A multi-dimensional optical fiber operation quality monitoring method and system

Abstract

The application discloses a kind of multi-dimensional optical fiber operation quality monitoring method and system, it is related to data processing technical field, the method includes: obtaining the monitoring point distribution information of target area in last operation cycle;Obtain N connection load and N historical transmission volume set, according to N historical transmission volume set, the quality monitoring analysis module of quality monitoring system is divided into regions, obtains N quality monitoring analysis unit;Obtain N monitoring data set and N actual operation fault information set;Input in N quality monitoring analysis unit, obtains N operation quality analysis result;Obtain N difference degree;Adjustment scheme iteration optimization is carried out, and optimal monitoring adjustment scheme is used as monitoring adjustment scheme;The quality monitoring of next operation cycle is carried out.The application solves the technical problems that the accuracy of optical fiber operation quality monitoring is poor and the monitoring adjustment efficiency is low in the prior art, and achieves the technical effect of improving monitoring quality.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and specifically to a multi-dimensional optical fiber operation quality monitoring method and system. Background Technology

[0002] With increasingly stringent requirements for communication quality, a method for monitoring the operational quality of optical fibers is needed. Currently, monitoring quality is achieved by setting fixed sensors. However, when adjustments are needed, these sensors cannot adapt to real-time optical fiber operating conditions, leading to unreliable monitoring results. Existing technologies suffer from poor accuracy in optical fiber operational quality monitoring and low efficiency in adjustment. Summary of the Invention

[0003] This application provides a multi-dimensional optical fiber operation quality monitoring method and system to address the technical problems of poor accuracy and low efficiency in monitoring and adjustment of optical fiber operation quality in existing technologies.

[0004] In view of the above problems, this application provides a multi-dimensional optical fiber operation quality monitoring method and system.

[0005] The first aspect of this application provides a multi-dimensional optical fiber operation quality monitoring method, wherein the method is applied to a quality monitoring system, the quality monitoring system being communicatively connected to a data interaction module, and the method includes:

[0006] Obtain the monitoring point distribution information of the target area in the previous operating cycle, wherein the monitoring point distribution information includes the set of operating monitoring points and the set of redundant monitoring points;

[0007] The data interaction module interacts with the monitoring device corresponding to the set of operation monitoring points to collect multiple connection loads and multiple transmission volumes of the optical fiber in the target area during the previous operation cycle, thereby obtaining N connection loads and N historical transmission volume sets. The N historical transmission volume sets are data sets that describe the changes in the amount of transmitted data of the N connection loads during the previous operation cycle, where N is an integer greater than or equal to 1.

[0008] Based on N historical transmission volume sets, the quality monitoring and analysis module of the quality monitoring system is divided into regions to obtain N quality monitoring and analysis units.

[0009] Based on the set of operational monitoring points, obtain N sets of monitoring data and N sets of actual operational fault information for the previous operational cycle;

[0010] Input N sets of monitoring data into N quality monitoring and analysis units of the quality monitoring and analysis module to obtain N operational quality analysis results;

[0011] The difference between the N sets of actual operational fault information and the N operational quality analysis results is calculated to obtain N difference values.

[0012] Based on N differences, the set of operational monitoring points and the set of redundant monitoring points, the adjustment scheme is iteratively optimized, and the optimal monitoring adjustment scheme is taken as the monitoring adjustment scheme.

[0013] According to the monitoring and adjustment plan, the quality of the optical fibers in the target area will be monitored for the next operating cycle.

[0014] A second aspect of this application provides a multi-dimensional fiber optic operation quality monitoring system, the system comprising:

[0015] The distribution information acquisition module is used to acquire the distribution information of monitoring points in the target area during the previous operating cycle, wherein the distribution information of monitoring points includes a set of operating monitoring points and a set of redundant monitoring points;

[0016] The transmission volume acquisition module is used to interact with the monitoring device corresponding to the set of operation monitoring points through the data interaction module, and to acquire multiple connection loads and multiple transmission volumes of the optical fiber in the target area in the previous operation cycle, so as to obtain N connection loads and N historical transmission volume sets. The N historical transmission volume sets are data sets describing the changes in the transmission data volume of the N connection loads in the previous operation cycle, and N is an integer greater than or equal to 1.

[0017] The monitoring and analysis unit acquisition module is used to divide the quality monitoring and analysis module of the quality monitoring system into regions based on N historical transmission volume sets, and obtain N quality monitoring and analysis units.

[0018] The fault information acquisition module is used to obtain N sets of monitoring data and N sets of actual operational fault information in the previous operating cycle based on the set of operating monitoring points.

