Fault positioning method and device, electronic equipment, chip and medium

Abstract

The invention provides a fault positioning method and device, electronic equipment and a medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: carrying out the sampling of optical power data based on a preset sampling frequency, and determining optical power sequence data, the optical power sequence data comprises the identification of a PON port, the equipment identification of a user, and an optical power parameter, each PON port corresponds to a plurality of optical power sequence data; based on the optical power sequence data, determining a similarity value between any two users through unsupervised clustering and time sequence alignment in sequence; and correlation analysis is carried out on the similarity value between any two users, fault information is determined, and the fault information comprises a fault position, a fault equipment identifier and an identifier of a fault PON port. According to the method, through clustering and time sequence alignment, similar value calculation of optical power sequences and accurate delimitation of faults are realized, and the accuracy of fault positioning is improved; and the fault analysis and positioning efficiency is improved. Furthermore, the network stability and the user experience are guaranteed.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence, and more particularly to a fault location method, apparatus, electronic device, chip, and medium. Background Technology

[0002] Optical path quality problem identification refers to the identification and location of fault points in the optical path of a fiber optic communication system using specific technical means to ensure the stable operation of the communication system. This process involves multiple methods, such as optical power monitoring, bit error rate testing, and delay measurement, to comprehensively assess the health status of the optical path. With the widespread application of fiber optic networks, the importance of optical path fault identification technology has become increasingly prominent, becoming a key link in ensuring network service quality. Summary of the Invention

[0003] This disclosure provides a fault location method, apparatus, electronic device, chip, and medium to locate optical path faults and improve the stability of fiber optic networks.

[0004] The first aspect of this disclosure proposes a fault location method, which includes: sampling optical power data based on a preset sampling frequency to determine optical power sequence data, wherein the optical power sequence data includes the identifier of the PON port, the device identifier of the user, and optical power parameters, wherein each PON port corresponds to multiple optical power sequence data; based on the optical power sequence data, determining the similarity value between any two users by sequentially performing unsupervised clustering and time series alignment; and performing correlation analysis on the similarity value between any two users to determine fault information, wherein the fault information includes the fault location, the fault device identifier, and the identifier of the faulty PON port.

[0005] In some embodiments of this disclosure, optical power data is sampled based on a preset sampling frequency to determine optical power sequence data, including: monitoring optical power data within a preset time period and determining a preset threshold; sampling optical power data based on the preset sampling frequency to obtain sampled data, wherein the relationship between the optical power parameters of the sampled data and the preset threshold satisfies a preset condition; and preprocessing the sampled data to obtain optical power sequence data.

[0006] In some embodiments of this disclosure, based on optical power sequence data, the similarity value between any two users is determined by unsupervised clustering and time series alignment in sequence, including: performing unsupervised clustering on the optical power sequence data to obtain multiple optical power category data, each optical power category data including multiple optical power sequence data; and determining the similarity value between any two users by time series alignment for the first optical power category data in the multiple optical power category data.

[0007] In some embodiments of this disclosure, for the first type of optical power category data in multiple types of optical power category data, the similarity value between any two users is determined by time series alignment, including: for the first type of optical power category data, determining the first optical power sequence data of multiple first users corresponding to the first PON port; and determining the distance value corresponding to any two first users in the multiple first optical power sequence data by time series alignment, thereby obtaining the similarity value between any two first users.

[0008] In some embodiments of this disclosure, correlation analysis is performed on the similarity values ​​between any two users to determine fault information, including: determining the second PON port corresponding to the weak light user; for multiple second users corresponding to the second PON port, determining the correlation between the weak light user and the multiple second users based on the similarity values ​​between the second user and the weak light user; and determining fault information based on the correlation, wherein the fault location is any one of the backbone segment, branch segment, and inlet segment.

[0009] In some embodiments of this disclosure, the correlation between a second user and a low-light user is determined based on the similarity value between the second user and the low-light user, including any of the following: if the number of similar users with similarity values ​​less than a preset similarity value is less than a first value, the correlation is determined to be unrelated; if the number of similar users with similarity values ​​less than the preset similarity value is greater than or equal to the first value, and the ratio of the number of similar users to the number of second users is less than a first ratio, the correlation is determined to be partially related; if the number of similar users with similarity values ​​less than the preset similarity value is greater than or equal to the first value, and the ratio of the number of similar users to the number of second users is greater than or equal to the first ratio, the correlation is determined to be fully related.

[0010] The fault location method proposed in this disclosure improves the accuracy of fault location by calculating similarity values ​​of optical power sequences and accurately delineating faults through clustering and time series alignment. Simultaneously, by sampling and processing large amounts of optical power data, it enhances data processing and analysis capabilities, further improving the efficiency of fault analysis and location. Furthermore, it ensures network stability and user experience.

[0011] A second aspect of this disclosure provides a fault location device, comprising: a sampling module for sampling optical power data based on a preset sampling frequency to determine optical power sequence data, wherein the optical power sequence data includes the identifier of a PON port, the device identifier of a user, and optical power parameters, wherein each PON port corresponds to multiple optical power sequence data; a determination module for determining the similarity value between any two users based on the optical power sequence data, sequentially through unsupervised clustering and time series alignment; and a location module for performing correlation analysis on the similarity values ​​between any two users to determine fault information, wherein the fault information includes the fault location, the identifier of the faulty device, and the identifier of the faulty PON port.

[0012] A third aspect of this disclosure provides an electronic device comprising: one or more processors and a storage device communicatively connected to the one or more processors, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to perform the methods described in the first aspect of this disclosure.

[0013] A fourth aspect of this disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the methods described in the first aspect of this disclosure.

[0014] A fifth aspect of this disclosure provides a chip including one or more interface circuits and one or more processors; the interface circuits are configured to receive signals from the memory of an electronic device and send signals to the processors, the signals including computer instructions stored in the memory, which, when executed by the processors, cause the electronic device to perform the methods described in the first aspect of this disclosure.

