Wavelength division equipment alarm analysis method and device, electronic equipment and storage medium

Abstract

The invention provides a wavelength division equipment alarm analysis method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring current alarm data of wavelength division equipment; according to the current alarm data and a pre-constructed alarm root cause tree, an alarm root factor tree is constructed, and the alarm root factor tree is used for representing a root cause tree corresponding to the alarm data; according to the current alarm data and the alarm root factor tree, an alarm root cause result tree is determined, and an alarm root cause result comprises an alarm list and an alarm processing suggestion; and outputting an alarm analysis result according to the alarm root cause result tree. The technical problems that according to a wavelength division equipment alarm analysis method provided in the related technology, it is difficult to accurately position faults in a complex dynamic network environment, a large number of chain reaction alarms cannot be effectively processed, systematic templates and hierarchical correlation analysis are lacked, and consequently the fault diagnosis efficiency is low are solved.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technology, and in particular to a wavelength division equipment alarm analysis method, device, electronic device and storage medium. Background Art

[0002] Wavelength Division Multiplexing (WDM) equipment is a key device used to achieve simultaneous transmission of multiple channels in modern optical fiber communication networks. By simultaneously transmitting multiple optical signals of different wavelengths on one optical fiber, it can improve the transmission capacity and efficiency of optical fibers. However, with the continuous expansion and complexity of optical networks, the failures and abnormal events encountered by wavelength division equipment during operation often do not occur in isolation, but may trigger a series of related alarms, including redundant alarms, associated alarms, and flash alarms. The above alarms are not only numerous, but also have intricate direct or indirect causal relationships with each other. When serious alarms occur and are not resolved in time, they will directly affect the continuity of the business and cause service interruptions, thus bringing severe challenges to network operation and maintenance. The wavelength division equipment alarm analysis method in the related technology usually adopts a rule-based matching strategy combined with simple statistical analysis methods to achieve rapid identification and classification of equipment alarms and preliminary fault location. However, the wavelength division equipment alarm analysis method in the related technology relies on predefined rules and statistical patterns of historical alarm data to analyze the relationship between current alarms and historical alarms, and lacks the hierarchical relationship of systematic templates, making it difficult to accurately locate the root cause of the fault in a complex and dynamically changing network environment.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present disclosure provide a wavelength division equipment alarm analysis method, device, electronic device and storage medium to at least solve the technical problems that the wavelength division equipment alarm analysis method provided in the related art is difficult to accurately locate faults in a complex dynamic network environment, cannot effectively handle a large number of chain reaction alarms, and lacks systematic templates and hierarchical correlation analysis, resulting in low fault diagnosis efficiency.

[0005] According to one aspect of an embodiment of the present disclosure, a wavelength division device alarm analysis method is provided, including: obtaining current alarm data of the wavelength division device; constructing an alarm root factor tree based on the current alarm data and a pre-constructed alarm root cause tree, wherein the alarm root factor tree is used to characterize the root cause tree corresponding to the alarm data; determining an alarm root cause result tree based on the current alarm data and the alarm root factor tree, wherein the alarm root cause result includes an alarm list and an alarm processing suggestion; and outputting an alarm analysis result based on the alarm root cause result tree.

[0006] Optionally, the alarm data includes: alarm time, alarm type, alarm level, and device identification.

[0007] Optionally, constructing the alarm root cause tree includes: obtaining historical alarm data, wherein the historical alarm data includes multiple alarm data corresponding to multiple wavelength division devices; processing the historical alarm data using a preset association rule learning algorithm to determine association rules; and determining the alarm root cause tree based on the association rules and the historical alarm data.

[0008] Optionally, the historical alarm data is processed using a preset association rule learning algorithm to determine the association rules, including: based on the preset association rule learning algorithm, traversing the historical alarm data to determine the support of each single alarm, wherein the historical alarm data includes multiple single alarms; determining frequent item sets based on the support and a preset support threshold; determining rule confidence based on the frequent item sets; and determining association rules based on the rule confidence and a preset confidence threshold.

[0009] Optionally, determining an alarm root cause tree based on association rules and historical alarm data includes: determining a root node from historical alarm data based on preset root node confirmation rules; determining child nodes based on association rules, the root node and historical alarm data; and constructing an alarm root cause tree based on the root node and child nodes.

[0010] Optionally, an alarm root factor tree is constructed based on current alarm data and a pre-constructed alarm root cause tree, including: matching alarm root cause nodes from the alarm root cause tree based on current alarm data; determining associated nodes from the alarm root cause tree based on the alarm root cause nodes; and determining the alarm root factor tree based on the associated nodes and the root cause nodes.

[0011] Optionally, the types of the alarm root cause node include first-level nodes, second-level nodes and third-level nodes. According to the alarm root cause node, associated nodes are determined from the alarm root cause tree, including: in response to the type of the alarm root cause node being a first-level node, determining the associated node to be a null value; or, in response to the type of the alarm root cause node being a second-level node, determining the first-level node and the third-level node associated with the alarm root cause node as associated nodes; or, in response to the type of the alarm root cause node being a third-level node, determining the second-level node and the first-level node associated with the alarm root cause node as associated nodes.

[0012] Optionally, based on the current alarm data and the alarm root factor tree, an alarm root cause result tree is determined, including: based on the alarm root factor tree, obtaining associated alarm data associated with the current alarm data; matching the associated alarm data to the alarm root factor tree and adding alarm processing suggestions to the alarm root factor tree to obtain the alarm root cause result tree.

[0013] According to one embodiment of the present disclosure, there is also provided a wavelength division equipment alarm analysis device, including: an acquisition module, used to acquire current alarm data of the wavelength division equipment; a construction module, used to construct an alarm root factor tree according to the current alarm data and a pre-constructed alarm root cause tree, wherein the alarm root factor tree is used to characterize the root cause tree corresponding to the alarm data; a determination module, used to determine an alarm root cause result tree according to the current alarm data and the alarm root factor tree, wherein the alarm root cause result data includes an alarm list and an alarm suggestion; and an output module, used to output the alarm analysis result according to the alarm root cause result tree.

[0014] Optionally, the construction module is also used to: obtain historical alarm data, wherein the historical alarm data includes multiple alarm data corresponding to multiple wavelength division devices; process the historical alarm data using a preset association rule learning algorithm to determine association rules; and determine an alarm root cause tree based on the association rules and the historical alarm data.