[0019] The analysis result acquisition module is used to input N sets of monitoring data into N quality monitoring and analysis units of the quality monitoring and analysis module to obtain N operational quality analysis results;

[0020] The difference degree acquisition module is used to calculate the difference degree between the N sets of actual operational fault information and the N operational quality analysis results, and obtain N difference degrees.

[0021] The adjustment scheme acquisition module is used to iteratively optimize the adjustment scheme based on N differences, a set of operational monitoring points and a set of redundant monitoring points, and take the optimal monitoring adjustment scheme as the monitoring adjustment scheme.

[0022] A quality monitoring module is used to monitor the quality of optical fibers in the target area for the next operating cycle according to the monitoring and adjustment scheme.

[0023] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0024] This application obtains the monitoring point distribution information of the target area during the previous operating cycle. This information includes a set of operating monitoring points and a set of redundant monitoring points. Then, through a data interaction module, it interacts with the monitoring devices corresponding to the operating monitoring point set to collect multiple connection loads and multiple transmission volumes of the optical fibers within the target area during the previous operating cycle. This yields N connection loads and N historical transmission volume sets. The N historical transmission volume sets are data sets describing the changes in the transmission data volume of the N connection loads during the previous operating cycle, where N is an integer greater than or equal to 1. Finally, the quality monitoring analysis module of the quality monitoring system is used based on these N historical transmission volume sets. The system divides the area into N quality monitoring and analysis units. Then, based on the set of operational monitoring points, it obtains N sets of monitoring data and N sets of actual operational fault information from the previous operational cycle. By inputting these N sets of monitoring data into the N quality monitoring and analysis units of the quality monitoring and analysis module, it obtains N operational quality analysis results. Next, it calculates the difference between the N sets of actual operational fault information and the N operational quality analysis results, obtaining N difference scores. Based on these N difference scores, the set of operational monitoring points, and the set of redundant monitoring points, iterative optimization of the adjustment scheme is performed. The optimal monitoring adjustment scheme is then adopted as the monitoring adjustment scheme, and quality monitoring of the optical fibers within the target area is conducted for the next operational cycle according to this scheme. This achieves the technical effect of improving the accuracy of optical fiber operational quality monitoring from the dimensions of optimized monitoring point settings and optimized area division of the quality monitoring and analysis module. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 A schematic flowchart of a multi-dimensional fiber optic operation quality monitoring method provided in this application embodiment;

[0027] Figure 2 A flowchart illustrating the process of using N historical transmission information entropies as a third constraint factor in a multi-dimensional optical fiber operation quality monitoring method provided in this application embodiment;

[0028] Figure 3 This is a flowchart illustrating the optimal monitoring and adjustment scheme as the monitoring and adjustment scheme in a multi-dimensional optical fiber operation quality monitoring method provided in this application embodiment;

[0029] Figure 4 This is a schematic diagram of a multi-dimensional fiber optic operation quality monitoring system provided in an embodiment of this application.

[0030] Explanation of reference numerals in the attached figures: Module 11 for obtaining distribution information, Module 12 for acquiring transmission volume, Module 13 for obtaining monitoring and analysis unit information, Module 14 for obtaining fault information, Module 15 for obtaining analysis results, Module 16 for obtaining difference, Module 17 for obtaining adjustment scheme, and Module 18 for quality monitoring. Detailed Implementation

[0031] This application provides a multi-dimensional optical fiber operation quality monitoring method and system to address the technical problems of poor accuracy and low efficiency in monitoring and adjustment of optical fiber operation quality in existing technologies.

[0032] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0033] It should be noted that the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to such process, method, product, or device.

[0034] Example 1

[0035] like Figure 1 As shown, this application provides a multi-dimensional optical fiber operation quality monitoring method, wherein the method is applied to a quality monitoring system, the quality monitoring system being communicatively connected to a data interaction module, and the method includes:

[0036] Step S100: Obtain the monitoring point distribution information of the target area in the previous operating cycle, wherein the monitoring point distribution information includes the set of operating monitoring points and the set of redundant monitoring points;

[0037] In one possible embodiment, the quality monitoring system is used to monitor and process the operational quality of optical fibers. By connecting the port of a data interaction device to the port of the quality monitoring system, the data collected by the data interaction device is transmitted to the quality monitoring system for analysis and processing. The operational cycle is a time interval between two adjacent quality monitoring sessions, set by those skilled in the art, and can be 3 months, 6 months, etc. The target area is any area where optical fiber operational quality monitoring is required. Monitoring point distribution information is obtained by collecting data on the distribution of monitoring points in the target area during the previous operational cycle. This monitoring point distribution information includes a set of operational monitoring points and a set of redundant monitoring points. The set of operational monitoring points is obtained by summarizing the monitoring points that were active during the previous operational cycle. The set of redundant monitoring points consists of monitoring points that were not active during the previous operational cycle.

