CN110493025A - It is a kind of based on the failure root of multilayer digraph because of the method and device of diagnosis - Google Patents
It is a kind of based on the failure root of multilayer digraph because of the method and device of diagnosis Download PDFInfo
- Publication number
- CN110493025A CN110493025A CN201810461456.6A CN201810461456A CN110493025A CN 110493025 A CN110493025 A CN 110493025A CN 201810461456 A CN201810461456 A CN 201810461456A CN 110493025 A CN110493025 A CN 110493025A
- Authority
- CN
- China
- Prior art keywords
- node
- service
- root
- service node
- multilayer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
- H04L41/065—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis involving logical or physical relationship, e.g. grouping and hierarchies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0677—Localisation of faults
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Debugging And Monitoring (AREA)
- Monitoring And Testing Of Exchanges (AREA)
Abstract
Embodiment of the invention discloses a kind of based on the failure root of multilayer digraph because of the method and device of diagnosis, this method determines the call relation of each service node according to original service data and attribute information jointly, it can be comprehensively in view of the service node newly increased in practice or the call relation newly increased, ensure that can be added to each service node in multilayer Directed Graph Model when establishing multilayer Directed Graph Model according to call relation, accurately quickly to search the root for generating abnormal traffic data based on multilayer Directed Graph Model because node is laid a good foundation.It is generated by the service node in multilayer Directed Graph Model in this present embodiment according to practical business node, the comprehensive of node avoids method to emerging failure progress root because of the case where inquiring, simultaneously, analysis to data is not only to be based on call relation, but the multilayer Directed Graph Model based on creation analyzes data comprehensively.
Description
Technical field
The present embodiments relate to computer software technical fields, more particularly, to a kind of failure based on multilayer digraph
Method and device of the root because of diagnosis.
Background technique
Cloud computing and container cloud it is universal so that a large amount of IT application systems are gradually deployed in virtualization, containerization environment
In.And with all kinds of business scenarios enrich constantly and the blowout of portfolio increase, in system and the ease for maintenance of application
Bring huge challenge.Especially in telecommunications industry, it is vast consumption that operator, which inherently constructs very more application systems,
Person provides various special services, and some system functions further relate to the subfunction of multiple operation systems, and multisystem is needed to cooperate with
It could work normally.The differentiation of framework more aggravates the complexity of such operation system, mentions to O&M fault location and resolution ability
Higher requirement is gone out.
Current method for diagnosing faults includes three types, and scheme is first is that the failure based on prediction scheme storehouses forms such as alarms is examined
It is disconnected, scheme second is that the fault diagnosis based on prediction scheme storehouses forms such as alarms, scheme third is that fault diagnosis based on decision-tree model and
Restorative procedure.Wherein, the fault diagnosis based on prediction scheme storehouses forms such as alarms: most O&M departments are generally according to phenomenon of the failure and place
Reason record is aggregated into Troubleshooting Manual, and equipment component supplier can also provide similar simple fault stationkeeping ability, is come with this
Realize the Primary Location and solution of failure.It further include other dimensions such as QoE (user experience quality) in addition to being based on historical failure experience
Degree is to carry out fault diagnosis.Once failure occurs, key message is alerted by collecting, and finds corresponding diagnosis handbook and is retrieved
Generate diagnostic result.Therefore, the positioning of completion fault routine and repair that the mode based on alarm can be simple and quick, once and face
It is then helpless when be not inconsistent with known warning information unknown failure etc..Fault diagnosis side based on offline index analysis tool
Method: offline index analysis tool includes operational indicator and system performance measure, the former is mainly put in storage data by business and reflects industry
Business figureofmerit, the latter, which mainly passes through after the external datas such as log import database, to be analyzed, by system performance measure point
Analysis, to system performance, success rate, unsuccessfully the information such as distribution are analyzed, to judge that system runs health degree.Based on database
Mode is convenient for extraction system key index, each link operating status of effective monitoring program, but in contrast the time extends larger, meeting
To being had some impact in system monitoring timeliness.Fault diagnosis and restorative procedure based on decision-tree model: most systems are set
Meter uses multilayer system topological structure, based on the principle that layering is called, establishes the topological diagram of tree-like relationship, and tree-like is opened up based on this
Flutter the decision tree for establishing service-oriented and the system failure.Once failure occurs, by collecting failure key message, and phase is found
It answers decision tree to carry out retrieval and generates diagnostic result.Therefore, the completion fault routine that the mode based on decision tree can be simple and quick
Positioning and repair, and once face non-tree structure call relation when if it is helpless.
However, in the ring based on the virtualizations such as big data platform, DCOS platform, modular system, micro services system, containerization
In border, for the diagnosis and reparation of clustered node failure or exception, existing scheme is not enough to support quick response, efficient analysis solution
Capability Requirement certainly, is mainly manifested in the following aspects: (1) usage scenario is narrow, can not handle unknown scene.Such as scheme
Fault diagnosis and restorative procedure in one based on alarm and prediction scheme storehouse form depend on the experience product to known fault information
It is tired, and this mode has great requirement to fault scenes.Same phenomenon of the failure may under different fault scenes
There is different processing modes, also just has exceeded the process range of simple prediction scheme storehouse.Especially when facing unknown failure information,
The means such as some handbooks are entirely ineffective, need manually gradually to be checked, positioning failure, repair problem, O&M is caused to be imitated
Rate is low.(2) index poor in timeliness can not timely feedback information.Existing scheme is only limitted to add to the promotion of fault location ability
Strong fault information collection, and the judgement and execution of operation maintenance personnel are also to rely on to the final positioning and reparation of failure.Pass through sea
The monitor control index data of amount, largely expand fault message source, but also higher to the acquisition delay of index, cause this
A little data automatically process and analyze upper scarce capacity, can not show the information point and root of problem in time.(3) magnanimity is needed to go through
History data are not suitable with agility mode.Existing scheme mainly promotes analysis ability using training decision tree, but trains decision tree
A large amount of historical data is needed, due to this department system business feature, the accounting that newly goes wrong is more, can not provide enough effective instructions
Practice data, causes decision-tree model accuracy not high, to failure root cause analysis scarce capacity, effective support can not be provided.
