Fault finding method, device and equipment of monitoring system and storage medium

Abstract

The application discloses a fault finding method, device and equipment of a monitoring system and a storage medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: when detecting that a total fault index is abnormal, obtaining a current value of a leaf element, obtaining a deviation degree set based on the current value and calculating a root cause potential score; based on the root cause potential score, performing screening to obtain a root cause set and deleting descendant leaf elements; and if a set condition is met, taking the current root cause set as a fault root cause. In the application, when the deviation degree of the leaf element is calculated, the calculation amount is small, the descendant leaf elements are deleted after the candidate root cause elements are screened, the iterative calculation amount of each layer of candidate root cause elements is reduced, the finding speed is improved, and the preset set condition improves the accuracy of the found root cause, that is, the efficiency of fault finding of the monitoring system is improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method, apparatus, device and storage medium for fault finding in a monitoring system. Background Technology

[0002] Currently, the scale of cloud computing continues to expand, which places higher demands on the operational reliability of corresponding monitoring systems. Timely and accurate diagnosis of faults when they occur is one of the factors that measure system operation and maintenance capabilities.

[0003] When a monitoring system malfunctions, time-series indicators are acquired, and the root cause is searched by traversing all dimensions of the time-series indicators. However, when the computational dimensions are large, determining the potential root cause score of elements based on Euclidean distance is very time-consuming. The large amount of computational tasks reduces the speed of root cause search. Furthermore, the search for root causes relies on manual parameter tuning, which is highly dependent on the personnel's experience in parameter tuning. The accuracy of the root cause search results is not high. In other words, the existing technology has the problem of low efficiency in finding the cause of faults in the monitoring system.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this invention is to provide a method, apparatus, device, and storage medium for fault finding in monitoring systems, aiming to solve the problem of low efficiency in fault finding in existing technologies.

[0006] To achieve the above objectives, this application provides a fault diagnosis method for a monitoring system, the method comprising:

[0007] When an abnormality is detected in the total fault index of the monitoring system, the current value of the preset leaf element is obtained, wherein the leaf element and non-leaf element together form a data cube of candidate root cause elements, and the data cube is multi-layered;

[0008] Based on the current value, calculate the deviation of the leaf element to obtain a deviation set;

[0009] Based on the deviation set, the potential root cause score corresponding to each layer of candidate root cause elements is calculated according to the order of aggregation degree of the candidate root cause elements in the data cube from low to high.

[0010] Based on the root cause potential score, the candidate root cause elements are filtered, the filtered root cause elements are added to the root cause set, and the descendant leaf elements of the root cause elements are deleted from the data cube.

[0011] Determine whether the root cause set meets the preset set conditions. If so, the current root cause set is taken as the root cause of the monitoring system failure.

[0012] In one possible implementation of this application, the step of calculating the root cause potential score corresponding to each candidate root cause element based on the deviation set includes:

[0013] Based on the aforementioned set of deviations, the partition threshold is determined;

[0014] Based on the partitioning threshold, the leaf elements are partitioned to obtain normal leaf areas and abnormal leaf areas.

[0015] Based on the partition threshold and the deviation, a first weight of each leaf element in the normal leaf region and a second weight of each leaf element in the abnormal leaf region are determined.

[0016] Based on the first weight and the second weight, the root cause potential score corresponding to each candidate root cause element is calculated.

[0017] In one possible implementation of this application, the step of calculating the root cause potential score corresponding to each candidate root cause element based on the first weight and the second weight includes:

[0018] Based on the first weight and the second weight, the potential score of the first root cause is calculated;

[0019] Based on the current value of the descendant leaf element and the predicted value of the descendant leaf element, the second root cause potential score is calculated, wherein the predicted value of the descendant leaf element is proportional to the predicted value of the candidate root cause element.

[0020] The root cause potential score is calculated based on the first root cause potential score and the second root cause potential score, wherein when the candidate root cause element is the leaf element, the second root cause potential score is 0.

[0021] In one possible implementation of this application, the step of determining the partition threshold based on the deviation set includes:

[0022] Determine the distribution of the deviation set, wherein the distribution includes the expected value;

[0023] Based on the distribution, a first number of maximum values ​​and a second number of minimum values ​​are removed from the deviation, wherein the distribution of the deviation after removal includes the left endpoint and the right endpoint.

[0024] The partition threshold is determined based on the deviation of the expected value between the left endpoint and the right endpoint;

[0025] Wherein, the absolute value of the left endpoint and the expected value is the first absolute value, and the absolute value of the right endpoint and the expected value is the second absolute value. If the first absolute value is less than the second absolute value, then the expected value is the average value of the left endpoint and the partition threshold. If the first absolute value is greater than the second absolute value, then the expected value is the average value of the right endpoint and the partition threshold.

[0026] In one possible implementation of this application, the step of calculating the deviation degree of the leaf element based on the current value to obtain the deviation degree set includes:

[0027] Based on the current value, the current value of the non-leaf element is calculated;

[0028] Based on the current value, the predicted value of the leaf element is calculated;

[0029] Based on the predicted values ​​of the leaf elements, the predicted values ​​of the non-leaf elements are calculated.

[0030] Based on the current value of the non-leaf element and the predicted value of the non-leaf element, the deviation degree of the leaf element is calculated to obtain a deviation degree set, wherein the deviation degree of leaf elements with the same root cause is equal.

[0031] In one possible implementation of this application, the step of screening candidate root cause elements based on the root cause potential score and adding the screened root cause elements to the root cause set includes:

[0032] Based on the root cause potential score, the candidate root cause elements are filtered, wherein the candidate root cause elements whose root cause potential score is greater than a preset root cause threshold are retained.

[0033] If there are multiple candidate root cause elements in the same layer of the data cube, then root cause elements are selected from the retained candidate root cause elements based on the set conditions.

[0034] Add the selected root cause elements to the root cause set.

