Automatic detection and identification method for network infrastructure elements

Abstract

The invention relates to the technical field of network infrastructure, and discloses a network infrastructure element automatic detection and identification method, which comprises the following steps: acquiring network delay and network broadband at the current moment, determining reference network delay and reference network broadband, and determining a facility element detection and identification model; predicting a future moment of the network infrastructure based on the facility element detection and identification model to obtain an initial detection and identification result; collecting feature parameter values corresponding to a plurality of historical moments to obtain a feature parameter value group, and determining a parameter fluctuation confidence coefficient; analyzing the parameter fluctuation confidence coefficient set to obtain a single-parameter fluctuation coefficient; and adjusting the initial detection and identification result based on the multi-parameter fluctuation coefficient to obtain a target detection and identification result of the network infrastructure, fusing the multi-parameter fluctuation characteristics, ensuring the detection and identification precision and comprehensiveness of the network infrastructure, and further improving the accuracy and adaptability of network performance analysis. And the operation reliability and safety of the network infrastructure are ensured.

Description

Technical Field

[0001] The present invention relates to the field of network infrastructure technology, and in particular to a method for automatically detecting and identifying network infrastructure elements. Background Art

[0002] With the rapid development of information technology, the scale and complexity of network infrastructure are increasing, and the dynamic changes in key parameters such as network latency and bandwidth are having an increasingly significant impact on network performance and service quality.

[0003] Traditional network infrastructure detection and identification methods rely primarily on static configuration or manual intervention, making them difficult to adapt to dynamic network environments. This results in inaccurate and poor real-time detection results. The state of network infrastructure elements fluctuates frequently, and traditional methods are unable to effectively capture the correlations between multiple parameters, making it difficult to achieve accurate automated detection and identification. Summary of the Invention

[0004] The embodiment of the present invention provides a method for automated detection and identification of network infrastructure elements, integrating multi-parameter fluctuation characteristics to ensure the detection and identification accuracy and comprehensiveness of network infrastructure, thereby improving the accuracy and adaptability of network performance analysis and ensuring the operational reliability and security of network infrastructure.

[0005] To achieve the above objectives, the present invention provides a method for automatically detecting and identifying network infrastructure elements, comprising: Obtaining the network delay and network bandwidth corresponding to the current network environment, and determining the corresponding reference network delay and reference network bandwidth, and determining a network infrastructure facility element detection and identification model based on the reference network delay and reference network bandwidth; Predicting the future time of the network infrastructure based on the facility element detection and identification model to obtain an initial detection and identification result; Collecting characteristic parameter values ​​corresponding to the network infrastructure at multiple historical moments, grouping all characteristic parameter values ​​to obtain characteristic parameter value groups, and performing fluctuation analysis to determine parameter fluctuation confidence levels corresponding to the characteristic parameter values ​​in each characteristic parameter value group; Combining the parameter fluctuation confidence levels corresponding to each characteristic parameter value group to obtain a parameter fluctuation confidence level set, and analyzing the parameter fluctuation confidence level set to obtain a single parameter fluctuation coefficient of the parameter fluctuation confidence level set; The single-parameter fluctuation coefficient corresponding to each parameter fluctuation confidence set is fused to obtain a multi-parameter fluctuation coefficient of the network infrastructure, and the initial detection and identification result is adjusted based on the multi-parameter fluctuation coefficient to obtain a target detection and identification result of the network infrastructure.

[0006] Furthermore, when determining a facility element detection and identification model of the network infrastructure according to the reference network delay and the reference network bandwidth, it includes: Determine a network delay difference between the network delay and a corresponding reference network delay, and determine a network bandwidth difference between the network bandwidth and a corresponding reference network bandwidth; A facility element detection and identification model of the network infrastructure is determined based on the network delay difference and the network bandwidth difference.

[0007] Furthermore, when determining a facility element detection and identification model of the network infrastructure according to the reference network delay and the reference network bandwidth, it includes: Determine a network delay difference between the network delay and a corresponding reference network delay, and determine a network bandwidth difference between the network bandwidth and a corresponding reference network bandwidth; A facility element detection and identification model of the network infrastructure is determined based on the network delay difference and the network bandwidth difference.

[0008] Furthermore, when determining a facility element detection and identification model of the network infrastructure based on the network delay difference and the network bandwidth difference, it includes: The facility element detection and identification model of the network infrastructure is determined according to the following formula: ; Among them, q(t) is the facility element detection and identification model of the network infrastructure at the current moment, w1 is the first calculation coefficient, w2 is the second calculation coefficient, r1(t) is the network bandwidth corresponding to the current moment, r2(t) is the reference network bandwidth corresponding to the current moment, y1(t) is the network delay corresponding to the current moment, and y2(t) is the reference network delay corresponding to the current moment.