[0038] Step S200: Interact with the monitoring device corresponding to the set of operation monitoring points through the data interaction module, collect multiple connection loads and multiple transmission volumes of the optical fiber in the target area in the previous operation cycle, and obtain N connection loads and N historical transmission volume sets. The N historical transmission volume sets are data sets describing the changes in the transmission data volume of the N connection loads in the previous operation cycle, and N is an integer greater than or equal to 1.

[0039] In one embodiment, a data interaction module interacts with the monitoring device corresponding to the set of operational monitoring points to obtain the fiber optic usage in the target area during the previous operational cycle, including N connection loads and N historical transmission volume sets. The N connection loads represent the users of the fiber optic cables within the target area. The N historical transmission volume sets are data sets describing the changes in the amount of data transmitted by the N connection loads during the previous operational cycle, reflecting the magnitude of the data transmitted by the N connection loads.

[0040] Step S300: Divide the quality monitoring and analysis module of the quality monitoring system into regions based on N historical transmission volume sets to obtain N quality monitoring and analysis units;

[0041] Furthermore, such as Figure 2 As shown, step S300 in this embodiment further includes:

[0042] Step S310: Obtain the attribute information of N connected loads and identify the attributes of the N connected loads to obtain N attribute identifiers, wherein the attribute identifiers include commercial attribute identifiers, residential attribute identifiers, and public attribute identifiers;

[0043] Step S320: Extract the transmission frequency from the N historical transmission volume sets to obtain N historical transmission frequencies, and use the N historical transmission frequencies as the first constraint factor.

[0044] Step S330: Extract the average transmission interval time from the N historical transmission volume sets to obtain the average of the N historical transmission interval times, and use the average of the N historical transmission interval times as the second constraint factor.

[0045] Step S340: Extract information entropy from N sets of historical transmission volumes to obtain N historical transmission information entropies, and use the N historical transmission information entropies as the third constraint factor.

[0046] Furthermore, after using N historical transmission efficiencies as a third constraint factor, step S300 of this application embodiment also includes:

[0047] Step S350: Calculate the unit transmission capacity based on the first constraint factor and the third constraint factor, and use the calculation result as the fourth constraint factor;

[0048] Step S360: Input the second constraint factor, the fourth constraint factor, and N attribute identifiers into the regional coefficient calculation unit to obtain N regional coefficients;

[0049] Step S370: Divide the quality monitoring and analysis module of the quality monitoring system into regions according to N regional coefficients to obtain N quality monitoring and analysis units.

[0050] Furthermore, step S360 in this embodiment of the application also includes:

[0051] Step S361: The regional coefficient calculation unit includes the regional coefficient calculation formula:

[0052] The formula for calculating the regional coefficient is as follows:

[0053]

[0054] Where Y is the region coefficient corresponding to the i-th connected load, U i f is the entropy of the historical transmission information corresponding to the i-th connection load. i T is the unit transmission capacity corresponding to the i-th connection load. i It is the average historical transmission interval time corresponding to the i-th connection load, and α is an empirical coefficient.

[0055] In one embodiment, the monitoring and analysis modules in the quality monitoring system, which perform monitoring and analysis operations, are divided into regions based on information included in N historical transmission volume sets. This improves the accuracy and efficiency of data processing, resulting in the N quality monitoring and analysis units. Each of the N quality monitoring and analysis units corresponds one-to-one with one of the N historical transmission volume sets. By analyzing the N historical transmission volume sets with different information sizes, the computing power of the monitoring and analysis modules is allocated accordingly, thereby optimizing computing power allocation and improving processing efficiency.

[0056] In one embodiment of this application, N connection loads are acquired using attributes, and these N connection loads are then identified based on their acquired load attributes to obtain N attribute identifiers. These attribute identifiers include commercial attribute identifiers, residential attribute identifiers, and public attribute identifiers. The connection loads corresponding to different attribute identifiers have different requirements for fiber optic operation quality. Preferably, the requirements for public attribute identifiers are greater than those for residential attribute identifiers, and vice versa. The public attribute identifiers refer to connection loads used for public services, including telephone communication and subway communication. The commercial attribute identifiers refer to connection loads used for commercial purposes, including gaming and competition communication.