During realizing the embodiment of the present invention, inventor find existing lookup failure root because method environment it is suitable
Should be able to power it is poor, can not to emerging failure carry out root because inquiry, and it is existing search failure root because method only in accordance with business
The call relation of node is searched, and more single to the analysis of data, data analysis capabilities are weaker.
Summary of the invention
The technical problem to be solved by the present invention is to how to solve it is existing lookup failure root because method environment adaptation
Ability is poor, can not to emerging failure carry out root because inquiry, and it is existing search failure root because method only in accordance with business section
The call relation of point is searched, data analysis capabilities weaker problem more single to the analysis of data.
Against the above technical problems, the embodiment provides a kind of based on the failure root of multilayer digraph because of diagnosis
Method, comprising:
Obtain the original service data generated at each service node of pre-set business, according to the original service data and
The attribute information of pre-stored each service node determines the call relation of each service node;
According to the call relation of each service node determined by the original service data and the attribute information and with it is pre-
Layer belonging to each service node first divided establishes the multilayer Directed Graph Model of each service node;
The abnormal traffic data in the original service data are obtained, institute is led to according to multilayer Directed Graph Model determination
At least one root of abnormal traffic data described in business service generation is stated because of node, leads to described preset from root because determining in node
The target root of service exception is because of node.
The embodiment provides a kind of based on the failure root of multilayer digraph because of the device of diagnosis, comprising:
Module is obtained, for obtaining the original service data generated at each service node of pre-set business, according to described
The attribute information of original service data and pre-stored each service node determines the call relation of each service node;
Module is established, for the tune according to each service node determined by the original service data and the attribute information
The multilayer Directed Graph Model of each service node is established with relationship and with layer belonging to each service node for dividing in advance;
Root has according to the multilayer because of determining module for obtaining the abnormal traffic data in the original service data
Cause at least one root of abnormal traffic data described in the business service generation because of node to graph model determination, from root because of node
Middle determination causes the target root of the pre-set business exception because of node.
Present embodiments provide a kind of electronic equipment, comprising:
At least one processor, at least one processor, communication interface and bus;Wherein,
The processor, memory, communication interface complete mutual communication by the bus;
The communication interface is for the information transmission between the electronic equipment and the communication equipment of terminal device;
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program to refer to
Order is able to carry out the process described above.
A kind of computer program product is present embodiments provided, the computer program product includes being stored in non-transient meter
Computer program on calculation machine readable storage medium storing program for executing, the computer program include program instruction, when described program instruction is counted
When calculation machine executes, the computer is made to execute the process described above.
The embodiment provides a kind of method and device based on the failure root of multilayer digraph because of diagnosis, the party
Method determines the call relation of each service node according to original service data and attribute information jointly, can be comprehensively in view of in practice
The service node newly increased or the call relation newly increased, ensure that when establishing multilayer Directed Graph Model according to call relation
Each service node can be added in multilayer Directed Graph Model, be produced accurately quickly to be searched based on multilayer Directed Graph Model
The root of raw abnormal traffic data is laid a good foundation because of node.By the service node in multilayer Directed Graph Model in this present embodiment
It is generated according to practical business node, the comprehensive of node avoids method to emerging failure progress root because of the case where inquiring hair
It is raw, meanwhile, the analysis to data be not only be based on call relation, but the multilayer Directed Graph Model based on creation to data into
Row analysis comprehensively.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is that the process of the method provided by one embodiment of the present invention based on the failure root of multilayer digraph because of diagnosis is shown
It is intended to;
Fig. 2 is configuration diagram of the failure root because of diagnosis for the multilayer digraph that another embodiment of the present invention provides;
Fig. 3 is flow diagram of the carry out failure root because of inquiry of another embodiment of the present invention offer;
Fig. 4 is the structure based on the failure root of multilayer digraph because of the device of diagnosis that another embodiment of the present invention provides
Block diagram;
Fig. 5 is the structural block diagram for the electronic equipment that another embodiment of the present invention provides.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Fig. 1 is the flow diagram of the method provided in this embodiment based on the failure root of multilayer digraph because of diagnosis, ginseng
See Fig. 1, this method comprises:
101: the original service data generated at each service node of pre-set business are obtained, according to the original service number
The call relation of each service node is determined according to the attribute information with pre-stored each service node;
102: according to the call relation of each service node determined by the original service data and the attribute information and
The multilayer Directed Graph Model of each service node is established with layer belonging to each service node for dividing in advance;
103: obtaining the abnormal traffic data in the original service data, led according to multilayer Directed Graph Model determination
Cause at least one root of abnormal traffic data described in the business service generation because of node, from root because described in determining and causing in node
The target root of pre-set business exception is because of node.
Method provided in this embodiment is usually held by the equipment for carrying out fault diagnosis and reparation whether normal operation to business
Row, for example, server, the present embodiment is not particularly limited this.This method is used to carry out root to the business of a certain failure
Because of inquiry.Service node is the node in the pre-set business operational process, and the data acquired at each service node are the business
Original service data.Attribute information is the attribute information of each service node predetermined, and attribute information has reacted each business
The call relation of node.Each service node can also be layered according to attribute information, for example, be located at application layer node,
The node etc. of transport layer.It is needed when creating the multilayer Directed Graph Model of each service node referring to preparatory ready-portioned each service node
Affiliated layer.When leading to the root of pre-set business exception because of node by the lookup of multilayer digraph, according to the calling of each service node
Relationship is successively searched.Target root is because node is usually obtained by calculation, and specific calculation method can be set, the present embodiment
It is not specifically limited in this embodiment.