[0009] In this embodiment, the present invention can use a subjective weighting method or an objective weighting method to set the first calculation coefficient and the second calculation coefficient. The first calculation coefficient is the weight of the network bandwidth, which is preferably 0.6 here. The second calculation coefficient is the weight of the network delay, which is preferably 0.4 here. The specific weighting process is relatively mature and will not be repeated here.

[0010] Furthermore, when predicting the future time of the network infrastructure based on the facility element detection and identification model to obtain an initial detection and identification result, the method includes: Obtain the actual network delay and actual network bandwidth corresponding to the future time, as well as the corresponding actual reference network delay and actual reference network bandwidth; The actual network delay and actual network bandwidth, as well as the corresponding actual reference network delay and actual reference network bandwidth, are input into the facility element detection and recognition model, and the initial detection and recognition result corresponding to the future moment is output.

[0011] Furthermore, when all characteristic parameter values ​​are grouped to obtain characteristic parameter value groups, and fluctuation analysis is performed to determine the parameter fluctuation confidence level corresponding to the characteristic parameter value in each characteristic parameter value group, the following steps are included: Grouping the characteristic parameter values ​​of the same type corresponding to each historical moment to obtain multiple characteristic parameter value groups; Randomly selecting a characteristic parameter value from the characteristic parameter value group as a standard characteristic parameter value; Determining adjacent feature parameter values ​​corresponding to the standard feature parameter value, wherein the adjacent feature parameter values ​​are a left adjacent feature parameter value and a right adjacent feature parameter value; Determining a local fluctuation factor of the standard characteristic parameter value based on the left neighbor characteristic parameter value and the right neighbor characteristic parameter value; Determine the standard historical moment and the initial moment corresponding to the standard characteristic parameter value, and determine the parameter fluctuation confidence corresponding to each characteristic parameter value based on the standard historical moment, the initial moment and the local fluctuation factor.

[0012] Furthermore, when determining the parameter fluctuation confidence level corresponding to each characteristic parameter value based on the historical moment, the initial moment, and the local fluctuation factor, the method includes: The parameter fluctuation confidence level corresponding to each characteristic parameter value is determined according to the following formula: ; Among them, u is the parameter fluctuation confidence corresponding to the characteristic parameter value, p is the standard characteristic parameter value, p1 is the left neighbor characteristic parameter value, p2 is the right neighbor characteristic parameter value, a1 is the standard historical moment, and a is the initial moment.

[0013] Furthermore, when analyzing the parameter fluctuation confidence set to obtain a single parameter fluctuation coefficient of the parameter fluctuation confidence set, the method includes: Randomly matching the parameter fluctuation confidence levels in the parameter fluctuation confidence level set in pairs to obtain a plurality of parameter fluctuation confidence level sequences; Calculating a parameter fluctuation confidence sum value corresponding to the parameter fluctuation confidence sequence; Extracting a maximum parameter fluctuation confidence and a minimum parameter fluctuation confidence from the parameter fluctuation confidence set, and calculating an extreme parameter fluctuation confidence sum of the maximum parameter fluctuation confidence and the minimum parameter fluctuation confidence; Determining a ratio of the parameter fluctuation confidence sum value to the extreme parameter fluctuation confidence sum value as a discrete degree corresponding to the parameter fluctuation confidence sequence; Determining a parameter fluctuation confidence difference between two parameter fluctuation confidences in the parameter fluctuation confidence sequence, wherein the parameter fluctuation confidence difference is an absolute value of a difference between the two parameter fluctuation confidences; A single parameter fluctuation coefficient of the parameter fluctuation confidence set is obtained based on the degree of dispersion and the parameter fluctuation confidence difference.

[0014] Furthermore, when the single parameter fluctuation coefficient corresponding to each parameter fluctuation confidence set is fused to obtain the multi-parameter fluctuation coefficient of the network infrastructure, the method includes: Perform curve fitting on all single-parameter fluctuation coefficients based on a preset curve fitting method to obtain a single-parameter fluctuation coefficient curve; determining the slopes of the curve fitting points on the single-parameter fluctuation coefficient curve, and extracting the maximum slope as a symbolic fusion value; The variances corresponding to all single-parameter fluctuation coefficients are determined, and the product of the variances and the symbolic fusion value is used as the multi-parameter fluctuation coefficient of the network infrastructure.

