Network state evaluation method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of deterministic networks, in particular to a network state evaluation method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring target performance data corresponding to a to-be-detected network; according to a preset performance data weight and the target performance data, performing network state evaluation on the to-be-detected network to obtain a target state score corresponding to the to-be-detected network; wherein the performance data weight is obtained based on the sample performance data of the to-be-detected network and the sample influence weight of the sample performance data on the state score of the to-be-detected network. The target performance data is adaptively adjusted through the performance data weight, it is guaranteed that the target state score can reflect the actual situation of the to-be-detected network, the adaptivity of the target state score is enriched, and determination of the target state score can be suitable for different network environments and service requirements.

Description

Technical Field

[0001] The present application relates to the field of deterministic network technology, and in particular to a network status assessment method, apparatus, computer equipment and storage medium. Background Art

[0002] Obtaining network performance evaluation parameters of the IP (Internet Protocol) bearer network is the basis for achieving end-to-end deterministic service quality assurance for 5G (5th Generation Mobile Communication Technology).

[0003] However, in the prior art, a single indicator is usually used to represent the network performance evaluation parameters of the IP bearer network, and therefore, it is difficult to adapt to different network environments and business requirements. Summary of the invention

[0004] Based on this, it is necessary to provide a network status assessment method, device, computer equipment and storage medium that can adapt to different network environments and business needs in response to the above technical problems.

[0005] In a first aspect, the present application provides a network status assessment method. The method comprises:

[0006] Obtain target performance data corresponding to the network to be tested;

[0007] According to the preset performance data weight and the target performance data, the network status of the network to be detected is evaluated to obtain the target status score corresponding to the network to be detected; wherein the performance data weight is obtained based on the sample performance data of the network to be detected and the sample impact weight of the sample performance data on the status score of the network to be detected.

[0008] In one embodiment, the performance data weight is determined as follows:

[0009] Obtaining sample performance data corresponding to the network to be detected, and an initial sample weight of the sample performance data for scoring the state of the network to be detected;

[0010] Determining a sample status score corresponding to the network to be detected according to the sample performance data and the initial sample weight;

[0011] If it is determined according to the sample status score that the initial sample weight meets the data weight setting conditions, the initial data weight is used as the performance data weight.

[0012] In one embodiment, the method further comprises:

[0013] If it is determined according to the sample status score that the initial sample weight does not meet the data weight setting condition, new sample performance data and a new initial sample weight corresponding to the new sample performance data are obtained;

[0014] According to the new sample performance data and the new initial sample weight, return to the step of determining the sample state score corresponding to the network to be detected according to the sample performance data and the initial sample weight, until it is determined that the initial sample weight meets the data weight setting condition according to the sample state score.

[0015] In one embodiment, determining that the initial sample weight meets the data weight setting condition according to the sample status score includes:

[0016] Determine the training reward value and expected value of benefit corresponding to the network to be tested according to the sample status score;

[0017] Determine the number of updates corresponding to the initial sample weight;

[0018] According to the update times, the training reward value and the expected value of the benefit, it is determined that the initial sample weight meets the data weight setting condition.

[0019] In one embodiment, determining that the initial sample weight meets the data weight setting condition according to the update number, the training reward value and the expected value of the benefit includes:

[0020] When the initial sample weight meets at least one of the following conditions: the number of updates is greater than or equal to the number threshold, the change in the reward value of the training reward value is less than the first change threshold, and the change in the expected value of the expected benefit is less than the second change threshold, it is determined that the initial sample weight meets the data weight setting conditions.

[0021] In one embodiment, the network status evaluation of the network to be detected is performed according to the preset performance data weight and the target performance data to obtain the target status score corresponding to the network to be detected, including:

[0022] The target performance data is input into a state assessment model whose model parameters include the performance data weights, and a target state score corresponding to the network to be detected output by the state assessment model is obtained.

[0023] In a second aspect, the present application also provides a network status assessment device. The device comprises:

[0024] An acquisition module is used to obtain target performance data corresponding to the network to be detected;

[0025] An evaluation module is used to evaluate the network status of the network to be detected according to a preset performance data weight and the target performance data, and obtain a target status score corresponding to the network to be detected; wherein the performance data weight is obtained based on the sample performance data of the network to be detected and the sample influence weight of the sample performance data on the status score of the network to be detected.