[0057] In one possible embodiment, N historical transmission frequencies are obtained by extracting transmission frequencies from N historical transmission volume sets. These N historical transmission frequencies reflect the number of times the N connection loads transmitted in the previous operating cycle. These N historical transmission frequencies are used as a first constraint factor to constrain the region division. Furthermore, the average transmission interval time is extracted from the N historical transmission volume sets to obtain N historical average transmission interval times. These N historical average transmission interval times reflect the frequency of use of the N connection loads. Preferably, the average transmission interval time is calculated by acquiring the time between every two adjacent transmissions in the N historical transmission volume sets. This calculated result is used as the average historical transmission interval time, and the average of the N historical average transmission interval times is used as a second constraint factor. Next, information entropy is extracted from the N historical transmission volume sets to calculate the amount of information contained in the N historical transmission volume sets. The larger the amount of information, the more important the data, and the greater the processing power required. The information entropy of the N historical transmissions is used as a third constraint factor.

[0058] Specifically, by dividing the data in the third constraint factor by the data in the first constraint factor, the calculation result is used as the unit transmission capacity, reflecting the amount of information transmitted per unit by N connected loads in the previous operating cycle, and this is used as the fourth constraint factor. Then, the second constraint factor, the fourth constraint factor, and N attribute identifiers are input into the regional coefficient calculation unit, and after quantification calculation, N regional coefficients are obtained. These N regional coefficients reflect the regional division weight corresponding to each connected load. By dividing the quality monitoring and analysis module of the quality monitoring system into regions based on the N regional coefficients, N quality monitoring and analysis units are obtained.

[0059] Step S400: Based on the set of operation monitoring points, obtain N sets of monitoring data and N sets of actual operation fault information from the previous operation cycle;

[0060] Step S500: Input N sets of monitoring data into N quality monitoring and analysis units of the quality monitoring and analysis module to obtain N operational quality analysis results;

[0061] Furthermore, step S500 in this embodiment of the application also includes:

[0062] Step S510: Obtain multiple sample monitoring data sets and multiple sample running quality analysis results as construction data;

[0063] Step S520: Train the framework built with the BP neural network using the constructed data until the training converges, and obtain the trained quality monitoring and analysis unit.

[0064] In one embodiment, a data interaction module collects monitoring data from the previous operating cycle and faults that occurred during actual operation from the set of operating monitoring points, obtaining N sets of monitoring data and N sets of actual operating fault information. The N sets of monitoring data reflect the operating status of the optical fibers corresponding to the N connected loads in the previous operating cycle, including cable bending loss and pressure loss. The N sets of actual operating fault information reflect the faults that occurred in the optical fibers corresponding to the N connected loads in the previous operating cycle, including excessive bending, cable pressure or breakage, and poor cable splicing. By collecting data from the sets of operating monitoring points, a basis is provided for subsequent analysis of whether the monitoring of each connected load's corresponding optical fiber is qualified and whether additional monitoring points are needed, thereby improving monitoring accuracy.

[0065] In one possible embodiment, the N quality monitoring and analysis units are functional units used to intelligently analyze monitoring data and obtain optical fiber operation quality analysis results, wherein the N quality monitoring and analysis units correspond to N connection loads. By inputting N sets of monitoring data into the N quality monitoring and analysis units of the quality monitoring and analysis module, N operation quality analysis results are obtained, and intelligent analysis is performed on the optical fiber operation quality corresponding to each connection load.

[0066] Specifically, multiple sample monitoring data sets and multiple sample running quality analysis results are obtained as construction data. Then, the framework built with a BP neural network is trained using the construction data. During the training process, the network parameters of the framework are updated according to the degree of deviation of each output result until the output result converges, and the trained quality monitoring and analysis unit is obtained.

[0067] Step S600: Calculate the difference degree between the N sets of actual operational fault information and the N operational quality analysis results to obtain N difference degrees;

[0068] In one possible embodiment, N sets of actual operational fault information and N operational quality analysis results are compared and analyzed. The successfully compared fault data is compared to the total number of faults in each set of actual operational fault information, and the calculated result is used as the degree of difference. This yields a result reflecting the degree of difference between the monitoring results of the monitoring and analysis unit and the actual operational faults, providing a basis for subsequent monitoring optimization.

[0069] Step S700: Based on N differences, the set of running monitoring points, and the set of redundant monitoring points, iteratively optimize the adjustment scheme and select the optimal monitoring adjustment scheme as the monitoring adjustment scheme.