A kind of method based on the failure root of multilayer digraph because of diagnosis is present embodiments provided, this method is according to original industry
Business data and attribute information determine the call relation of each service node jointly, can consider the business newly increased in practice comprehensively
Node or the call relation newly increased, ensure that can be by each industry when establishing multilayer Directed Graph Model according to call relation
Business node is added in multilayer Directed Graph Model, generates abnormal traffic number accurately quickly to search based on multilayer Directed Graph Model
According to root lay a good foundation because of node.By the service node in multilayer Directed Graph Model in this present embodiment according to practical business
Node generates, and the comprehensive of node avoids method to emerging failure progress root because of the case where inquiring, meanwhile, to data
Analysis be not only to be based on call relation, but the multilayer Directed Graph Model based on creation analyzes data comprehensively.
Further, on the basis of the above embodiments, the acquisition generates at each service node of pre-set business
Original service data determine each business section according to the attribute information of the original service data and pre-stored each service node
The call relation of point, comprising:
It obtains the original service data generated at each service node of pre-set business and is stored in CMDB database each
The attribute information of service node obtains the original call relationship between each service node according to the attribute information of each service node;
The practical call relation that each service node is analyzed according to the original service data, according to practical call relation to institute
It states original call relationship to be adjusted, obtains each service node determined by the original service data and the attribute information
Call relation.
CMDB database is the database of the various configuration informations of equipment in storage and management enterprise IT architecture.To default industry
Each service node of business, the first attribute information according to defined in CMDB database, obtain the call relation of each service node.So
And the service node since pre-set business may have been increased newly in practice, and may be without the newly-increased business in CMDB database
Node, therefore need newly-increased node and other each service nodes after determining original call relationship further according to original service data
Call relation supplemented, finally obtain meet it is actual determined by the original service data and the attribute information it is each
The call relation of service node.
Present embodiments provide it is a kind of based on the failure root of multilayer digraph because of the method for diagnosis, this method is to according to CMDB
The original call relationship that database obtains is adjusted, and guarantees that finally determining call relation includes business actual moving process
In all call relations, also to can be carried out root because inquiry provides guarantee to emerging failure.
Further, on the basis of the various embodiments described above, the basis is by the original service data and the attribute
The call relation for each service node that information determines and each service node is established with layer belonging to each service node for dividing in advance
Multilayer Directed Graph Model, comprising:
According to the call relation of each service node determined by the original service data and the attribute information, to described
The service node stored in CMDB database is modified;
The service node for obtaining i-th layer in the revised CMDB database divided in advance, to i-th layer in CMDB database
Service node vn, obtained according to the call relation of each service node determined by the original service data and the attribute information
It takes by service node vnIt reaches and service node v can be reachednTarget service node;
I-th layer in CMDB database of the corresponding target service node of each service node is added to the i-th node layer collection
In conjunction, then the point in the i-th node layer set is i-th layer of node in the multilayer Directed Graph Model.
For example, service node has been increased newly when business actual motion, then needing for the service node to be added to CMDB data
In library, CMDB database is updated in time.Each service node is in CMDB database previously according to the category of each service node
Property divided layer, for example, the service node for belonging to application layer is divided into same layer, the service node that will belong to transport layer is divided
For same layer.
In multilayer Directed Graph Model, the i-th node layer set can pass through formula Li={ R1∩A1, R2∩A2... ..., Rn
∩AnIndicate.Wherein, RnIndicate all from vnThe set of the node of arrival, AnV can be reached by indicating allnNode set.
The shared n of i-th layer of service node is each in CMDB database, respectively v1, v2... ... vn。
A kind of method based on the failure root of multilayer digraph because of diagnosis is present embodiments provided, this method is according to CMDB number
The service node of each layer in multilayer Directed Graph Model is obtained according to layer belonging to service node each in library.
Further, on the basis of the various embodiments described above, the abnormal traffic obtained in the original service data
Data determine at least one for leading to abnormal traffic data described in the business service generation according to the multilayer Directed Graph Model
Root causes the target root of the pre-set business exception because of node because of node, from root because determining in node, comprising:
Judge whether the original service data generated at each service node are abnormal, obtain according to preset threshold interval
Take all abnormal abnormal traffic data in original service data;
Each abnormal traffic data are mapped to the business that the abnormal traffic data are generated in the multilayer Directed Graph Model
It is oriented in the multilayer according to the call relation of each service node in the multilayer Directed Graph Model and each service node on node
Affiliated layer lookup causes at least one root of the business business because of node in graph model;
Construct time series data < m, k, T, Em×k>, with xiIt (t) is independent variable, with Em×k-xiIt (t) is dependent variable, construction
Function f [xi(t)]=Em×k-xi(t), to each because of the value x in all time serieses of nodei(t)~xi(t-k) it is disturbed
It is dynamic, obtain each undulating value y [δ, the f [x because of nodei(t)]], using undulating value be less than the root of default undulating value because node as
The target root is because of node;
Wherein, m is service node number in the multilayer Directed Graph Model, and k is time lag existing for each service node
Number, T are the length of time series, Em×kFor set of all service nodes in all time lags in the multilayer Directed Graph Model,
δ is parameter related with the multilayer Directed Graph Model, and root is j, x because of the total number of nodei(t) exist for i-th of service node
Length of time series corresponding business datum when being t.
Judge whether business datum is that abnormal traffic data can be judged according to the threshold range of setting, it can also be right
After business datum carries out calculation process, judge whether business datum is abnormal, and the present embodiment is to this according to the result after calculation process
It is not particularly limited.During carrying out root because searching, it is only necessary to which abnormal traffic data are mapped to multilayer Directed Graph Model
In.