[0035] In one possible implementation of this application, the step of determining whether the root cause set meets a preset set condition includes:

[0036] Determine whether the root cause set meets a preset set condition, wherein it is determined whether the explanatory power of the elements in the root cause set is higher than a preset explanatory power threshold.

[0037] If not, return to the step of calculating the potential root cause score corresponding to each candidate root cause element based on the bias set, according to the order of aggregation degree of the candidate root cause elements in the data cube from low to high, to obtain the root cause set, until the explanatory power of the elements in the root cause set is higher than the explanatory power threshold.

[0038] Furthermore, to achieve the above objectives, this application also provides a fault finding device for a monitoring system, the fault finding device for a monitoring system comprising:

[0039] The acquisition module is used to acquire the current value of preset leaf elements when an abnormality is detected in the total fault index of the monitoring system. The leaf elements and non-leaf elements together form a data cube of candidate root cause elements, and the data cube is multi-layered.

[0040] The first calculation module is used to calculate the deviation degree of the leaf element based on the current value, and obtain a deviation degree set;

[0041] The second calculation module is used to calculate the root cause potential score corresponding to each layer of candidate root cause elements based on the deviation set, according to the order of aggregation degree of the candidate root cause elements in the data cube from low to high.

[0042] The filtering module is used to filter the candidate root cause elements based on the root cause potential score, add the filtered root cause elements to the root cause set, and delete the leaf elements associated with the root cause elements from the data cube.

[0043] The judgment module is used to determine whether the root cause set meets the preset set conditions. If so, the current root cause set is taken as the root cause of the monitoring system failure.

[0044] In addition, to achieve the above objectives, this application also provides a fault finding device for a monitoring system. The fault finding device for the monitoring system is a physical node device. The fault finding device for the monitoring system includes: a memory, a processor, and a fault finding program for the monitoring system stored in the memory and executable on the processor. The processor executes the fault finding program for the monitoring system to implement the steps of the fault finding method for the monitoring system.

[0045] In addition, to achieve the above objectives, this application also provides a storage medium storing a program for implementing a fault finding method for a monitoring system. When the fault finding program for the monitoring system is executed by a processor, it implements the steps of the fault finding method for the monitoring system described above.

[0046] This application provides a method, apparatus, device, and storage medium for fault finding in a monitoring system. Compared with the low efficiency of fault finding in existing technologies, this application, when an abnormality is detected in the overall fault index of the monitoring system, obtains the current value of a preset leaf element, wherein the leaf element and non-leaf elements together form a data cube of candidate root cause elements, and the data cube has multiple layers; based on the current value, calculates the deviation degree of the leaf element to obtain a deviation degree set; according to the aggregation degree of the candidate root cause elements in the data cube from low to high, calculates the root cause potential score corresponding to each layer of candidate root cause elements based on the deviation degree set; based on the root cause potential score, filters the candidate root cause elements, adds the filtered root cause elements to the root cause set, and deletes the descendant leaf elements of the root cause elements from the data cube; determines whether the root cause set meets the preset set conditions, and if so, takes the current root cause set as the root cause of the monitoring system's fault. In this application, the computational load is small when calculating the deviation of leaf elements. Candidate root cause elements are screened according to the order of aggregation degree from low to high. After screening, the corresponding descendant leaf elements are deleted, which reduces the iterative computation load of each layer of candidate root cause elements, improves the speed of fault finding, and determines whether the obtained root cause set meets the set conditions, which improves the accuracy of the found root cause, that is, improves the efficiency of fault finding in the monitoring system. Attached Figure Description

[0047] Figure 1 This is a schematic flowchart of the solution involved in the first embodiment of this application;

[0048] Figure 2 This is a schematic flowchart of the solution involved in the third embodiment of this application;

[0049] Figure 3 This is a schematic flowchart of the solution involved in the fourth embodiment of this application;

[0050] Figure 4 This is a logical architecture diagram of the fault finding device of the monitoring system according to the fifth embodiment of this application;

[0051] Figure 5 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the fault finding method of the monitoring system in this application.

[0052] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0053] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0054] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, components, features, and elements with the same names in different embodiments of this application may have the same meaning or different meanings, the specific meaning of which must be determined by its interpretation in that specific embodiment or further in conjunction with the context of that specific embodiment.

[0055] It should be understood that although the terms first, second, third, etc., may be used herein to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this document, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if," as used herein, may be interpreted as "when," "when," or "in response to determination." Furthermore, as used herein, the singular forms "a," "an," and "the" are intended to also include the plural forms unless the context indicates otherwise. It should be further understood that the terms "comprising," "including," indicate the presence of the stated feature, step, operation, element, component, item, kind, and / or group, but do not exclude the presence, occurrence, or addition of one or more other features, steps, operations, elements, components, items, kinds, and / or groups. The terms "or," "and / or," "including at least one of the following," etc., as used in this application, may be interpreted as inclusive, or mean any one or any combination thereof. For example, "including at least one of the following: A, B, C" means "any one of the following: A; B; C; A and B; A and C; B and C; A and B and C." Similarly, "A, B, or C" or "A, B, and / or C" means "any one of the following: A; B; C; A and B; A and C; B and C; A and B and C." Exceptions to this definition only occur when the combination of elements, functions, steps, or operations is inherently mutually exclusive in some way.

[0056] It should be understood that although the steps in the flowcharts of this application's embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0057] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0058] It should be noted that step designations such as S10 and S20 are used in this document for the purpose of more clearly and concisely describing the corresponding content, and do not constitute a substantial limitation on the order. In specific implementation, those skilled in the art may execute S20 first and then S10, etc., but these should all be within the protection scope of this application.

[0059] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0060] In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the purpose of illustrative purposes and has no specific meaning in itself. Therefore, "module," "part," or "unit" may be used interchangeably.