[0026] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0027] Obtain target performance data corresponding to the network to be tested;

[0028] According to the preset performance data weight and the target performance data, the network status of the network to be detected is evaluated to obtain the target status score corresponding to the network to be detected; wherein the performance data weight is obtained based on the sample performance data of the network to be detected and the sample impact weight of the sample performance data on the status score of the network to be detected.

[0029] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0030] Obtain target performance data corresponding to the network to be tested;

[0031] According to the preset performance data weight and the target performance data, the network status of the network to be detected is evaluated to obtain the target status score corresponding to the network to be detected; wherein the performance data weight is obtained based on the sample performance data of the network to be detected and the sample impact weight of the sample performance data on the status score of the network to be detected.

[0032] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0033] Obtain target performance data corresponding to the network to be tested;

[0034] According to the preset performance data weight and the target performance data, the network status of the network to be detected is evaluated to obtain the target status score corresponding to the network to be detected; wherein the performance data weight is obtained based on the sample performance data of the network to be detected and the sample impact weight of the sample performance data on the status score of the network to be detected.

[0035] The above-mentioned network status evaluation method, device, computer equipment and storage medium obtain the target performance data corresponding to the network to be detected, so as to realize the network status evaluation of the network to be detected according to the preset performance data weight and target performance data, and obtain the target status score corresponding to the network to be detected. According to the above content, in the process of determining the target status score corresponding to the network to be detected, the present application does not use a single indicator to represent the target status score of the network to be detected, but uses the performance data weight and the target performance data to evaluate the network status of the network to be detected, and then determines the target status score corresponding to the network to be detected, thereby realizing the adaptive adjustment of the target performance data through the performance data weight, ensuring that the target status score can reflect the actual situation of the network to be detected, and enriching the adaptability of the target status score, so that the determination of the target status score can be applicable to different network environments and business needs; and, in the case where the target performance data contains multiple performance data, it is also possible to realize the status evaluation of the large detection network from multiple aspects, ensuring that the target status score can effectively reflect the overall performance of the network to be detected. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 An application environment diagram of a network status assessment method provided in an embodiment of the present application;

[0037] Figure 2 A flowchart of a first network status assessment method provided in an embodiment of the present application;

[0038] Figure 3 A flowchart of a second network status assessment method provided in an embodiment of the present application;

[0039] Figure 4 A schematic diagram of a flow chart of a third network status assessment method provided in an embodiment of the present application;

[0040] Figure 5 A structural block diagram of a network status assessment device provided in an embodiment of the present application;

[0041] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0043] It is understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. In the description of the present application, the description of the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily have to be directed to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples without contradicting each other.

[0044] The network status evaluation method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. By obtaining the target performance data corresponding to the network to be detected, the network status of the network to be detected is evaluated according to the preset performance data weights and target performance data, and the target status score corresponding to the network to be detected is obtained. Among them, the terminal 102 can be but is not limited to various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0045] In one embodiment, Figure 2 As shown, a network status assessment method is provided, which is applied to Figure 1 The terminal 102 in the example is used as an example to illustrate, and the following steps are included:

[0046] S201, obtaining target performance data corresponding to the network to be detected.

[0047] It should be noted that the target performance data includes at least one of delay data, jitter data, bandwidth data and isolation data; therefore, when it is necessary to obtain the target performance data corresponding to the network to be detected, the data type contained in the target performance data can be determined in advance, and then different measurement systems can be used according to different data types to obtain the target performance data corresponding to the network to be detected.

[0048] It is further explained that in order to ensure that when the network status of the network to be tested is subsequently evaluated based on the target performance data, the accuracy of the target status score corresponding to the network to be tested that is finally determined will not be affected by the data differences between different target performance data, the performance data of the network to be tested obtained by measurement can be normalized in advance to obtain the target performance data corresponding to the network to be tested.

[0049] In one embodiment of the present application, when it is necessary to obtain target performance data corresponding to the network to be detected, different measurement systems can be used to obtain initial performance data corresponding to the network to be detected according to the type of data contained in the target performance data, and each initial performance data can be normalized to obtain the target performance data corresponding to the network to be detected.

[0050] Specifically, when the initial performance data needs to be normalized, the maximum value and the minimum value of the initial performance data within a preset period, as well as the mean value of the initial performance data within the preset period can be obtained in advance; then, the difference between the mean value and the minimum value is ratioed to the difference between the maximum value and the minimum value, and the obtained calculation result is the normalized target performance data.