When searching root because of node, need call relation between the layer according to belonging to each service node and each service node into
Row is searched.For example, the group node with call relation has an abnormal point in each layer, then the bottom is usually located at
Service node is root because of node;If abnormal traffic node is not present in a certain layer in one group of service node with call relation,
Root should be carried out because searching using the service node on this layer and under this layer as independent two parts.
After root is found because of node, according to calculated each because of the corresponding undulating value of node to root because node is arranged
Sequence, undulating value is smaller, illustrates the root because a possibility that node leads to service exception is bigger, it would be possible to the biggish several Gen Yinjie of property
Point is as target root because of node.
A kind of method based on the failure root of multilayer digraph because of diagnosis is present embodiments provided, this method has by multilayer
Root is carried out because of inquiry to graph model, and multiple dimensional analysis data improve accuracy of the root because of lookup.From root because being determined in node
Target root reduces range of nodes in need of consideration when repairing to business, improves the efficiency of reconditioning work because of node out.
Further, on the basis of the various embodiments described above, the acquisition generates at each service node of pre-set business
Original service data before, further includes:
To each business carry out KEI index evaluation, judge whether the business is in health status, if the business be not in it is strong
Health state, then using the business as the pre-set business, acquisition generates original at each service node of the pre-set business
Business datum.
KEI (KPI Key Performance Indicator) is used to whether be in business health filling and assesses, side provided in this embodiment
Method only carries out root because of diagnosis to the business in unhealthy condition.
A kind of method based on the failure root of multilayer digraph because of diagnosis is present embodiments provided, this method is referred to by KEI
Mark filters out the business in unhealthy condition, carries out root because of diagnosis to the business in unhealthy condition, avoids to health
The business of state carries out unnecessary diagnosis.
Further, described to lead to the pre-set business because determining in node from root on the basis of the various embodiments described above
After abnormal target root is because of node, further includes:
Judge whether to be stored with the troubleshooting prediction scheme for repairing the target root because of node, if so, according to failure
It handles prediction scheme and repairs the target root because of node, and send the first prompt information repaired to target root by node,
Otherwise, the target root is sent because of the nodal information of node and the second prompt information that do not repaired to target root by node.
After determining target root because of node, need to guarantee the normal operation of system because node is repaired for target root.The
One prompt information and the second prompt information can be the information for sending by mail or sending by short message, and the present embodiment is to this
It is not specifically limited.
Present embodiments provide a kind of method based on the failure root of multilayer digraph because of diagnosis, this method is can be timely
Failure is repaired in time in the case where repairing failure, issues prompt information in time in the case where failure can not be repaired, and
When inform staff take recovery scenario carry out fault restoration, guarantee the normal operation of business.
As more specifically embodiment, Fig. 2 is frame of the failure root because of diagnosis of multilayer digraph provided in this embodiment
Structure schematic diagram relates generally to CMDB database, applied topology relation management, Directed Graph Model converter, model referring to fig. 2
Library, INDEX MANAGEMENT device, fault rootstock analytical equipment, failure automatic processing device etc..Wherein, digraph converter by pair
Existing assets data continue to analyze, and generate failure multilayer Directed Graph Model (FSDG), and fault rootstock diagnostic device utilizes FSDG mould
Type carries out assessment calculating to real-time KEI index, it is final excavate failure root because.
In each section as shown in Figure 2, (1) is in real time handled the operation of user using production system, at business
When reason generates abnormal, abnormal point is certainly existed using production system.It is connect using production system with applied topology management system: when
When generating call relation between each application service, topology management system gets call relation data.
(2) applied topology relation management is mainly made of 6 devices, including calls data acquisition, and data cleansing, rule turns
It changes, behavioural analysis, regular continuous learning are called in call relation analysis.Applied topology relation management is divided by calling data acquisition
Call relation in analysis system between each node provides data for subsequent digraph and supports, and submits jointly with CMDB data
Multilayer Directed Graph Model is produced to model transformer.
(3) each CI of attribute in application system is saved in CMDB database, a variety of relationships between CI are fixed
Justice.By CMDB data, the FSDG hierarchical mode in multilayer digraph can be defined, and model is committed to model transformer
Produce multilayer Directed Graph Model.
(4) model transformer is handled and is converted to input data, is converted to corresponding coding according to data attribute.Pass through
The complicated call relation of system is converted to multilayer Directed Graph Model by applied topology relation data and CMDB data.Model conversion
Device is connected with model library, is committed to FSDG model library after data are carried out code conversion;
By CMDB data, node set V={ v is obtainedi|viFor the asset node managed in CMDB };
By applied topology relation data, set of fingers E={ e is obtainedi,j| node viIt is directed toward node vjDirected edge;
In multilayer Directed Graph Model, i-th layer of all service nodes pass through set Li={ R1∩A1, R2∩A2... ..., Rn
∩AnIndicate.
(5) include known system topological model in model library, classified according to business and system, CRM, canal can be divided into
Road, CBOSS model etc., the topological level of homologous ray and call relation be not all variant.It is connected with fault rootstock analytical equipment:
After model library enters information into fault rootstock analytical equipment, for analysis module point together with the achievement data of INDEX MANAGEMENT device
Analyse fault rootstock.
(6) business in INDEX MANAGEMENT device management system, the achievement datas such as system, comprising each in multilayer Directed Graph Model
Node achievement data, the key indexes such as including health degree.It is connect with fault rootstock analytical equipment: index is pushed into analysis dress
It sets, and analyzes fault rootstock with model cooperation in index storehouse.
(7) fault rootstock analytical equipment is based on big data STORM stream calculation framework, is calculated by real time data, by failure
Root calculates time-consuming and foreshortens to second grade;According to multilayer Directed Graph Model and node achievement data, judge whether system has exception, such as
Fruit has exception, according to the oriented nomography of multilayer, calculates root node, that is, analyze the root of the system failure because.It is automatic with failure
Change processing unit connection: when analyzing fault rootstock, fault rootstock being sent to processing unit and carries out troubleshooting.