[0015] Optionally, the construction module is also used to: traverse the historical alarm data based on a preset association rule learning algorithm to determine the support of each single alarm, wherein the historical alarm data includes multiple single alarms; determine frequent item sets based on the support and a preset support threshold; determine rule confidence based on the frequent item sets; determine association rules based on the rule confidence and a preset confidence threshold.

[0016] Optionally, the construction module is also used to: determine the root node from the historical alarm data according to a preset root node confirmation rule; determine the child node according to the association rule, the root node and the historical alarm data; and construct an alarm root cause tree according to the root node and the child nodes.

[0017] Optionally, the construction module is further used to: match an alarm root cause node from the alarm root cause tree according to current alarm data; determine an associated node from the alarm root cause tree according to the alarm root cause node; and determine an alarm root factor tree according to the associated node and the root cause node.

[0018] Optionally, the construction module is also used to: in response to the type of the alarm root cause node being a first-level node, determine that the associated node is a null value; or, in response to the type of the alarm root cause node being a second-level node, determine the first-level node and the third-level node associated with the alarm root cause node as associated nodes; or, in response to the type of the alarm root cause node being a third-level node, determine the second-level node and the first-level node associated with the alarm root cause node as associated nodes.

[0019] Optionally, the determination module is further used to: obtain associated alarm data associated with the current alarm data according to the alarm root factor tree; match the associated alarm data to the alarm root factor tree and add alarm processing suggestions to the alarm root factor tree to obtain an alarm root cause result tree.

[0020] According to one embodiment of the present disclosure, an electronic device is also provided, including: a memory storing an executable program; and a processor for running the program, wherein the wavelength division equipment alarm analysis method in the embodiment of the present disclosure is executed when the program is running.

[0021] According to one embodiment of the present disclosure, a computer-readable storage medium is also provided, which includes a stored executable program, wherein when the executable program runs, the device where the storage medium is located is controlled to execute the wavelength division equipment alarm analysis method in the embodiment of the present disclosure.

[0022] According to one embodiment of the present disclosure, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, the wavelength division device alarm analysis method in the embodiment of the present disclosure is implemented.

[0023] In the disclosed embodiment, by acquiring the current alarm data of the wavelength division multiplexing device, and constructing an alarm root factor tree based on the current alarm data and the pre-constructed alarm root cause tree, and then determining the alarm root cause result tree based on the current alarm data and the alarm root factor tree, and finally outputting the alarm analysis result based on the alarm root cause result tree, the purpose of quickly and accurately locating the root cause of the fault in a complex network environment is achieved, thereby achieving the technical effect of improving network operation and maintenance efficiency and reducing the risk of business interruption, and further solving the technical problems of the wavelength division multiplexing device alarm analysis method provided in the related technology that it is difficult to accurately locate the fault in a complex dynamic network environment, cannot effectively handle a large number of chain reaction alarms, and lacks systematic templates and hierarchical correlation analysis, resulting in low fault diagnosis efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure. In the drawings:

[0025] Figure 1 is a flow chart of a wavelength division equipment alarm analysis method according to one embodiment of the present disclosure;

[0026] Figure 2 is a schematic diagram of a wavelength division equipment alarm analysis method according to one embodiment of the present disclosure;

[0027] Figure 3 is a schematic diagram of a wavelength division equipment alarm analysis system according to one embodiment of the present disclosure;

[0028] Figure 4 is a schematic diagram of another wavelength division equipment alarm analysis method according to one embodiment of the present disclosure;

[0029] Figure 5is a schematic diagram of another wavelength division equipment alarm analysis method according to one embodiment of the present disclosure;

[0030] Figure 6 It is a structural block diagram of a wavelength division equipment alarm analysis device according to one embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the scheme of the present disclosure, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present disclosure.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0033] The WDM equipment alarm analysis method in the related art usually adopts a rule-based matching strategy combined with simple statistical analysis methods to achieve rapid identification and classification of equipment alarms and preliminary fault location. However, the WDM equipment alarm analysis method in the related art relies on predefined rules and statistical patterns of historical alarm data to analyze the relationship between current alarms and historical alarms, lacks a hierarchical relationship of systematic templates, and is therefore difficult to accurately locate the root cause of the fault in a complex and dynamically changing network environment.

[0034] Specifically, the rule-based WDM equipment alarm analysis method in the related art is limited by its static rule set and statistical dependence on past data, and is often unable to dynamically adapt to the immediate changes in the network and the emerging fault modes. When processing the current alarm, it is impossible to effectively distinguish which are derivative alarms and which are core problems, resulting in the analysis process being disturbed by a large amount of non-critical information, increasing the risk of misjudgment. In addition, when constructing the alarm association model, the method in the related art does not fully consider the inherent connection between the level and type of the alarm, and lacks a template that can systematically and intuitively display the causal chain between alarms, so that when facing complex network architectures and multi-level alarms, it is impossible to accurately locate the root cause of the fault. Especially when the network environment undergoes large-scale upgrades or architectural adjustments, or when a new type of fault appears for the first time, the limitations of the preset rules and the lag of historical data jointly weaken the accuracy and response speed of the alarm analysis, making it difficult to give effective fault diagnosis and solution suggestions in the first time, thereby delaying the time for service recovery and increasing the burden on network operation and maintenance.

[0035] According to an embodiment of the present disclosure, a method embodiment of a wavelength division multiplexing device alarm analysis method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0036] The method embodiment can be executed in an electronic device or a similar computing device including a memory and a processor. Taking running on a computer terminal as an example, the computer terminal may include one or more processors (processors may include but are not limited to central processing units (CPU), graphics processing units (GPU), digital signal processing (DSP) chips, microprocessors (MCU), programmable logic devices (Field Programmable Gate Array, FPGA), neural network processors (Neural-network Processor Unit, NPU), tensor processors (TensorProcessing Unit, TPU), artificial intelligence (Artificial Intelligence, AI) type processors and other processing devices) and a memory for storing data. Optionally, the above-mentioned computer terminal may also include a transmission device, an input and output device, and a display device for communication functions. It can be understood by those of ordinary skill in the art that the above-mentioned structural description is only for illustration, and it does not limit the structure of the above-mentioned computer terminal. For example, the computer terminal may also include more or fewer components than the above-mentioned structural description, or have a configuration different from the above-mentioned structural description.