[0051] As a method, if the initial performance data includes initial delay data, initial jitter data, initial bandwidth data and initial isolation data, when it is necessary to obtain the target performance data corresponding to the initial delay data, the following formula (1) can be used:

[0052]

[0053] Among them, D norm Refers to the target performance data corresponding to the initial delay data. Refers to the average value of the initial delay data within the preset period; D min Refers to the minimum value of the initial delay data within the preset period; D max Refers to the maximum value of the initial delay data within a preset period.

[0054] When it is necessary to obtain the target performance data corresponding to the initial jitter data, the following formula (2) can be used:

[0055]

[0056] Among them, J norm Refers to the target performance data corresponding to the initial jitter data, Refers to the average value of the initial jitter data within a preset period; J min Refers to the minimum value of the initial jitter data within a preset period; J max Refers to the maximum value of the initial jitter data within a preset period.

[0057] When it is necessary to obtain the target performance data corresponding to the initial bandwidth data, the following formula (3) can be used:

[0058]

[0059] Among them, B norm Refers to the target performance data corresponding to the initial bandwidth data. Refers to the average value of the initial bandwidth data within the preset period; B min Refers to the minimum value of the initial bandwidth data within the preset period; B max Refers to the maximum value of the initial bandwidth data within a preset period.

[0060] When it is necessary to obtain the target performance data corresponding to the initial isolation data, the following formula (4) can be used:

[0061]

[0062] Among them, I norm Refers to the target performance data corresponding to the initial isolation data, Refers to the average value of the initial isolation data within the preset period; I min Refers to the minimum value of the initial isolation data within the preset period; I max Refers to the maximum value of the initial isolation data within a preset period.

[0063] S202: Perform a network status evaluation on the network to be detected according to preset performance data weights and target performance data to obtain a target status score corresponding to the network to be detected.

[0064] The performance data weight is obtained based on the sample performance data of the network to be detected and the sample impact weight of the sample performance data on the state score of the network to be detected.

[0065] In one embodiment of the present application, a state assessment model for the network to be detected can be pre-trained, and then, a state assessment is performed on the target performance data corresponding to the network to be detected according to the state assessment model to obtain a target state score corresponding to the network to be detected; in the training process of the state assessment model, the model parameters of the state assessment model can be trained through the sample performance data of the network to be detected and the sample influence weights of the sample performance data on the state score of the network to be detected, wherein the model parameters include performance data weights.

[0066] Specifically, the target performance data is input into a state evaluation model whose model parameters include performance data weights, and a target state score corresponding to the network to be tested outputted by the state evaluation model is obtained.

[0067] The above network status evaluation method obtains the target performance data corresponding to the network to be detected, so as to realize the network status evaluation of the network to be detected according to the preset performance data weight and target performance data, and obtain the target status score corresponding to the network to be detected. According to the above content, in the process of determining the target status score corresponding to the network to be detected, the present application does not use a single indicator to represent the target status score of the network to be detected, but uses the performance data weight and the target performance data to evaluate the network status of the network to be detected, and then determines the target status score corresponding to the network to be detected, thereby realizing the adaptive adjustment of the target performance data through the performance data weight, ensuring that the target status score can reflect the actual situation of the network to be detected, and enriching the adaptability of the target status score, so that the determination of the target status score can be applicable to different network environments and business needs; and, in the case where the target performance data contains multiple performance data, it is also possible to realize the status evaluation of the large detection network from multiple aspects, ensuring that the target status score can effectively reflect the overall performance of the network to be detected.

[0068] In one embodiment, if Figure 3 As shown, when it is necessary to determine the performance data weight, the following contents may be specifically included:

[0069] S301, obtaining sample performance data corresponding to the network to be detected, and initial sample weights of the sample performance data for the state score of the network to be detected.

[0070] It should be noted that when it is necessary to obtain sample performance data corresponding to the network to be tested, in order to ensure the accuracy of the subsequent determination of the target state score corresponding to the network to be tested, the initial sample data corresponding to the network to be tested can be obtained in advance, and the initial sample data can be normalized to obtain the sample performance data corresponding to the network to be tested.

[0071] Among them, the initial sample data can be historical performance data corresponding to the network to be detected, and / or real-time performance data corresponding to the network to be detected. The method for obtaining the initial sample data corresponding to the network to be detected and the data type are not limited here.

[0072] It should be noted that when it is necessary to determine the initial sample weights of sample performance data, different weight determination strategies can be selected based on actual conditions, and then the initial sample weights of the sample performance data for the state score of the network to be detected can be determined according to different weight determination strategies.