Fig. 3 is progress failure root provided in this embodiment because of the flow diagram of inquiry, and referring to Fig. 3, which includes:
It is assessed using the KEI model achievement data top to FSDG model, if assessment result is in healthy shape
State, system is without subsequent analysis;If assessment result is in unhealthy condition, FSDG fault rootstock analysis process is triggered,
Calculate the source of trouble.
FSDG malfunctioning node set is handled using simple cause and effect mining algorithm, building failure cause and effect excavates object
FCS, FCS are all time series datas that each element generates in system, and Formal Representation is at four-tuple < m, k, T, Em×k>, m
It is element number in FSDG, k is each element there are time lag number, and T indicates the length of time series, Em×kInstitute in expression system
There is set of the element in all time lags.FSDG figure may be needed to carry out by the link that a plurality of service node forms failure root because examining
Disconnected, the FSDG corresponding to each link that C1 ... Cn indicates that the related link circuits formed for different service nodes are split schemes.
During fluctuation words calculate, target=xi(t), variables=Em×k-xi(t), using target as because
Variable carries out the Function Fitting based on GEP by independent variable of variables, obtains function fxi(t);Successively to fxi(t) from change
Each element in duration set variable is disturbed.Since the time lag of system is k, therefore to each element xjInstitute's having time sequence
Value x on columni(t)~xj(t-k) it is all disturbed;Each element undulating value δ fx is calculated based on disturbancei(t)(xi, δ) and then root
Cause and effect judgement is carried out according to fluctuation size, lesser undulating value is fault rootstock.
(8) failure automatic processing device handles prediction scheme if any corresponding failure for automatically processing to fault rootstock,
Device presses prediction scheme execution automatically, repairs in time to system, and notify system responsible person concerned.
It is confined to known fault analysis root for existing scheme, can not flexibly cope with new discovery failure, and can not mention
The shortcomings that for real-time computing, it is provided in this embodiment based on the failure root of multilayer digraph because the method for diagnosis is based on
Storm stream calculation technology, the method combined using fault factors algorithm FSDG and simplicity cause and effect mining algorithm NCM, is provided
Real-time high-efficiency flexible fault rootstock analysis ability.On the other hand, it is difficult to provide for current IT operational system modeling method
The shortcomings that mass data is trained, method provided in this embodiment propose a kind of based on CMDB data and applied topology relationship
Management module generates the fast modeling method of FSDG model, and the convenience of the model foundation of promotion avoids training data deficiency from making
It is larger at model error.
It is provided in this embodiment based on the failure root of multilayer digraph because the method for diagnosis is not limited to known fault
Localization process can carry out automatically root cause analysis according to model for new failure.Failure data analyzing ability is strengthened, is passed through
Data calculate in real time, and avoiding the brings data such as information explosion and overstocking influences.Failure automatic processing capabilities are improved, are introduced certainly
Dynamicization processing unit realizes failure from the closed loop management for finding, navigating to final process automatically.
Fig. 4 is the structural block diagram of the device provided in this embodiment based on the failure root of multilayer digraph because of diagnosis, referring to
Fig. 4, the device include obtaining module 401, establishing module 402 and Gen Yin determining module 403, wherein
Module 401 is obtained, for obtaining the original service data generated at each service node of pre-set business, according to institute
The attribute information for stating original service data and pre-stored each service node determines the call relation of each service node;
Module 402 is established, for according to each service node determined by the original service data and the attribute information
Call relation and the multilayer Directed Graph Model of each service node is established with layer belonging to each service node for dividing in advance;
Root is because of determining module 403, for obtaining the abnormal traffic data in the original service data, according to the multilayer
Directed Graph Model determination causes at least one root of abnormal traffic data described in the business service generation because of node, from Gen Yinjie
Determination causes the target root of the pre-set business exception because of node in point.
It is provided in this embodiment based on the failure root of multilayer digraph because diagnosis device suitable for above-described embodiment provide
Based on the failure root of multilayer digraph because of the method for diagnosis, details are not described herein.
A kind of device based on the failure root of multilayer digraph because of diagnosis is present embodiments provided, this method is according to original industry
Business data and attribute information determine the call relation of each service node jointly, can consider the business newly increased in practice comprehensively
Node or the call relation newly increased, ensure that can be by each industry when establishing multilayer Directed Graph Model according to call relation
Business node is added in multilayer Directed Graph Model, generates abnormal traffic number accurately quickly to search based on multilayer Directed Graph Model
According to root lay a good foundation because of node.By the service node in multilayer Directed Graph Model in this present embodiment according to practical business
Node generates, and the comprehensive of node avoids method to emerging failure progress root because of the case where inquiring, meanwhile, to data
Analysis be not only to be based on call relation, but the multilayer Directed Graph Model based on creation analyzes data comprehensively.
Fig. 5 is the structural block diagram for showing electronic equipment provided in this embodiment.
Referring to Fig. 5, the electronic equipment includes: processor (processor) 501, memory (memory) 502, communication
Interface (Communications Interface) 503 and bus 504;
Wherein,
The processor 501, memory 502, communication interface 503 complete mutual communication by the bus 504;
The communication interface 503 is for the information transmission between the electronic equipment and the communication equipment of other electronic equipments;
The processor 501 is used to call the program instruction in the memory 502, to execute above-mentioned each method embodiment
Provided method, for example, the original service data generated at each service node of pre-set business are obtained, according to described
The attribute information of original service data and pre-stored each service node determines the call relation of each service node;According to by institute
State each service node that original service data and the attribute information determine call relation and with each business section for dividing in advance
Layer belonging to point establishes the multilayer Directed Graph Model of each service node;The abnormal traffic data in the original service data are obtained,
According to the multilayer Directed Graph Model determine cause at least one root of abnormal traffic data described in the business service generation because
Node causes the target root of the pre-set business exception because of node from root because determining in node.