[0037] The memory can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the wavelength division equipment alarm analysis method in the embodiment of the present disclosure. The processor executes various functional applications and data processing by running the computer program stored in the memory, that is, the above-mentioned wavelength division equipment alarm analysis method is realized. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0038] The transmission device is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0039] The display device may be, for example, a touch screen type liquid crystal display (LCD) and a touch display (also referred to as a "touch screen" or "touch display screen"). The liquid crystal display may enable a user to interact with a user interface of a mobile terminal. In some embodiments, the mobile terminal has a graphical user interface (GUI), and a user may interact with the GUI by finger contacts and / or gestures on a touch-sensitive surface, wherein the human-computer interaction functions here may optionally include the following interactions: creating web pages, drawing, word processing, making electronic documents, games, video conferencing, instant messaging, sending and receiving emails, call interfaces, playing digital videos, playing digital music and / or web browsing, etc. The executable instructions for executing the above human-computer interaction functions are configured / stored in a computer program product or readable storage medium executable by one or more processors.

[0040] Figure 1 is a flow chart of a wavelength division equipment alarm analysis method according to one embodiment of the present disclosure, such as Figure 1 As shown, the method comprises the following steps:

[0041] Step S11, obtaining current alarm data of the wavelength division device;

[0042] Step S12, constructing an alarm root factor tree according to the current alarm data and the pre-constructed alarm root cause tree, wherein the alarm root factor tree is used to characterize the root cause tree corresponding to the alarm data;

[0043] Step S13, determining an alarm root cause result tree according to current alarm data and the alarm root factor tree, wherein the alarm root cause result includes an alarm list and alarm handling suggestions;

[0044] Step S14: output the alarm analysis result according to the alarm root cause result tree.

[0045] The above-mentioned wavelength division equipment refers to the communication equipment that uses wavelength division multiplexing technology (Wavelength Division Multiplexing, WDM) in the optical fiber communication network, which is mainly divided into two categories: dense wavelength division multiplexing (DWDM) equipment and coarse wavelength division multiplexing (CWDM) equipment. In addition, wavelength division equipment can be further subdivided into box-type wavelength division equipment and rack-type wavelength division equipment according to its physical form and functional characteristics. The above-mentioned wavelength division equipment realizes channel multiplexing by simultaneously transmitting multiple optical signals of different wavelengths in a single optical fiber, thereby greatly improving the transmission capacity of the optical fiber and the data transmission efficiency of the network. Specifically, wavelength division equipment usually includes components such as optical amplifiers, splitters, combiners, tunable laser sources, optical monitoring channels, etc., which can provide high-bandwidth, low-latency data transmission services in scenarios such as long-distance transmission and data center interconnection. When a wavelength division device fails or is abnormal, corresponding alarm data will be generated to indicate the health status of the device or network, helping operation and maintenance personnel to promptly discover and handle problems and ensure the stable operation of the network.

[0046] The above alarm root cause tree refers to a multi-level, structured fault correlation model constructed by deeply analyzing a large amount of historical alarm data in the management of wavelength division multiplexing network equipment. Specifically, the alarm root cause tree uses data mining and machine learning technology to process alarm data, identify the correlation and potential causal chain between different alarms, and thus form a tree structure with a certain alarm as the root node and other related or derived alarms as child nodes.

[0047] The above alarm root factor tree refers to the analysis tree structure that is dynamically generated and specific to the current alarm situation in the WDM device alarm analysis based on the specific alarm data generated by the current device and the pre-built alarm root cause tree model. Specifically, when a WDM device reports a new alarm, the system will filter and match the nodes related to the current alarm from the alarm root cause tree through the construction process of the alarm root factor tree, forming a subtree structure centered on the current alarm and including its potential causes and impacts.

[0048] The above alarm root cause result tree refers to the tree structure obtained through a series of data analysis and matching algorithms during the alarm analysis process of the wavelength division multiplexing equipment, which can intuitively display the cause-effect relationship and processing suggestions of the current alarm and its related alarms. This structure not only contains detailed information about the alarm, but also clarifies the hierarchical relationship and correlation between alarms through the construction and matching of the alarm root factor tree, as well as the fault handling suggestions given based on the alarm analysis.

[0049] For example, suppose a box-type wavelength division multiplexing device suddenly reports an alarm, and the wavelength division multiplexing device alarm analysis system immediately starts the alarm analysis process. First, the alarm collection module receives the current alarm data reported by the wavelength division multiplexing device through the NETCONF protocol; secondly, the wavelength division multiplexing device alarm analysis system cross-compares the current alarm data with the pre-built alarm root cause tree model to construct a subtree structure that reflects the root cause of the current alarm data, namely the alarm root factor tree. Furthermore, combining the above alarm root factor tree with the detailed information of the current alarm data, the wavelength division multiplexing device alarm analysis system deeply analyzes the correlation between the alarms and generates an alarm root cause result tree. Finally, the alarm display module presents the constructed alarm root cause result tree in an intuitive and user-friendly interface, which not only makes the fault location clear, but also makes the handling suggestions for each alarm clear at a glance, thereby enhancing the convenience of operation.

[0050] Based on the above steps S11 to S14, by obtaining the current alarm data of the wavelength division equipment, and constructing an alarm root factor tree according to the current alarm data and the pre-constructed alarm root cause tree, and then determining the alarm root cause result tree according to the current alarm data and the alarm root factor tree, and finally outputting the alarm analysis result according to the alarm root cause result tree, the purpose of quickly and accurately locating the root cause of the fault in a complex network environment is achieved, thereby achieving the technical effect of improving network operation and maintenance efficiency and reducing the risk of business interruption, and thus solving the technical problems that the wavelength division equipment alarm analysis method provided in the related technology is difficult to accurately locate the root cause of the fault in a complex dynamic network environment, cannot effectively handle a large number of chain reaction alarms, and lacks systematic templates and hierarchical correlation analysis, resulting in low fault diagnosis efficiency.

[0051] The following is a further introduction to the wavelength division equipment alarm analysis method in the embodiment of the present disclosure.

[0052] Optionally, in step S11, the alarm data includes: alarm time, alarm type, alarm level, and device identification.

[0053] The alarm time refers to the precise time point when the wavelength division device detects and generates the alarm, which is usually expressed in the form of a timestamp and is used to record the specific time when the alarm first occurs or the state changes.