[0015] Furthermore, when the initial detection and identification result is adjusted based on the multi-parameter fluctuation coefficient to obtain the target detection and identification result of the network infrastructure, the method includes: Presetting a first preset multi-parameter fluctuation coefficient and a second preset multi-parameter fluctuation coefficient; Presetting a first preset adjustment value, a second preset adjustment value, and a third preset adjustment value; When the multi-parameter fluctuation coefficient is less than the first preset multi-parameter fluctuation coefficient, calculating a third product value of the third preset adjustment value and the initial detection and identification result as the target detection and identification result of the network infrastructure; When the multi-parameter fluctuation coefficient is greater than or equal to the first preset multi-parameter fluctuation coefficient and less than the second preset multi-parameter fluctuation coefficient, a second product value of the second preset adjustment value and the initial detection and identification result is calculated as the target detection and identification result of the network infrastructure; When the multi-parameter fluctuation coefficient is greater than or equal to the second preset multi-parameter fluctuation coefficient, a first product value of the first preset adjustment value and the initial detection and identification result is calculated as the target detection and identification result of the network infrastructure.

[0016] Furthermore, after adjusting the initial detection and identification result based on the multi-parameter fluctuation coefficient to obtain the target detection and identification result of the network infrastructure, the method further includes: Determining whether the network infrastructure meets working requirements based on a relationship between the target detection and identification result and a preset target detection and identification result; When the target detection and identification result is less than the preset target detection and identification result, it is determined that the network infrastructure does not meet the working requirements; When the target detection and identification result is greater than or equal to the preset target detection and identification result, it is determined that the network infrastructure meets the working requirements.

[0017] Compared with the prior art, the present invention has the following beneficial effects: The present invention discloses a method for automatic detection and identification of network infrastructure elements, which obtains the network delay and network bandwidth at the current moment, determines the reference network delay and reference network bandwidth, and determines the facility element detection and identification model; predicts the future moment of the network infrastructure based on the facility element detection and identification model to obtain an initial detection and identification result; collects characteristic parameter values ​​corresponding to multiple historical moments to obtain a characteristic parameter value group, and determines the parameter fluctuation confidence; analyzes the parameter fluctuation confidence set to obtain a single parameter fluctuation coefficient; adjusts the initial detection and identification result based on the multi-parameter fluctuation coefficient to obtain a target detection and identification result of the network infrastructure, integrates the multi-parameter fluctuation characteristics, ensures the detection and identification accuracy and comprehensiveness of the network infrastructure, thereby improving the accuracy and adaptability of network performance analysis, and ensuring the operational reliability and security of the network infrastructure. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings: Figure 1 A flow chart of a method for automatic detection and identification of network infrastructure elements in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0019] The following embodiments of the present invention are described in further detail with reference to the accompanying drawings and examples. The following examples are used to illustrate the present invention but are not intended to limit the scope of the present invention.

[0020] In the description of this application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application.

[0021] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this application, unless otherwise specified, "plurality" means two or more.

[0022] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0023] The following is a description of preferred embodiments of the present invention with reference to the accompanying drawings.

[0024] like Figure 1 As shown, an embodiment of the present invention discloses a method for automatically detecting and identifying network infrastructure elements, including: S110: Obtaining a network delay and a network bandwidth corresponding to the current network environment, and determining a corresponding reference network delay and reference network bandwidth, and determining a network infrastructure facility element detection and identification model based on the reference network delay and reference network bandwidth; In some embodiments of the present application, when determining a facility element detection and identification model of a network infrastructure according to the reference network delay and the reference network bandwidth, the method includes: Determine a network delay difference between the network delay and a corresponding reference network delay, and determine a network bandwidth difference between the network bandwidth and a corresponding reference network bandwidth; A facility element detection and identification model of the network infrastructure is determined based on the network delay difference and the network bandwidth difference.

[0025] In this embodiment, the reference network delay and reference network bandwidth here depend on the deployment scenario and performance standards. For example, the reference network delay corresponding to the optical fiber backbone network is 3 milliseconds, and the reference network bandwidth is 300 gigabits / second. The specific settings can be based on the actual scenario and actual needs.

[0026] The beneficial effect of the above technical solution is: the present invention determines the facility element detection and identification model of the network infrastructure based on network delay differences and network bandwidth differences, which can lay the foundation for the automatic detection and identification of network infrastructure elements and characterize the network stability of the network infrastructure.