[0070] Step S800: Perform quality monitoring on the optical fibers in the target area for the next operating cycle according to the monitoring and adjustment scheme.

[0071] Furthermore, such as Figure 3 As shown, step S700 in this embodiment further includes:

[0072] Step S710: Iterate through the N differences and determine whether they are greater than the preset difference threshold. If they are greater, add the corresponding connection load to the monitoring list to be adjusted.

[0073] Step S720: Match the list of monitoring points to be adjusted with the set of running monitoring points and the set of redundant monitoring points to obtain M sets of monitoring points to be adjusted and M sets of redundant monitoring points;

[0074] Step S730: Based on the list of monitoring points to be adjusted, the set of M monitoring points to be adjusted, and the set of M redundant monitoring points, obtain a set of K adjustment schemes. Iterate and optimize the set of K adjustment schemes to obtain the optimal monitoring adjustment scheme, and use the optimal monitoring adjustment scheme as the monitoring adjustment scheme.

[0075] Furthermore, step S700 in this embodiment of the application also includes:

[0076] Step S740: Randomly select one set of adjustment schemes from the K sets of adjustment schemes without replacement, and use it as the first set of adjustment schemes;

[0077] Step S750: Evaluate the fitness of the first adjustment scheme set according to the scheme evaluation index set to obtain the first fitness, wherein the scheme evaluation index set includes monitoring point concurrency rate and redundant scheduling cost;

[0078] Step S760: Randomly select another set of adjustment schemes from the K sets of adjustment schemes without replacement, and use it as the second set of adjustment schemes to calculate the second fitness;

[0079] Step S770: Determine whether the second fitness is greater than the first fitness. If it is greater, then the second set of adjustment schemes is taken as the optimal adjustment scheme for the stage. If it is less, then the first set of adjustment schemes is taken as the optimal adjustment scheme for the stage.

[0080] Step S780: Perform iterative optimization. After reaching the preset number of iterations, the optimal adjustment scheme obtained in the final iteration is taken as the optimal monitoring and adjustment scheme.

[0081] In one possible embodiment, multiple adjustment schemes are obtained based on the set of operating monitoring points and the set of redundant monitoring points according to N differences, and then iterative optimization is performed to achieve the technical effect of improving the adaptability of the monitoring adjustment schemes.

[0082] Specifically, by iterating through the N differences, it is determined whether they exceed a preset difference threshold. If they do, the corresponding connection load is added to the monitoring list to be adjusted. Then, the monitoring list to be adjusted is matched with the set of running monitoring points and the set of redundant monitoring points to obtain a set of redundant monitoring points in the monitoring list where the connection load is successfully matched, resulting in M ​​sets of monitoring points to be adjusted and M sets of redundant monitoring points. Based on the monitoring list to be adjusted and the M sets of monitoring points to be adjusted, an arbitrary number of redundant monitoring points are randomly selected from the M sets of redundant monitoring points to obtain K sets of adjustment schemes. The number of redundant monitoring points added to the M connection loads corresponding to the M sets of monitoring points to be adjusted varies in each adjustment scheme set. As the number of redundant monitoring points in the adjustment scheme set increases, the monitoring accuracy increases, but the amount of monitoring data also increases, and the corresponding monitoring efficiency decreases. Therefore, it is necessary to comprehensively consider both monitoring accuracy and monitoring efficiency to iteratively optimize the K sets of adjustment schemes to obtain the optimal monitoring adjustment scheme.

[0083] In one possible embodiment, an adjustment scheme set is randomly selected without replacement from K adjustment scheme sets as the first adjustment scheme set. The first adjustment scheme set is then evaluated for fitness based on a scheme evaluation index set to obtain a first fitness. Preferably, the fitness of the first adjustment scheme set is evaluated based on the scheme evaluation index set and the preset weights corresponding to the indices. The first fitness reflects the quality of the adjustment scheme; the higher the fitness, the higher the quality of the scheme. The scheme evaluation index set includes monitoring point concurrency rate and redundancy scheduling cost. The monitoring point concurrency rate refers to the number of times a redundant monitoring point is invoked by multiple connections to be adjusted. The redundancy scheduling cost is the cost required to adjust a redundant monitoring point to the monitoring position of the connection to be adjusted. Another adjustment scheme set is randomly selected again without replacement from the K adjustment scheme sets as the second adjustment scheme set, and a second fitness is calculated. It is determined whether the second fitness is greater than the first fitness. If it is greater, the second adjustment scheme set is considered the optimal adjustment scheme for the stage; if it is less, the first adjustment scheme set is considered the optimal adjustment scheme for the stage. The preset number of iterations can be set by those skilled in the art and is not limited here. By conducting quality monitoring of the optical fibers in the target area for the next operating cycle according to the monitoring adjustment plan, monitoring efficiency and quality can be improved.