[0073] Specifically, it can be verified whether the process of determining the initial sample weights of the sample performance data for the state score of the network to be detected in this round is the first process of determining the initial sample weights. If so, the first weight determination strategy is used to determine the initial sample weights of the sample performance data for the state score of the network to be detected. If not, the second weight determination strategy is used to determine the initial sample weights of the sample performance data for the state score of the network to be detected.

[0074] In one embodiment of the present application, if the first weight determination strategy is adopted to determine the initial sample weight of the sample performance data on the state score of the network to be detected, the sample influence weight of the sample performance data on the state score of the network to be detected is randomly determined; if the second weight determination strategy is adopted to determine the initial sample weight of the sample performance data on the state score of the network to be detected, the historical sample weights determined in each historical process are obtained, and the expected value of the benefit corresponding to each group of historical sample weights is determined; and the historical sample weight with the largest expected value of benefit in each group of historical sample weights is used as the initial sample weight of the sample performance data on the state score of the network to be detected.

[0075] S302: Determine a sample status score corresponding to the network to be detected based on the sample performance data and the initial sample weight.

[0076] It should be noted that when it is necessary to determine the sample state score corresponding to the network to be detected based on the sample performance data and the initial sample weight, a state score determination formula (5) for the sample performance data and the initial sample weight can be pre-specified, and then the sample performance data and the initial sample weight are substituted into the state score determination formula (5) to obtain the sample state score corresponding to the network to be detected.

[0077] Further explanation: since the sample performance data contains many data types, the corresponding state score determination formula (5) for sample performance data containing different data types also has differences, and the specific content of the state score determination formula (5) is not limited here.

[0078] As an example, if the sample performance data includes sample delay data, sample jitter data, sample bandwidth data and sample isolation data, the state score determination formula (5) is as follows:

[0079] C=W D (1-D norm )+W J (1-J norm )+W N* N norm +W I* I norm (5)

[0080] Among them, C refers to the sample state score corresponding to the network to be tested; WD Refers to the initial sample weight corresponding to the sample delay data; W J Refers to the initial sample weight corresponding to the sample jitter data; W N Refers to the initial sample weight corresponding to the sample bandwidth data; W I Refers to the initial sample weight corresponding to the sample isolation data.

[0081] S303: If it is determined according to the sample status score that the initial sample weight meets the data weight setting conditions, the initial data weight is used as the performance data weight.

[0082] It should be noted that when it is necessary to judge whether the initial sample weight meets the data weight setting conditions based on the sample status score, the following contents may be specifically included: determining the training reward value and the expected value of profit corresponding to the network to be tested based on the sample status score; determining the number of updates corresponding to the initial sample weight; and determining that the initial sample weight meets the data weight setting conditions based on the number of updates, the training reward value and the expected value of profit.

[0083] To further illustrate, when it is necessary to determine whether the initial sample weight meets the data weight setting conditions based on the number of updates, training reward value and expected value of profit, the following contents may also be included: when the initial sample weight meets at least one of the following conditions: the number of updates is greater than or equal to the number threshold, the change in the reward value of the training reward value is less than the first change threshold, and the change in the expected value of the expected value of profit is less than the second change threshold, then it is determined that the initial sample weight meets the data weight setting conditions.

[0084] In one embodiment of the present application, when it is necessary to determine the training reward value corresponding to the network to be detected, the sample state score corresponding to the network to be detected determined in this round and the actual state score corresponding to the network to be detected actually determined can be differenced, and the obtained calculation result is the training reward value corresponding to the network to be detected.

[0085] Specifically, the formula (6) for determining the training reward value corresponding to the network to be tested is as follows:

[0086] R=-|C actual -C predicted | (6)

[0087] Among them, R refers to the training reward value corresponding to the network to be tested; C actual Refers to the actual state score corresponding to the network to be tested; C predicted Refers to the sample status score corresponding to the network to be tested determined in this round.

[0088] Furthermore, the actual status score actually determined corresponding to the network to be detected is a status score determined based on historical performance data of the network to be detected, as well as by network element operation and maintenance personnel and experts based on historical experience and actual conditions; or, the actual status score actually determined corresponding to the network to be detected can also be a status score obtained after a third-party performance evaluation tool performs performance evaluation on the network to be detected.