[0061] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0062] Example 1

[0063] This application provides a fault finding method for a monitoring system. In the common embodiments of the fault finding method for the monitoring system in this application, refer to... Figure 1 The fault finding method of the monitoring system includes:

[0064] Step S10: When an abnormality is detected in the total fault index of the monitoring system, the current value of the preset leaf element is obtained, wherein the leaf element and non-leaf element together form a data cube of candidate root cause elements, and the data cube is multi-layered.

[0065] Step S20: Based on the current value, calculate the deviation degree of the leaf element to obtain a deviation degree set;

[0066] Step S30: Based on the bias set, calculate the potential root cause score corresponding to each layer of candidate root cause elements according to the order of aggregation degree of the candidate root cause elements in the data cube from low to high.

[0067] Step S40: Based on the root cause potential score, filter the candidate root cause elements, add the filtered root cause elements to the root cause set, and delete the descendant leaf elements of the root cause elements from the data cube.

[0068] Step S50: Determine whether the root cause set meets the preset set conditions. If so, use the current root cause set as the root cause of the monitoring system failure.

[0069] This embodiment aims to improve the efficiency of troubleshooting in monitoring systems.

[0070] As an example, the monitoring system could be a cloud monitoring system, monitoring network operation or storage status, without being specifically limited here.

[0071] As an example, the total failure index (M) serves as a standard for measuring whether a monitoring system has malfunctioned. If M is normal, it indicates that the monitored items are operating normally; if M is abnormal, it indicates that the monitored items have malfunctioned. Individual time-series indicators are aggregated according to a standard for fault monitoring. The aggregated indicators can be considered multi-dimensional time-series indicators. When the aggregated multi-dimensional time-series indicators generate a fault alarm, the root cause of the fault needs to be quickly located (fault cause analysis) to provide a basis for subsequent fault handling solutions.

[0072] In this embodiment, time-series indicators from different dimensions are aggregated to obtain aggregated multi-dimensional time-series indicators (elements). As an example, the monitoring system monitors the network situation in region a, which includes multiple dimensions such as city dimension, router dimension, and model dimension in region a.

[0073] Elements include leaf elements and non-leaf elements, with leaf elements being the finest granular element.

[0074] In this embodiment, leaf elements and non-leaf elements together form a data cube of candidate root cause elements, and the data cube has multiple layers. In the data cube, each element may be a root cause element, so every element in the data cube, whether a leaf element or a non-leaf element, is a candidate root cause element.

[0075] When an anomaly is detected in the overall fault index of the monitoring system, the current value of a preset leaf element is obtained. Based on the current value, the deviation degree of the leaf element is calculated to obtain a deviation degree set. According to the aggregation degree of the candidate root cause elements in the data cube from low to high, the root cause potential score corresponding to each layer of candidate root cause elements is calculated based on the deviation degree set. Based on the root cause potential score, the candidate root cause elements are filtered, and the filtered root cause elements are added to the root cause set. The descendant leaf elements of the root cause elements are deleted from the data cube. It is determined whether the root cause set meets the preset set conditions. If so, the current root cause set is taken as the root cause of the fault of the monitoring system.

[0076] The specific steps are as follows:

[0077] Step S10: When an abnormality is detected in the total fault index of the monitoring system, the current value of the preset leaf element is obtained, wherein the leaf element and non-leaf element together form a data cube of candidate root cause elements, and the data cube is multi-layered.

[0078] Step S20: Based on the current value, calculate the deviation degree of the leaf element to obtain a deviation degree set;

[0079] In this embodiment, the deviation of the leaf element reflects the discrepancy between the actual value and the predicted value of the leaf element. The current value of the leaf element is its actual value.

[0080] When an abnormality is detected in the overall fault index of the monitoring system, the current value of the preset leaf element is obtained. Based on the current value, the deviation degree of the leaf element is calculated. If there are multiple leaf elements, there are multiple deviation degrees, thus obtaining a set of deviation degrees.

[0081] Step S20, which involves calculating the deviation of the leaf element based on the current value to obtain the deviation set, includes steps S21-S24:

[0082] Step S21: Calculate the current value of the non-leaf element based on the current value;

[0083] In this embodiment, since leaf elements and non-leaf elements together form a data cube, the current value v of the non-leaf elements can be calculated based on the current value of the leaf elements and the aggregation relationship between the elements in the data cube.

[0084] Step S22: Based on the current value, calculate the predicted value of the leaf element;

[0085] As an example, based on the current value at the time of failure and the current values ​​at several times before the time of failure, the predicted value of the leaf element can be inferred and calculated.

[0086] Step S23: Based on the predicted values ​​of the leaf elements, calculate the predicted values ​​of the non-leaf elements;

[0087] In this embodiment, the predicted value f of non-leaf elements that have an aggregation relationship with the leaf elements is calculated from the predicted value of the leaf elements.

[0088] Step S24: Based on the current value of the non-leaf element and the predicted value of the non-leaf element, calculate the deviation degree of the leaf element to obtain a deviation degree set, wherein the deviation degree of leaf elements with the same root cause is equal.

[0089] In this embodiment, the deviation ds of the leaf elements is calculated based on the current value v of the non-leaf elements and the predicted value f of the non-leaf elements. The calculation method is as follows:

[0090]

[0091] Calculate the deviation degree ds for each leaf element to obtain the deviation degree set. The deviation degrees of leaf elements with the same root cause are equal.

[0092] Step S30: Based on the bias set, calculate the potential root cause score corresponding to each layer of candidate root cause elements according to the order of aggregation degree of the candidate root cause elements in the data cube from low to high.

[0093] As an example, the order of aggregation degree of candidate root cause elements from low to high is the same as the order from top to bottom in the data cube. If the data cube has multiple layers, the root cause potential score is calculated for each candidate root cause element layer by layer from top to bottom. The higher the root cause potential score, the greater the probability that the current candidate root cause element is the real root cause element.