[0084] In summary, the embodiments of this application have at least the following technical effects:

[0085] This application analyzes the operational status of different loads monitored at monitoring points during the previous operating cycle using an intelligent quality monitoring unit. Based on N differences, the set of operating monitoring points, and the set of redundant monitoring points, iterative optimization of adjustment schemes is performed to obtain the optimal monitoring and adjustment scheme. This optimal scheme is then used as the monitoring and adjustment plan for the next operating cycle of optical fiber in the target area. This achieves the technical effect of improving the accuracy of optical fiber operational quality monitoring.

[0086] Example 2

[0087] Based on the same inventive concept as the multi-dimensional fiber optic operation quality monitoring method in the foregoing embodiments, such as Figure 4 As shown, this application provides a multi-dimensional fiber optic operation quality monitoring system. The system and method embodiments in this application are based on the same inventive concept. The system includes:

[0088] Distribution information acquisition module 11 is used to acquire the distribution information of monitoring points in the target area during the previous operating cycle, wherein the distribution information of monitoring points includes a set of operating monitoring points and a set of redundant monitoring points;

[0089] The transmission volume acquisition module 12 is used to interact with the monitoring device corresponding to the set of operation monitoring points through the data interaction module, and to acquire multiple connection loads and multiple transmission volumes of the optical fiber in the target area in the previous operation cycle, so as to obtain N connection loads and N historical transmission volume sets. The N historical transmission volume sets are data sets describing the changes in the transmission data volume of the N connection loads in the previous operation cycle, and N is an integer greater than or equal to 1.

[0090] The monitoring and analysis unit acquisition module 13 is used to divide the quality monitoring and analysis module of the quality monitoring system into regions according to N historical transmission volume sets, and obtain N quality monitoring and analysis units.

[0091] The fault information acquisition module 14 is used to obtain N sets of monitoring data and N sets of actual operating fault information in the previous operating cycle based on the set of operating monitoring points.

[0092] The analysis result acquisition module 15 is used to input N sets of monitoring data into N quality monitoring and analysis units of the quality monitoring and analysis module to obtain N operational quality analysis results;

[0093] The difference degree acquisition module 16 is used to calculate the difference degree between the N sets of actual operating fault information and the N operating quality analysis results to obtain N difference degrees.

[0094] The adjustment scheme acquisition module 17 is used to iteratively optimize the adjustment scheme based on N differences, the set of operating monitoring points and the set of redundant monitoring points, and take the optimal monitoring adjustment scheme as the monitoring adjustment scheme.

[0095] The quality monitoring module 18 is used to monitor the quality of the optical fiber in the target area for the next operating cycle according to the monitoring and adjustment scheme.

[0096] Furthermore, the monitoring and analysis unit obtaining module 13 is used to perform the following method:

[0097] Obtain the attribute information of N connected loads, and identify the attributes of the N connected loads to obtain N attribute identifiers, including commercial attribute identifiers, residential attribute identifiers, and public attribute identifiers;

[0098] Transmission frequency is extracted from N sets of historical transmission volumes to obtain N historical transmission frequencies, which are then used as the first constraint factor.

[0099] The mean transmission interval time is extracted from N historical transmission volume sets to obtain N historical transmission interval time averages, and the N historical transmission interval time averages are used as the second constraint factor.

[0100] Information entropy is extracted from N sets of historical transmission volumes to obtain N historical transmission information entropies, which are then used as the third constraint factor.

[0101] Furthermore, the monitoring and analysis unit obtaining module 13 is used to perform the following method:

[0102] The unit transmission capacity is calculated based on the first and third constraint factors, and the calculation result is used as the fourth constraint factor.

[0103] Input the second constraint factor, the fourth constraint factor, and N attribute identifiers into the regional coefficient calculation unit to obtain N regional coefficients;

[0104] The quality monitoring and analysis module of the quality monitoring system is divided into regions based on N regional coefficients, resulting in N quality monitoring and analysis units.

[0105] Furthermore, the monitoring and analysis unit obtaining module 13 is used to perform the following method:

[0106] The regional coefficient calculation unit includes the regional coefficient calculation formula:

[0107] The formula for calculating the regional coefficient is as follows:

[0108]

[0109] Where Y is the region coefficient corresponding to the i-th connected load, U i f is the entropy of the historical transmission information corresponding to the i-th connection load. i T is the unit transmission capacity corresponding to the i-th connection load. i It is the average historical transmission interval time corresponding to the i-th connection load, and α is an empirical coefficient.