[0015] In summary, the fault location method proposed in this disclosure includes: sampling optical power data based on a preset sampling frequency to determine optical power sequence data, which includes the PON port identifier, user device identifier, and optical power parameters, wherein each PON port corresponds to multiple optical power sequence data; based on the optical power sequence data, determining the similarity value between any two users through unsupervised clustering and time series alignment; and performing correlation analysis on the similarity values ​​between any two users to determine fault information, including fault location, fault device identifier, and fault PON port identifier. This method, through clustering and time series alignment, achieves accurate calculation of optical power sequence similarity values ​​and precise fault delimitation, improving the accuracy of fault location; simultaneously, by sampling and processing a large amount of optical power data, it improves data processing and analysis capabilities, further enhancing the efficiency of fault analysis and location. Furthermore, it ensures network stability and user experience.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0018] Figure 1 This is a flowchart of a fault location method proposed in an embodiment of the present disclosure;

[0019] Figure 2 This is a flowchart of the time series alignment method proposed in the embodiments of this disclosure;

[0020] Figure 3 This is a flowchart of the association analysis method proposed in the embodiments of this disclosure;

[0021] Figure 4 A schematic diagram illustrating the optimization scheme for potential clustering risks in ODN networks;

[0022] Figure 5 This is a schematic diagram of the structure of a fault location device provided in an embodiment of the present disclosure;

[0023] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0024] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments are described below with reference to the accompanying drawings.

[0025] To address the degradation of quality in point-to-point fiber optic networks (transmission network, end-line leased access, and wireless base station access), the main method is to manually test each segment of the optical path using an OTDR instrument to eventually locate the optical loss point. OTDR testing requires interrupting the fiber optic network, which can cause service interruptions for users during the process of identifying optical loss points.

[0026] In the operation and maintenance of end-to-end broadband services, the maintenance of passive optical networks is the weakest link in digital capabilities: massive low-light rectification requires continuous investment over a long period, resulting in low efficiency and slow results; the ODN network is invisible, making clustering problems difficult to perceive, and the continuous deterioration of the ODN network cannot be addressed in advance of fault rectification, leading to poor user experience due to passive handling.

[0027] The related technologies have the following drawbacks:

[0028] 1. Highly reliant on manual labor and personal experience. It requires manual assessment using OTDR instruments and on-site visits.

[0029] 2. Incomplete coverage of technical scenarios: OTDR instruments can accurately locate fault diagnosis and optical loss points by analyzing optical characteristic data, but they are not suitable for point-to-multipoint fiber optic networks.

[0030] 3. Low accuracy of technical means: The delineation of point-to-multipoint network backbones, branches, and access segments relies on optical performance and alarm data to draw conclusions, which has low accuracy (85%). The scope of investigation required for manual intervention is still quite large.

[0031] To address quality issues caused by optical path degradation, it is necessary to identify degradation trends in the main beam and branch beams, construct degradation models, provide early warnings of clustering problems, accurately delineate the locations of weak light occurrences in pigtails, secondary beam splitters, or the main beam, reduce complaints about weak light, optimize weak light in batches, and promptly resolve potential faults in the optical path.

[0032] To address the problems existing in related technologies, this disclosure proposes a fault location method. By sampling historical data based on soft probe data and employing a time-series clustering algorithm, the ONT lifespan power index is subjected to time warping and trend analysis, thereby achieving accurate identification and delimitation of quality problems in weak light generation pigtails, secondary beam splitters, or PON port trunks.

[0033] The fault location method provided in this application will be described in detail below with reference to the accompanying drawings.

[0034] Figure 1 A flowchart illustrating a fault location method provided in an embodiment of this disclosure. Figure 1 As shown, it includes the following steps:

[0035] Step 101: Sample the optical power data based on the preset sampling frequency to determine the optical power sequence data.

[0036] In the embodiments of this disclosure, the optical power sequence data includes the identifier of the PON port, the user's device identifier, and optical power parameters, wherein each PON port corresponds to multiple optical power sequence data.

[0037] In the embodiments of this disclosure, the preset sampling frequency can be customized according to the scenario or needs. For example, the preset sampling frequency can be once every 10 minutes or once every 15 minutes. This disclosure does not limit the specific value of the preset sampling frequency.

[0038] In some embodiments, optical power data can be sampled by acquiring soft probe data through a docking system platform. The docking method can be FTP, and the probe data must strictly comply with the prescribed probe specifications.

[0039] In some embodiments, optical power data is sampled based on a preset sampling frequency. This can be achieved by obtaining soft probe data through an RMS digital platform within the province to complete the optical power acquisition of all ONUs. The RMS (digital platform as a terminal platform for managed optical modems and routers) connects to the system through network routing to obtain the optical power records of all probes for the ONUs.

[0040] In the embodiments of this disclosure, optical power data is sampled based on a preset sampling frequency to determine optical power sequence data, including: monitoring optical power data within a preset time period and determining a preset threshold; sampling optical power data based on the preset sampling frequency to obtain sampled data, wherein the relationship between the optical power parameters of the sampled data and the preset threshold satisfies a preset condition; and preprocessing the sampled data to obtain optical power sequence data.

[0041] In some embodiments, the preset time period can be customized according to the scenario or requirements, such as continuously monitoring optical power data for 48 hours to determine a preset threshold based on the detection data. The preset threshold can serve as a sampling rule, i.e., used to filter optical power data to obtain sampling data that meets the conditions.

[0042] In some embodiments, there may be multiple preset thresholds, that is, the preset thresholds may be different for different fault types. For example, a first preset threshold is set for low-light users and a second preset threshold is set for degraded users, which are used to sample low-light users and degraded users respectively.

[0043] In some embodiments, optical power data is sampled based on a preset sampling frequency to obtain sampled data. The relationship between the optical power parameters of the sampled data and a preset threshold satisfies a preset condition. This can be achieved by continuously monitoring the optical power data within a preset time period. When the optical power parameters before and after weakening exceed the preset threshold, sampling is triggered, and continuous sampling is performed on this group of users according to the preset sampling frequency to obtain sampled data.

[0044] In some embodiments, the method further includes: monitoring optical power data within a preset time period and determining a third preset threshold, the third preset threshold being used for unsupervised clustering.

[0045] In some embodiments, a preset threshold is, for example, 1 dBm. When the optical power value exceeds 1 dBm of the power value before the light weakens or deteriorates, it is necessary to sample the optical power data of the user (the user under the PON port). It is understood that if the optical power value is within ±1 dBm of the power value before the light weakens or deteriorates, it is not necessary to sample the optical power data of the user.