[0094] Step S30, which involves calculating the root cause potential score corresponding to each candidate root cause element based on the deviation set, includes steps S31-S34:

[0095] Step S31: Determine the partition threshold based on the deviation set;

[0096] As an example, the partition threshold is t.

[0097] Step S32: Based on the partitioning threshold, partition the leaf elements to obtain normal leaf areas and abnormal leaf areas;

[0098] Since each leaf element has a corresponding deviation, some leaf elements may be root causes, or some non-leaf elements corresponding to leaf elements may be root causes. Therefore, based on the partitioning threshold, all leaf elements are divided into two regions: the normal leaf region and the abnormal leaf region.

[0099] During partitioning, specifically, as an example, the deviation of a normal leaf area, as perceived by the user, is around 0, while the deviation of an abnormal leaf area is significantly different from 0. Therefore, based on a partitioning threshold of 0.5, leaf elements with a deviation range of -0.5 to 0.5 are classified as normal leaf areas, and leaf elements with a deviation range of 0.5 to 1.5 are classified as abnormal leaf areas.

[0100] Step S33: Based on the partition threshold and the deviation, determine the first weight of each leaf element in the normal leaf region and the second weight of each leaf element in the abnormal leaf region;

[0101] In this embodiment, each leaf element in the normal leaf region corresponds to a weight, which is the first weight. The first weights of the leaf elements can be equal or unequal. Similarly, each leaf element in the abnormal leaf region corresponds to a weight, which is the second weight. The second weights of the leaf elements can be equal or unequal.

[0102] In this embodiment, the first weight is determined based on the partition threshold t and the deviation as follows:

[0103] w1 = min{t - ds, 1}

[0104] The second weight is determined based on the partition threshold t and the deviation as follows:

[0105] w2 = min{ds, 1}

[0106] Based on the above weight determination method, the first weight of the leaf element in the normal leaf area and the second weight of the leaf element in the abnormal leaf area are obtained respectively.

[0107] Step S34: Based on the first weight and the second weight, calculate the root cause potential score corresponding to each candidate root cause element.

[0108] In this embodiment, there are multiple candidate root cause elements in the current layer of the data cube, and the corresponding root cause potential score is calculated for each candidate root cause element.

[0109] As an example, in a data cube, a candidate root cause element has multiple descendant leaf elements. When calculating the root cause potential score of the current candidate root cause element, only its corresponding descendant leaf elements are selected for calculation. Specifically, the sum of the first weights (W1) of the normal leaf areas and the sum of the second weights (W2) of the abnormal leaf areas are calculated for each descendant leaf element. For example, if the current candidate root cause element corresponds to 5 descendant leaf elements, of which 3 are normal leaf areas and 2 are abnormal leaf areas, then the sum of the first weights of the 3 descendant leaf elements is W1, and the sum of the second weights of the 2 descendant leaf elements is W2. Therefore, the root cause potential score of the current candidate root cause element is P1 = W2 / (W1 + W2 + 1).

[0110] Step S40: Based on the root cause potential score, filter the candidate root cause elements, add the filtered root cause elements to the root cause set, and delete the descendant leaf elements of the root cause elements from the data cube.

[0111] In this embodiment, multiple candidate root cause elements in the current layer are screened based on the calculated root cause potential score P1. Since a higher root cause potential score indicates a higher probability of being a true root cause element, the candidate root cause element with the highest root cause potential score is selected as the root cause element. The screened root cause element is added to the root cause set, and the descendant leaf elements of the root cause element are deleted from the data cube.

[0112] Step S50: Determine whether the root cause set meets the preset set conditions. If so, use the current root cause set as the root cause of the monitoring system failure.

[0113] In this embodiment, after obtaining the root cause set, it is necessary to determine whether the root cause set meets the conditions. Only when the conditions are met can the current root cause set be used as the root cause of the monitoring system's failure.

[0114] As an example, the set condition is a preset interpretability threshold.

[0115] As an example, the explanatory power of elements in the root cause set is calculated as follows: select leaf elements belonging to the abnormal leaf area in the root cause set, subtract the actual value from the predicted value of these leaf elements to obtain the abnormal difference value, subtract the actual value from the predicted value of the total fault index to obtain the total index difference value, and the quotient of the abnormal difference value and the total index difference value is the explanatory power of elements in the root cause set.

[0116] The higher the explanatory power, the stronger the explanatory power of the corresponding root cause set for the system's failure. If the explanatory power is higher than the preset explanatory power threshold, the current root cause set will be used as the root cause of the system's failure.

[0117] In step S50, the step of determining whether the root cause set meets the preset set conditions includes steps S51-S52:

[0118] Step S51: Determine whether the root cause set meets the preset set conditions, wherein it is determined whether the explanatory power of the elements in the root cause set is higher than the preset explanatory power threshold.

[0119] Step S52, if not, return to the step of calculating the potential root cause score corresponding to each layer of candidate root cause elements based on the bias set, according to the order of aggregation degree of the candidate root cause elements in the data cube from low to high, to obtain the root cause set, until the explanatory power of the elements in the root cause set is higher than the explanatory power threshold.

[0120] In this embodiment, if the explanatory power is lower than a preset explanatory power threshold, the process returns to the step of calculating the potential root cause score for each layer of candidate root cause elements based on the bias set, in ascending order of the aggregation degree of the candidate root cause elements in the data cube. The potential root cause score for the next layer of candidate root cause elements is then calculated, and a new root cause set is obtained. If the explanatory power of elements in the new root cause set does not meet the explanatory power threshold, the loop continues until the explanatory power of elements in the root cause set exceeds the explanatory power threshold. When the explanatory power of an element exceeds the preset explanatory power threshold, the current root cause set is taken as the root cause of the monitoring system's failure.