[0027] In some embodiments of the present application, when determining a facility element detection and identification model of the network infrastructure based on the network delay difference and the network bandwidth difference, the method includes: The facility element detection and identification model of the network infrastructure is determined according to the following formula: ; Among them, q(t) is the facility element detection and identification model of the network infrastructure at the current moment, w1 is the first calculation coefficient, w2 is the second calculation coefficient, r1(t) is the network bandwidth corresponding to the current moment, r2(t) is the reference network bandwidth corresponding to the current moment, y1(t) is the network delay corresponding to the current moment, and y2(t) is the reference network delay corresponding to the current moment.

[0028] S120: Predicting the future time of the network infrastructure based on the facility element detection and identification model to obtain an initial detection and identification result; In some embodiments of the present application, when predicting the future time of the network infrastructure based on the facility element detection and identification model to obtain an initial detection and identification result, the method includes: Obtain the actual network delay and actual network bandwidth corresponding to the future time, as well as the corresponding actual reference network delay and actual reference network bandwidth; The actual network delay and actual network bandwidth, as well as the corresponding actual reference network delay and actual reference network bandwidth, are input into the facility element detection and recognition model, and the initial detection and recognition result corresponding to the future moment is output.

[0029] In this embodiment, the future time refers to the time when it is desired to automatically detect and identify network infrastructure elements.

[0030] In this embodiment, the actual reference network delay and actual reference network bandwidth corresponding to the future moment are used as input and input into the facility element detection and identification model, and the initial detection and identification result of the network infrastructure can be output, that is, a specific numerical value. The initial detection and identification result is used to characterize the network stability of the network infrastructure.

[0031] In this embodiment, the larger the initial detection and identification result is, the more stable the network infrastructure is. Conversely, the smaller the initial detection and identification result is, the weaker the stability of the network infrastructure is.

[0032] S130: collecting characteristic parameter values ​​corresponding to the network infrastructure at multiple historical moments, grouping all characteristic parameter values ​​to obtain characteristic parameter value groups, and performing fluctuation analysis to determine parameter fluctuation confidence levels corresponding to the characteristic parameter values ​​in each characteristic parameter value group; In some embodiments of the present application, when grouping all characteristic parameter values ​​to obtain characteristic parameter value groups, performing fluctuation analysis, and determining the parameter fluctuation confidence level corresponding to the characteristic parameter value in each characteristic parameter value group, the following steps are included: Grouping the characteristic parameter values ​​of the same type corresponding to each historical moment to obtain multiple characteristic parameter value groups; Randomly selecting a characteristic parameter value from the characteristic parameter value group as a standard characteristic parameter value; Determining adjacent feature parameter values ​​corresponding to the standard feature parameter value, wherein the adjacent feature parameter values ​​are a left adjacent feature parameter value and a right adjacent feature parameter value; Determining a local fluctuation factor of the standard characteristic parameter value based on the left neighbor characteristic parameter value and the right neighbor characteristic parameter value; Determine the standard historical moment and the initial moment corresponding to the standard characteristic parameter value, and determine the parameter fluctuation confidence corresponding to each characteristic parameter value based on the standard historical moment, the initial moment and the local fluctuation factor.

[0033] In this embodiment, the number of historical moments is preferably 15. Taking the current moment as the benchmark, the past 5th minute, the past 10th minute, the past 15th minute, the past 20th minute, the past 25th minute, the past 30th minute, the past 35th minute, the past 40th minute, the past 45th minute, the past 50th minute, the past 55th minute, the past 60th minute, the past 65th minute, the past 70th minute, and the past 75th minute are collected.

[0034] In this embodiment, the characteristic parameter values ​​include port throughput, traffic fluctuation rate, packet loss rate, CRC error count and transaction processing rate, etc., which are not shown here one by one.

[0035] In this embodiment, characteristic parameter values ​​of the same type corresponding to each historical moment are grouped. For example, the port throughput is extracted from the 5th minute, the port throughput is extracted from the 10th minute, and the port throughput is extracted from the 15th minute, and so on. The port throughput is extracted from 15 historical moments respectively, and the same type of characteristic parameter value group is obtained. The characteristic parameter values ​​in this characteristic parameter value group are all port throughputs.

[0036] In this embodiment, the adjacent feature parameter value refers to a left adjacent feature parameter value and a right adjacent feature parameter value. It should be noted here that if the left adjacent feature parameter value or the right adjacent feature parameter value does not exist, only the corresponding right adjacent feature parameter value or the left adjacent feature parameter value needs to be determined.