[0110] Furthermore, the analysis result acquisition module 15 is used to perform the following method:

[0111] Multiple sample monitoring datasets and multiple sample operational quality analysis results were obtained as the construction data.

[0112] The framework constructed using the constructed data is trained until it converges, thus obtaining the trained quality monitoring and analysis unit.

[0113] Furthermore, the adjustment scheme obtaining module 17 is used to perform the following method:

[0114] Iterate through the N differences to determine whether they are greater than a preset difference threshold. If they are, add the corresponding connection load to the monitoring list to be adjusted.

[0115] The list of monitoring points to be adjusted is matched with the set of running monitoring points and the set of redundant monitoring points to obtain M sets of monitoring points to be adjusted and M sets of redundant monitoring points.

[0116] Based on the list of monitoring points to be adjusted, the set of M monitoring points to be adjusted, and the set of M redundant monitoring points, K sets of adjustment schemes are obtained. The K sets of adjustment schemes are iteratively optimized to obtain the optimal monitoring adjustment scheme, which is then used as the monitoring adjustment scheme.

[0117] Furthermore, the adjustment scheme obtaining module 17 is used to perform the following method:

[0118] Randomly select one set of adjustment schemes from the K sets of adjustment schemes without replacement, and use it as the first set of adjustment schemes;

[0119] The fitness of the first set of adjustment schemes is evaluated based on the set of scheme evaluation indicators to obtain the first fitness. The set of scheme evaluation indicators includes the monitoring point concurrency rate and the redundant scheduling cost.

[0120] From the set of K adjustment schemes, another set of adjustment schemes is randomly selected without replacement and used as the second set of adjustment schemes. The second fitness is then calculated.

[0121] Determine whether the second fitness is greater than the first fitness. If it is greater, then the second set of adjustment schemes is taken as the optimal adjustment scheme for the stage. If it is less, then the first set of adjustment schemes is taken as the optimal adjustment scheme for the stage.

[0122] The optimization process is iterative. After reaching the preset number of iterations, the optimal adjustment scheme obtained in the final iteration is taken as the optimal monitoring and adjustment scheme.

[0123] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0124] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0125] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A multi-dimensional method for monitoring the operational quality of optical fibers, characterized in that, The method is applied to a quality monitoring system, which is communicatively connected to a data interaction module. The method includes: Obtain the monitoring point distribution information of the target area in the previous operating cycle, wherein the monitoring point distribution information includes the set of operating monitoring points and the set of redundant monitoring points; The data interaction module interacts with the monitoring device corresponding to the set of operation monitoring points to collect multiple connection loads and multiple transmission volumes of the optical fiber in the target area during the previous operation cycle, thereby obtaining N connection loads and N historical transmission volume sets. The N historical transmission volume sets are data sets that describe the changes in the amount of transmitted data of the N connection loads during the previous operation cycle, where N is an integer greater than or equal to 1. Based on N historical transmission volume sets, the quality monitoring and analysis module of the quality monitoring system is divided into regions to obtain N quality monitoring and analysis units. Based on the set of operational monitoring points, obtain N sets of monitoring data and N sets of actual operational fault information for the previous operational cycle; Input N sets of monitoring data into N quality monitoring and analysis units of the quality monitoring and analysis module to obtain N operational quality analysis results; The difference between the N sets of actual operational fault information and the N operational quality analysis results is calculated to obtain N difference values. Based on N differences, the set of operational monitoring points and the set of redundant monitoring points, the adjustment scheme is iteratively optimized, and the optimal monitoring adjustment scheme is taken as the monitoring adjustment scheme. According to the monitoring and adjustment plan, the quality of the optical fibers in the target area will be monitored for the next operating cycle.

2. The method as described in claim 1, characterized in that, include: Obtain the attribute information of N connected loads, and identify the attributes of the N connected loads to obtain N attribute identifiers, including commercial attribute identifiers, residential attribute identifiers, and public attribute identifiers; Transmission frequency is extracted from N sets of historical transmission volumes to obtain N historical transmission frequencies, which are then used as the first constraint factor. The mean transmission interval time is extracted from N historical transmission volume sets to obtain N historical transmission interval time averages, and the N historical transmission interval time averages are used as the second constraint factor. Information entropy is extracted from N sets of historical transmission volumes to obtain N historical transmission information entropies, which are then used as the third constraint factor.

