modules based on the indicator types: domain name recursive resolution service quality, recursive hierarchy dependency, recursive resolution security assurance capability, and the overall model. Except for the overall model, the other three sub-modules score the domain name recursive resolution service separately, and the scores from the three dimensions are used as input to the overall model. For the overall model, since the number of indicators is small and their correlation is weak, a multi-level logistic regression or ordered logistic regression model with strong interpretability and low overfitting risk is proposed. This model will output the final category of the domain name recursive resolution service rating (i.e., the model analysis results in the aforementioned embodiment).

[0171] The aforementioned domain recursive resolution service quality section is used to evaluate the service quality of business data across various dimensions. This evaluation involves numerous metrics, including both discrete and continuous data. Currently, supervised data is unavailable, and direct manual labeling and scoring yields low accuracy. Therefore, a weakly supervised learning approach is adopted, dividing the formation of the domain recursive resolution service quality section into training and evaluation phases.

[0172] In other words, in one example, the business quality model to be trained may include the domain name recursive resolution service quality component to be trained.

[0173] The process of training the business quality model to be trained includes training the domain name recursive resolution service quality part, which includes a training phase and an evaluation phase. In the training phase, valuable supervisory data (model training data) can be obtained first, and a usable domain name recursive resolution service quality part can be trained.

[0174] First, based on the business data acquired by the system, data corresponding to the evaluation labels of the domain recursive resolution service quality dimension are selected as training data for the domain recursive resolution service quality part. When obtaining the above training data, KMeans and DBSCAN algorithms can be used to cluster the business data. Clustering results with a moderate number of data points within each label category and minimal differences within each label category are manually selected. Each label category is then manually scored based on experience, serving as the first round of supervision data for the domain recursive resolution service quality part. Using the training data and the first round of supervision data, the business quality model is trained, i.e., the domain recursive resolution service quality part of the business quality model is trained.

[0175] After obtaining a converged business quality model, the model is used to evaluate the quality of the training data and / or updated training data. The evaluation results are then used as the second round of supervised data for retraining to obtain the final business quality model. Throughout the training process, the quality of the data generated by the business quality model must be checked and adjusted as needed to ultimately obtain a fully trained business quality model (including the domain name recursive resolution service quality component).

[0176] In the evaluation phase, a trained business quality model can be used. By inputting the data item to be evaluated (equivalent to business data), a quality score for that data item can be obtained.

[0177] In the recursive hierarchical dependency part and the recursive parsing security assurance part, the business data or sample business data corresponding to the relevant evaluation labels are all discrete data types. The sample business data corresponding to the evaluation labels can be manually labeled and then rated using a decision tree algorithm.

[0178] For example, recursive hierarchical data dependencies can be categorized into three types: no dependencies, dependencies only on domestic data, and dependencies on foreign data. The security assurance capabilities of recursive parsing can be categorized into three types based on the level of assurance.

[0179] For sample business data in the recursive hierarchical dependency dimension and the recursive parsing security assurance capability dimension, after labeling the business data, the labeled business data is used as supervision data to train the corresponding decision tree algorithm. After the algorithm converges, inputting a single data point will output the evaluation and classification result for that data point.

[0180] Reference Figure 7The evaluation results of a single submodule (i.e., the processing results of the submodule) need to be converted into numerical scores as input to the overall model. Furthermore, the output results of the submodules in the recursive hierarchical dependency part and the recursive parsing security assurance capability part need to be continuous. The non-continuous hierarchical results within the submodule can be converted as follows: the recursive dependency rating results of no dependency, only domestic dependency, and foreign dependency correspond to values ​​of 0, 50, and 100, respectively; the recursive security rating results of good, medium, and poor correspond to values ​​of 100, 50, and 0, respectively.

[0181] After the business quality model has been trained, the model analysis results need to be continuously monitored to ensure that the results gradually converge to match the actual situation of domain name recursive resolution service. When the following situations occur, steps such as indicator fine-tuning, algorithm fine-tuning, model optimization, and continuous convergence need to be performed to optimize the business quality model.

[0182] In scenario one, the evaluation tags for the domain recursive resolution service remain unchanged, but the default weight values ​​for the evaluation tags need to be adjusted, such as adjusting the default weight value corresponding to protocol support completeness.

[0183] Scenario 2: The label type for the recursive parsing service quality assessment remains unchanged, but the indicator items (i.e., assessment labels) within the label type need to be adjusted. For example, if a new assessment indicator (i.e. assessment label) is added, the weight values ​​of all indicator items within this assessment indicator dimension need to be recalculated and adjusted.

[0184] Scenario 3: Changes occur in the evaluation metrics (i.e., tag types) of the domain recursive resolution service. For example, if a new evaluation metric dimension is added, the default weight values ​​corresponding to all evaluation metric dimensions need to be adjusted.

[0185] Scenario 4: When the relevant regulations change the requirements for domain name recursive resolution service companies, making the existing domain name recursive resolution service classification and business quality model inapplicable, it is necessary to reimplement the domain name recursive resolution service classification (confirm service level), quality assessment indicator identification and sorting, domain name recursive resolution service business quality model assessment and monitoring, model convergence, algorithm optimization, and other processes.

[0186] Figure 8 This example demonstrates the various devices involved in the process from acquiring sample business data to creating, training, and using a business quality model.

[0187] Figure 8The multi-device architecture shown implements a product framework for large-scale discovery, analysis, and rating of domain name recursive resolution services, based on the principles of "high usability and simple operation." It comprehensively monitors domain name resolution services using active and passive monitoring nodes deployed nationwide, acquiring data sources for analysis (either business data or sample business data). It detects abnormal resolution behavior in real time from dimensions such as recursive resolution dependency, geographical scope of the domain name recursive resolution service, service quality, and deployment of security enhancement measures. Through central data analysis combined with a recursive analysis and rating model, it outputs a recursive resolution service quality assessment report, achieving long-term monitoring of the security status of the domain name recursive resolution service.

[0188] exist Figure 8 The framework shown includes a data and business layer, a central management layer, and a terminal detection layer. The data and business layer supports business visualization and includes a recursive business module, a domain name detection module, and a visualization detection tool module. Through the data and business layer, recursive business data and domain name detection data can be visualized. The visualization detection tool allows for the probing of the visualized information.

[0189] The central management layer includes an infrastructure management module, a probe management center module, a recursive service quality assessment module, and a recursive hierarchical classification module. The infrastructure management module manages probe nodes, recursive nodes, and probe targets. Recursive nodes implement recursive domain name resolution services, and probe targets can include business objects. The probe management center module includes a task bus and a scheduling center. The task bus manages various recursive or probe tasks, and the scheduling center schedules resources such as probe nodes. The recursive service quality assessment module runs the business quality model and obtains the business quality based on the model analysis results. The recursive hierarchical classification module includes hierarchical management and an indicator system. Hierarchical management manages service levels, and the indicator system manages assessment labels. The central management layer issues tasks to the terminal probe layer and sets up basic information management. The terminal probe layer includes a domain name resolution probe module, which further includes multiple probe nodes. These probe nodes obtain business data or sample business data.

[0190] Figure 9 for Figure 8 The diagram shows the framework's topology, which includes Nginx (engine X), a page gateway cluster, an application program interface (API), a registry discovery (load balancing) system, a Nacos (dynamic naming and configuration service) cluster, an application server cluster, a database, and a file server. The application server cluster is used to deploy the business quality model.

[0191] Nginx serves as the entry point for static resources in HTML (Hypertext Markup Language) and is used for internal network load balancing. The page gateway handles authentication, access control, and load balancing. Authentication can be extracted to the gateway layer, allowing microservices to focus solely on their business logic without needing to handle authentication. It also allows for setting whitelists, access limits, and other configurations for specific interfaces. Furthermore, load balancing strategies can be flexibly defined at the gateway layer, and an additional layer of protection can be added to prevent malicious attacks.

[0192] The service API (web, network) serves as the entry point for service interface calls, primarily handling API call authentication, billing, and service-driven calls.

[0193] Registration reveals that it can be used to achieve service load balancing.

[0194] Figure 8 The domain name detection and resolution module encompasses two main detection capabilities: general capabilities and basic detection capabilities. General capabilities primarily include task reception and resolution, task hierarchical fragmentation, (local) consistency comparison, and data reporting. The basic detection capabilities support DNS detection (basic configuration settings), ping (Internet Packet Explorer) / traceroute, and MTR (My Traceroute) functions, initiating network probing requests to domain names or IP addresses to evaluate and analyze the performance, security, and reliability of the DNS system. The functional architecture of the domain name resolution detection module is as follows: Figure 10 As shown.

[0195] exist Figure 10 The architecture shown includes business support, a detection management center, and an endpoint detection layer. Business support manages DNS resolution accuracy, domain name service quality, recursive configuration security, and recursive hierarchical classification. The detection management center manages task execution status.

[0196] As the basic framework for detection, the detection terminal can be flexibly configured with detection tasks, supports scanning of the entire network IP address range, can initiate active detection on any IP and port, and makes judgments on the type of detection target (public recursion, carrier recursion, etc.).

[0197] The detection terminal receives and parses detection tasks, identifying attributes such as task type, target, cycle, and source address. It then categorizes and segments the data based on target size and service type to ensure efficient operation of the detection system. Simultaneously, the terminal compares and labels the detection results against the expected outcome. After data processing and classification, it reports the detection data and preliminary comparison results to the data center according to a specified method. The detection task processing flow is as follows: Figure 11 As shown, it includes the following steps.

[0198] Step S111: The detection management center module issues a task.

[0199] Step S112: The domain name resolution detection module receives and resolves the task.

[0200] Step S113: The domain name resolution detection module successfully resolved the domain name.

[0201] Step S114: The domain name resolution detection module classifies and fragments the task.

[0202] Step S115: The probe node performs the probe task.

[0203] Step S116: Collect business data corresponding to the task.

[0204] Step S117: Business data consistency comparison.

[0205] Step S118: Data reporting.

[0206] During the reception and parsing of detection tasks, the detection terminal center receives and parses the detection tasks from the detection management center, and parses out information such as the detection task ID, detection type, detection target (port), detection source address, detection target level (domain name), detection cycle, detection frequency, and expected result.

[0207] During the tiered and segmented process, the tiers and segmentation methods can be determined based on the scale of the detection targets and the characteristics of the operations. Simultaneously, maintaining communication and collaboration between tiers and segments ensures the entire detection system can operate efficiently and collaboratively.

[0208] During the consistency comparison process, the collected detection results data are compared with the expected results data based on the parsed expected results data. The comparison content can be divided into types such as complete match, partial match, and detection results included in the expected results. At the same time, the comparison results are labeled to facilitate data classification and reporting.

[0209] When reporting data, depending on the task type and the timeliness requirements, it supports message queue reporting, SFTP / FTP (Secure File Transfer Protocol) reporting, and one-time interface return reporting. Different reported data support different storage modes according to business needs.

[0210] The detection management center comprises two parts: a task bus and a scheduling center. These two components work together to schedule and manage tasks. The collaboration between the task bus and the scheduling center enables a more flexible and scalable task scheduling mechanism. Dynamic monitoring of task status improves overall system performance and response speed, and better meets various business needs. The functional architecture of the detection management center is as follows: Figure 12 As shown.

[0211] The task bus allows for the dynamic addition or removal of tasks, making the system more flexible and scalable.

[0212] The task bus can also provide the scheduling center with information such as task metadata and execution status.

[0213] The task bus can also execute probe task instructions according to the scheduling policy.

[0214] The scheduling center can identify the attributes, status, and priority of tasks, and formulate more efficient scheduling strategies based on the task's bus information and other system statuses, and issue scheduling instructions to the task bus for execution.

[0215] This disclosure also provides a processing apparatus for a network resolution service, including:

[0216] The first acquisition module is used to acquire the business data to be analyzed.

[0217] The first input module is used to input the business data to be analyzed into the service level branch of the business quality model; the data specifications processed by the service level branch correspond to the service level of the business data to be analyzed; the business quality model includes multiple service level branches.

[0218] The first output module is used to obtain the model analysis results of the service quality model based on the output data of the service level branch; the model analysis results are used to evaluate the quality of the service corresponding to the service data.

[0219] The second acquisition module is used to obtain sample business data of the domain name recursive resolution service.

[0220] The clustering module is used to cluster the sample business data to obtain the label category to which the sample business data belongs;

[0221] The third acquisition module is used to obtain model training samples based on the sample service data of the label categories; the model training samples include multiple label categories, and the model training samples of each label category include the sample service data corresponding to multiple evaluation labels; the multiple evaluation labels are pre-set labels for the quality of network resolution services;

[0222] The fourth module is used to obtain a converged business quality model based on the model training samples.

[0223] The update module is used to update the sample business data to obtain updated model training samples;

[0224] The second input module is used to input the updated model training samples into the business quality model to be trained and the converged business quality model, and to retrain the converged business quality model according to the output results to obtain the completed business quality model.

[0225] Below, for reference Figure 13 This describes an electronic device according to embodiments of the present disclosure. The electronic device may be either or both of a first device and a second device, or a standalone device independent of them, which may communicate with the first device and the second device to receive acquired input signals from them.