[0037] The beneficial effects of the above technical solution are: the present invention determines the standard historical moment and initial moment corresponding to the standard characteristic parameter value, and determines the parameter fluctuation confidence corresponding to each characteristic parameter value based on the standard historical moment, initial moment and local fluctuation factor. The present invention can determine the local fluctuation situation and local moment change situation corresponding to each characteristic parameter value, and then determine the parameter fluctuation confidence level corresponding to each characteristic parameter value. The parameter fluctuation confidence level can characterize the comprehensive change situation corresponding to the standard characteristic parameter value, as well as the degree of credibility among all characteristic parameter values, providing reliable technical support for automatic detection and identification.

[0038] In some embodiments of the present application, when determining the parameter fluctuation confidence level corresponding to each characteristic parameter value based on the historical moment, the initial moment, and the local fluctuation factor, the process includes: The parameter fluctuation confidence level corresponding to each characteristic parameter value is determined according to the following formula: ; Among them, u is the parameter fluctuation confidence corresponding to the characteristic parameter value, p is the standard characteristic parameter value, p1 is the left neighbor characteristic parameter value, p2 is the right neighbor characteristic parameter value, a1 is the standard historical moment, and a is the initial moment.

[0039] In this embodiment, The local fluctuation factor that characterizes the standard characteristic parameter value. If there is no left or right neighboring characteristic parameter value, the corresponding value is recorded as 0.

[0040] S140: combining the parameter fluctuation confidences corresponding to each characteristic parameter value group to obtain a parameter fluctuation confidence set, and analyzing the parameter fluctuation confidence set to obtain a single parameter fluctuation coefficient of the parameter fluctuation confidence set; In this embodiment, multiple parameter fluctuation confidence levels can be calculated for each characteristic parameter value group.

[0041] In some embodiments of the present application, when analyzing the parameter fluctuation confidence set to obtain a single parameter fluctuation coefficient of the parameter fluctuation confidence set, the method includes: Randomly matching the parameter fluctuation confidence levels in the parameter fluctuation confidence level set in pairs to obtain a plurality of parameter fluctuation confidence level sequences; Calculating a parameter fluctuation confidence sum value corresponding to the parameter fluctuation confidence sequence; Extracting a maximum parameter fluctuation confidence and a minimum parameter fluctuation confidence from the parameter fluctuation confidence set, and calculating an extreme parameter fluctuation confidence sum of the maximum parameter fluctuation confidence and the minimum parameter fluctuation confidence; Determining a ratio of the parameter fluctuation confidence sum value to the extreme parameter fluctuation confidence sum value as a discrete degree corresponding to the parameter fluctuation confidence sequence; Determining a parameter fluctuation confidence difference between two parameter fluctuation confidences in the parameter fluctuation confidence sequence, wherein the parameter fluctuation confidence difference is an absolute value of a difference between the two parameter fluctuation confidences; A single parameter fluctuation coefficient of the parameter fluctuation confidence set is obtained based on the degree of dispersion and the parameter fluctuation confidence difference.

[0042] In this embodiment, if there is a separate, unmatched parameter fluctuation confidence, it can be deleted and does not participate in the calculation.

[0043] In this embodiment, the parameter fluctuation confidence sum refers to the sum of all parameter fluctuation confidences in the parameter fluctuation confidence sequence.

[0044] In this embodiment, the extreme parameter fluctuation confidence sum refers to the sum of the maximum parameter fluctuation confidence and the minimum parameter fluctuation confidence.

[0045] In this embodiment, each parameter fluctuation confidence sequence corresponds to a discrete degree and a parameter fluctuation confidence difference.

[0046] In this embodiment, the single parameter fluctuation coefficient of the parameter fluctuation confidence set is calculated according to the following formula: ; Among them, g is the single parameter fluctuation coefficient of the parameter fluctuation confidence set, j is the number of parameter fluctuation confidence sequences, c k is the discrete degree corresponding to the kth parameter fluctuation confidence set, v k is the parameter fluctuation confidence difference corresponding to the kth parameter fluctuation confidence set.

[0047] The beneficial effect of the above technical solution is: based on the degree of discreteness and the difference in parameter fluctuation confidence, a single parameter fluctuation coefficient of the parameter fluctuation confidence set is obtained, which further ensures the fluctuation analysis accuracy of the network infrastructure, and then ensures the accuracy of detection and identification, avoiding errors.