[0089] In one embodiment of the present application, when it is necessary to determine the expected value of the benefit corresponding to the network to be detected, it can be verified whether the process of determining the initial sample weight of the state score of the network to be detected by the sample performance data in this round is the process of determining the initial sample weight for the first time; if so, the empty matrix is ​​used as the expected value of the benefit, and the dimension corresponding to the expected value of the benefit is (sample performance data, initial sample weight); if not, the expected value of the benefit is determined by calculating formula (7); wherein the calculation formula (7) is as follows:

[0090] Q(S,A1)=Q(S,A1)+α[R+γ*max a′ Q(S′, A′)-Q(S, A1)] (7)

[0091] Among them, Q refers to the expected value of the return corresponding to the network to be tested; S refers to the sample performance data, that is, the state of the network to be tested; A1 refers to the initial sample weight, that is, the action corresponding to the state of the network to be tested; α, R and γ are pre-set parameters, max a′ Q(S′, A′) refers to the maximum future reward.

[0092] To further explain, when determining whether the initial sample weight meets the data weight setting conditions, it is necessary to predetermine the reward value change of the training reward value and the expected value change of the expected value of the benefit, and then, based on the number of updates, the reward value change of the training reward value and the expected value change of the expected value of the benefit, determine whether the initial sample weight meets the data weight setting conditions.

[0093] Among them, the reward value change of the training reward value refers to the difference between the training reward value obtained in the process of determining the performance data weights in this round and the training reward value obtained in the process of determining the performance data weights in the previous round; the expected value change of the benefit expected value refers to the difference between the benefit expected value obtained in the process of determining the performance data weights in this round and the benefit expected value obtained in the process of determining the performance data weights in the previous round.

[0094] Among them, the number threshold, the first change threshold and the second change threshold can be determined or adjusted according to actual conditions, and the value ranges of the number threshold, the first change threshold and the second change threshold are not limited here.

[0095] To further explain, if it is determined based on the sample state score that the initial sample weight does not meet the data weight setting conditions, new sample performance data and new initial sample weights corresponding to the new sample performance data are obtained; then, based on the new sample performance data and the new initial sample weights, the process returns to the step of determining the sample state score corresponding to the network to be tested based on the sample performance data and the initial sample weights, until it is determined based on the sample state score that the initial sample weight meets the data weight setting conditions.

[0096] Among them, each time new sample performance data and new initial sample weights corresponding to the new sample performance data are obtained, the update times corresponding to the initial sample weights need to be updated; as an example, when updating the update times, the value of the update times can be increased by one.

[0097] The above network status evaluation method obtains the sample performance data and initial sample weight corresponding to the network to be detected, and determines the sample status score corresponding to the network to be detected according to the sample performance data and the initial sample weight, and then uses the initial data weight as the performance data weight when the initial sample weight meets the data weight setting conditions according to the sample status score. In this way, it is ensured that the determined performance data weight can effectively realize the process of evaluating the network status of the network to be detected and obtaining the target status score corresponding to the network to be detected, and the accuracy of the target status score determination is ensured.

[0098] In one embodiment, if Figure 4 As shown, when it is necessary to determine the performance data weight, the following contents may be specifically included:

[0099] S401, obtaining sample performance data corresponding to the network to be detected, and initial sample weights of the sample performance data for the state score of the network to be detected.

[0100] S402: Determine a sample status score corresponding to the network to be detected based on the sample performance data and the initial sample weight.

[0101] S403, determining the training reward value and expected value of benefit corresponding to the network to be tested according to the sample state score.

[0102] S404, determining the number of updates corresponding to the initial sample weights.

[0103] S405, when the initial sample weight meets at least one of the following conditions: the number of updates is greater than or equal to the number threshold, the change in the reward value of the training reward value is less than the first change threshold, and the change in the expected value of the benefit is less than the second change threshold, it is determined that the initial sample weight meets the data weight setting conditions, and the initial data weight is used as the performance data weight.

[0104] S405, if it is determined according to the sample status score that the initial sample weight does not meet the data weight setting condition, then new sample performance data and a new initial sample weight corresponding to the new sample performance data are obtained;

[0105] S406, based on the new sample performance data and the new initial sample weight, return to the step of determining the sample state score corresponding to the network to be detected based on the sample performance data and the initial sample weight, until it is determined that the initial sample weight meets the data weight setting conditions based on the sample state score.