[0046] In some embodiments, determining whether to sample users under a certain PON port can be done by randomly sampling the optical power data of some users, judging its relationship with the power value before the light weakens or deteriorates, and when it meets the relationship with a preset threshold, then the users under that PON port are sampled.

[0047] For example, a risk threshold is preset based on 48 hours of continuous monitoring of optical power fluctuations. The optical power of all ONUs is collected through a soft probe platform. The high-frequency sampling rules are as follows: (1) There is clustered weak light under the PON port: randomly select 3 users and check the optical power. The optical power should be restored to the optical power value before the weak light ±1dBm; (2) There is batch degradation of the backbone under the PON port: if there is degradation to weak light, take 1 weak light user and 2 degraded users. The optical power should be restored to the optical power value before the degradation ±1dBm. If there is no degradation to weak light, randomly select 3 users and check the optical power. The optical power should be restored to the optical power value before the degradation ±1dBm; There is batch degradation of the branch under the PON port: if there is degradation to weak light, take 1 weak light user and 1 degraded user. The optical power should be restored to the optical power value before the degradation ±1dBm. If there is no degradation to weak light, randomly select 2 users and check the optical power. The optical power should be restored to the optical power value before the degradation ±1dBm.

[0048] In some embodiments, the sampled data is preprocessed to obtain optical power sequence data, which can be achieved through data cleaning and verification. It is understood that the optical power sequence data is a sequence of data that has been cleaned and verified and is sorted by time, with each optical power sequence data corresponding to one user.

[0049] In some embodiments, data cleaning and verification may employ methods from related technologies, which are not limited herein.

[0050] For example, ONT optical power sequence data is collected, cleaned, and verified.

[0051] Step 102: Based on the optical power sequence data, the similarity value between any two users is determined by unsupervised clustering and time series alignment in sequence.

[0052] In the embodiments of this disclosure, based on optical power sequence data, the similarity value between any two users is determined by unsupervised clustering and time series alignment in sequence, including: performing unsupervised clustering on the optical power sequence data to obtain multiple optical power category data, each optical power category data including multiple optical power sequence data; and determining the similarity value between any two users by time series alignment for the first optical power category data in the multiple optical power category data.

[0053] In some embodiments, unsupervised clustering is performed on the optical power sequence data to obtain multiple optical power category data. Each optical power category data includes multiple optical power sequence data. The multiple optical power category data can be divided into four categories: falling, fluctuating, level, and recovery.

[0054] In some embodiments, unsupervised clustering can be the K-means algorithm, or a hierarchical clustering algorithm such as AGNES, or a distribution-based clustering algorithm, etc. Through unsupervised clustering, the acquired optical power sequence data can be classified to obtain multiple optical power category data.

[0055] In some embodiments, the conditions to be met for each type of optical power data are different. For example, for the declining type, the optical power needs to show a significant and continuous downward trend of more than ±3dB and has not recovered. Here, 3dB can be the third preset threshold corresponding to the declining type determined by the above process. For the fluctuating type, the optical power of a single ONU needs to show a trend of repeated splitting and recovery. For the level type, the optical power needs to be continuously stable without a change of 1-2dB. Here, 1-2dB can be the third preset threshold corresponding to the level type determined by the above process. For the recovery type, the optical power needs to show a significant split of ±3dB recorded at the time node and recover to the normal state in the sampling of the same day (the level value recorded before the splitting).

[0056] In some embodiments, the unsupervised clustering process may involve: first dividing the data into K groups, then randomly selecting K objects as initial cluster centers, calculating the distance between each object and each seed cluster center, and assigning each object to the nearest cluster center. Each cluster center and the objects assigned to it represent a cluster. Each time a sample is assigned, the cluster centers are recalculated based on the existing objects in the cluster. This process is repeated until a termination condition is met. The termination condition may be that no (or a minimum number) objects are reassigned to different clusters, no (or a minimum number) cluster centers change, or the sum of squared errors reaches a local minimum.

[0057] For example, based on the K-means algorithm, four categories of descriptions of optical power change trends are generated: decline, fluctuation, level, and recovery. A decline indicates a sustained downward trend in optical power exceeding ±3 dB without recovery; fluctuation indicates repeated fluctuations and recovery in the optical power of a single ONU; level indicates stable optical power with no change of 1-2 dB; and recovery indicates a significant fluctuation of ±3 dB recorded at a given time point, which returns to normal during the sampling on that day (the level value was recorded before the fluctuation).

[0058] In some embodiments, the similarity value between any two users can be determined by time series alignment of the multi-class optical power category data obtained through unsupervised clustering. This can be done for any two users under the same PON port.

[0059] In some embodiments, time series alignment can be achieved using the Dynamic Time Warping algorithm, which calculates the similarity of user optical power category data under the same PON port to obtain the similarity value between any two users.

[0060] In the above embodiments, by combining unsupervised clustering and time series alignment, similarity values ​​can be calculated for users of the same class, thereby improving the efficiency and accuracy of locating faults from the same source.

[0061] Step 103: Perform correlation analysis on the similarity values ​​between any two users to determine the fault information.

[0062] In the embodiments of this disclosure, the fault information includes the fault location, the faulty device identifier, and the faulty PON port identifier.

[0063] In the embodiments of this disclosure, correlation analysis of similarity values ​​between any two users can be performed on the similarity values ​​between any two users under the same PON port to determine whether the optical power change trends of the two users are correlated. By the correlation of optical power change trends between any two users, it can be determined whether there is a fault in the PON port, as well as the type and location of the fault.

[0064] In some embodiments, correlation analysis can be performed by comparing the similarity values ​​of any two users with a preset similarity value. When the similarity value is greater than the preset similarity value, it indicates that there is a correlation in optical power change trends between the two users. When the number of users with correlation in optical power change trends under the same PON port exceeds a preset number, the fault category of the PON port is determined, and the fault location is determined accordingly. The preset number corresponding to different fault categories can be different.

[0065] In some embodiments, the preset similarity value and preset quantity can be customized according to the scenario or requirements, or can be calibrated through experimental testing.

[0066] In some embodiments, the fault category is, for example, backbone fault, branch fault, or inbound fault, thereby determining the corresponding fault location as the backbone fault location, branch fault location, or inbound fault location of the corresponding PON port. The preset quantities for backbone fault, branch fault, and inbound fault are different, and different preset quantities can be set for each to determine the fault category of the current PON port.