3. The method as described in claim 2, characterized in that, After taking N historical transmission efficiencies as the third constraint factor, the following are included: The unit transmission capacity is calculated based on the first and third constraint factors, and the calculation result is used as the fourth constraint factor. Input the second constraint factor, the fourth constraint factor, and N attribute identifiers into the regional coefficient calculation unit to obtain N regional coefficients; The quality monitoring and analysis module of the quality monitoring system is divided into regions based on N regional coefficients, resulting in N quality monitoring and analysis units.

4. The method as described in claim 3, characterized in that, include: The regional coefficient calculation unit includes the regional coefficient calculation formula: The formula for calculating the regional coefficient is as follows: Where Y is the region coefficient corresponding to the i-th connected load, U i f is the entropy of the historical transmission information corresponding to the i-th connection load. i T is the unit transmission capacity corresponding to the i-th connection load. i It is the average historical transmission interval time corresponding to the i-th connection load, and α is an empirical coefficient.

5. The method as described in claim 1, characterized in that, include: Multiple sample monitoring datasets and multiple sample operational quality analysis results were obtained as the construction data. The framework constructed using the constructed data is trained until it converges, thus obtaining the trained quality monitoring and analysis unit.

6. The method as described in claim 1, characterized in that, include: Iterate through the N differences to determine whether they are greater than a preset difference threshold. If they are, add the corresponding connection load to the monitoring list to be adjusted. The list of monitoring points to be adjusted is matched with the set of running monitoring points and the set of redundant monitoring points to obtain M sets of monitoring points to be adjusted and M sets of redundant monitoring points. Based on the list of monitoring points to be adjusted, the set of M monitoring points to be adjusted, and the set of M redundant monitoring points, K sets of adjustment schemes are obtained. The K sets of adjustment schemes are iteratively optimized to obtain the optimal monitoring adjustment scheme, which is then used as the monitoring adjustment scheme.

7. The method as described in claim 6, characterized in that, include: Randomly select one set of adjustment schemes from the K sets of adjustment schemes without replacement, and use it as the first set of adjustment schemes; The fitness of the first set of adjustment schemes is evaluated based on the set of scheme evaluation indicators to obtain the first fitness. The set of scheme evaluation indicators includes the monitoring point concurrency rate and the redundant scheduling cost. From the set of K adjustment schemes, another set of adjustment schemes is randomly selected without replacement and used as the second set of adjustment schemes. The second fitness is then calculated. Determine whether the second fitness is greater than the first fitness. If it is greater, then the second set of adjustment schemes is taken as the optimal adjustment scheme for the stage. If it is less, then the first set of adjustment schemes is taken as the optimal adjustment scheme for the stage. The optimization process is iterative. After reaching the preset number of iterations, the optimal adjustment scheme obtained in the final iteration is taken as the optimal monitoring and adjustment scheme.

8. A multi-dimensional fiber optic operation quality monitoring system, characterized in that, The system includes: The distribution information acquisition module is used to acquire the distribution information of monitoring points in the target area during the previous operating cycle, wherein the distribution information of monitoring points includes a set of operating monitoring points and a set of redundant monitoring points; The transmission volume acquisition module is used to interact with the monitoring device corresponding to the set of operation monitoring points through the data interaction module, and to acquire multiple connection loads and multiple transmission volumes of the optical fiber in the target area in the previous operation cycle, so as to obtain N connection loads and N historical transmission volume sets. The N historical transmission volume sets are data sets describing the changes in the transmission data volume of the N connection loads in the previous operation cycle, and N is an integer greater than or equal to 1. The monitoring and analysis unit acquisition module is used to divide the quality monitoring and analysis module of the quality monitoring system into regions based on N historical transmission volume sets, and obtain N quality monitoring and analysis units. The fault information acquisition module is used to obtain N sets of monitoring data and N sets of actual operational fault information in the previous operating cycle based on the set of operating monitoring points. The analysis result acquisition module is used to input N sets of monitoring data into N quality monitoring and analysis units of the quality monitoring and analysis module to obtain N operational quality analysis results; The difference degree acquisition module is used to calculate the difference degree between the N sets of actual operational fault information and the N operational quality analysis results, and obtain N difference degrees. The adjustment scheme acquisition module is used to iteratively optimize the adjustment scheme based on N differences, a set of operational monitoring points and a set of redundant monitoring points, and take the optimal monitoring adjustment scheme as the monitoring adjustment scheme. A quality monitoring module is used to monitor the quality of optical fibers in the target area for the next operating cycle according to the monitoring and adjustment scheme.

Images