[0054] The above alarm types refer to the classification of various specific abnormal situations that occur in wavelength division equipment, including but not limited to optical module mismatch, uplink interruption, downlink interruption, and optical module loss. Among them, uplink interruption includes loss of received signal, loss of transmitted signal, Ethernet signal desynchronization, Ethernet signal loss, and input optical power over-limit, etc.; downlink interruption includes remote received signal loss, remote input optical power over-limit, etc.; optical module loss includes laser life pre-alarm, laser transmission failure, signal loss, and input optical signal loss alarm, etc.

[0055] The above alarm levels refer to the classification of the severity of alarms that occur in WDM equipment. Usually, the alarm levels can be divided into several levels from high to low, such as "urgent", "important", "minor" and "prompt":

[0056] 1) Emergency: Indicates the most serious fault, which may have or will soon cause the entire system to stop operating and requires immediate action.

[0057] 2) Important: Indicates a serious fault that may affect some functions of the system, but the system can still operate and needs to be resolved as soon as possible.

[0058] 3) Minor: Indicates a less serious fault that generally does not immediately affect system operation, but if not handled, it may develop into a more serious problem.

[0059] 4) Prompt: Indicates some abnormal conditions in the equipment or system, but not enough to constitute a fault. It is used to remind operation and maintenance personnel that there may be potential problems that need attention.

[0060] The above-mentioned device identification refers to a specific identifier used to uniquely identify each device in a wavelength division network. It can be the device's serial number, MAC address, IP address, device name, or any other information that can ensure the unique identity of the device in the network environment.

[0061] For example, assume that at a certain time point, a wavelength division multiplexing device reports alarm data, and the specific information is as follows:

[0062] Alarm time: 2023-04-05 14:30:00;

[0063] Alarm type: Receive signal lost;

[0064] Alarm level: important;

[0065] Device identification: IP address: 192.168.1.5 or device name: WDM-EdgeNode-01.

[0066] The above alarm data means that at 14:30 on April 5, 2023, the device WDM-EdgeNode-01 (or its IP address is 192.168.1.5) detected a reception signal loss alarm, indicating that there was a problem with the reception signal, and this alarm was marked as "important", which means that it needs to be processed as soon as possible to avoid possible impact on network services.

[0067] Based on the above optional embodiments, the information such as timestamp, type, level and device identification contained in the alarm data can be used for subsequent fault analysis and historical records, helping the operation and maintenance team to summarize fault modes and optimize network design and maintenance processes.

[0068] Optionally, in step S12, the construction of the alarm root cause tree includes:

[0069] Step S121, obtaining historical alarm data, wherein the historical alarm data includes multiple alarm data corresponding to multiple wavelength division devices;

[0070] Step S122, using a preset association rule learning algorithm to process historical alarm data and determine association rules;

[0071] Step S123: Determine the alarm root cause tree according to the association rules and historical alarm data.

[0072] The above-mentioned preset association rule learning algorithm refers to a statistical method for data mining, which aims to discover the strong correlation between different alarm events from a large amount of alarm data, that is, the alarm combination that frequently appears at the same time in the alarm data set. Specifically, the preset association rule learning algorithm can be a priori algorithm (Apriori algorithm), frequent pattern growth algorithm (Frequent Pattern Growth Algorithm, referred to as FP-growth algorithm), equivalence class clustering and bottom-up lattice traversal algorithm (Equivalence Class Clustering and bottom-up Lattice Traversal, referred to as ECLAT algorithm), etc.

[0073] Exemplarily, first, a data acquisition module is used to extract a variety of alarm data corresponding to a variety of wavelength division equipment from the historical operation data of the wavelength division equipment, and the historical alarm data obtained above is cleaned and encoded to remove duplicate, erroneous and incomplete alarm data, and the text information such as the alarm type is converted into a digital code for algorithm processing. Secondly, the Apriori algorithm is used to process the collected historical alarm data to find out the combination of alarm events that frequently occur at the same time, and to determine the strong association rules between the above alarm events. Finally, based on the mined association rules and the original historical alarm data, an alarm root cause tree is constructed.

[0074] Based on the above optional embodiments, the association rule learning algorithm can reveal the potential causal relationship between different alarm events, so that the generated alarm root cause tree can more accurately reflect the causal chain of equipment failure, help operation and maintenance personnel to diagnose and solve problems more accurately, and thus improve the accuracy and efficiency of alarm analysis.

[0075] Optionally, in step S122, the historical alarm data is processed using a preset association rule learning algorithm to determine an association rule, including:

[0076] Step S1221, based on a preset association rule learning algorithm, traverse the historical alarm data to determine the support of each single alarm, wherein the historical alarm data includes multiple single alarms;

[0077] Step S1222, determining frequent itemsets according to the support and a preset support threshold;

[0078] Step S1223, determining the rule confidence according to the frequent item set;

[0079] Step S1224, determining the association rule according to the rule confidence and the preset confidence threshold.

[0080] The above support refers to the frequency of a single alarm or alarm combination in the historical alarm data set. Specifically, in association rule learning, support is an indicator that measures the prevalence of a specific item set (such as a certain alarm or alarm combination) in a data set.

[0081] The frequent itemset is a set of items whose frequency of occurrence in a data set exceeds or is equal to a preset threshold. In the method for analyzing alarms of wavelength division equipment, the frequent itemset specifically refers to a set of one or more alarm events, where the number of times the alarm events co-occur in historical alarm data is greater than or equal to a preset support threshold.

[0082] The above rule confidence refers to the proportion of all samples containing event A in which event B also occurs at the same time. It is used to measure the reliability of predicting the occurrence of event B by association rules when event A is known to occur.

[0083] For example, in the scenario of WDM equipment alarm analysis, rule confidence can help determine the possible causal relationship between alarm events. For example, if a rule is expressed as "When alarm A occurs, the probability of alarm B also occurring is X%", then the confidence X% reflects the frequency of alarm B occurring when alarm A exists. A high confidence means that when alarm A occurs, there is a high probability that alarm B will occur, indicating that alarm A may be a possible cause or trigger condition of alarm B.

[0084] For example, assuming that the preset association rule learning algorithm is the Apriori algorithm, the support degree of each single alarm can be determined by the calculation process shown in formula (1):

[0085]

[0086] Among them, Support(A) is the support of each single alarm; A is the item set; count(A) is the number of transactions containing item set A; N is the total number of transactions.