[0067] In some embodiments, after determining the fault category and the corresponding fault location, the fault device identifier and the fault PON port identifier corresponding to the fault location can be obtained.

[0068] In some embodiments, the method further includes: analyzing and verifying the fault information through the system, establishing a fault repair work order, and pushing the fault repair work order to the corresponding maintenance personnel through the electronic operation and maintenance platform.

[0069] In some embodiments, fault information can be stored in the system and updated based on real-time monitoring and location. Users can view the corresponding optical path quality through their personal accounts, and maintenance personnel can also view it.

[0070] For example, a user interface is provided to the platform, allowing users to view the current optical path quality on the network side through their user accounts, thus providing support for installation and maintenance.

[0071] For example, after verifying the accuracy of the analyzed sample data, the system pushes it to the electronic maintenance team: There is batch degradation of the backbone (number of weak light users X) under the PON port, and batch degradation of the branch (number of weak light users Y) under the PON port. Work orders are then dispatched based on resource information: The electronic maintenance platform triggers a work order dispatch once a day per port by combining information such as PON port, broadband account, and primary splitter with the pushed events. The path of the push interface is consistent with the precise work order dispatch for customer complaints, and the recipient is also the same. Work order processing by maintenance personnel: Similar to the precise work order dispatch for customer complaints, work orders are automatically dispatched through the assigned personnel. After processing, maintenance personnel return a response containing the handling measures and the root cause of the degradation. Quality inspection and archiving: After processing the work order, maintenance personnel complete on-site testing. The electronic maintenance system can also use the account provided by the network administrator to call the one-click diagnostic capability of the platform to perform optical power diagnosis for weak light users and users with batch degradation. Once qualified, the quality inspection is automatically completed.

[0072] The fault location method proposed in this disclosure improves the accuracy of fault location by calculating similarity values ​​of optical power sequences and accurately delineating faults through clustering and time series alignment. Furthermore, by sampling and processing large amounts of optical power data, it enhances data processing and analysis capabilities, further improving the efficiency of fault analysis and location. Moreover, the improved efficiency and accuracy of fault location also improve the efficiency of operation and maintenance.

[0073] Figure 2 This is a flowchart of the time series alignment method proposed in this disclosure, based on Figure 1 The embodiment shown, Figure 2 Step 102 is further defined. For example... Figure 2 As shown, it includes the following steps:

[0074] Step 201: For the first type of optical power category data, determine the first optical power sequence data of multiple first users corresponding to the first PON port.

[0075] In the embodiments of this disclosure, the first type of optical power category data can be any one of multiple types of optical power category data, and the first PON port can be any one of multiple PON ports corresponding to multiple optical power sequence data included in the first type of optical power category data.

[0076] In some embodiments, for the same type of optical power category data, the optical power sequence data of multiple users under multiple PON ports may be included. The optical power sequence trend of each user satisfies the optical power trend of the optical power category data. For example, in the decreasing optical power category data, the optical power trend of each user is decreasing, or in the fluctuating optical power category data, the optical power trend of each user is fluctuating, and so on.

[0077] In some embodiments, determining the first optical power category data of multiple first users corresponding to the first PON port for the first type of optical power category data may involve determining the first optical power category data of multiple first users corresponding to the same PON port within the first type of optical power category data. A first user is a user with the same type of optical power trend under the same PON port.

[0078] For example, similarity calculations are performed on the trend sequence data of user optical power under the same PON.

[0079] Step 202: By aligning the time series, determine the distance value between any two first users in the multiple first optical power sequence data, and obtain the similarity value between any two first users.

[0080] In the embodiments of this disclosure, by time series alignment, the distance value between any two first users can be determined, thereby obtaining the similarity value between any two first users.

[0081] In some embodiments, determining the distance value between any two first users can be achieved using the Dynamic Time Warping (DTW) algorithm. This involves normalizing the optical power sequence data of multiple first users under the first PON port, calculating the Euclidean distance between each pair of points in the optical power sequence data of any two first users, and forming a distance matrix. From the upper left corner to the upper right corner of the matrix, the path with the minimum cumulative distance is determined. The path must satisfy the constraints of monotonicity and continuity, i.e., it cannot skip data points. The smaller the cumulative distance value at the end of the path, the more similar the sequences are. The cumulative distance value is divided by the path length to eliminate the influence of the sequence length, thereby obtaining the similarity value between any two first users.

[0082] In some embodiments, time series alignment can also be achieved using algorithms such as Euclidean distance (ED), longest common subsequence (LCSS), Pearson correlation coefficient (PCC), and fast DTW. For different algorithms, the relationship between the similarity value and the similarity can be positive or negative. For example, for DTW, ED, and fast DTW algorithms, a smaller similarity value indicates greater similarity, while for LCSS and PCC algorithms, a larger similarity value indicates greater similarity.

[0083] In the above embodiments, the introduction of DTW distance preserves the information of the original waveform of the optical power sequence, making the calculation and reasoning more accurate.

[0084] In the above embodiments, by performing time series alignment and similarity calculation on any two users in the same type of optical power category data, the efficiency and accuracy of locating faults from the same source can be improved, thereby improving the overall efficiency and accuracy of the fault location method.

[0085] Figure 3 This is a flowchart of the association analysis method proposed in this disclosure, based on Figures 1-2 The illustrated embodiments, such as Figure 3 As shown, Figure 3 right Figure 1 Step 103 is further defined, including the following steps:

[0086] Step 301: Determine the second PON port corresponding to the low-light user.

[0087] In the embodiments of this disclosure, the low-light user can be determined according to the low-light user standard, which can be determined according to industry standards or specifications, or it can be customized according to the scenario or needs.

[0088] In some embodiments, the low-light user standard can be that the ONT received light power is less than -27dB at least three times a day.

[0089] In some embodiments, determining the second PON port corresponding to a weak light user can be done by identifying the weak light user from among multiple users in the same type of optical power category data, thereby determining the second PON port corresponding to the weak light user.

[0090] In some embodiments, based on Figure 2 The embodiment shown can determine weak light users from among the multiple first users corresponding to multiple first PON ports in the first type of optical power category data, and then determine the corresponding first PON port as the second PON port based on the weak light users.

[0091] For example, the low-light user standard is: the ONT received light power is less than -27dB at least 3 times a day.

[0092] Step 302: For the multiple second users corresponding to the second PON port, determine the correlation between the low-light user and the multiple second users based on the similarity value between the second user and the low-light user.

[0093] In the embodiments of this disclosure, the conditions for determining correlation based on similarity values ​​are illustrated using the DTW algorithm as an example. For different algorithms, the conditions for correlation may be different.

[0094] For example, for weak light users, the optical power change trend of the same PON port users is taken, and the similarity between the optical power change trend of weak light users and the optical power change trend of other users under the same PON port is determined based on the algorithm.

[0095] In embodiments of this disclosure, the correlation between a second user and a low-light user is determined based on the similarity value between the second user and the low-light user, including any of the following: if the number of similar users with similarity values ​​less than a preset similarity value is less than a first value, the correlation is determined to be unrelated; if the number of similar users with similarity values ​​less than the preset similarity value is greater than or equal to the first value, and the ratio of the number of similar users to the number of second users is less than a first ratio, the correlation is determined to be partially related; if the number of similar users with similarity values ​​less than the preset similarity value is greater than or equal to the first value, and the ratio of the number of similar users to the number of second users is greater than or equal to the first ratio, the correlation is determined to be fully related.

[0096] In some embodiments, the second PON port corresponds to multiple second users. For each second user, it has a similarity value with the low-light user. The association between the low-light user and the multiple second users is determined by the similarity value between the second user and the low-light user.

[0097] In some embodiments, the preset similarity value, the first value, and the first ratio can be pre-set, and can be customized according to the scenario or requirements, or can be calibrated according to experiments or tests. The specific values ​​are not limited herein.

[0098] In some embodiments, for multiple users under the same PON port, the correlation between the low-light user and the multiple users is determined based on the similarity value between each user and the low-light user under the same PON port.

[0099] In some embodiments, when a user's similarity value with a user in low light is less than a preset similarity value, it indicates that the user and the user in low light are similar, and the number of similar users can be obtained accordingly.

[0100] In some embodiments, the first value is, for example, 3. If the number of similar users whose similarity value is less than the preset similarity value is less than the first value, the correlation is determined to be unrelated. This can be because if the number of users who are similar to the weak light user is less than 3, it means that the number of users with similar optical power change trends under the second PON port is small, and the users under the second PON port are unrelated to the weak light user.

[0101] For example, based on the sequence similarity value results, a correlation analysis is performed between weak light users and users under the same PON port. If the number of users with similar optical power change trends under the same PON port is less than 3, then they are considered unrelated.

[0102] In some embodiments, the first ratio is, for example, 0.75. If the number of similar users with a similarity value less than a preset similarity value is greater than or equal to the first value, and the ratio of the number of similar users to the number of second users is less than the first ratio, the correlation is determined to be partially correlated. This can be because the number of users similar to the weak light user is greater than or equal to 3, and the ratio of the number of similar users to the number of users under the second PON port is less than 0.75. This indicates that at least some users under the second PON port have the same fault as the weak light user, and the correlation is determined to be partially correlated.

[0103] For example, based on the sequence similarity results, a correlation analysis is performed between weak light users and users under the same PON port. The number of similar users is greater than or equal to 3, and the ratio of the number of users with similar optical power change trends under the same PON port to the number of effective users under the same PON port is less than 0.75; the number of users with similar optical power change trends under the same PON port is ≥3; the ratio of the number of users with similar optical power change trends under the same PON port to the total number of effective users under the same PON port is <0.75; effective users are users whose optical power sequence fluctuates, and are used to filter out users whose non-weak light optical power is in a steady state.

[0104] In some embodiments, if the number of similar users whose similarity value is less than a preset similarity value is greater than or equal to a first value, and the ratio of the number of similar users to the number of second users is greater than or equal to a first ratio, the correlation is determined to be fully correlated. For example, if the number of users under the second PON port similar to the weak light user is greater than or equal to 3, and the ratio of the number of similar users to the number of users under the second PON port is greater than or equal to 0.75, it indicates that the users under the second PON port have the same fault as the weak light user, and the correlation is determined to be fully correlated.

[0105] For example, based on the sequence similarity results, a correlation analysis is performed between weak light users and users under the same PON port. If the number of similar users is greater than or equal to 3 and the above ratio is greater than or equal to 0.75, then all are considered to be correlated.

[0106] Step 303: Determine fault information based on correlation.

[0107] In the embodiments of this disclosure, the fault location is any one of the main trunk section, branch section, and inlet section.

[0108] In the embodiments of this disclosure, fault information can be determined based on correlation. This can be done by obtaining the corresponding fault category based on the correlation between multiple users and weak light users under the same PON port, thereby determining the fault information.

[0109] In some embodiments, when the correlation is uncorrelated, the fault type is the inlet section fault, and the fault location is the inlet section; when the correlation is partially correlated, the fault type is the branch section fault, and the fault location is the branch section; when the correlation is fully correlated, the fault type is the trunk section fault, and the fault location is the trunk section.

[0110] In some embodiments, when the fault location is the inlet segment, the device identifier of the user corresponding to the inlet segment and the identifier of the corresponding PON port can be obtained; when the fault location is the branch segment, the device identifier of the branch or secondary splitter and the identifier of the corresponding PON port can be obtained; when the fault location is the main segment, the device identifier of the main segment or primary splitter and the identifier of the corresponding PON port can be obtained.

[0111] For example, based on the sequence similarity results, a correlation analysis is performed between low-light users and users under the same PON port: if they are not correlated, they are in the inbound segment; if they are partially correlated, they are in the branch segment; and if they are completely correlated, they are in the backbone segment. Here, the inbound segment corresponds to the user's equipment, the branch segment corresponds to the equipment in the branch or secondary splitter, and the backbone segment corresponds to the equipment in the backbone or primary splitter.

[0112] In the above embodiments, by determining the fault information based on the correlation between weak light users and users under the same PON port, the accurate location of the fault can be obtained through the correlation, thereby improving the accuracy and efficiency of the fault location method.

[0113] In summary, the fault location method proposed in this disclosure improves the accuracy of fault location by calculating similarity values ​​of optical power sequences and accurately delineating faults through clustering and time series alignment. Simultaneously, by sampling and processing large amounts of optical power data, it enhances data processing and analysis capabilities, further improving the efficiency of fault analysis and location. Furthermore, it ensures network stability and user experience.

[0114] The following is a specific implementation method for fault location:

[0115] like Figure 4 The diagram shows the ODN network clustering vulnerability optimization scheme. The optical path passes through the aggregation room, through the backbone and the primary optical cross-connect (backbone ring network), to the branch section (street / residential community) and multiple secondary optical cross-connects, and finally to multiple drop sections (buildings).

[0116] Based on 48-hour continuous monitoring of optical power fluctuations and preset risk thresholds, potential optical path faults are detected in a timely manner through high-frequency sampling. For users with predicted optical path faults, clustering and grouping are implemented, and the received optical power change trends of all users under the PON port are entered into the database model for resource correlation association, accurately locating the trunk / branch / access fault location.

[0117] I. Implementation Principles

[0118] By sampling historical data and employing a time-series clustering algorithm, the ONT received power index is subjected to time warping and trend clustering analysis, enabling precise delineation and identification of the weak light source location, such as the pigtail, secondary splitter branch, or PON port backbone.

[0119] 1. Optical power statistical acquisition

[0120] The optical power of all ONUs is collected through the provincial RMS platform. The RMS (digital platform as the terminal platform for managed optical modems and routers) connects to the system through network routing to obtain the optical power records of all probes and assist in the diagnosis of optical path hazards.

[0121] 2. The high-frequency sampling rules are as follows:

[0122] (1) There is clustered weak light under the PON port: Randomly select 3 users to check the optical power. The optical power needs to be restored to the optical power value before the weak light ±1dBm.

[0123] (2) There is a batch degradation of the backbone under the PON port: If there is degradation to weak light, take 1 weak light user and 2 degraded users, and the optical power should be restored to the optical power value before degradation ±1dBm. If there is no degradation to weak light, randomly select 3 users and check that the optical power should be restored to the optical power value before degradation ±1dBm.

[0124] There is a branch-based batch degradation under the PON port: If the degradation is reduced to weak light, take one weak light user and one degraded user, and the optical power should be restored to the pre-degradation optical power value ±1dBm. If there is no degradation to weak light, randomly select two users and check their optical power, which should be restored to the pre-degradation optical power value ±1dBm.

[0125] 3. Feature mining of optical power sequences

[0126] ONT optical power sequence data were collected, and the data was cleaned and verified. Based on the K-means algorithm, four categories of descriptions of optical power change trends were generated: decline, fluctuation, level, and recovery.

[0127] (1) K-means Algorithm Logic: The k-means clustering algorithm is an iterative clustering analysis algorithm. Its steps are as follows: First, the data is divided into K groups. Then, K objects are randomly selected as initial cluster centers. Next, the distance between each object and each seed cluster center is calculated, and each object is assigned to the nearest cluster center. Each cluster center and the objects assigned to it represent a cluster. Each time a sample is assigned, the cluster centers are recalculated based on the existing objects in the cluster. This process is repeated until a termination condition is met. The termination condition can be that no (or a minimum number) objects are reassigned to different clusters, no (or a minimum number) cluster centers change, or the sum of squared errors reaches a local minimum.

[0128] (2) Four types of trend descriptions: Decline, the optical power shows a significant and continuous downward trend of more than ±3dB and has not recovered; Fluctuation, the optical power of a single ONU shows a trend of repeated splitting and recovery; Horizontal, the optical power remains stable without any change of 1-2dB; Recovery, the time node recorded shows a significant split of ±3dB and returns to normal in the sampling on the same day (the horizontal value was recorded before the splitting).

[0129] 4. Dynamic Time Warping (DTW) Algorithm

[0130] Based on the Dynamic Time Warping (DTW) algorithm, similarity calculations are performed on user optical power trend sequence data under the same PON. The introduction of DTW distance preserves information about the original waveform of the optical power sequence, making the calculation and inference more accurate.

[0131] (1) Low light user standard: The ONT received light power is less than -27dB at least 3 times a day.

[0132] (2) Boundary rule: For weak light users, take the optical power change trend of users under the same PON port, and determine the similarity between the optical power change trend of weak light users and the optical power change trend of other users under the same PON port based on the algorithm.

[0133] (3) Branch or secondary splitting: The number of similar users is greater than or equal to 3 and the ratio of the number of users with similar optical power change trends under the same PON port to the number of effective users under the same PON port is less than 0.75; the number of users with similar optical power change trends under the same PON port is ≥3; the ratio of the number of users with similar optical power change trends under the same PON port to the total number of effective users under the same PON port is <0.75; effective users are users whose optical power sequence fluctuates, used to filter out users whose non-weak optical power is in a steady state.

[0134] (4) Main or first-level spectrophotometry: The number of similar users is greater than or equal to 3 and the above ratio is greater than or equal to 0.75.

[0135] (5) Inbound segment: The optical power change trend is similar to that of the PON port, and the number of users is less than 3.

[0136] 5. Cluster Association Analysis

[0137] Based on the sequence similarity results, a correlation analysis was performed between weak light users and users under the same PON port.

[0138] Unrelated: Entry section

[0139] Partially related: branch segment

[0140] All related: Main section

[0141] 6. Quality issues and auxiliary maintenance

[0142] Provide a user interface to the middleware platform, allowing users to view the current optical path quality on the network side through their user accounts, thus providing support for installation and maintenance.

[0143] II. Implementation Process

[0144] 1. Acquisition of soft probe data: Currently, probe data is acquired by connecting to the RMS digital platform via FTTP. The probe data strictly follows the prescribed probe specifications.

[0145] 2. Optical power trend analysis: Based on 48-hour continuous monitoring of optical power fluctuations and preset risk thresholds, high-frequency sampling is used to promptly detect potential optical path faults; for users with predicted optical path faults, clustering and grouping are implemented, and the received optical power change trends of all users under the PON port are entered into the database model for resource correlation association, accurately locating the trunk / branch / access fault location.

[0146] 3. Identification of weak light and degradation trends: High-frequency sampling is performed every 10 minutes using a probe to collect ONT optical power sequence data, followed by data cleaning and verification. Based on the K-means algorithm, four categories of descriptions of optical power change trends are generated: decline, fluctuation, level, and recovery.

[0147] Decline: Optical power has shown a clear and continuous downward trend of more than ±3dB, and has not recovered.