[0121] This application provides a method, apparatus, device, and storage medium for fault finding in a monitoring system. Compared with the low efficiency of fault finding in existing technologies, this application, when an abnormality is detected in the overall fault index of the monitoring system, obtains the current value of a preset leaf element, wherein the leaf element and non-leaf elements together form a data cube of candidate root cause elements, and the data cube has multiple layers; based on the current value, calculates the deviation degree of the leaf element to obtain a deviation degree set; according to the aggregation degree of the candidate root cause elements in the data cube from low to high, calculates the root cause potential score corresponding to each layer of candidate root cause elements based on the deviation degree set; based on the root cause potential score, filters the candidate root cause elements, adds the filtered root cause elements to the root cause set, and deletes the descendant leaf elements of the root cause elements from the data cube; determines whether the root cause set meets the preset set conditions, and if so, takes the current root cause set as the root cause of the monitoring system's fault. In this application, the computational load is small when calculating the deviation of leaf elements. Candidate root cause elements are screened according to the order of aggregation degree from low to high. After screening, the corresponding descendant leaf elements are deleted, which reduces the iterative computation load of each layer of candidate root cause elements, improves the speed of fault finding, and determines whether the obtained root cause set meets the set conditions, which improves the accuracy of the found root cause, that is, improves the efficiency of fault finding in the monitoring system.

[0122] Example 2

[0123] Furthermore, based on Embodiment 1 of this application, another embodiment of this application is provided. In this embodiment, step S31, the step of determining the partition threshold based on the deviation set, includes steps A1-A3:

[0124] Step A1: Determine the distribution of the deviation set, wherein the distribution includes the expected value;

[0125] Step A2: Based on the distribution, remove a first number of maximum values ​​and a second number of minimum values ​​from the deviation, wherein the distribution of the deviation after removal includes the left endpoint and the right endpoint.

[0126] Step A3: Determine the partition threshold based on the deviation of the expected value between the left endpoint and the right endpoint;

[0127] Wherein, the absolute value of the left endpoint and the expected value is the first absolute value, and the absolute value of the right endpoint and the expected value is the second absolute value. If the first absolute value is less than the second absolute value, then the expected value is the average value of the left endpoint and the partition threshold. If the first absolute value is greater than the second absolute value, then the expected value is the average value of the right endpoint and the partition threshold.

[0128] In this embodiment, the distribution of the deviation set is based on the expected value, which is the median average value. As an example, the expected value is 0.

[0129] The first number of maximum values ​​and the second number of minimum values ​​are removed from the distribution. The deviation of the partially removed values ​​is not of much reference significance in this embodiment and belongs to a special case.

[0130] After removing some deviation from the distribution, the left endpoint of the distribution is referred to as the left endpoint, and the right endpoint is referred to as the right endpoint.

[0131] In this embodiment, the deviation in the distribution comes from both normal leaf elements and abnormal leaf elements. Therefore, when a normal leaf element is near the expected value of 0, two scenarios can occur: Scenario 1: the abnormal leaf element is to the left of the normal leaf element; Scenario 2: the abnormal leaf element is to the right of the normal leaf element. In other words, the expected value is biased towards the left or right endpoint. Therefore, it is necessary to distinguish between Scenario 1 and Scenario 2, and determine the partition threshold based on either scenario.

[0132] The partition threshold is determined based on the deviation of the expected value between the left and right endpoints.

[0133] As an example, the left endpoint has a value of -0.5, the right endpoint has a value of 1.5, and the expected value is 0. The absolute value of the left endpoint's value and the expected value is 0.5 (the first absolute value), and the absolute value of the right endpoint's value and the expected value is 1.5 (the second absolute value). Since the first absolute value is less than the second absolute value, the abnormal leaf element is determined to be to the right of the normal leaf element. The expected value is biased towards the left endpoint. Therefore, based on the average of the expected value of the left endpoint's value and the partition threshold, the partition threshold is determined to be 0.5. The average of 0.5 and -0.5 is the expected value of 0.

[0134] In this embodiment, a partitioning threshold is determined based on the distribution of the deviation set. By incorporating the partitioning threshold of the deviation set, the division of normal and abnormal leaf regions becomes more precise. This more precise division of normal and abnormal leaf regions leads to root causes that better reflect the actual fault conditions, thus further improving the efficiency of fault finding in the monitoring system.

[0135] Example 3

[0136] Furthermore, based on all the above embodiments, another embodiment of this application is provided, in which, as shown... Figure 2 Step S34, the step of calculating the root cause potential score corresponding to each candidate root cause element based on the first weight and the second weight, includes steps B1-B3:

[0137] Step B1: Calculate the first root cause potential score based on the first weight and the second weight;

[0138] Step B2: Based on the current value of the descendant leaf element and the predicted value of the descendant leaf element, calculate the second root cause potential score, wherein the predicted value of the descendant leaf element is proportional to the predicted value of the candidate root cause element.

[0139] Step B3: Calculate the root cause potential score based on the first root cause potential score and the second root cause potential score, wherein when the candidate root cause element is the leaf element, the second root cause potential score is 0.

[0140] In this embodiment, the first root cause potential score is calculated based on the first weight and the second weight. Specifically, the calculation method of the first root cause potential score is as described in Embodiment 1. In this embodiment, the first root cause potential score is P1 in Embodiment 1. The first root cause potential score measures the degree of abnormality of the offspring leaf elements, which will not be described in detail in this embodiment.

[0141] In this embodiment, the root cause element follows a chain reaction characteristic, that is, when the value of the root cause element changes, the value of the corresponding descendant root cause element changes proportionally. As an example, the current value of the candidate root cause element is 5, and the predicted value is 10. Among the leaf elements of the descendant of the candidate root cause element, one of the leaf elements has a current value of 2. Based on the relationship of 2 times the predicted value and the current value of the candidate root cause element, the predicted value of the descendant leaf element is determined to be twice the current value of 2, that is, twice the predicted value of 4.

[0142] In this embodiment, the second root cause potential score measures the inference bias after following the chain reaction characteristics. The lower the second root cause potential score, the more the inference bias of the offspring leaf element conforms to the chain reaction characteristics, and the higher the probability that the candidate root cause element is the true root cause element.

[0143] In this embodiment, the current value of the descendant leaf element is v(e), the predicted value of the descendant leaf element is a(e), the current value of the candidate root cause element is v(er), and the predicted value of the candidate root cause element is a(er). Therefore, the predicted value of the descendant leaf element a(e) = v(e) * a(er) / v(er). Here, the descendant leaf element e is a descendant of the candidate root cause element er. Based on the current value and the predicted value of the descendant leaf element, the second root cause potential score P2 is calculated as follows:

[0144]

[0145] Where e∈LD(er) indicates that e is a descendant leaf element under the candidate root element er, and ds(e) is the deviation degree of the descendant leaf element under the root element er. The sum of the deviation degrees of all descendant leaf elements is the denominator.

[0146] Based on the first root cause potential score and the second root cause potential score, the root cause potential score is calculated, and the difference between the first root cause potential score and the second root cause potential score is taken as the root cause potential score (P1-P2).

[0147] Wherein, when the candidate root cause element is the leaf element, the potential score of the second root cause is 0.

[0148] In this embodiment, a second root cause potential score is added. The root cause potential score is obtained by summing the first and second root cause potential scores. This second root cause potential score reflects the inference bias that occurs when the subsequent leaf elements more closely match the chain reaction characteristics, leading to more accurate identification of the root cause of the fault. Furthermore, it employs linear calculation, simplifying the computation and accelerating the cause-finding process. This further improves the efficiency of fault cause finding in the monitoring system.

[0149] Example 4

[0150] Furthermore, based on all the above embodiments, another embodiment of this application is provided, in which, as shown... Figure 3 In step S40, the step of filtering candidate root cause elements based on the root cause potential score and adding the filtered root cause elements to the root cause set includes steps S41-S43:

[0151] Step S41: Based on the root cause potential score, filter the candidate root cause elements, wherein the candidate root cause elements whose root cause potential score is greater than a preset root cause threshold are retained.

[0152] Step S42: If there are multiple candidate root cause elements in the same layer of the data cube, then based on the set conditions, select root cause elements from the retained candidate root cause elements.

[0153] Step S43: Add the selected root cause elements to the root cause set.

[0154] In this embodiment, when screening candidate root cause elements, candidate root cause elements whose potential root cause score is greater than a preset root cause threshold are retained. If there are multiple retained candidate root cause elements in the same layer of the data cube, then based on the set conditions, root cause elements are selected from the retained candidate root cause elements and added to the root cause set.

[0155] As an example, the set condition is to determine whether the explanatory power of the elements in the root cause set is higher than a preset explanatory power threshold. If multiple candidate root cause elements in the same data cube have root cause potential scores greater than the preset root cause threshold, then the element with the highest explanatory power is selected as the root cause element, and the selected root cause element is added to the root cause set.

[0156] In this embodiment, if multiple candidate root cause elements in the same layer of the data cube have root cause potential scores greater than a preset root cause threshold, the element with the highest explanatory power is selected as the root cause element. This allows for the selection of the optimal root cause element from multiple candidate elements, thus further improving the efficiency of fault finding in the monitoring system.

[0157] Example 5

[0158] Furthermore, based on all the above embodiments, another embodiment of this application is provided, in which, as shown... Figure 4 A fault finding device for a monitoring system is provided, the device comprising:

[0159] The acquisition module is used to acquire the current value of preset leaf elements when an abnormality is detected in the total fault index of the monitoring system. The leaf elements and non-leaf elements together form a data cube of candidate root cause elements, and the data cube is multi-layered.

[0160] The first calculation module is used to calculate the deviation degree of the leaf element based on the current value, and obtain a deviation degree set;

[0161] The second calculation module is used to calculate the root cause potential score corresponding to each layer of candidate root cause elements based on the deviation set, according to the order of aggregation degree of the candidate root cause elements in the data cube from low to high.

[0162] The filtering module is used to filter the candidate root cause elements based on the root cause potential score, add the filtered root cause elements to the root cause set, and delete the leaf elements associated with the root cause elements from the data cube.

[0163] The judgment module is used to determine whether the root cause set meets the preset set conditions. If so, the current root cause set is taken as the root cause of the monitoring system failure.

[0164] In one possible implementation of this application, the apparatus for calculating the root cause potential score corresponding to each candidate root cause element based on the deviation set includes:

[0165] The first determining module is used to determine the partition threshold based on the deviation set;

[0166] The partitioning module is used to partition the leaf elements based on the partitioning threshold to obtain normal leaf areas and abnormal leaf areas;

[0167] The second determining module is used to determine a first weight of each leaf element in the normal leaf region and a second weight of each leaf element in the abnormal leaf region based on the partition threshold and the deviation degree.

[0168] The third calculation module is used to calculate the root cause potential score corresponding to each candidate root cause element based on the first weight and the second weight.

[0169] In one possible implementation of this application, the apparatus for calculating the root cause potential score corresponding to each candidate root cause element based on the first weight and the second weight includes:

[0170] The fourth calculation module is used to calculate the first root cause potential score based on the first weight and the second weight;

[0171] The fifth calculation module is used to calculate the second root cause potential score based on the current value of the descendant leaf element and the predicted value of the descendant leaf element, wherein the predicted value of the descendant leaf element is proportional to the predicted value of the candidate root cause element.

[0172] The sixth calculation module is used to calculate the root cause potential score based on the first root cause potential score and the second root cause potential score, wherein when the candidate root cause element is the leaf element, the second root cause potential score is 0.

[0173] In one possible implementation of this application, the apparatus for determining the partition threshold based on the deviation set includes:

[0174] The third determining module is used to determine the distribution of the deviation set, wherein the distribution includes the expected value;

[0175] The elimination module is used to eliminate a first number of maximum values ​​and a second number of minimum values ​​from the deviation based on the distribution, wherein the distribution of the deviation after elimination includes the left endpoint and the right endpoint.

[0176] The fourth determining module is used to determine the partitioning threshold based on the deviation of the expected value between the left endpoint and the right endpoint;

[0177] Wherein, the absolute value of the left endpoint and the expected value is the first absolute value, and the absolute value of the right endpoint and the expected value is the second absolute value. If the first absolute value is less than the second absolute value, then the expected value is the average value of the left endpoint and the partition threshold. If the first absolute value is greater than the second absolute value, then the expected value is the average value of the right endpoint and the partition threshold.

[0178] In one possible implementation of this application, the apparatus for the step of calculating the deviation of the leaf element based on the current value to obtain a deviation set includes:

[0179] The seventh calculation module is used to calculate the current value of the non-leaf element based on the current value;

[0180] The eighth calculation module is used to calculate the predicted value of the leaf element based on the current value;

[0181] The ninth calculation module is used to calculate the predicted values ​​of non-leaf elements based on the predicted values ​​of the leaf elements;

[0182] The tenth calculation module is used to calculate the deviation degree of the leaf element based on the current value of the non-leaf element and the predicted value of the non-leaf element, and obtain a deviation degree set, wherein the deviation degree of leaf elements with the same root cause is equal.

[0183] In one possible implementation of this application, the apparatus for the step of screening candidate root cause elements based on the root cause potential score and adding the screened root cause elements to the root cause set includes:

[0184] The first screening module is used to screen the candidate root cause elements based on the root cause potential score, wherein the candidate root cause elements whose root cause potential score is greater than a preset root cause threshold are retained.

[0185] The second filtering module is used to filter out root cause elements from the retained candidate root cause elements based on the set conditions if there are multiple retained candidate root cause elements in the same layer data cube.

[0186] The Add module is used to add the filtered root cause elements to the root cause set.

[0187] In one possible implementation of this application, the apparatus for determining whether the root cause set meets preset set conditions includes:

[0188] The first judgment and calculation module is used to determine whether the root cause set meets the preset set conditions, wherein it determines whether the explanatory power of the elements in the root cause set is higher than the preset explanatory power threshold.

[0189] The return module is used to return, if not, the step of calculating the potential root cause score corresponding to each layer of candidate root cause elements based on the bias set, according to the aggregation degree of the candidate root cause elements in the data cube from low to high, to obtain the root cause set, until the explanatory power of the elements in the root cause set is higher than the explanatory power threshold.

[0190] The specific implementation of the fault finding device of the monitoring system in this application is basically the same as the various embodiments of the fault finding method of the monitoring system described above, and will not be repeated here.

[0191] Example 6

[0192] Furthermore, based on all the above embodiments, another embodiment of this application is provided. In this embodiment, a fault finding device for a monitoring system is provided. The fault finding device for the monitoring system is a physical node device. The fault finding device for the monitoring system includes: a memory, a processor, and a program stored in the memory for implementing the fault finding method of the monitoring system. The memory is used to store the program for implementing the fault finding method of the monitoring system; the processor is used to execute the program for implementing the fault finding method of the monitoring system to implement the steps of the fault finding method of the monitoring system in the above embodiments.

[0193] Reference Figure 5 , Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of this application.

[0194] like Figure 5As shown, the fault-finding device of this monitoring system may include: a processor 1001, such as a CPU, a memory 1005, and a communication bus 1002. The communication bus 1002 is used to establish communication between the processor 1001 and the memory 1005. The memory 1005 may be a high-speed RAM or a stable, non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0195] Optionally, the fault diagnosis device of the monitoring system may also include a network interface, audio circuit, display, connecting cable, sensor, input module, etc. The network interface may include a standard wired interface or a wireless interface (such as a WI-FI interface or a Bluetooth interface). The input module may include a keyboard, a system soft keyboard, voice input, wireless receiver input, etc.

[0196] Those skilled in the art will understand that the structure of the fault finding device for the monitoring system does not constitute a limitation on the fault finding device for the monitoring system, and may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0197] A memory, as a computer storage medium, may include an operating system, an information exchange module, and a fault-finding program for the monitoring system. The operating system is a program that manages and controls the hardware and software resources of the fault-finding equipment in the monitoring system, supporting the operation of the fault-finding program and other software and / or programs. The information exchange module is used to enable communication between the various components within the memory, as well as communication with other hardware and software in the fault-finding system of the monitoring system.

[0198] In the fault finding device of the monitoring system, the processor is used to execute the fault finding program of the monitoring system stored in the memory to implement the above-mentioned fault finding steps of the monitoring system.

[0199] The specific implementation of the fault finding device of the monitoring system in this application is basically the same as the various embodiments of the fault finding method of the monitoring system described above, and will not be repeated here.

[0200] Example 7

[0201] This application provides a storage medium that stores one or more programs, which can be executed by one or more processors to implement the steps of the fault finding method of the monitoring system in the above embodiments.

[0202] The specific implementation of the storage medium in this application is basically the same as the various embodiments of the fault finding method of the monitoring system described above, and will not be repeated here.

[0203] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0204] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0205] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM or RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0206] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A fault diagnosis method for a monitoring system, characterized in that, The method includes: When an abnormality is detected in the total fault index of the monitoring system, the current value of the preset leaf element is obtained, wherein the leaf element and non-leaf element together form a data cube of candidate root cause elements, and the data cube is multi-layered; Based on the current value, according to the formula Calculate the deviation of the leaf element to obtain the deviation set, where f is the predicted value of the non-leaf element and v is the current value of the non-leaf element; Based on the set of biases, the potential root cause score corresponding to each layer of candidate root cause elements is calculated in order of increasing aggregation degree of the candidate root cause elements in the data cube. The step of calculating the potential root cause score corresponding to each candidate root cause element based on the deviation set includes: determining a partitioning threshold based on the deviation set; partitioning leaf elements based on the partitioning threshold to obtain normal leaf areas and abnormal leaf areas; determining a first weight for each leaf element in the normal leaf area and a second weight for each leaf element in the abnormal leaf area based on the partitioning threshold and the deviation set; and calculating the potential root cause score corresponding to each candidate root cause element based on the first weight and the second weight. The calculation of the root cause potential score corresponding to each candidate root cause element includes: calculating a first root cause potential score based on a first weight and a second weight; calculating a second root cause potential score based on the current value of the descendant leaf element and the predicted value of the descendant leaf element, wherein the predicted value of the descendant leaf element is proportional to the candidate root cause element; calculating the root cause potential score based on the first root cause potential score and the second root cause potential score, wherein when the candidate root cause element is a leaf element, the second root cause potential score is 0. Based on the root cause potential score, the candidate root cause elements are filtered, the filtered root cause elements are added to the root cause set, and the descendant leaf elements of the root cause elements are deleted from the data cube. Determine whether the root cause set meets the preset set conditions. If so, the current root cause set is taken as the root cause of the monitoring system failure.

2. The fault finding method for the monitoring system according to claim 1, characterized in that, The step of determining the partition threshold based on the deviation set includes: Determine the distribution of the deviation set, wherein the distribution includes the expected value; Based on the distribution, a first number of maximum values ​​and a second number of minimum values ​​are removed from the deviation, wherein the distribution of the deviation after removal includes the left endpoint and the right endpoint. The partition threshold is determined based on the deviation of the expected value between the left endpoint and the right endpoint; Wherein, the absolute value of the left endpoint and the expected value is the first absolute value, and the absolute value of the right endpoint and the expected value is the second absolute value. If the first absolute value is less than the second absolute value, then the expected value is the average value of the left endpoint and the partition threshold. If the first absolute value is greater than the second absolute value, then the expected value is the average value of the right endpoint and the partition threshold.

3. The fault finding method for the monitoring system according to claim 1, characterized in that, The step of calculating the deviation of the leaf element based on the current value to obtain the deviation set includes: Based on the current value of the leaf element, the current value of the non-leaf element is calculated; Based on the current value of the leaf element, the predicted value of the leaf element is calculated; Based on the predicted values ​​of the leaf elements, the predicted values ​​of the non-leaf elements are calculated. Based on the current value of the non-leaf element and the predicted value of the non-leaf element, the deviation degree of the leaf element is calculated to obtain a deviation degree set, wherein the deviation degree of leaf elements with the same root cause is equal.

4. The fault diagnosis method for the monitoring system according to claim 1, characterized in that, The step of filtering candidate root cause elements based on the root cause potential score and adding the filtered root cause elements to the root cause set includes: Based on the root cause potential score, the candidate root cause elements are filtered, wherein the candidate root cause elements whose root cause potential score is greater than a preset root cause threshold are retained. If there are multiple candidate root cause elements in the same layer of the data cube, then root cause elements are selected from the retained candidate root cause elements based on the set conditions. Add the selected root cause elements to the root cause set.

5. The fault finding method for the monitoring system according to claim 1, characterized in that, The step of determining whether the root cause set meets the preset set conditions includes: Determine whether the root cause set meets a preset set condition, wherein it is determined whether the explanatory power of the elements in the root cause set is higher than a preset explanatory power threshold. If not, return to the step of calculating the potential root cause score corresponding to each candidate root cause element based on the bias set, according to the order of aggregation degree of the candidate root cause elements in the data cube from low to high, to obtain the root cause set, until the explanatory power of the elements in the root cause set is higher than the explanatory power threshold.

6. A fault-finding device for a monitoring system, characterized in that, The fault finding device of the monitoring system includes: The acquisition module is used to acquire the current value of preset leaf elements when an abnormality is detected in the total fault index of the monitoring system. The leaf elements and non-leaf elements together form a data cube of candidate root cause elements, and the data cube is multi-layered. The first calculation module is used to calculate based on the current value according to the formula. Calculate the deviation of the leaf element to obtain the deviation set, where f is the predicted value of the non-leaf element and v is the current value of the non-leaf element; The second calculation module is used to calculate the root cause potential score corresponding to each layer of candidate root cause elements based on the deviation set, according to the aggregation degree of the candidate root cause elements in the data cube from low to high. Specifically, the second calculation module is used to determine a partitioning threshold based on the deviation set; partition the leaf elements based on the partitioning threshold to obtain normal leaf areas and abnormal leaf areas; determine a first weight for each leaf element in the normal leaf area and a second weight for each leaf element in the abnormal leaf area based on the partitioning threshold and the deviation set; calculate the root cause potential score corresponding to each layer of candidate root cause elements based on the first weight and the second weight; calculate a first root cause potential score based on the first weight and the second weight; calculate a second root cause potential score based on the current value of the descendant leaf element and the predicted value of the descendant leaf element, wherein the predicted value of the descendant leaf element is proportional to the candidate root cause element; calculate the root cause potential score based on the first root cause potential score and the second root cause potential score, wherein the second root cause potential score is 0 when the candidate root cause element is a leaf element. The filtering module is used to filter the candidate root cause elements based on the root cause potential score, add the filtered root cause elements to the root cause set, and delete the leaf elements associated with the root cause elements from the data cube. The judgment module is used to determine whether the root cause set meets the preset set conditions. If so, the current root cause set is taken as the root cause of the fault in the monitoring system.

7. A fault-finding device for a monitoring system, characterized in that, The system includes a memory, a processor, and a fault finding program for a monitoring system stored in the memory and executable on the processor. The processor executes the fault finding program for the monitoring system to implement the steps of the fault finding method for the monitoring system according to any one of claims 1 to 5.

8. A storage medium, characterized in that, The storage medium stores a program for implementing a fault finding method for a monitoring system, which is executed by a processor to implement the steps of the fault finding method for a monitoring system as described in any one of claims 1 to 5.

Images