[0226] Figure 13 A block diagram of an electronic device according to an embodiment of the present disclosure is shown.

[0227] like Figure 13 As shown, the electronic device includes one or more processors and memory.

[0228] A processor can be a central processing unit (CPU) or other form of processing unit with data processing and / or instruction execution capabilities, and can control other components in an electronic device to perform desired functions.

[0229] The memory can store one or more computer program products, and the memory can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, etc. One or more computer program products can be stored on the computer-readable storage medium, and the processor can run the computer program products to implement the methods of the various embodiments of this disclosure described above and / or other desired functions.

[0230] In one example, the electronic device may also include input devices and output devices, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0231] In addition, the input device may also include, for example, a keyboard, a mouse, etc.

[0232] This output device can output various information to the outside, including determined distance information, direction information, etc. The output device may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0233] Of course, for the sake of simplicity, Figure 13Only some of the components of the electronic device relevant to this disclosure are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device may include any other suitable components depending on the specific application.

[0234] In addition to the methods and devices described above, embodiments of this disclosure may also be computer program products, including computer program instructions that, when executed by a processor, cause the processor to perform the steps in the processing methods of the network resolution service according to various embodiments of this disclosure as described in the foregoing portions of this specification.

[0235] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this disclosure. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on a user's computing device, partially on a user's computing device, as a standalone software package, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0236] Furthermore, embodiments of this disclosure may also be computer-readable storage media storing computer program instructions that, when executed by a processor, cause the processor to perform the steps of the processing methods for network resolution services according to various embodiments of this disclosure as described in the foregoing portion of this specification.

[0237] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0238] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0239] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0240] The block diagrams of devices, apparatuses, devices, and systems disclosed herein are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0241] The methods and apparatus of this disclosure may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of this disclosure are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, this disclosure may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the methods according to this disclosure. Thus, this disclosure also covers recording media storing programs for performing the methods according to this disclosure.

[0242] It should also be noted that in the apparatus, devices, and methods of this disclosure, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions to this disclosure.

[0243] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0244] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A method for processing network resolution services, characterized in that, include: Obtain the business data to be analyzed; Input the business data to be analyzed into the service level branch of the business quality model; The data specifications processed by the service level branch correspond to the service level of the business data to be analyzed; the business quality model includes multiple service level branches. Based on the output data of the service level branch, the model analysis results of the service quality model are obtained; the model analysis results are used to evaluate the quality of the service corresponding to the service data. The business quality model is obtained through the following steps: Obtain sample business data for domain name recursive resolution services; Cluster the sample business data to obtain the label category to which the sample business data belongs; Based on the sample service data of the label categories, model training samples are obtained; the model training samples include multiple label categories, and the model training samples of each label category include sample service data corresponding to multiple evaluation labels; the multiple evaluation labels are pre-defined labels for the quality of network resolution services; Based on the training samples of the model, a converged business quality model is obtained; The sample business data is updated to obtain updated model training samples; The updated model training samples are input into the business quality model to be trained and the converged business quality model. Based on the output results, the converged business quality model is retrained to obtain the fully trained business quality model.

2. The method according to claim 1, characterized in that, The process of obtaining a converged business quality model based on the model training samples includes: For each target label category among the multiple label categories, determine the number of sample business data corresponding to each evaluation label; Based on the number of sample business data corresponding to each evaluation label, determine the initial weight of each evaluation label in each service level branch of the business quality model to be trained; Output the model analysis results during the training phase of the sample business data for the target label category; Based on the model analysis results and sample analysis results during the training phase, the initial weights are adjusted to obtain the adjusted weights. Based on the adjusted weights, a converged business quality model is obtained.

3. The method according to claim 2, characterized in that, The step of determining the initial weight of each evaluation label in each service level branch of the service quality model to be trained, based on the number of sample business data corresponding to each evaluation label, includes: For a single evaluation label, if the number of sample business data corresponding to the evaluation label meets the set quantity threshold requirement, the initial weight of the evaluation label is set according to the default weight value pre-set for the evaluation label.

4. The method according to claim 2 or 3, characterized in that, The step of determining the initial weight of each evaluation label in each service level branch of the converged service quality model based on the number of sample business data corresponding to each evaluation label includes: For a single evaluation label, if the number of sample business data corresponding to the evaluation label does not meet the set number threshold requirement, obtain the first evaluation label that meets the set number threshold requirement and the second evaluation label that does not meet the set number threshold requirement among the multiple evaluation labels; Determine the sum of the default weight values ​​pre-set for the first evaluation label, and the proportion of the default weight values ​​pre-set for the second evaluation label; Based on the ratio, determine the allocation ratio of the sum to the sample business data corresponding to the second evaluation label; Based on the allocation ratio, adjust the default weight values ​​pre-set for each of the evaluation labels to obtain the updated weight values ​​corresponding to each of the evaluation labels; Based on the updated weight values, the initial weights of each evaluation label are determined.