The present embodiment provides a kind of non-transient computer readable storage medium, the non-transient computer readable storage medium
Computer instruction is stored, the computer instruction makes the computer execute method provided by above-mentioned each method embodiment, example
Such as include: the original service data for obtaining and being generated at each service node of pre-set business, according to the original service data and
The attribute information of pre-stored each service node determines the call relation of each service node;According to by the original service data
It the call relation of each service node determined with the attribute information and is established with layer belonging to each service node for dividing in advance each
The multilayer Directed Graph Model of service node;The abnormal traffic data in the original service data are obtained, are had according to the multilayer
Cause at least one root of abnormal traffic data described in the business service generation because of node to graph model determination, from root because of node
Middle determination causes the target root of the pre-set business exception because of node.
The present embodiment discloses a kind of computer program product, and the computer program product includes being stored in non-transient calculating
Computer program on machine readable storage medium storing program for executing, the computer program include program instruction, when described program instruction is calculated
When machine executes, computer is able to carry out method provided by above-mentioned each method embodiment, it may for example comprise: it obtains in pre-set business
Each service node at the original service data that generate, according to the original service data and pre-stored each service node
Attribute information determines the call relation of each service node;It is each according to being determined by the original service data and the attribute information
The call relation of service node and the oriented artwork of multilayer that each service node is established with layer belonging to each service node for dividing in advance
Type;The abnormal traffic data in the original service data are obtained, the industry is led to according to multilayer Directed Graph Model determination
At least one root for abnormal traffic data described in service generation of being engaged in leads to the pre-set business because of node, from root because determining in node
Abnormal target root is because of node.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above method embodiment can pass through
The relevant hardware of program instruction is completed, and program above-mentioned can be stored in a computer readable storage medium, the program
When being executed, step including the steps of the foregoing method embodiments is executed;And storage medium above-mentioned includes: ROM, RAM, magnetic disk or light
The various media that can store program code such as disk.
The embodiments such as electronic equipment described above are only schematical, wherein it is described as illustrated by the separation member
Unit may or may not be physically separated, and component shown as a unit may or may not be object
Manage unit, it can it is in one place, or may be distributed over multiple network units.It can select according to the actual needs
Some or all of the modules therein is selected to achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying wound
In the case where the labour for the property made, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above various embodiments is only to illustrate the technical solution of the embodiment of the present invention, rather than it is right
It is limited;Although the embodiment of the present invention is described in detail referring to foregoing embodiments, the ordinary skill of this field
Personnel are it is understood that it is still possible to modify the technical solutions described in the foregoing embodiments, or to part
Or all technical features are equivalently replaced;And these are modified or replaceed, it does not separate the essence of the corresponding technical solution
The range of each embodiment technical solution of the embodiment of the present invention.
Claims (9)
1. it is a kind of based on the failure root of multilayer digraph because of the method for diagnosis characterized by comprising
The original service data generated at each service node of pre-set business are obtained, according to the original service data and in advance
The attribute information of each service node of storage determines the call relation of each service node;
It is drawn according to the call relation of each service node determined by the original service data and the attribute information and with preparatory
Layer belonging to each service node divided establishes the multilayer Directed Graph Model of each service node;
The abnormal traffic data in the original service data are obtained, the industry is led to according to multilayer Directed Graph Model determination
At least one root for abnormal traffic data described in service generation of being engaged in leads to the pre-set business because of node, from root because determining in node
Abnormal target root is because of node.
2. the method according to claim 1, wherein the acquisition generates at each service node of pre-set business
Original service data, each business is determined according to the attribute information of the original service data and pre-stored each service node
The call relation of node, comprising:
Each business for obtaining the original service data generated at each service node of pre-set business and being stored in CMDB database
The attribute information of node obtains the original call relationship between each service node according to the attribute information of each service node;
The practical call relation that each service node is analyzed according to the original service data, according to practical call relation to the original
Beginning call relation is adjusted, and obtains the calling of each service node determined by the original service data and the attribute information
Relationship.
3. according to the method described in claim 2, it is characterized in that, the basis is by the original service data and the attribute
The call relation for each service node that information determines and each service node is established with layer belonging to each service node for dividing in advance
Multilayer Directed Graph Model, comprising:
According to the call relation of each service node determined by the original service data and the attribute information, to the CMDB
The service node stored in database is modified;
The service node for obtaining i-th layer in the revised CMDB database divided in advance, to i-th layer in CMDB database of industry
Be engaged in node vn, according to the call relation of each service node determined by the original service data and the attribute information obtain by
Service node vnIt reaches and service node v can be reachednTarget service node;
I-th layer in CMDB database of the corresponding target service node of each service node is added in the i-th node layer set,
The then node that the point in the i-th node layer set is i-th layer in the multilayer Directed Graph Model.
4. according to the method described in claim 3, it is characterized in that, the abnormal traffic obtained in the original service data
Data determine at least one for leading to abnormal traffic data described in the business service generation according to the multilayer Directed Graph Model
Root causes the target root of the pre-set business exception because of node because of node, from root because determining in node, comprising:
Judge whether the original service data generated at each service node are abnormal according to preset threshold interval, obtains former
All abnormal abnormal traffic data in beginning business datum;
Each abnormal traffic data are mapped to the service node that the abnormal traffic data are generated in the multilayer Directed Graph Model
On, according to the call relation of each service node in the multilayer Directed Graph Model and each service node in the oriented artwork of the multilayer
Affiliated layer lookup causes at least one root of the business business because of node in type;
Construct time series data < m, k, T, Em×k>, with xiIt (t) is independent variable, with Em×k-xiIt (t) is dependent variable, constructed fuction f
[xi(t)]=Em×k-xi(t), to each because of the value x in all time serieses of nodei(t)~xi(t-k) it is disturbed, is obtained
Each undulating value y [δ, the f [x because of nodei(t)] undulating value], is less than the root of default undulating value because node is as the mesh
Root is marked because of node;
Wherein, m is service node number in the multilayer Directed Graph Model, and k is time lag number, T existing for each service node
For the length of time series, Em×kFor set of all service nodes in all time lags in the multilayer Directed Graph Model, δ is
Parameter related with the multilayer Directed Graph Model, root are j, x because of the total number of nodeiIt (t) is i-th of service node in the time
Sequence length corresponding business datum when being t.