[0148] Fluctuation: The optical power of a single ONU exhibits a trend of repeated fluctuations and recovery.

[0149] Level: Optical power remained stable with no change of 1-2 dB.

[0150] Recovery: The timeline records show a significant split of ±3dB, which returned to normal during the sampling on the same day (the level value recorded before the split).

[0151] 4. Reliability verification before dispatching orders: The system will push the analyzed sample data to the electronic maintenance department after verifying its accuracy: There is a batch degradation of the backbone under the PON port (number of weak light users X), and there is a batch degradation of the branch under the PON port (number of weak light users Y).

[0152] 5. Dispatch work orders based on resource information: The electronic operation and maintenance platform triggers a work order dispatch once a day on port 1 by combining information such as PON port, broadband account, and primary optical splitter with the pushed events. The path of the push interface is consistent with the accurate dispatch of home customer complaints, and the person in charge is also the same.

[0153] 6. Work order processing by maintenance personnel: In line with the precise dispatching of customer complaints, work orders are automatically dispatched by the charterer. After processing, maintenance personnel will return the work order, and the response will include the handling measures and the root cause of the deterioration.

[0154] 7. Quality Inspection and Archiving: After the maintenance personnel complete the work order, the on-site test is completed. The electronic operation and maintenance system can also call the one-click diagnostic capability of the platform through the account provided by the network administrator to perform optical power diagnosis for users with weak light and users with batch degradation. After passing the test, the quality inspection is automatically completed.

[0155] The optical path degradation trend clustering model is constructed to realize weak light clustering of PON ports and identification of optical path fluctuation trends. Multi-level rule layering pushes the real-time identified weak light hazards of ODN optical path backbone, branches, and home access into the process system, and accurately assigns orders according to responsibilities, helping outsourced maintenance and installation maintenance to take the initiative in operation and maintenance, and improve efficiency in troubleshooting.

[0156] III. Application of Abilities

[0157] Based on 48-hour continuous monitoring of optical power fluctuations and preset risk thresholds, potential optical path faults are detected in a timely manner through high-frequency sampling. For users with predicted optical path faults, clustering and grouping are implemented, and the received optical power change trends of all users under the PON port are entered into the database model for resource correlation association, accurately locating the trunk / branch / access fault location.

[0158] Capability 1: Early detection of weak light fluctuations

[0159] Based on the probe principle (digital platform RMS), the optical power is sampled and recorded at a high frequency every 15 minutes to ensure that the optical changes of a single ONU are accurately recorded every hour. This is continuously accumulated and updated with the first and last fault reporting times. The optical power of the fault is continuously sampled and compared, with the values ​​of the previous 15 minutes compared with those of the next 15 minutes. This is monitored and recorded to avoid false detections of temporary weak light and to avoid data entry errors.

[0160] Capability 2: Accurate Demarcation of Optical Path

[0161] The boundary algorithm runs on an hourly basis, performs correlation analysis on the data, determines the location of the fault, and continuously corrects and updates the judgment results.

[0162] In summary, this method has the following beneficial effects:

[0163] 1. Improved accuracy: High-frequency sampling and data cleaning and verification ensure the real-time nature and accuracy of the data, enabling timely detection and resolution of potential optical path faults; by introducing dynamic time warping and temporal clustering algorithms, similarity calculation and precise delimitation of optical power trend sequences are achieved, improving the accuracy of fault location.

[0164] 2. Comprehensive coverage: Optical feature data analysis and positioning methods can be used in point-to-multipoint fiber optic networks.

[0165] 3. Efficiency Improvement: The adoption of big data processing technology has improved data processing and analysis capabilities, further enhancing the efficiency of fault analysis and location.

[0166] Figure 5 This is a schematic diagram of a fault location device provided in an embodiment of the present disclosure. The device 500 includes...

[0167] The sampling module 510 is used to sample optical power data based on a preset sampling frequency to determine optical power sequence data. The optical power sequence data includes the identifier of the PON port, the user's device identifier, and optical power parameters. Each PON port corresponds to multiple optical power sequence data.

[0168] The determination module 520 is used to determine the similarity value between any two users based on optical power sequence data, through unsupervised clustering and time series alignment in sequence.

[0169] The positioning module 530 is used to perform correlation analysis on the similarity values ​​between any two users to determine fault information, including fault location, fault device identifier, and fault PON port identifier.

[0170] In some embodiments, the sampling module is further configured to: monitor optical power data within a preset time period and determine a preset threshold; sample optical power data based on a preset sampling frequency to obtain sampled data, wherein the relationship between the optical power parameters of the sampled data and the preset threshold satisfies a preset condition; and preprocess the sampled data to obtain optical power sequence data.

[0171] In some embodiments, the determining module is further configured to: perform unsupervised clustering on the optical power sequence data to obtain multiple optical power category data, each optical power category data including multiple optical power sequence data; and determine the similarity value between any two users by time series alignment for the first category of optical power category data in the multiple optical power category data.

[0172] In some embodiments, the determining module is further configured to: determine the first optical power sequence data of multiple first users corresponding to the first PON port for the first type of optical power category data; and determine the distance value between any two first users in the multiple first optical power sequence data by time series alignment, thereby obtaining the similarity value between any two first users.

[0173] In some embodiments, the positioning module is further configured to: determine the second PON port corresponding to the low-light user; for multiple second users corresponding to the second PON port, determine the correlation between the low-light user and the multiple second users based on the similarity value between the second user and the low-light user; and determine fault information based on the correlation, wherein the fault location is any one of the main segment, branch segment, and inlet segment.

[0174] In some embodiments, the positioning module is further configured to: determine the correlation as unrelated when the number of similar users with a similarity value less than a preset similarity value is less than a first value; determine the correlation as partially related when the number of similar users with a similarity value less than a preset similarity value is greater than or equal to the first value, and the ratio of the number of similar users to the number of second users is less than a first ratio; and determine the correlation as fully related when the number of similar users with a similarity value less than a preset similarity value is greater than or equal to the first value, and the ratio of the number of similar users to the number of second users is greater than or equal to the first ratio.

[0175] In summary, the fault location device proposed in this disclosure can improve the accuracy of fault location, thereby improving the efficiency and accuracy of fault handling, as well as the efficiency of fault analysis and location, and further ensuring network stability and user experience.