5. The method according to claim 4, characterized in that, The step of determining the allocation ratio of the sum to the sample business data corresponding to the second evaluation label based on the ratio includes: The proportion of each second evaluation label on each first evaluation label is determined by multiplying the proportion of each second evaluation label on the sum.

6. The method according to claim 5, characterized in that, The step of adjusting the default weight values ​​pre-set for each evaluation label according to the allocation ratio to obtain the updated weight values ​​corresponding to each evaluation label includes: The default weight values ​​pre-set for each of the second evaluation labels are adjusted to zero to obtain the updated weight values ​​corresponding to each of the second evaluation labels. For a single first evaluation label, the allocation ratio of each second evaluation label on the first evaluation label is added to the default weight value pre-set for the first evaluation label to obtain the updated weight value corresponding to the first evaluation label.

7. The method according to claim 1, characterized in that, Before obtaining the model analysis results of the business quality model based on the output data of the service level branch, the process includes: Obtain the submodule processing result obtained by at least one submodule in the service level branch processing the business data; each submodule in the at least one submodule is used to process the business data in the dimension of at least one tag category among the plurality of tag categories; The output data is obtained based on the processing results of the submodule.

8. The method according to claim 7, characterized in that, The submodule processing result obtained by processing the business data by at least one submodule in the service level branch includes: Based on the weight value of each evaluation tag in the service level branch and the score corresponding to the business data value of each evaluation tag, calculate the score of each evaluation tag in the sub-module; Based on the scores corresponding to each evaluation label in the submodule, calculate the total score corresponding to all evaluation labels in the submodule to obtain the processing result of the submodule.

9. The method according to claim 1, characterized in that, The sample business data for obtaining the domain name recursive resolution service includes: Send a sample business data collection task to the business data detection terminal; the collection task is generated based on the evaluation label where there is missing sample business data; Receive the detection data returned by the detection end in response to the acquisition task; The consistency of the detection data is determined based on the uniform identifier in the detection data; Based on the consistency, the probe data is filtered to obtain the sample service data.

10. The method according to claim 1, characterized in that, The service level is determined based on the scope and level of the business service recipients; the service levels include: national level, provincial level and enterprise level.

11. The method according to claim 1, characterized in that, The network resolution service includes a domain name recursive resolution service; the business data includes business log data of the domain name recursive resolution service; the tag categories include: the geographical scope of the domain name recursive resolution service, the quality of the domain name recursive resolution service, recursion level dependency, and recursion resolution security.

12. A processing apparatus for network resolution services, characterized in that, include: The first acquisition module is used to acquire the business data to be analyzed. The first input module is used to input the business data to be analyzed into the service level branch of the business quality model; The data specifications processed by the service level branch correspond to the service level of the business data to be analyzed; the business quality model includes multiple service level branches. The first output module is used to obtain the model analysis results of the service quality model based on the output data of the service level branch; the model analysis results are used to evaluate the quality of the service corresponding to the service data. The second acquisition module is used to obtain sample business data of the domain name recursive resolution service. The clustering module is used to cluster the sample business data to obtain the label category to which the sample business data belongs; The third acquisition module is used to obtain model training samples based on the sample service data of the label categories; the model training samples include multiple label categories, and the model training samples of each label category include the sample service data corresponding to multiple evaluation labels; the multiple evaluation labels are pre-set labels for the quality of network resolution services; The fourth module is used to obtain a converged business quality model based on the model training samples. The update module is used to update the sample business data to obtain updated model training samples; The second input module is used to input the updated model training samples into the business quality model to be trained and the converged business quality model, and to retrain the converged business quality model according to the output results to obtain the completed business quality model.

13. An electronic device, characterized in that, include: Memory, used to store computer program products; A processor is configured to execute a computer program product stored in the memory, wherein, when the computer program product is executed, it implements the method described in any one of claims 1-11.

14. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, they implement the method described in any one of claims 1-11.

15. A computer program product comprising computer program instructions, characterized in that, When the computer program instructions are executed by the processor, they implement the method described in any one of claims 1-11.

Images