[0087] Exemplarily, first, the entire historical alarm data set is traversed, and the support of each single alarm is calculated by formula (1). If the support of a single alarm is greater than or equal to a preset support threshold, it is added to the frequent 1-item set. Subsequently, frequent 2-item sets, frequent 3-item sets, etc. are generated in an iterative manner until no larger frequent item sets that meet the preset support threshold can be generated.

[0088] For example, assuming that the preset support threshold is 30%, the historical alarm data set includes the following alarm events:

[0089] 1) The optical module is lost (EQPT_TRANSCEIVER_MISSING);

[0090] 2) Communication failure (COMM_FAIL);

[0091] 3) Receive signal loss (RX_LOS);

[0092] 4) Transmit signal loss (TX_LOS).

[0093] The alarm record update table of the historical alarm data set is shown in Table 1:

[0094] Table 1 Alarm record update table

[0095]

[0096] In Table 1:

[0097] 1)EQPT_TRANSCEIVER_MISSING: It appears 4 times, and its support is 0.364, which is greater than the preset support threshold;

[0098] 2) COMM_FAIL: It occurs 5 times, and its support is 0.455, which is greater than the preset support threshold;

[0099] 3) RX_LOS: appears 7 times, and its support is 0.636, which is greater than the preset support threshold;

[0100] 4) TX_LOS: appears 4 times, and its support is 0.364, which is greater than the preset support threshold.

[0101] Therefore, the frequent 1-item sets include: [EQPT_TRANSCEIVER_MISSING, COMM_FAIL, RX_LOS, TX_LOS].

[0102] Furthermore, in the frequent 1-item set:

[0103] 1)EQPT_TRANSCEIVER_MISSING, COMM_FAIL: It occurs twice, and its support is 0.182, which is less than the preset support threshold.

[0104] 2)EQPT_TRANSCEIVER_MISSING, RX_LOS: It appears 3 times, and its support is 0.273, which is less than the preset support threshold.

[0105] 3) EQPT_TRANSCEIVER_MISSING, TX_LOS: It occurs twice, and its support is 0.182, which is less than the preset support threshold.

[0106] 4) COMM_FAIL, RX_LOS: It occurs 3 times, and its support is 0.273, which is less than the preset support threshold.

[0107] 5) COMM_FAIL, TX_LOS: Occurs 0 times, so this item is not considered.

[0108] 6) RX_LOS, TX_LOS: appears 4 times, and its support is 0.364, which is greater than the preset support threshold.

[0109] Therefore, the frequent 2-item sets include: [RX_LOS, TX_LOS]. Since there is no combination that can form a frequent 3-item set that meets the support threshold, no higher-order frequent item sets are generated.

[0110] For example, after determining the frequent item sets, the rule confidence can be calculated according to formula (2):

[0111]

[0112] Among them, A and B are two different item sets; A→B represents the association rule from item set A to item set B; Support(A∪B) represents the proportion of the number of samples where item sets A and item sets B occur simultaneously to the total number of samples; Confidence(A→B) represents the rule confidence between item sets A and item sets B.

[0113] For example, taking the frequent two-item set constructed above as an example, since the frequent two-item set only contains [RX_LOS, TX_LOS], the rule confidence and association rules calculated according to formula (2) are as follows:

[0114] (1) Association rules:

[0115] 1) Rule 1: (RX_LOS→TX_LOS) (loss of received signal leads to loss of transmitted signal);

[0116] 2) Rule 2: (TX_LOS→RX_LOS) (loss of transmit signal results in loss of receive signal).

[0117] (2) The confidence of the rule is:

[0118] 1)Confidence(RX_LOS→TX_LOS)=0.571;

[0119] 2)Confidence(TX_LOS→RX_LOS)=1.

[0120] Based on the above analysis, the rule confidence of Rule 2: (TX_LOS→RX_LOS) is 1, i.e., 100%, indicating that when TX_LOS (transmit signal loss) occurs, RX_LOS (receive signal loss) will definitely occur as well, thereby revealing that TX_LOS may be the direct cause or trigger condition of RX_LOS.

[0121] Based on the above optional embodiments, the historical alarm data is processed using a preset association rule learning algorithm, which can not only determine frequently occurring alarm events and their combinations, but also identify possible causal relationships between alarm events by calculating rule confidence, thereby generating high-confidence association rules, which can help operation and maintenance personnel to more quickly and accurately identify possible root causes of faults when handling current alarms, take effective solutions, improve operation and maintenance efficiency and reduce the risk of business interruption.

[0122] Optionally, in step S123, determining an alarm root cause tree according to the association rule and the historical alarm data includes:

[0123] Step S1231, determining the root node from the historical alarm data according to the preset root node confirmation rule;

[0124] Step S1232, determining the child node according to the association rule, the root node and the historical alarm data;

[0125] Step S1233: construct an alarm root cause tree based on the root node and the child nodes.

[0126] The root node is a specific alarm event selected as the starting point of the alarm root cause tree in alarm analysis. In the alarm analysis scenario of WDM equipment, the root node is usually an alarm that occurs frequently, has a wide impact, or is considered to have a higher priority. The alarm may directly or indirectly trigger a series of other alarm events.

[0127] Exemplarily, assuming that the EQPT_TRANSCEIVER_MISSING alarm event frequently appears in historical data and often leads to a series of subsequent alarms, this event may be selected as the root node.

[0128] The above subnodes refer to the alarm events directly or indirectly triggered by the root node in the alarm root cause tree. The subnodes are located below the root node in the hierarchy and are connected to the root node or other subnodes through preset association rules, reflecting the causal relationship or correlation between alarm events.

[0129] Exemplarily, after determining the root node, a series of association rules are obtained through the Apriori algorithm or other association rule learning algorithms. For example, "Rule: EQPT_TRANSCEIVER_MISSING→COMM_FAIL" indicates that when the "optical module loss" alarm occurs, there is a high probability that the "communication failure" alarm will occur subsequently, with a confidence level of more than 80%. Therefore, the "communication failure" alarm is determined to be a direct child node of the "optical module loss" alarm. Further, continue to traverse the historical alarm data to find other alarm events that are strongly associated with "optical module loss" or "communication failure", such as "RX_LOS" and "TX_LOS", which may also be added to the alarm root cause tree as child nodes.