5. the method according to claim 1, wherein the acquisition generates at each service node of pre-set business
Original service data before, further includes:
KEI index evaluation is carried out to each business, judges whether the business is in health status, if the business is not in healthy shape
State obtains the original service generated at each service node of the pre-set business then using the business as the pre-set business
Data.
6. the method according to claim 1, wherein described lead to the pre-set business because determining in node from root
After abnormal target root is because of node, further includes:
Judge whether to be stored with the troubleshooting prediction scheme for repairing the target root because of node, if so, according to troubleshooting
Prediction scheme repairs the target root because of node, and sends the first prompt information repaired to target root by node, otherwise,
The target root is sent because of the nodal information of node and the second prompt information that do not repaired to target root by node.
7. it is a kind of based on the failure root of multilayer digraph because of the device of diagnosis characterized by comprising
Module is obtained, for obtaining the original service data generated at each service node of pre-set business, according to described original
The attribute information of business datum and pre-stored each service node determines the call relation of each service node;
Module is established, for closing according to the calling of each service node determined by the original service data and the attribute information
System and the multilayer Directed Graph Model that each service node is established with layer belonging to each service node for dividing in advance;
Root is because of determining module, for obtaining the abnormal traffic data in the original service data, according to the multilayer digraph
Model, which determines, causes at least one root of abnormal traffic data described in the business service generation because of node, from root because true in node
Cause the target root of the pre-set business exception because of node surely.
8. a kind of electronic equipment characterized by comprising
At least one processor, at least one processor, communication interface and bus;Wherein,
The processor, memory, communication interface complete mutual communication by the bus;
The communication interface is for the information transmission between the electronic equipment and the communication equipment of other electronic equipments;
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program to instruct energy
It is enough to execute such as method described in any one of claims 1 to 6.
9. a kind of computer program product, which is characterized in that the computer program product includes being stored in non-transient computer
Computer program on readable storage medium storing program for executing, the computer program include program instruction, when described program is instructed by computer
When execution, the computer is made to execute such as method as claimed in any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810461456.6A CN110493025B (en) | 2018-05-15 | 2018-05-15 | Fault root cause diagnosis method and device based on multilayer digraphs |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810461456.6A CN110493025B (en) | 2018-05-15 | 2018-05-15 | Fault root cause diagnosis method and device based on multilayer digraphs |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110493025A true CN110493025A (en) | 2019-11-22 |
CN110493025B CN110493025B (en) | 2022-06-14 |
Family
ID=68545155
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810461456.6A Active CN110493025B (en) | 2018-05-15 | 2018-05-15 | Fault root cause diagnosis method and device based on multilayer digraphs |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110493025B (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111107158A (en) * | 2019-12-26 | 2020-05-05 | 远景智能国际私人投资有限公司 | Alarm method, device, equipment and medium for Internet of things equipment cluster |
CN111639115A (en) * | 2020-04-29 | 2020-09-08 | 国家电网有限公司客户服务中心 | Five-dimensional model-based analysis method for operation and maintenance data abnormity of power grid information system |
CN111858123A (en) * | 2020-07-29 | 2020-10-30 | 中国工商银行股份有限公司 | Fault root cause analysis method and device based on directed graph network |
CN111913824A (en) * | 2020-06-23 | 2020-11-10 | 中国建设银行股份有限公司 | Method for determining data link fault reason and related equipment |
CN112506763A (en) * | 2020-11-30 | 2021-03-16 | 清华大学 | Automatic positioning method and device for database system fault root |
CN112541098A (en) * | 2020-12-17 | 2021-03-23 | 杉数科技(北京)有限公司 | Directed graph drawing method and chemical material planning method |
CN112580810A (en) * | 2020-12-22 | 2021-03-30 | 济南中科成水质净化有限公司 | Sewage treatment process analysis and diagnosis method based on directed acyclic graph |
CN112711493A (en) * | 2020-12-25 | 2021-04-27 | 上海精鲲计算机科技有限公司 | Scenario root cause analysis application |
CN112887108A (en) * | 2019-11-29 | 2021-06-01 | 中兴通讯股份有限公司 | Fault positioning method, device, equipment and storage medium |
CN113282884A (en) * | 2021-04-28 | 2021-08-20 | 沈阳航空航天大学 | General root cause analysis method |
CN113793128A (en) * | 2021-09-18 | 2021-12-14 | 北京京东振世信息技术有限公司 | Method, device, equipment and computer readable medium for generating business fault reason information |
CN114629776A (en) * | 2020-12-11 | 2022-06-14 | 中国联合网络通信集团有限公司 | Fault analysis method and device based on graph model |
CN117061332A (en) * | 2023-10-11 | 2023-11-14 | 中国人民解放军国防科技大学 | Fault diagnosis method and system based on probability directed graph deep learning |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090157723A1 (en) * | 2007-12-14 | 2009-06-18 | Bmc Software, Inc. | Impact Propagation in a Directed Acyclic Graph |