[0048] S150: Fusing the single-parameter fluctuation coefficient corresponding to each parameter fluctuation confidence set to obtain a multi-parameter fluctuation coefficient of the network infrastructure, and adjusting the initial detection and identification result based on the multi-parameter fluctuation coefficient to obtain a target detection and identification result of the network infrastructure.

[0049] In some embodiments of the present application, when the single parameter fluctuation coefficient corresponding to each parameter fluctuation confidence set is fused to obtain the multi-parameter fluctuation coefficient of the network infrastructure, the method includes: Perform curve fitting on all single-parameter fluctuation coefficients based on a preset curve fitting method to obtain a single-parameter fluctuation coefficient curve; determining the slopes of the curve fitting points on the single-parameter fluctuation coefficient curve, and extracting the maximum slope as a symbolic fusion value; The variances corresponding to all single-parameter fluctuation coefficients are determined, and the product of the variances and the symbolic fusion value is used as the multi-parameter fluctuation coefficient of the network infrastructure.

[0050] In this embodiment, as described above, the single parameter fluctuation coefficient corresponding to each parameter fluctuation confidence set can be obtained.

[0051] In this embodiment, the curve fitting process is relatively mature and will not be repeated here.

[0052] In this embodiment, the variance can reflect the degree of dispersion corresponding to the single parameter fluctuation coefficient, and therefore, the product of the variance and the symbolic fusion value is calculated.

[0053] The beneficial effect of the above technical solution is: the present invention uses the product value of the variance and the symbolic fusion value as the multi-parameter fluctuation coefficient of the network infrastructure, processes the parameters of different dimensions, obtains the same-dimensional analysis results, and then feeds back the fluctuation impact of multiple different-dimensional data on the network infrastructure through the multi-parameter fluctuation coefficient.

[0054] In some embodiments of the present application, when adjusting the initial detection and identification result based on the multi-parameter fluctuation coefficient to obtain the target detection and identification result of the network infrastructure, the method includes: Presetting a first preset multi-parameter fluctuation coefficient and a second preset multi-parameter fluctuation coefficient; Presetting a first preset adjustment value, a second preset adjustment value, and a third preset adjustment value; When the multi-parameter fluctuation coefficient is less than the first preset multi-parameter fluctuation coefficient, calculating a third product value of the third preset adjustment value and the initial detection and identification result as the target detection and identification result of the network infrastructure; When the multi-parameter fluctuation coefficient is greater than or equal to the first preset multi-parameter fluctuation coefficient and less than the second preset multi-parameter fluctuation coefficient, a second product value of the second preset adjustment value and the initial detection and identification result is calculated as the target detection and identification result of the network infrastructure; When the multi-parameter fluctuation coefficient is greater than or equal to the second preset multi-parameter fluctuation coefficient, a first product value of the first preset adjustment value and the initial detection and identification result is calculated as the target detection and identification result of the network infrastructure.

[0055] In this embodiment, the first preset multi-parameter fluctuation coefficient is preferably 4, and the second preset multi-parameter fluctuation coefficient is preferably 6, which can be adaptively adjusted according to actual conditions.

[0056] In this embodiment, the first preset adjustment value is preferably 0.85, the second preset adjustment value is preferably 1.15, and the third preset adjustment value is preferably 1.25. The specific values ​​can be adaptively adjusted according to actual conditions.

[0057] The beneficial effect of the above technical solution is: the present invention selects the corresponding preset adjustment value according to the relationship between the multi-parameter fluctuation coefficient, the first preset multi-parameter fluctuation coefficient and the second preset multi-parameter fluctuation coefficient, realizes the correction and adjustment of the initial detection and identification results, thereby ensuring the accuracy of the target detection and identification results, realizing dynamic adjustment, and avoiding errors.

[0058] In some embodiments of the present application, after adjusting the initial detection and identification result based on the multi-parameter fluctuation coefficient to obtain the target detection and identification result of the network infrastructure, the method further includes: Determining whether the network infrastructure meets working requirements based on a relationship between the target detection and identification result and a preset target detection and identification result; When the target detection and identification result is less than the preset target detection and identification result, it is determined that the network infrastructure does not meet the working requirements; When the target detection and identification result is greater than or equal to the preset target detection and identification result, it is determined that the network infrastructure meets the working requirements.

[0059] In this embodiment, the preset target detection and recognition result is preferably 40, and can be adaptively adjusted according to actual conditions.

[0060] The beneficial effect of the above technical solution is that the present invention determines whether the network infrastructure meets the working requirements based on the relationship between the target detection and identification results and the preset target detection and identification results, thereby ensuring the operational reliability and security of the network infrastructure.