[0130] For example, an alarm root cause tree in the alarm analysis process is shown in Table 2:

[0131] Table 2 Alarm root cause tree

[0132]

[0133] Table 2 (continued)

[0134] 010101 0101 EQPT_DEG Unit disk hardware degradation alarm HARDWARE 3 010102 0101 FAN_SPD_HIGH Fan speed too high HARDWARE 3 010103 0101 FAN_SPD_LOW Fan speed too low alarm HARDWARE 3 010104 0101 IN_CURR_ABN Input current abnormal alarm HARDWARE 3 010105 0101 IN_CURR_HIGH Input current too high alarm HARDWARE 3 010106 0101 IN_CURR_LOW Input current too low alarm HARDWARE 3 010201 0102 EQPT_DEG Unit disk hardware degradation alarm HARDWARE 3 010202 0102 FAN_SPD_HIGH Fan speed too high HARDWARE 3 010203 0102 FAN_SPD_LOW Fan speed too low alarm HARDWARE 3 … … … … … …

[0135] In Table 2, the identifier is used to track, match and manage alarm events in the database; the parent node ID is used to indicate the directly associated node of the current node. In the alarm root cause tree, each node (except the root node) has a parent node, and the hierarchical relationship between nodes can be constructed through the parent node ID; "HARDWARE" usually refers to alarms related to physical hardware devices; "ETH" represents alarms related to Ethernet interfaces or communications; "OCH" represents alarms related to signal transmission and quality of optical channels; "OSC" represents alarms related to optical monitoring paths; "LOCAL" usually refers to alarms related to the internal equipment or local operating environment.

[0136] Based on the above optional implementation example, an alarm root cause tree is constructed according to the root node and child nodes, which can help operation and maintenance personnel quickly and accurately locate problems, reduce troubleshooting time, and improve decision-making quality. At the same time, it provides automated analysis and suggestions, optimizes resource allocation, and thus significantly enhances network maintenance and service recovery capabilities.

[0137] Optionally, in step S12, an alarm root factor tree is constructed according to current alarm data and a pre-constructed alarm root cause tree, including:

[0138] Step S21, matching the alarm root cause node from the alarm root cause tree according to the current alarm data;

[0139] Step S22, determining a related node from the alarm root cause tree according to the alarm root cause node;

[0140] Step S23: determining the alarm root factor tree according to the associated nodes and the root cause nodes.

[0141] For example, assuming that the current alarm data is "EQPT_DEG", the node information directly related to "EQPT_DEG" in the alarm root cause tree shown in Table 2 is shown in Table 3:

[0142] Table 3 "EQPT_DEG" associated nodes

[0143] 010101 0101 EQPT_DEG Unit disk hardware degradation alarm HARDWARE 3 010201 0102 EQPT_DEG Unit disk hardware degradation alarm HARDWARE 3

[0144] Furthermore, based on the above determined "EQPT_DEG" associated node, the root cause node is traced back to the parent node of the "EQPT_DEG" associated node as shown in Table 4:

[0145] Table 4 "EQPT_DEG" parent node

[0146] 0101 01 EQPT_MISMATCH Unit disk mismatch HARDWARE 2 0102 01 COMM_FAIL Communication failure HARDWARE 2

[0147] Furthermore, the parent nodes of "EQPT_MISMATCH" and "COMM_FAIL" are shown in Table 5:

[0148] Table 5 Parent nodes of "EQPT_MISMATCH" and "COMM_FAIL"

[0149]

[0150] In Table 5, the parent node ID of "EQPT_ABSENCE_WARNING" is 0, which means that the current alarm event has no parent node, that is, "EQPT_ABSENCE_WARNING" is the root cause node of "EQPT_DEG".

[0151] Exemplarily, the alarm root factor tree may be determined according to the associated nodes and root cause nodes of "EQPT_DEG".

[0152] Based on the above optional embodiments, determining the alarm root factor tree according to the associated nodes and the root cause nodes can provide a more systematic, efficient and accurate fault analysis tool for network maintenance, helping the operation and maintenance team to identify and solve network problems more quickly, thereby ensuring the stable operation of the network and the continuity of business.

[0153] Optionally, in step S22, the types of the alarm root cause node include a first-level node, a second-level node, and a third-level node, and according to the alarm root cause node, determining the associated node from the alarm root cause tree includes:

[0154] Step S221, in response to the alarm root cause node being a first-level node, determining that the associated node is a null value;

[0155] Step S222, or, in response to the type of the alarm root cause node being a level 2 node, determining a level 1 node and a level 3 node associated with the alarm root cause node as associated nodes;

[0156] Step S223, or, in response to the type of the alarm root cause node being a level 3 node, determining a level 2 node and a level 1 node associated with the alarm root cause node as associated nodes.

[0157] Exemplarily, still taking "EQPT_DEG" as an example, its root cause node "EQPT_ABSENCE_WARNING" is a first-level node, "EQPT_MISMATCH" and "COMM_FAIL" are second-level nodes, and "EQPT_DEG" itself is a third-level node.

[0158] Based on the above optional embodiments, by determining the level of the alarm root cause node and searching for its associated nodes accordingly, a more accurate and targeted alarm root factor tree can be constructed, thereby significantly improving the efficiency of fault diagnosis and resolution.

[0159] Optionally, in step S13, determining an alarm root cause result tree according to current alarm data and the alarm root factor tree includes:

[0160] Step S131, acquiring associated alarm data associated with current alarm data according to the alarm root factor tree;

[0161] Step S132, matching the associated alarm data to the alarm root factor tree and adding alarm processing suggestions to the alarm root factor tree to obtain an alarm root cause result tree.

[0162] Exemplarily, assuming that the current alarm is a third-level node "EQPT_DEG", by traversing the node relationship in the alarm root factor tree, the wavelength division equipment alarm analysis system will find the node directly associated with "EQPT_DEG" in the alarm root factor tree, and continue to find all second-level and first-level nodes directly or indirectly associated with the current alarm. Further, after obtaining the associated node of "EQPT_DEG", the wavelength division equipment alarm analysis system will collect the alarm time, alarm type, alarm level, equipment identification and other information of the above-mentioned associated nodes. After obtaining all the associated alarm data, the wavelength division equipment alarm analysis system will match the above data to the corresponding position of the alarm root factor tree, and add specific processing suggestions for each associated alarm node. For each matched alarm node, the wavelength division equipment alarm analysis system will provide corresponding processing suggestions based on the preset fault response strategy or expert maintenance knowledge base.