[0176] The methods and apparatus provided in the embodiments of this application have been described above. To implement the functions of the methods provided in the embodiments of this application, the electronic device may include a hardware structure and software modules, and may implement the above functions in the form of a hardware structure, software modules, or a hardware structure plus software modules. One of the above functions may be executed in the form of a hardware structure, software modules, or a hardware structure plus software modules.

[0177] Figure 6 This is a block diagram illustrating an electronic device 600 for implementing the above-described fault location method according to an exemplary embodiment.

[0178] Reference Figure 6 The electronic device 600 may include a communication interface 601, capable of interacting with other devices; a processor 602, connected to the communication interface 601 to interact with other devices, used to execute the methods provided by one or more of the above-described technical solutions when running a computer program; and a memory 603, on which the computer program is stored. Specifically, the specific processing procedure of the processor 602 can refer to the fault location method described in the above embodiments of this disclosure.

[0179] Of course, in practical applications, the various components in electronic device 600 are coupled together through bus system 604. It can be understood that bus system 604 is used to realize the connection and communication between these components. In addition to a data bus, bus system 604 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, in... Figure 6 The general designated all buses as Bus System 604.

[0180] The memory 603 in this embodiment is used to store various types of data to support the operation of the electronic device 600. Examples of such data include any computer program used to operate on the electronic device 600.

[0181] The methods disclosed in the embodiments of this application can be applied to processor 602, or implemented by processor 602. Processor 602 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 602 or by instructions in the form of software. The processor 602 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 602 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. A general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this application can be directly manifested as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in memory 603. Processor 602 reads the information in memory 603 and combines its hardware to complete the steps of the aforementioned method.

[0182] In an exemplary embodiment, the electronic device 600 may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to perform the aforementioned method.

[0183] Embodiments of this disclosure also propose a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the fault location method described in the above embodiments of this disclosure.

[0184] Embodiments of this disclosure also provide a computer program product, including a computer program that is executed by a processor using the fault location method described in the above embodiments of this disclosure.

[0185] Embodiments of this disclosure also propose a chip including one or more interface circuits and one or more processors; the interface circuits are used to receive signals from the memory of an electronic device and send signals to the processors, the signals including computer instructions stored in the memory, which, when executed by the processor, cause the electronic device to perform the fault location method described in the above embodiments of this disclosure.

[0186] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0187] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0188] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0189] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processing module, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (control method), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic device, and portable optical disc read-only memory (CD ROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0190] It should be understood that various parts of the embodiments of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0191] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0192] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc.

[0193] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A fault location method, characterized in that, The method includes: Optical power data is sampled based on a preset sampling frequency to determine optical power sequence data. The optical power sequence data includes the PON port identifier, the user's device identifier, and optical power parameters. Each PON port corresponds to multiple optical power sequence data. Based on the optical power sequence data, the similarity value between any two users is determined sequentially through unsupervised clustering and time series alignment. The similarity values ​​between any two users are correlated to determine the fault information, which includes the fault location, fault device identifier, and fault PON port identifier.

2. The method according to claim 1, characterized in that, The step of sampling optical power data based on a preset sampling frequency to determine optical power sequence data includes: The optical power data is monitored within a preset time period to determine a preset threshold. Based on the preset sampling frequency, the optical power data is sampled to obtain sampled data, and the relationship between the optical power parameter of the sampled data and the preset threshold satisfies the preset condition; The sampled data is preprocessed to obtain the optical power sequence data.

3. The method according to claim 2, characterized in that, Based on the optical power sequence data, the similarity value between any two users is determined sequentially through unsupervised clustering and time series alignment, including: The unsupervised clustering is performed on the optical power sequence data to obtain multiple optical power category data, and each optical power category data includes multiple optical power sequence data. For the first category of optical power data in the multiple categories of optical power data, the similarity value between any two users is determined by the time series alignment.

4. The method according to claim 3, characterized in that, The step of determining the similarity value between any two users based on the first category of optical power data in the multi-category optical power data through time series alignment includes: For the first type of optical power category data, determine the first optical power sequence data of multiple first users corresponding to the first PON port; By aligning the time series, the distance value between any two first users in the plurality of first optical power sequence data is determined, and the similarity value between any two first users is obtained.

5. The method according to claim 3, characterized in that, The step of performing correlation analysis on the similarity values ​​between any two users to determine fault information includes: Determine the second PON port corresponding to the user with low light intensity; For multiple second users corresponding to the second PON port, the correlation between the low-light user and the multiple second users is determined based on the similarity value between the second user and the low-light user; Based on the correlation, the fault information is determined, wherein the fault location is any one of the main section, branch section, and entrance section.

6. The method according to claim 5, characterized in that, The determination of the association between the low-light user and the plurality of second users based on the similarity value between the second user and the low-light user includes any one of the following: If the number of similar users whose similarity value is less than a preset similarity value is less than a first value, the correlation is determined to be unrelated. If the number of similar users whose similarity value is less than the preset similarity value is greater than or equal to the first value, and the ratio of the number of similar users to the number of second users is less than the first ratio, then the correlation is determined to be partially correlated. If the number of similar users whose similarity value is less than the preset similarity value is greater than or equal to the first value, and the ratio of the number of similar users to the number of second users is greater than or equal to the first ratio, then the correlation is determined to be fully correlated.

7. A fault location device, characterized in that, include: The sampling module is used to sample optical power data based on a preset sampling frequency to determine optical power sequence data. The optical power sequence data includes the identifier of the PON port, the user's device identifier, and optical power parameters. Each PON port corresponds to multiple optical power sequence data. The determination module is used to determine the similarity value between any two users based on the optical power sequence data, through unsupervised clustering and time series alignment in sequence; The positioning module is used to perform correlation analysis on the similarity values ​​between any two users to determine fault information, including fault location, fault device identifier, and fault PON port identifier.

8. An electronic device, characterized in that, include: One or more processors; A storage device communicatively connected to the one or more processors, wherein one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the method as described in any one of claims 1-6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

10. A chip, characterized in that, The device includes one or more interface circuits and one or more processors; the interface circuits are configured to receive signals from the memory of the electronic device and send the signals to the processors, the signals including computer instructions stored in the memory, which, when executed by the processors, cause the electronic device to perform the method of any one of claims 1-6.

Images