[0106] The above network status evaluation method obtains the target performance data corresponding to the network to be detected, so as to realize the network status evaluation of the network to be detected according to the preset performance data weight and target performance data, and obtain the target status score corresponding to the network to be detected. According to the above content, in the process of determining the target status score corresponding to the network to be detected, the present application does not use a single indicator to represent the target status score of the network to be detected, but uses the performance data weight and the target performance data to evaluate the network status of the network to be detected, and then determines the target status score corresponding to the network to be detected, thereby realizing the adaptive adjustment of the target performance data through the performance data weight, ensuring that the target status score can reflect the actual situation of the network to be detected, and enriching the adaptability of the target status score, so that the determination of the target status score can be applicable to different network environments and business needs; and, in the case where the target performance data contains multiple performance data, it is also possible to realize the status evaluation of the large detection network from multiple aspects, ensuring that the target status score can effectively reflect the overall performance of the network to be detected.

[0107] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0108] Based on the same inventive concept, the embodiment of the present application also provides a network status assessment device for implementing the network status assessment method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more network status assessment device embodiments provided below can refer to the limitations of the network status assessment method above, and will not be repeated here.

[0109] In one embodiment, Figure 5 As shown, a network status evaluation device is provided, comprising: an acquisition module 10 and an evaluation module 20, wherein:

[0110] The acquisition module 10 is used to acquire target performance data corresponding to the network to be detected.

[0111] The evaluation module 20 is used to perform network status evaluation on the network to be detected according to preset performance data weights and target performance data, and obtain a target status score corresponding to the network to be detected; wherein the performance data weight is obtained based on the sample performance data of the network to be detected and the sample influence weight of the sample performance data on the status score of the network to be detected.

[0112] In one embodiment, sample performance data corresponding to the network to be detected and an initial sample weight of the sample performance data for a state score of the network to be detected are obtained;

[0113] Determine the sample status score corresponding to the network to be tested based on the sample performance data and the initial sample weight;

[0114] If the initial sample weight is determined to meet the data weight setting conditions based on the sample status score, the initial data weight will be used as the performance data weight.

[0115] In one embodiment, if it is determined according to the sample status score that the initial sample weight does not meet the data weight setting condition, new sample performance data and a new initial sample weight corresponding to the new sample performance data are obtained;

[0116] According to the new sample performance data and the new initial sample weight, return to execute the step of determining the sample state score corresponding to the network to be detected according to the sample performance data and the initial sample weight, until it is determined according to the sample state score that the initial sample weight meets the data weight setting conditions.

[0117] In one embodiment, the training reward value and expected value of benefit corresponding to the network to be tested are determined according to the sample state score;

[0118] Determine the number of updates corresponding to the initial sample weights;

[0119] According to the number of updates, training reward value and expected value of benefit, it is determined that the initial sample weight meets the data weight setting conditions.

[0120] In one embodiment, when the initial sample weight meets at least one of the following conditions: the number of updates is greater than or equal to the number threshold, the change in the reward value of the training reward value is less than the first change threshold, and the change in the expected value of the expected benefit is less than the second change threshold, then it is determined that the initial sample weight meets the data weight setting conditions.

[0121] In one embodiment, the target performance data is input into a state assessment model whose model parameters include performance data weights, and a target state score corresponding to the network to be detected output by the state assessment model is obtained.

[0122] In one embodiment, the target performance data includes at least one of delay data, jitter data, bandwidth data, and isolation data.

[0123] The above-mentioned network status evaluation device obtains the target performance data corresponding to the network to be detected, so as to realize the network status evaluation of the network to be detected according to the preset performance data weight and target performance data, and obtain the target status score corresponding to the network to be detected. According to the above content, it can be known that in the process of determining the target status score corresponding to the network to be detected, the present application does not use a single indicator to represent the target status score of the network to be detected, but uses the performance data weight and the target performance data to evaluate the network status of the network to be detected, and then determines the target status score corresponding to the network to be detected, thereby realizing the adaptive adjustment of the target performance data through the performance data weight, ensuring that the target status score can reflect the actual situation of the network to be detected, and enriching the adaptability of the target status score, so that the determination of the target status score can be applicable to different network environments and business needs; and, in the case where the target performance data contains multiple performance data, it can also realize the status evaluation of the large detection network from multiple aspects, ensuring that the target status score can effectively reflect the overall performance of the network to be detected.

[0124] Each module in the above network status assessment device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0125] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 6As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a network status assessment method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0126] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0127] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0128] Obtain target performance data corresponding to the network to be tested;

[0129] According to the preset performance data weights and target performance data, the network status of the network to be detected is evaluated to obtain the target status score corresponding to the network to be detected; wherein the performance data weight is obtained based on the sample performance data of the network to be detected and the sample influence weight of the sample performance data on the status score of the network to be detected.

[0130] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0131] Obtaining sample performance data corresponding to the network to be tested, and initial sample weights of the sample performance data for the state score of the network to be tested;

[0132] Determine the sample status score corresponding to the network to be tested based on the sample performance data and the initial sample weight;

[0133] If the initial sample weight is determined to meet the data weight setting conditions based on the sample status score, the initial data weight will be used as the performance data weight.

[0134] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0135] If it is determined according to the sample status score that the initial sample weight does not meet the data weight setting conditions, new sample performance data and a new initial sample weight corresponding to the new sample performance data are obtained;

[0136] According to the new sample performance data and the new initial sample weight, return to execute the step of determining the sample state score corresponding to the network to be detected according to the sample performance data and the initial sample weight, until it is determined according to the sample state score that the initial sample weight meets the data weight setting conditions.

[0137] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0138] According to the sample status score, determine the training reward value and expected value of benefit corresponding to the network to be tested;

[0139] Determine the number of updates corresponding to the initial sample weights;

[0140] According to the number of updates, training reward value and expected value of benefit, it is determined that the initial sample weight meets the data weight setting conditions.

[0141] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0142] When the initial sample weight meets at least one of the following conditions: the number of updates is greater than or equal to the number threshold, the change in the reward value of the training reward value is less than the first change threshold, and the change in the expected value of the expected benefit is less than the second change threshold, then it is determined that the initial sample weight meets the data weight setting conditions.

[0143] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0144] The target performance data is input into a state evaluation model whose model parameters include performance data weights, and the target state score corresponding to the network to be tested output by the state evaluation model is obtained.

[0145] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0146] The target performance data includes at least one of delay data, jitter data, bandwidth data and isolation data.

[0147] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0148] Obtain target performance data corresponding to the network to be tested;

[0149] According to the preset performance data weights and target performance data, the network status of the network to be detected is evaluated to obtain the target status score corresponding to the network to be detected; wherein the performance data weight is obtained based on the sample performance data of the network to be detected and the sample influence weight of the sample performance data on the status score of the network to be detected.

[0150] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0151] Obtaining sample performance data corresponding to the network to be tested, and initial sample weights of the sample performance data for the state score of the network to be tested;

[0152] Determine the sample status score corresponding to the network to be tested based on the sample performance data and the initial sample weight;

[0153] If the initial sample weight is determined to meet the data weight setting conditions based on the sample status score, the initial data weight will be used as the performance data weight.

[0154] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0155] If it is determined according to the sample status score that the initial sample weight does not meet the data weight setting conditions, new sample performance data and a new initial sample weight corresponding to the new sample performance data are obtained;

[0156] According to the new sample performance data and the new initial sample weight, return to execute the step of determining the sample state score corresponding to the network to be detected according to the sample performance data and the initial sample weight, until it is determined according to the sample state score that the initial sample weight meets the data weight setting conditions.

[0157] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0158] According to the sample status score, determine the training reward value and expected value of benefit corresponding to the network to be tested;

[0159] Determine the number of updates corresponding to the initial sample weights;

[0160] According to the number of updates, training reward value and expected value of benefit, it is determined that the initial sample weight meets the data weight setting conditions.

[0161] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0162] When the initial sample weight meets at least one of the following conditions: the number of updates is greater than or equal to the number threshold, the change in the reward value of the training reward value is less than the first change threshold, and the change in the expected value of the expected benefit is less than the second change threshold, then it is determined that the initial sample weight meets the data weight setting conditions.

[0163] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0164] The target performance data is input into a state evaluation model whose model parameters include performance data weights, and the target state score corresponding to the network to be tested output by the state evaluation model is obtained.

[0165] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0166] The target performance data includes at least one of delay data, jitter data, bandwidth data and isolation data.

[0167] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0168] Obtain target performance data corresponding to the network to be tested;

[0169] According to the preset performance data weights and target performance data, the network status of the network to be detected is evaluated to obtain the target status score corresponding to the network to be detected; wherein the performance data weight is obtained based on the sample performance data of the network to be detected and the sample influence weight of the sample performance data on the status score of the network to be detected.

[0170] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0171] Obtaining sample performance data corresponding to the network to be tested, and initial sample weights of the sample performance data for the state score of the network to be tested;

[0172] Determine the sample status score corresponding to the network to be tested based on the sample performance data and the initial sample weight;

[0173] If the initial sample weight is determined to meet the data weight setting conditions based on the sample status score, the initial data weight will be used as the performance data weight.