[0163] Based on the above optional embodiments, fault analysis and handling suggestions are integrated into a structured model, which improves the standardization and automation of the fault handling process, reduces human errors, and improves operation and maintenance efficiency.

[0164] Figure 2 is a schematic diagram of a wavelength division equipment alarm analysis method according to one embodiment of the present disclosure, such as Figure 2 As shown, in the process of analyzing the alarm of wavelength division equipment, first, the acquisition module is used to obtain the equipment alarm events and resource models, and the alarm root cause tree of all rules is constructed based on the prior association analysis algorithm of the association rules. Then, based on the above alarm root cause tree, the alarm root factor tree corresponding to the current alarm and the current node position are constructed. Subsequently, the corresponding resource alarm is added to the relevant alarm list according to the resource tree type. Finally, the relevant alarm is matched to the corresponding alarm root cause tree, and the corresponding alarm matching suggestion is given, and the root cause alarm list and alarm suggestion list data are output.

[0165] Figure 3 is a schematic diagram of a wavelength division equipment alarm analysis system according to one embodiment of the present disclosure, such as Figure 3 As shown, the system includes: a box-type wavelength division device, an alarm collection module, an alarm analysis module, an alarm matching module, an alarm display module and a graphical user interface. Among them, the alarm collection module is used to obtain the alarm information of the box-type wavelength division device and input the target alarm into the alarm analysis module; the alarm analysis module is used to analyze and process the target alarm and generate a corresponding alarm root cause tree; the alarm matching module is used to generate an alarm root cause result tree according to the target alarm and the alarm root cause tree; the alarm display module is used to display the alarm root cause result tree on the graphical user interface.

[0166] Figure 4 is a schematic diagram of another wavelength division equipment alarm analysis method according to one embodiment of the present disclosure, such as Figure 4 As shown, when the original analysis alarm is received, it must first be converted into an alarm root cause node, and at the same time, the original alarm of the same resource as the original analysis alarm is queried in the database. Furthermore, for the alarm root cause node constructed above, the alarm root factor tree framework is constructed with the node as the core and based on the filtered root cause tree total template. Finally, the corresponding positions of the original alarm of the same resource and the alarm root factor tree framework are matched to generate the alarm root cause result tree.

[0167] Figure 5 is a schematic diagram of another wavelength division equipment alarm analysis method according to one embodiment of the present disclosure, such as Figure 5 As shown, first, the alarm resource and the root cause tree template are used as input to obtain the tree node where the current alarm is located, the alarm root cause node. Specifically, the corresponding alarm type is converted according to the alarm code name and the resource type, and the specific node information is obtained through the alarm code name and the alarm type. The above node information includes but is not limited to the root cause tree node type, identification, hierarchy, etc. Secondly, construct the node tree of each level of the type to which the alarm belongs, and the alarm root factor tree framework. Specifically, the upper level nodes are saved based on the alarm, and the lower level nodes are saved based on the alarm, and then the overall alarm root factor tree framework is synthesized. Further, all alarms of this category are obtained, and the relevant alarms are traversed to determine whether the coding and hierarchy are consistent. According to the rules of the alarm tree, the coding and resources are matched to the corresponding position. Finally, the root cause result tree of the corresponding alarm is generated, and the corresponding alarm and suggestion are matched.

[0168] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present disclosure.

[0169] In the embodiments of the present disclosure, a wavelength division equipment alarm analysis device is also provided, which is used to implement the above embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0170] Figure 6is a structural block diagram of a wavelength division equipment alarm analysis device according to one embodiment of the present disclosure, such as Figure 6 As shown, the device comprises:

[0171] An acquisition module 601 is used to acquire current alarm data of a wavelength division device;

[0172] A construction module 602 is used to construct an alarm root factor tree according to current alarm data and a pre-constructed alarm root cause tree, wherein the alarm root factor tree is used to represent the root cause tree corresponding to the alarm data;

[0173] The determination module 603 is used to determine the alarm root cause result tree according to the current alarm data and the alarm root factor tree, wherein the alarm root cause result data includes an alarm list and an alarm suggestion;

[0174] The output module 604 is used to output the alarm analysis result according to the alarm root cause result tree.

[0175] Optionally, the construction module 602 is also used to: obtain historical alarm data, wherein the historical alarm data includes multiple alarm data corresponding to multiple wavelength division devices; process the historical alarm data using a preset association rule learning algorithm to determine association rules; and determine an alarm root cause tree based on the association rules and the historical alarm data.

[0176] Optionally, the construction module 602 is also used to: traverse the historical alarm data based on a preset association rule learning algorithm to determine the support of each single alarm, wherein the historical alarm data includes multiple single alarms; determine frequent item sets based on the support and a preset support threshold; determine rule confidence based on the frequent item sets; determine association rules based on the rule confidence and a preset confidence threshold.

[0177] Optionally, the construction module 602 is further used to: determine the root node from the historical alarm data according to a preset root node confirmation rule; determine the child node according to the association rule, the root node and the historical alarm data; and construct an alarm root cause tree according to the root node and the child nodes.

[0178] Optionally, the construction module 602 is further used to: match an alarm root cause node from the alarm root cause tree according to current alarm data; determine an associated node from the alarm root cause tree according to the alarm root cause node; and determine an alarm root factor tree according to the associated node and the root cause node.

[0179] Optionally, construction module 602 is also used to: in response to the type of the alarm root cause node being a first-level node, determine that the associated node is a null value; or, in response to the type of the alarm root cause node being a second-level node, determine the first-level node and the third-level node associated with the alarm root cause node as associated nodes; or, in response to the type of the alarm root cause node being a third-level node, determine the second-level node and the first-level node associated with the alarm root cause node as associated nodes.

[0180] Optionally, the determination module 603 is further used to: obtain associated alarm data associated with the current alarm data according to the alarm root factor tree; match the associated alarm data to the alarm root factor tree and add alarm processing suggestions to the alarm root factor tree to obtain an alarm root cause result tree.

[0181] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0182] According to one embodiment of the present disclosure, an electronic device is also provided, including: a memory storing an executable program; and a processor for running the program, wherein the wavelength division equipment alarm analysis method in the embodiment of the present disclosure is executed when the program is running.