[0061] In the description of the above embodiments, specific features, structures, materials or characteristics may be combined in an appropriate manner in any one or more embodiments or examples.

[0062] While the present invention has been described above with reference to exemplary embodiments, various modifications may be made and equivalent components may be substituted without departing from the scope of the present invention. In particular, the various features of the disclosed embodiments may be combined with one another in any manner, provided no structural conflicts exist. These combinations are not fully described in this specification for reasons of space and resource conservation.

[0063] Those skilled in the art will understand that the above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will still be able to modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein with equivalents. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A method for automatic detection and identification of network infrastructure elements, characterized in that: include: Obtaining the network delay and network bandwidth corresponding to the current network environment, and determining the corresponding reference network delay and reference network bandwidth, and determining a network infrastructure facility element detection and identification model based on the reference network delay and reference network bandwidth; Predicting the future time of the network infrastructure based on the facility element detection and identification model to obtain an initial detection and identification result; Collecting characteristic parameter values ​​corresponding to the network infrastructure at multiple historical moments, grouping all characteristic parameter values ​​to obtain characteristic parameter value groups, and performing fluctuation analysis to determine parameter fluctuation confidence levels corresponding to the characteristic parameter values ​​in each characteristic parameter value group; Combining the parameter fluctuation confidence levels corresponding to each characteristic parameter value group to obtain a parameter fluctuation confidence level set, and analyzing the parameter fluctuation confidence level set to obtain a single parameter fluctuation coefficient of the parameter fluctuation confidence level set; The single-parameter fluctuation coefficient corresponding to each parameter fluctuation confidence set is fused to obtain a multi-parameter fluctuation coefficient of the network infrastructure, and the initial detection and identification result is adjusted based on the multi-parameter fluctuation coefficient to obtain a target detection and identification result of the network infrastructure.

2. The method for automatic detection and identification of network infrastructure elements according to claim 1, characterized in that: When determining a facility element detection and identification model of a network infrastructure according to the reference network delay and the reference network bandwidth, the method includes: Determine a network delay difference between the network delay and a corresponding reference network delay, and determine a network bandwidth difference between the network bandwidth and a corresponding reference network bandwidth; A facility element detection and identification model of the network infrastructure is determined based on the network delay difference and the network bandwidth difference.

3. The method for automatic detection and identification of network infrastructure elements according to claim 2, characterized in that: When determining a facility element detection and identification model of the network infrastructure based on the network delay difference and the network bandwidth difference, the method includes: The facility element detection and identification model of the network infrastructure is determined according to the following formula: ； Among them, q(t) is the facility element detection and identification model of the network infrastructure at the current moment, w1 is the first calculation coefficient, w2 is the second calculation coefficient, r1(t) is the network bandwidth corresponding to the current moment, r2(t) is the reference network bandwidth corresponding to the current moment, y1(t) is the network delay corresponding to the current moment, and y2(t) is the reference network delay corresponding to the current moment.

4. The method for automatic detection and identification of network infrastructure elements according to claim 1, characterized in that: When predicting the future time of the network infrastructure based on the facility element detection and identification model to obtain an initial detection and identification result, the method includes: Obtain the actual network delay and actual network bandwidth corresponding to the future time, as well as the corresponding actual reference network delay and actual reference network bandwidth; The actual network delay and actual network bandwidth, as well as the corresponding actual reference network delay and actual reference network bandwidth, are input into the facility element detection and recognition model, and the initial detection and recognition result corresponding to the future moment is output.

5. The method for automatic detection and identification of network infrastructure elements according to claim 1, characterized in that: When all characteristic parameter values ​​are grouped to obtain characteristic parameter value groups, and fluctuation analysis is performed to determine the parameter fluctuation confidence level corresponding to the characteristic parameter value in each characteristic parameter value group, the following steps are included: Grouping the characteristic parameter values ​​of the same type corresponding to each historical moment to obtain multiple characteristic parameter value groups; Randomly selecting a characteristic parameter value from the characteristic parameter value group as a standard characteristic parameter value; Determining adjacent feature parameter values ​​corresponding to the standard feature parameter value, wherein the adjacent feature parameter values ​​are a left adjacent feature parameter value and a right adjacent feature parameter value; Determining a local fluctuation factor of the standard characteristic parameter value based on the left neighbor characteristic parameter value and the right neighbor characteristic parameter value; Determine the standard historical moment and the initial moment corresponding to the standard characteristic parameter value, and determine the parameter fluctuation confidence corresponding to each characteristic parameter value based on the standard historical moment, the initial moment and the local fluctuation factor.