[0174] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0175] If it is determined according to the sample status score that the initial sample weight does not meet the data weight setting conditions, new sample performance data and a new initial sample weight corresponding to the new sample performance data are obtained;

[0176] According to the new sample performance data and the new initial sample weight, return to execute the step of determining the sample state score corresponding to the network to be detected according to the sample performance data and the initial sample weight, until it is determined according to the sample state score that the initial sample weight meets the data weight setting conditions.

[0177] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0178] According to the sample status score, determine the training reward value and expected value of benefit corresponding to the network to be tested;

[0179] Determine the number of updates corresponding to the initial sample weights;

[0180] According to the number of updates, training reward value and expected value of benefit, it is determined that the initial sample weight meets the data weight setting conditions.

[0181] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0182] When the initial sample weight meets at least one of the following conditions: the number of updates is greater than or equal to the number threshold, the change in the reward value of the training reward value is less than the first change threshold, and the change in the expected value of the expected benefit is less than the second change threshold, then it is determined that the initial sample weight meets the data weight setting conditions.

[0183] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0184] The target performance data is input into a state evaluation model whose model parameters include performance data weights, and the target state score corresponding to the network to be tested output by the state evaluation model is obtained.

[0185] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0186] The target performance data includes at least one of delay data, jitter data, bandwidth data and isolation data.

[0187] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0188] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0189] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0190] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A network status assessment method, characterized in that: The method comprises: Obtain target performance data corresponding to the network to be tested; According to the preset performance data weight and the target performance data, the network status of the network to be detected is evaluated to obtain the target status score corresponding to the network to be detected; wherein the performance data weight is obtained based on the sample performance data of the network to be detected and the sample impact weight of the sample performance data on the status score of the network to be detected.

2. The method according to claim 1, characterized in that: The process of determining the performance data weight is as follows: Obtaining sample performance data corresponding to the network to be detected, and an initial sample weight of the sample performance data for a status score of the network to be detected; Determine a sample status score corresponding to the network to be detected according to the sample performance data and the initial sample weight; If it is determined according to the sample status score that the initial sample weight meets the data weight setting conditions, the initial data weight is used as the performance data weight.

3. The method according to claim 2, characterized in that The method further comprises: If it is determined according to the sample status score that the initial sample weight does not meet the data weight setting condition, new sample performance data and a new initial sample weight corresponding to the new sample performance data are obtained; According to the new sample performance data and the new initial sample weight, return to the step of determining the sample state score corresponding to the network to be detected according to the sample performance data and the initial sample weight, until it is determined that the initial sample weight meets the data weight setting condition according to the sample state score.

4. The method according to claim 2, characterized in that: The determining, according to the sample status score, that the initial sample weight meets the data weight setting condition includes: Determine the training reward value and expected value of benefit corresponding to the network to be tested according to the sample status score; Determine the number of updates corresponding to the initial sample weight; According to the update times, the training reward value and the expected value of the benefit, it is determined that the initial sample weight meets the data weight setting condition.

5. The method according to claim 4, characterized in that The determining, based on the update number, the training reward value and the expected value of the benefit, that the initial sample weight meets the data weight setting condition comprises: When the initial sample weight meets at least one of the following conditions: the number of updates is greater than or equal to the number threshold, the change in the reward value of the training reward value is less than the first change threshold, and the change in the expected value of the expected benefit is less than the second change threshold, it is determined that the initial sample weight meets the data weight setting conditions.

6. The method according to any one of claims 1 to 5, characterized in that The step of performing a network status evaluation on the network to be detected according to the preset performance data weight and the target performance data to obtain a target status score corresponding to the network to be detected includes: The target performance data is input into a state assessment model whose model parameters include the performance data weights, and a target state score corresponding to the network to be detected output by the state assessment model is obtained.

7. The method according to any one of claims 1 to 5, characterized in that The target performance data includes at least one of delay data, jitter data, bandwidth data and isolation data.

8. A network status assessment device, characterized in that: The device comprises: An acquisition module is used to obtain target performance data corresponding to the network to be detected; An evaluation module is used to evaluate the network status of the network to be detected according to a preset performance data weight and the target performance data, and obtain a target status score corresponding to the network to be detected; wherein the performance data weight is obtained based on the sample performance data of the network to be detected and the sample influence weight of the sample performance data on the status score of the network to be detected.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images