[0183] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0184] S1, obtain the current alarm data of the wavelength division equipment;

[0185] S2, constructing an alarm root factor tree according to the current alarm data and the pre-constructed alarm root cause tree, wherein the alarm root factor tree is used to represent the root cause tree corresponding to the alarm data;

[0186] S3, determining an alarm root cause result tree according to current alarm data and the alarm root factor tree, wherein the alarm root cause result includes an alarm list and alarm handling suggestions;

[0187] S4: Output the alarm analysis result according to the alarm root cause result tree.

[0188] According to one embodiment of the present disclosure, a computer-readable storage medium is also provided, which includes a stored executable program, wherein when the executable program runs, the device where the storage medium is located is controlled to execute the wavelength division equipment alarm analysis method in the embodiment of the present disclosure.

[0189] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0190] S1, obtain the current alarm data of the wavelength division equipment;

[0191] S2, constructing an alarm root factor tree according to the current alarm data and the pre-constructed alarm root cause tree, wherein the alarm root factor tree is used to represent the root cause tree corresponding to the alarm data;

[0192] S3, determining an alarm root cause result tree according to current alarm data and the alarm root factor tree, wherein the alarm root cause result includes an alarm list and alarm handling suggestions;

[0193] S4: Output the alarm analysis result according to the alarm root cause result tree.

[0194] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0195] According to one embodiment of the present disclosure, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, the wavelength division device alarm analysis method in the embodiment of the present disclosure is implemented.

[0196] Optionally, in this embodiment, the computer program product may be configured as a computer program for executing the following steps:

[0197] S1, obtain the current alarm data of the wavelength division equipment;

[0198] S2, constructing an alarm root factor tree according to the current alarm data and the pre-constructed alarm root cause tree, wherein the alarm root factor tree is used to represent the root cause tree corresponding to the alarm data;

[0199] S3, determining an alarm root cause result tree according to current alarm data and the alarm root factor tree, wherein the alarm root cause result includes an alarm list and alarm handling suggestions;

[0200] S4: Output the alarm analysis result according to the alarm root cause result tree.

[0201] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0202] In the above embodiments of the present disclosure, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0203] In the several embodiments provided in the present disclosure, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0204] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0205] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0206] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0207] The above is only a preferred embodiment of the present disclosure. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present disclosure. These improvements and modifications should also be regarded as the scope of protection of the present disclosure.

Claims

1. A wavelength division equipment alarm analysis method, characterized in that: include: Get the current alarm data of the WDM equipment; Constructing an alarm root factor tree according to the current alarm data and a pre-constructed alarm root cause tree, wherein the alarm root factor tree is used to characterize the root cause tree corresponding to the alarm data; Determine an alarm root cause result tree according to the current alarm data and the alarm root factor tree, wherein the alarm root cause result includes an alarm list and alarm handling suggestions; According to the alarm root cause result tree, the alarm analysis result is output.

2. The wavelength division equipment alarm analysis method according to claim 1, characterized in that: The alarm data includes: alarm time, alarm type, alarm level, and device identification.

3. The wavelength division equipment alarm analysis method according to claim 1, characterized in that: The construction of the alarm root cause tree includes: Acquire historical alarm data, wherein the historical alarm data includes multiple alarm data corresponding to multiple wavelength division devices; Processing the historical alarm data using a preset association rule learning algorithm to determine association rules; The alarm root cause tree is determined according to the association rule and the historical alarm data.

4. The wavelength division equipment alarm analysis method according to claim 3, characterized in that: The method of processing the historical alarm data using a preset association rule learning algorithm to determine the association rule includes: Based on the preset association rule learning algorithm, the historical alarm data is traversed to determine the support degree of each single alarm, wherein the historical alarm data includes multiple single alarms; Determining frequent itemsets according to the support and a preset support threshold; Determining the rule confidence according to the frequent item set; The association rule is determined according to the rule confidence and a preset confidence threshold.

5. The wavelength division equipment alarm analysis method according to claim 3, characterized in that: The step of determining the alarm root cause tree according to the association rule and the historical alarm data includes: Determine the root node from the historical alarm data according to a preset root node confirmation rule; Determine a child node according to the association rule, the root node and the historical alarm data; The alarm root cause tree is constructed according to the root node and the child nodes.

6. The wavelength division equipment alarm analysis method according to claim 1, characterized in that: The step of constructing an alarm root factor tree according to the current alarm data and the pre-constructed alarm root cause tree includes: According to the current alarm data, matching the alarm root cause node from the alarm root cause tree; According to the alarm root cause node, determining a related node from the alarm root cause tree; The alarm root factor tree is determined according to the associated nodes and the root cause nodes.

7. The wavelength division equipment alarm analysis method according to claim 6, characterized in that: The types of the alarm root cause node include a primary node, a secondary node, and a tertiary node, and the determining, according to the alarm root cause node, an associated node from the alarm root cause tree includes: In response to the type of the alarm root cause node being the first-level node, determining that the associated node is a null value; or, in response to the type of the alarm root cause node being a level 2 node, determining a level 1 node and a level 3 node associated with the alarm root cause node as the associated nodes; Or, in response to the type of the alarm root cause node being a level 3 node, a level 2 node and a level 1 node associated with the alarm root cause node are determined as the associated nodes.

8. The wavelength division equipment alarm analysis method according to claim 1, characterized in that: The step of determining an alarm root cause result tree according to the current alarm data and the alarm root factor tree includes: According to the alarm root factor tree, acquiring associated alarm data associated with the current alarm data; The associated alarm data is matched to the alarm root factor tree and the alarm processing suggestion is added to the alarm root factor tree to obtain the alarm root cause result tree.

9. A wavelength division equipment alarm analysis device, characterized in that: include: An acquisition module is used to obtain the current alarm data of the wavelength division device; A construction module, configured to construct an alarm root factor tree according to the current alarm data and a pre-constructed alarm root cause tree, wherein the alarm root factor tree is used to characterize a root cause tree corresponding to the alarm data; A determination module, configured to determine an alarm root cause result tree according to the current alarm data and the alarm root factor tree, wherein the alarm root cause result data includes an alarm list and an alarm suggestion; The output module is used to output the alarm analysis result according to the alarm root cause result tree.

10. An electronic device, characterized in that: include: A memory storing an executable program; A processor, configured to run the program, wherein the program executes the method according to any one of claims 1 to 8 when running.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is executed, the device where the storage medium is located is controlled to execute the method according to any one of claims 1 to 8.

12. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 8.

Images