6. The method for automatic detection and identification of network infrastructure elements according to claim 5, characterized in that: When determining the parameter fluctuation confidence level corresponding to each characteristic parameter value based on the historical moment, the initial moment, and the local fluctuation factor, the method includes: The parameter fluctuation confidence level corresponding to each characteristic parameter value is determined according to the following formula: ； Among them, u is the parameter fluctuation confidence corresponding to the characteristic parameter value, p is the standard characteristic parameter value, p1 is the left neighbor characteristic parameter value, p2 is the right neighbor characteristic parameter value, a1 is the standard historical moment, and a is the initial moment.

7. The method for automatic detection and identification of network infrastructure elements according to claim 1, characterized in that: When analyzing the parameter fluctuation confidence set to obtain a single parameter fluctuation coefficient of the parameter fluctuation confidence set, the method includes: Randomly matching the parameter fluctuation confidence levels in the parameter fluctuation confidence level set in pairs to obtain a plurality of parameter fluctuation confidence level sequences; Calculating a parameter fluctuation confidence sum value corresponding to the parameter fluctuation confidence sequence; Extracting a maximum parameter fluctuation confidence and a minimum parameter fluctuation confidence from the parameter fluctuation confidence set, and calculating an extreme parameter fluctuation confidence sum of the maximum parameter fluctuation confidence and the minimum parameter fluctuation confidence; Determining a ratio of the parameter fluctuation confidence sum value to the extreme parameter fluctuation confidence sum value as a discrete degree corresponding to the parameter fluctuation confidence sequence; Determining a parameter fluctuation confidence difference between two parameter fluctuation confidences in the parameter fluctuation confidence sequence, wherein the parameter fluctuation confidence difference is an absolute value of a difference between the two parameter fluctuation confidences; A single parameter fluctuation coefficient of the parameter fluctuation confidence set is obtained based on the degree of dispersion and the parameter fluctuation confidence difference.

8. The method for automatic detection and identification of network infrastructure elements according to claim 1, characterized in that: When the single parameter fluctuation coefficient corresponding to each parameter fluctuation confidence set is fused to obtain the multi-parameter fluctuation coefficient of the network infrastructure, the method includes: Perform curve fitting on all single-parameter fluctuation coefficients based on a preset curve fitting method to obtain a single-parameter fluctuation coefficient curve; determining the slopes of the curve fitting points on the single-parameter fluctuation coefficient curve, and extracting the maximum slope as a symbolic fusion value; The variances corresponding to all single-parameter fluctuation coefficients are determined, and the product of the variances and the symbolic fusion value is used as the multi-parameter fluctuation coefficient of the network infrastructure.

9. The method for automatic detection and identification of network infrastructure elements according to claim 1, characterized in that: When the initial detection and identification result is adjusted based on the multi-parameter fluctuation coefficient to obtain the target detection and identification result of the network infrastructure, the method includes: Presetting a first preset multi-parameter fluctuation coefficient and a second preset multi-parameter fluctuation coefficient; Presetting a first preset adjustment value, a second preset adjustment value, and a third preset adjustment value; When the multi-parameter fluctuation coefficient is less than the first preset multi-parameter fluctuation coefficient, calculating a third product value of the third preset adjustment value and the initial detection and identification result as the target detection and identification result of the network infrastructure; When the multi-parameter fluctuation coefficient is greater than or equal to the first preset multi-parameter fluctuation coefficient and less than the second preset multi-parameter fluctuation coefficient, a second product value of the second preset adjustment value and the initial detection and identification result is calculated as the target detection and identification result of the network infrastructure; When the multi-parameter fluctuation coefficient is greater than or equal to the second preset multi-parameter fluctuation coefficient, a first product value of the first preset adjustment value and the initial detection and identification result is calculated as the target detection and identification result of the network infrastructure.

10. The method for automatic detection and identification of network infrastructure elements according to claim 1, characterized in that: After adjusting the initial detection and identification result based on the multi-parameter fluctuation coefficient to obtain the target detection and identification result of the network infrastructure, the method further includes: Determining whether the network infrastructure meets working requirements based on a relationship between the target detection and identification result and a preset target detection and identification result; When the target detection and identification result is less than the preset target detection and identification result, it is determined that the network infrastructure does not meet the working requirements; When the target detection and identification result is greater than or equal to the preset target detection and identification result, it is determined that the network infrastructure meets the working requirements.

Images