CN106330501A (en) * | 2015-06-26 | 2017-01-11 | 中兴通讯股份有限公司 | Fault correlation method and device |
-
2018
- 2018-05-15 CN CN201810461456.6A patent/CN110493025B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090157723A1 (en) * | 2007-12-14 | 2009-06-18 | Bmc Software, Inc. | Impact Propagation in a Directed Acyclic Graph |
CN106330501A (en) * | 2015-06-26 | 2017-01-11 | 中兴通讯股份有限公司 | Fault correlation method and device |
Non-Patent Citations (2)
Title |
---|
赵靓: "一种基于多层有向图的故障根因诊断的方法", 《中国优秀硕士学位论文期刊网》 * |
郑皎凌: "基于扰动的亚复杂动力系统因果关系挖掘", 《计算机学报》 * |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112887108A (en) * | 2019-11-29 | 2021-06-01 | 中兴通讯股份有限公司 | Fault positioning method, device, equipment and storage medium |
CN111107158B (en) * | 2019-12-26 | 2023-02-17 | 远景智能国际私人投资有限公司 | Alarm method, device, equipment and medium for Internet of things equipment cluster |
CN111107158A (en) * | 2019-12-26 | 2020-05-05 | 远景智能国际私人投资有限公司 | Alarm method, device, equipment and medium for Internet of things equipment cluster |
CN111639115A (en) * | 2020-04-29 | 2020-09-08 | 国家电网有限公司客户服务中心 | Five-dimensional model-based analysis method for operation and maintenance data abnormity of power grid information system |
CN111913824B (en) * | 2020-06-23 | 2024-03-05 | 中国建设银行股份有限公司 | Method for determining data link fault cause and related equipment |
CN111913824A (en) * | 2020-06-23 | 2020-11-10 | 中国建设银行股份有限公司 | Method for determining data link fault reason and related equipment |
CN111858123B (en) * | 2020-07-29 | 2023-09-26 | 中国工商银行股份有限公司 | Fault root cause analysis method and device based on directed graph network |
CN111858123A (en) * | 2020-07-29 | 2020-10-30 | 中国工商银行股份有限公司 | Fault root cause analysis method and device based on directed graph network |
CN112506763A (en) * | 2020-11-30 | 2021-03-16 | 清华大学 | Automatic positioning method and device for database system fault root |
CN114629776A (en) * | 2020-12-11 | 2022-06-14 | 中国联合网络通信集团有限公司 | Fault analysis method and device based on graph model |
CN112541098A (en) * | 2020-12-17 | 2021-03-23 | 杉数科技(北京)有限公司 | Directed graph drawing method and chemical material planning method |
CN112580810A (en) * | 2020-12-22 | 2021-03-30 | 济南中科成水质净化有限公司 | Sewage treatment process analysis and diagnosis method based on directed acyclic graph |
CN112711493A (en) * | 2020-12-25 | 2021-04-27 | 上海精鲲计算机科技有限公司 | Scenario root cause analysis application |
CN113282884B (en) * | 2021-04-28 | 2023-09-26 | 沈阳航空航天大学 | Universal root cause analysis method |
CN113282884A (en) * | 2021-04-28 | 2021-08-20 | 沈阳航空航天大学 | General root cause analysis method |
CN113793128A (en) * | 2021-09-18 | 2021-12-14 | 北京京东振世信息技术有限公司 | Method, device, equipment and computer readable medium for generating business fault reason information |
CN117061332A (en) * | 2023-10-11 | 2023-11-14 | 中国人民解放军国防科技大学 | Fault diagnosis method and system based on probability directed graph deep learning |
CN117061332B (en) * | 2023-10-11 | 2023-12-29 | 中国人民解放军国防科技大学 | Fault diagnosis method and system based on probability directed graph deep learning |
Also Published As
Publication number | Publication date |
---|---|
CN110493025B (en) | 2022-06-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110493025A (en) | It is a kind of based on the failure root of multilayer digraph because of the method and device of diagnosis | |
CN111047082B (en) | Early warning method and device of equipment, storage medium and electronic device | |
KR102483025B1 (en) | Operational maintenance systems and methods | |
CN104142663B (en) | Industrial equipment and system in cloud platform are proved | |
CN109343995A (en) | Intelligent O&M analysis system based on multi-source heterogeneous data fusion, machine learning and customer service robot | |
KR20180108446A (en) | System and method for management of ict infra | |
CN112817280A (en) | Implementation method for intelligent monitoring alarm system of thermal power plant | |
CN107346466A (en) | A kind of control method and device of electric power dispatching system | |
KR101825881B1 (en) | Method of managing a manufacturing process and system using the same | |
CN108073497A (en) | A kind of multi objective unusual fluctuation analysis method based on data center's data acquisition platform | |
CN102735485B (en) | Excavator, and method and system for determining equipment fault | |
CN109501834A (en) | A kind of point machine failure prediction method and device | |
CN109961204A (en) | Quality of service analysis method and system under a kind of micro services framework | |
CN109840157A (en) | Method, apparatus, electronic equipment and the storage medium of fault diagnosis | |
CN109726200A (en) | Grid information system fault location system and method based on two-way deep neural network | |
CN112580678A (en) | Method and device for constructing cloud network alarm root relation tree model | |
CN103902816A (en) | Electrification detection data processing method based on data mining technology | |
CN109765863A (en) | A kind of device parameter edge calculations method based on cloud platform | |
CN112859822A (en) | Equipment health analysis and fault diagnosis method and system based on artificial intelligence | |
CN105467953A (en) | Knowledge representation facing industrial big data and automation application method thereof | |
CN113542039A (en) | Method for positioning 5G network virtualization cross-layer problem through AI algorithm | |
CN110162445A (en) | The host health assessment method and device of Intrusion Detection based on host log and performance indicator | |
CN112769605B (en) | Heterogeneous multi-cloud operation and maintenance management method and hybrid cloud platform | |
CN105967063A (en) | Failure analyzing and handling system and method of maintenance platform | |
JP7442001B1 (en) | Comprehensive failure diagnosis method for hydroelectric power generation units |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |