CN117194459A - Operation and maintenance knowledge base updating method, system, device and medium based on operation and maintenance event - Google Patents
Operation and maintenance knowledge base updating method, system, device and medium based on operation and maintenance event Download PDFInfo
- Publication number
- CN117194459A CN117194459A CN202311237118.1A CN202311237118A CN117194459A CN 117194459 A CN117194459 A CN 117194459A CN 202311237118 A CN202311237118 A CN 202311237118A CN 117194459 A CN117194459 A CN 117194459A
- Authority
- CN
- China
- Prior art keywords
- maintenance
- knowledge base
- maintenance event
- updating
- entry
- 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
- 238000012423 maintenance Methods 0.000 title claims abstract description 370
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000012549 training Methods 0.000 claims abstract description 45
- 238000012216 screening Methods 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims description 48
- 230000015654 memory Effects 0.000 claims description 11
- 238000010586 diagram Methods 0.000 description 15
- 230000006870 function Effects 0.000 description 11
- 238000012937 correction Methods 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000001351 cycling effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses an operation and maintenance knowledge base updating method, an operation and maintenance knowledge base updating system, an operation and maintenance knowledge base updating device and a storage medium based on operation and maintenance events, wherein the operation and maintenance knowledge base updating method comprises the following steps: acquiring operation and maintenance event data; performing correlation screening on the operation and maintenance event data to obtain a word vector training set; updating the historical operation and maintenance knowledge base model according to the word vector training set to obtain a first operation and maintenance knowledge base model; inputting the received new operation and maintenance event into the first operation and maintenance knowledge base model to obtain a first knowledge base entry, and inputting the new operation and maintenance event into a preset operation and maintenance knowledge base to obtain a second knowledge base entry; and updating the preset operation and maintenance knowledge base according to the first knowledge base entry and the second knowledge base entry. The method can improve the efficiency of data maintenance. The application can be widely applied to the technical field of computer operation and maintenance.
Description
Technical Field
The application relates to the technical field of computer operation and maintenance, in particular to an operation and maintenance knowledge base updating method, an operation and maintenance knowledge base updating system, an operation and maintenance knowledge base updating device and a storage medium based on operation and maintenance events.
Background
Firstly, in the traditional method, when the operation and maintenance knowledge base is updated and searched, and when a new operation and maintenance event is received, related solutions or prompts are searched in the operation and maintenance knowledge base. If found, return to the user directly. If not, judging which class or label the problem belongs to according to the detailed information of the event, then searching the knowledge base under the class continuously to see whether related content can be reused or referenced, and if so, updating the knowledge item. If no relevant solution is found, a new operation and maintenance knowledge base entry needs to be created to solve this problem. After the operation and maintenance event is solved, the contents of the scheme, the steps and the like are added into the new knowledge base entry for subsequent reuse. This conventional method requires manual maintenance and definition of classification, resulting in inefficient maintenance. Therefore, a new operation and maintenance knowledge base updating method based on operation and maintenance events is needed.
Disclosure of Invention
The present application aims to solve at least one of the technical problems existing in the prior art to a certain extent.
Therefore, an object of the embodiments of the present application is to provide a method, a system, a device and a storage medium for updating an operation and maintenance knowledge base based on operation and maintenance events, where the method can improve efficiency.
In order to achieve the technical purpose, the technical scheme adopted by the embodiment of the application comprises the following steps: an operation and maintenance knowledge base updating method based on operation and maintenance events comprises the following steps: acquiring operation and maintenance event data; performing correlation screening on the operation and maintenance event data to obtain a word vector training set; updating the historical operation and maintenance knowledge base model according to the word vector training set to obtain a first operation and maintenance knowledge base model; inputting the received new operation and maintenance event into the first operation and maintenance knowledge base model to obtain a first knowledge base entry, and inputting the new operation and maintenance event into a preset operation and maintenance knowledge base to obtain a second knowledge base entry; and updating the preset operation and maintenance knowledge base according to the first knowledge base entry and the second knowledge base entry.
In addition, according to the method for updating the operation and maintenance knowledge base based on the operation and maintenance event in the above embodiment of the present application, the following additional technical features may be provided:
further, in the embodiment of the present application, the step of performing relevance screening on the operation and maintenance event data to obtain a word vector training set specifically includes: extracting time data corresponding to each operation and maintenance event data; for any two pieces of operation and maintenance event data, when the difference value of the time data of the two pieces of operation and maintenance event data is smaller than or equal to a first preset time, the any two pieces of operation and maintenance event data are related operation and maintenance event combinations with time correlation; traversing and comparing all the operation and maintenance event data to obtain a plurality of operation and maintenance event sets, wherein any operation and maintenance event set comprises a plurality of relevant operation and maintenance event combinations; marking each operation and maintenance event set to a topological directed graph, and calculating to obtain the path length from the starting point to the end point of any two operation and maintenance event data in the operation and maintenance event set on a directed topological space; determining a first operation and maintenance event set according to the path length; the word vector training set is extracted from the first set of operation and maintenance events.
Further, in an embodiment of the present application, the step of determining the first operation and maintenance event set according to the path length specifically includes: when the path length is smaller than a first preset threshold value and the operation and maintenance event data do not have corresponding solutions or prompt data, the two operation and maintenance event data corresponding to the path length are a first operation and maintenance event set; when the operation and maintenance event data have corresponding solutions or prompt data and the path length is smaller than a second preset threshold, the two operation and maintenance event data corresponding to the path length are the first operation and maintenance event set.
Further, in an embodiment of the present application, the step of extracting the word vector training set from the first operation and maintenance event set specifically includes: and for each operation and maintenance event data, the alarm titles corresponding to the root cause objects in the alarm title, solution or prompt data corresponding to the operation and maintenance event data are combined according to the time data to obtain a word vector training set.
Further, in the embodiment of the present application, the step of inputting the new operation and maintenance event into a preset operation and maintenance knowledge base to obtain a second knowledge base entry specifically includes: inputting the new operation and maintenance event into a preset operation and maintenance knowledge base, searching related solutions or prompts, and obtaining root cause alarm data; and determining that the root cause alarm occurs within a preset time interval, and determining a second knowledge base entry.
Further, in the embodiment of the present application, the step of inputting the received new operation and maintenance event into the first operation and maintenance knowledge base model to obtain a first knowledge base entry specifically includes: inputting the new operation and maintenance event into the first operation and maintenance knowledge base model to obtain an associated alarm title with a confidence coefficient greater than a first preset confidence coefficient; and according to the associated alarm title, searching operation and maintenance events occurring in a preset time, marking the operation and maintenance events to the topological directed graph, and determining a plurality of first knowledge base items with confidence degrees sequenced to preset values.
Further, in an embodiment of the present application, the step of updating the preset operation and maintenance repository according to the first repository entry and the second repository entry specifically includes: combining the first knowledge base entry and the second knowledge base entry to obtain a combined knowledge base entry; when the confidence coefficient of any knowledge base entry in the combined knowledge base entries is greater than or equal to a second preset confidence coefficient, adding any knowledge base entry to a preset operation and maintenance knowledge base; and deleting any one knowledge base entry in the merged knowledge base entry when the confidence coefficient of the any one knowledge base entry is smaller than a second preset confidence coefficient.
On the other hand, the embodiment of the application also provides an operation and maintenance knowledge base updating system based on operation and maintenance events, which comprises the following steps:
the acquisition unit is used for acquiring the operation and maintenance event data;
the first processing unit is used for carrying out correlation screening on the operation and maintenance event data to obtain a word vector training set;
the second processing unit is used for updating the historical operation and maintenance knowledge base model according to the word vector training set to obtain a first operation and maintenance knowledge base model;
the third processing unit is used for inputting the received new operation and maintenance event into the first operation and maintenance knowledge base model to obtain a first knowledge base entry, and inputting the new operation and maintenance event into a preset operation and maintenance knowledge base to obtain a second knowledge base entry;
and the fourth processing unit is used for updating the preset operation and maintenance knowledge base according to the first knowledge base entry and the second knowledge base entry.
On the other hand, the application also provides an operation and maintenance knowledge base updating device based on operation and maintenance events, which comprises the following steps:
at least one processor;
at least one memory for storing at least one program;
the at least one program, when executed by the at least one processor, causes the at least one processor to implement an operation and maintenance event based operation and maintenance knowledge base updating method according to any of the summary of the application.
Furthermore, the present application provides a storage medium having stored therein processor-executable instructions which, when executed by a processor, are configured to perform an operation and maintenance knowledge base updating method based on an operation and maintenance event as described in any of the above.
The advantages and benefits of the application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application.
The application can obtain the operation and maintenance event data; performing correlation screening on the operation and maintenance event data to obtain a word vector training set; updating the historical operation and maintenance knowledge base model according to the word vector training set to obtain a first operation and maintenance knowledge base model; inputting the received new operation and maintenance event into a first operation and maintenance knowledge base model to obtain a first knowledge base entry, and inputting the new operation and maintenance event into a preset operation and maintenance knowledge base to obtain a second knowledge base entry; according to the first knowledge base entry and the second knowledge base entry, the preset operation and maintenance knowledge base is updated, and the application can adopt an artificial intelligent model to replace manual maintenance and definition classification, so that the efficiency of data maintenance can be improved.
Drawings
FIG. 1 is a schematic diagram illustrating steps of an operation and maintenance knowledge base updating method based on operation and maintenance events according to an embodiment of the present application;
FIG. 2 is a schematic diagram illustrating steps of performing correlation filtering on operation and maintenance event data to obtain a word vector training set according to an embodiment of the present application;
FIG. 3 is a schematic diagram illustrating steps for determining a first set of operation and maintenance events according to a path length in an embodiment of the present application;
FIG. 4 is a schematic diagram illustrating steps for inputting a new operation and maintenance event into a preset operation and maintenance knowledge base to obtain a second knowledge base entry according to an embodiment of the present application;
FIG. 5 is a schematic diagram illustrating steps for inputting a received new operation and maintenance event into a first operation and maintenance knowledge base model to obtain a first knowledge base entry according to an embodiment of the present application;
FIG. 6 is a schematic diagram illustrating steps for updating a preset operation and maintenance knowledge base according to a first knowledge base entry and a second knowledge base entry in an embodiment of the present application;
FIG. 7 is a schematic diagram illustrating a system for updating an operation and maintenance knowledge base based on operation and maintenance events according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of an operation and maintenance knowledge base updating device based on operation and maintenance events in an embodiment of the application.
Detailed Description
The following describes in detail the principles and processes of the operation and maintenance knowledge base updating method, system, device and storage medium based on operation and maintenance events in the embodiments of the present application with reference to the accompanying drawings.
In the prior art, the following methods are generally used to update and maintain the knowledge base.
Firstly, in the traditional method, when the operation and maintenance knowledge base is updated and searched, and when a new operation and maintenance event is received, related solutions or prompts are searched in the operation and maintenance knowledge base. If found, return to the user directly. If not, judging which class or label the problem belongs to according to the detailed information of the event, then searching the knowledge base under the class continuously to see whether related content can be reused or referenced, and if so, updating the knowledge item. If no relevant solution is found, a new operation and maintenance knowledge base entry needs to be created to solve this problem. After the operation and maintenance event is solved, the contents of the scheme, the steps and the like are added into the new knowledge base entry for subsequent reuse. This conventional method requires manual maintenance and definition of classification, and has a problem of processing efficiency.
And secondly, extracting high-frequency keywords from the operation and maintenance event information by adopting a method based on weak supervision, searching or updating an operation and maintenance knowledge base according to the corresponding classification of keyword association, and correcting the result by combining a knowledge base manual maintenance unit to ensure the accuracy of searching and matching of a knowledge management system. However, the method has the problem that the accuracy is proportional to the amount of manual maintenance, and a large amount of manual maintenance is still required to be input to ensure the accuracy.
In view of the above technical drawbacks, referring to fig. 1, fig. 1 is a schematic step diagram of an operation and maintenance knowledge base updating method based on operation and maintenance events. In fig. 1, the present application provides an operation and maintenance knowledge base updating method based on operation and maintenance events. The method may include, but is not limited to, steps S101-S105 of:
s101, acquiring operation and maintenance event data;
it is understood that the operation and maintenance event may include an alarm title, an alarm text, an alarm time, and an alarm object, and the operation and maintenance event may or may not include a solution or a prompt, and the solution or the prompt may include a root cause object, a root cause alarm, and a solution.
In some alternative embodiments of the present application, the gateway may obtain a search request for accessing a search service from a server or a hardware device connected to the gateway, where the search request may carry product identity information of a product to be accessed. After the gateway itself has processed the data, it can determine the instance of executing the search service and send the search request to the search service.
It will be appreciated that in some alternative embodiments of the application, the data acquisition or acquisition module may acquire the operational event data from a database, which may be operational event data that has occurred. The data acquisition or acquisition module may be a data processing module within the chip or other processing circuitry integrated with the processing chip. The processing circuit and the data processing module can be connected with any hardware device or server for sending the retrieval request, and the retrieval request for accessing the retrieval service can be obtained through wired connection or wireless connection. It should be noted that the limited connection manner may include a connection between a mobile device and a processing module, and may also include a connection between a processing module and a hardware device, and a wired connection between other now known or later developed devices and a processing module; the wireless connection may include, but is not limited to, 3G/4G/5G connection, wiFi connection, bluetooth connection, wiMAX connection, zigbee connection, UWB (Ultra Wid e Band) connection, and other now known or later developed wireless connection.
S102, carrying out correlation screening on operation and maintenance event data to obtain a word vector training set;
in some possible embodiments of the present application, the processor may process the existing operation and maintenance event, the solution or the prompt corresponding to the operation and maintenance event, the time correlation process according to the operation and maintenance event, the space correlation process according to the directed topology, and the error reasoning data saved by the manual correction device, and finally obtain the word vector training set of time-space correlation.
S103, updating the historical operation and maintenance knowledge base model according to the word vector training set to obtain a first operation and maintenance knowledge base model;
in some possible embodiments of the present application, the processor may update the historical operation and maintenance knowledge base model according to the word vector training set to obtain the first operation and maintenance knowledge base model
S104, inputting the received new operation and maintenance event into a first operation and maintenance knowledge base model to obtain a first knowledge base entry, and inputting the new operation and maintenance event into a preset operation and maintenance knowledge base to obtain a second knowledge base entry;
in some possible embodiments of the present application, the processor may input the received new operation and maintenance event into the first operation and maintenance knowledge base model to obtain a first knowledge base entry and input the new operation and maintenance event into the preset operation and maintenance knowledge base to obtain a second knowledge base entry.
S105, updating the preset operation and maintenance knowledge base according to the first knowledge base entry and the second knowledge base entry.
In some possible embodiments of the present application, the processor may update the preset operation and maintenance repository based on the first repository entry and the second repository entry.
It will be appreciated that the processors in steps 2-5 may be different processing modules of the same processor, or may be an integrated system formed by a plurality of processors.
Further, referring to fig. 2, fig. 2 is a schematic diagram of a step of performing correlation filtering on operation and maintenance event data to obtain a word vector training set. In fig. 2, the step of performing correlation filtering on the operation and maintenance event data to obtain a word vector training set may include, but is not limited to, step S201 to step S207.
S201, extracting time data corresponding to each operation and maintenance event data;
s202, for any two operation and maintenance event data, when the difference value of the time data of the two operation and maintenance event data is smaller than or equal to a first preset time, the any two operation and maintenance event data are related operation and maintenance event combinations with time correlation;
s203, traversing and comparing all operation and maintenance event data to obtain a plurality of operation and maintenance event sets, wherein any operation and maintenance event set comprises a plurality of relevant operation and maintenance event combinations;
s204, marking each operation and maintenance event set to a topological directed graph, and calculating to obtain the path length from the starting point to the end point of any two operation and maintenance event data in the operation and maintenance event set in a directed topological space;
s205, determining a first operation and maintenance event set according to the path length;
s206, extracting a word vector training set from the first operation and maintenance event set.
Further, referring to fig. 3, fig. 3 is a schematic diagram illustrating a step of determining a first set of operation and maintenance events according to a path length. In fig. 3, the step of determining the first set of operation and maintenance events may include, but is not limited to, step S301-step S302, depending on the path length.
S301, when the path length is smaller than a first preset threshold value, and the operation and maintenance event data does not have a corresponding solution or prompt data, the two operation and maintenance event data corresponding to the path length are a first operation and maintenance event set;
s302, when the operation and maintenance event data have corresponding solutions or prompt data, and the path length is smaller than a second preset threshold, two operation and maintenance event data corresponding to the path length are the first operation and maintenance event set.
Further, in some possible embodiments of the present application, the step of extracting the word vector training set from the first operation and maintenance event set specifically includes:
for each operation and maintenance event data, the alarm titles corresponding to the root cause objects in the solution or prompt data are combined according to the time data to obtain a word vector training set.
Further, referring to fig. 4, fig. 4 is a schematic diagram illustrating a step of inputting a new operation and maintenance event into a preset operation and maintenance knowledge base to obtain a second knowledge base entry. In fig. 4, the step of inputting a new operation event into the preset operation repository to obtain a second repository entry may include, but is not limited to, steps S401-S402.
S401, inputting a new operation and maintenance event into a preset operation and maintenance knowledge base, searching related solutions or prompts, and obtaining root cause alarm data;
s402, determining that root cause alarm occurs within a preset time interval, and determining a second knowledge base entry.
Further, referring to fig. 5, fig. 5 is a schematic diagram of a step of inputting a received new operation and maintenance event into a first operation and maintenance knowledge base model to obtain a first knowledge base entry. In fig. 5, the step of inputting the received new operation and maintenance event into the first operation and maintenance knowledge base model to obtain the first knowledge base entry may include, but is not limited to, step S501-step S502.
S501, inputting a new operation and maintenance event into a first operation and maintenance knowledge base model to obtain an associated alarm title with a confidence coefficient greater than a first preset confidence coefficient;
s502, according to the associated alarm title, searching operation and maintenance events occurring in a preset time, marking the operation and maintenance events to a topological directed graph, and determining a plurality of first knowledge base items with confidence degrees ordered to be preset values.
Further, referring to fig. 6, fig. 6 is a schematic diagram of a step of updating a preset operation and maintenance knowledge base according to a first knowledge base entry and a second knowledge base entry. In fig. 6, the step of updating the preset operation and maintenance knowledge base according to the first knowledge base entry and the second knowledge base entry may include, but is not limited to, step S601-step S603.
S601, merging the first knowledge base entry and the second knowledge base entry to obtain a merged knowledge base entry;
s602, when the confidence coefficient of any knowledge base entry in the combined knowledge base entries is greater than or equal to a second preset confidence coefficient, adding any knowledge base entry to a preset operation and maintenance knowledge base;
s603, deleting any one knowledge base item when the confidence coefficient of any one knowledge base item in the combined knowledge base items is smaller than the second preset confidence coefficient.
Specifically, the steps of the present application will be described below with reference to specific examples:
step 1, an existing operation and maintenance event training set Q1 is obtained, including a topology directed graph of a node where an operation and maintenance event object is located, an operation and maintenance event corresponding solution method, and a root cause alarm (an unnecessary item may be empty, and an existing operation and maintenance knowledge base is provided with a solution or a prompt).
And 2, processing the operation and maintenance event training set Q1 according to time correlation processing and space correlation processing on directed topology of the operation and maintenance events and error reasoning data stored by the manual correction device, and finally obtaining a word vector training set Wn of time-space correlation. Wherein step 2 may comprise steps a-e
a) Taking the time of each operation and maintenance event as a starting point, taking a time interval parameter of 30 minutes T as a slice, removing error reasoning data stored by the manual correction device, and obtaining operation and maintenance event sets S1, S2, sn and Sn which have time correlation in a time range of T, wherein the operation and maintenance event sets are ordered according to time;
b) And marking each operation and maintenance event set Sn to a topological directed graph through CMDB information, calculating to obtain the reachable path length L from the starting point to the end point of each operation and maintenance event on the directed topological space, and slicing the topological directed graph by path length parameters L1 and L2, wherein the parameter L1 is smaller than the parameter L2.
c) The method comprises the steps that an operation and maintenance event of a starting point is not solved, a path length parameter L1 and an operation and maintenance event of a path length L < =L1 of which the end point can reach are combined into an operation and maintenance event set Tn;
d) The method comprises the steps that a starting point operation and maintenance event has a corresponding root cause alarm, a path length parameter L2 is taken, a node where an object generating the root cause alarm is located is taken as an end point, and an operation and maintenance event combination of L < = L2 is added to an operation and maintenance event set Tn;
e) And for each operation and maintenance event set Tn, the alarm title and the alarm title of the root cause object are taken and combined into a word vector training set Wn according to time.
And step 3, periodically acquiring an incremental operation and maintenance event set Q2 relative to the Q1, wherein the incremental operation and maintenance event set Q2 comprises a topological directed graph of a node where an operation and maintenance event object is located, an operation and maintenance event corresponding solution method and a root cause alarm (an optional item can be empty, and an existing operation and maintenance knowledge base with a solution or a prompt is provided).
And 4, processing the incremental operation and maintenance event training set Q2, processing the time correlation processing and the space correlation processing on the directed topology according to the time of the operation and maintenance event, and processing the error reasoning data stored by the manual correction device, and finally obtaining a word vector training set Wn of time-space correlation. Wherein step 3 may comprise steps a1-e1
a1 Taking the time of each operation and maintenance event as a starting point, taking a time interval parameter of 30 minutes T as a slice, removing error reasoning data stored by the manual correction device, and obtaining operation and maintenance event sets S1, S2, sn and Sn which have time correlation in a time range of T, wherein the operation and maintenance event sets are ordered according to time;
b1 For each operation and maintenance event set Sn, marking the topology directed graph through CMDB information, calculating to obtain the reachable path length L from the starting point to the end point of each operation and maintenance event on the directed topology space, and slicing the topology directed graph by path length parameters L1 and L2, wherein the parameter L1 is smaller than the parameter L2.
c1 The starting point operation and maintenance event has no solution, and the operation and maintenance event combination of the path length parameter L1 and the path length L < = L1 which can be reached by the end point is taken as an operation and maintenance event set Tn;
d1 The starting point operation and maintenance event has a corresponding root cause alarm, a path length parameter L2 is taken, a node where an object generating the root cause alarm is located is taken as an end point, and an operation and maintenance event combination of L < = L2 is added to an operation and maintenance event set Tn;
e1 For each operation and maintenance event set Tn, the alarm title and the alarm title of the root cause object are taken and combined into a word vector training set In of increment according to time
And 5, combining the incremental Word vector training set W with the existing Word vector training set W to serve as a full Word vector training set W, training by using a Word2Vec algorithm to obtain a latest operation and maintenance knowledge base model M, and storing the full Word vector training set W for the next periodic training.
Step 6, when a new operation and maintenance event is received, firstly searching the knowledge item K1 obtained by the existing operation and maintenance knowledge base, and searching the operation and maintenance knowledge base model M to obtain the associated knowledge item K2 of model reasoning; wherein step 5 may comprise a2-c2
a2 When a new operation and maintenance event is received, searching for related solutions or prompts in the existing operation and maintenance knowledge base to obtain root cause alarms, judging whether related root cause alarms occur in the latest time interval T, and if so, obtaining a knowledge item K1.
b2 Meanwhile, the operation and maintenance knowledge base model M is searched for the new operation and maintenance event according to the alarm title, the associated alarm title and the confidence coefficient are obtained, and the result Rn of the confidence coefficient > =90%P of the parameter is obtained.
c2 And (3) as a result Rn, retrieving operation and maintenance events (eliminating error data stored by the manual correction device) occurring in the time interval T according to the time interval parameter T, marking data with an alarm title Rn to a topological directed graph, taking a starting point as a newly received alarm event, taking TOP N5 as an alternative knowledge base item K2 according to the confidence level ranking, wherein the length of an end point path does not exceed the set of the parameter L1.
Step 7, the confidence level cond of the knowledge item K1 retrieved by the existing knowledge base is 100%, the knowledge item K1 is combined into the operation and maintenance knowledge base model M, the retrieved knowledge item K2 is sequenced to an operation and maintenance engineer according to the confidence level, and the operation and maintenance engineer can directly correct the inferred knowledge item K2 through a manual correction device: if the mark is accurate, the existing knowledge base is newly added, and if the mark is wrong, the error data is kept.
Step 8, continuously cycling the steps 3 to 6 to obtain the operation and maintenance knowledge base updating method and device based on operation and maintenance events, and meanwhile, the method can improve the accuracy along with the use time, and meanwhile, the manual maintenance amount can be greatly reduced because model reasoning data are used as references.
In summary, compared with the traditional method, the method has the following advantages:
1. the knowledge item of model reasoning can greatly reduce the workload of manually maintaining the knowledge base and improve the efficiency of updating the knowledge base.
2. Compared with the weak supervision method, the method can improve the accuracy of reasoning knowledge items through the correlation in alarm time and the correlation in directed topology, and achieves the purpose of using less manual maintenance workload, thereby obtaining high accuracy.
In addition, referring to fig. 7, corresponding to the method of fig. 1, an operation and maintenance knowledge base updating system based on operation and maintenance events is further provided in an embodiment of the present application, where the system may include: an acquisition unit 1001, a first processing unit 1002, a second processing unit 1003, a third processing unit 1004, and a fourth processing unit 1005. The acquiring unit 1001 may be configured to acquire operation and maintenance event data; the first processing unit 1002 may be configured to perform correlation screening on the operation and maintenance event data, to obtain a word vector training set; the second processing unit 1003 may be configured to update the historical operation and maintenance knowledge base model according to the word vector training set, so as to obtain a first operation and maintenance knowledge base model; the third processing unit 1004 may be configured to input the received new operation and maintenance event into the first operation and maintenance knowledge base model to obtain a first knowledge base entry, and input the new operation and maintenance event into the preset operation and maintenance knowledge base to obtain a second knowledge base entry; the fourth processing unit 1005 may be configured to update the preset operation and maintenance repository according to the first repository entry and the second repository entry.
It is understood that the acquisition unit may be any integrated circuit unit or a micro processor unit obtained by integrating a chip having a processing function and its peripheral circuits by the existing integration technology. The processing unit may be any integrated circuit unit or micro-processor unit obtained by integrating a chip with a processing function and its peripheral circuits in the prior art. And the processing unit may also include one or more memories. One or more memories may be used to store data such as mapping table information or search results.
In some embodiments of the present application, the obtaining unit 1001 may be provided in the same gateway or a device with a processor as the first processing unit 1002. The acquisition unit 1001 may acquire a search request to access a search service through a chip inside its own processor. The first processing unit 1002 may receive the request, determine a first instance of the search service according to the product identity information and the mapping table information in the request, and send the search request to the search service, so that the search service obtains a search result according to the search request and a plurality of search service instances that have loaded the index file. The acquisition unit 1001 may be any unit connected to a gateway or a processor inside a device. The acquisition unit 1001 may transmit the acquired data to the processor of the first processing unit 1002 through a wired or wireless connection with the processor. The processor of the first processing unit 1002 may perform data processing through an internal chip, to finally obtain a search result. The specific device connection manner and the device arrangement of the acquisition unit 1001 and the first processing unit 1002 are not limited. It is understood that any two of the second processing unit 1003, the third processing unit 1004, and the fourth processing unit 1005 may be the same connection manner of the acquisition unit 1001 and the first processing unit 1002.
It should be noted that, the content in the embodiment of the operation and maintenance event-based operation and maintenance knowledge base updating method is applicable to the embodiment of the operation and maintenance knowledge base updating system based on operation and maintenance events, and the functions specifically realized by the embodiment of the operation and maintenance event-based operation and maintenance knowledge base updating system are the same as those of the embodiment of the operation and maintenance event-based operation and maintenance knowledge base updating method, and the achieved beneficial effects are the same as those of the embodiment of the operation and maintenance event-based operation and maintenance knowledge base updating method.
Corresponding to the method of fig. 1, the embodiment of the present application further provides an operation and maintenance knowledge base updating device based on operation and maintenance events, and the specific structure of the operation and maintenance knowledge base updating device may refer to fig. 8, including:
at least one processor 1011;
at least one memory 1012 for storing at least one program;
the at least one program, when executed by the at least one processor, causes the at least one processor to implement an operation and maintenance event based operation and maintenance knowledge base updating method.
It should be noted that, the content in the above method embodiment is applicable to the embodiment of the present device, and the specific functions implemented by the embodiment of the present device are the same as those of the embodiment of the above method, and the achieved beneficial effects are the same as those of the embodiment of the above method.
Corresponding to the method of fig. 1, an embodiment of the present application further provides a storage medium having stored therein processor-executable instructions which, when executed by a processor, are adapted to perform the described method for updating an operation and maintenance knowledge base based on operation and maintenance events.
It should be noted that, the content in the above embodiment of the operation and maintenance event-based operation and maintenance knowledge base updating method is applicable to the embodiment of the storage medium, and the functions specifically implemented by the embodiment of the storage medium are the same as those of the embodiment of the operation and maintenance event-based operation and maintenance knowledge base updating method, and the achieved beneficial effects are the same as those of the embodiment of the operation and maintenance event-based operation and maintenance knowledge base updating method.
In some alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flowcharts of the present application are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed, and in which sub-operations described as part of a larger operation are performed independently.
Furthermore, while the application is described in the context of functional modules, it should be appreciated that, unless otherwise indicated, one or more of the functions and/or features may be integrated in a single physical device and/or software module or may be implemented in separate physical devices or software modules. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary to an understanding of the present application. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be apparent to those skilled in the art from consideration of their attributes, functions and internal relationships. Accordingly, one of ordinary skill in the art can implement the application as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative and are not intended to be limiting upon the scope of the application, which is to be defined in the appended claims and their full scope of equivalents.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in the form of a software product stored in a storage medium, including several programs for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable programs for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with a program execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the programs from the program execution system, apparatus, or device and execute the programs. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the program execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable program execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
In the foregoing description of the present specification, reference has been made to the terms "one embodiment/example", "another embodiment/example", "certain embodiments/examples", and the like, means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present application have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the application, the scope of which is defined by the claims and their equivalents.
While the preferred embodiment of the present application has been described in detail, the present application is not limited to the embodiments described above, and various equivalent modifications and substitutions can be made by those skilled in the art without departing from the spirit of the present application, and these equivalent modifications and substitutions are intended to be included in the scope of the present application as defined in the appended claims.
Claims (10)
1. An operation and maintenance knowledge base updating method based on operation and maintenance events is characterized by comprising the following steps:
acquiring operation and maintenance event data;
performing correlation screening on the operation and maintenance event data to obtain a word vector training set;
updating the historical operation and maintenance knowledge base model according to the word vector training set to obtain a first operation and maintenance knowledge base model;
inputting the received new operation and maintenance event into the first operation and maintenance knowledge base model to obtain a first knowledge base entry, and inputting the new operation and maintenance event into a preset operation and maintenance knowledge base to obtain a second knowledge base entry;
and updating the preset operation and maintenance knowledge base according to the first knowledge base entry and the second knowledge base entry.
2. The method for updating an operation and maintenance knowledge base based on operation and maintenance events according to claim 1, wherein the step of performing correlation screening on the operation and maintenance event data to obtain a word vector training set specifically comprises the following steps:
extracting time data corresponding to each operation and maintenance event data;
for any two pieces of operation and maintenance event data, when the difference value of the time data of the two pieces of operation and maintenance event data is smaller than or equal to a first preset time, the any two pieces of operation and maintenance event data are related operation and maintenance event combinations with time correlation;
traversing and comparing all the operation and maintenance event data to obtain a plurality of operation and maintenance event sets, wherein any operation and maintenance event set comprises a plurality of relevant operation and maintenance event combinations;
marking each operation and maintenance event set to a topological directed graph, and calculating to obtain the path length from the starting point to the end point of any two operation and maintenance event data in the operation and maintenance event set on a directed topological space;
determining a first operation and maintenance event set according to the path length;
the word vector training set is extracted from the first set of operation and maintenance events.
3. The method for updating an operation and maintenance knowledge base based on operation and maintenance events according to claim 2, wherein the step of determining the first operation and maintenance event set according to the path length specifically comprises:
when the path length is smaller than a first preset threshold value and the operation and maintenance event data do not have corresponding solutions or prompt data, the two operation and maintenance event data corresponding to the path length are a first operation and maintenance event set;
when the operation and maintenance event data have corresponding solutions or prompt data and the path length is smaller than a second preset threshold, the two operation and maintenance event data corresponding to the path length are the first operation and maintenance event set.
4. The method for updating an operation and maintenance knowledge base based on operation and maintenance events according to claim 3, wherein the step of extracting the word vector training set from the first operation and maintenance event set specifically comprises:
and for each operation and maintenance event data, the alarm titles corresponding to the root cause objects in the alarm title, solution or prompt data corresponding to the operation and maintenance event data are combined according to the time data to obtain a word vector training set.
5. The method for updating an operation and maintenance knowledge base based on operation and maintenance events according to claim 1, wherein the step of inputting the new operation and maintenance event into a preset operation and maintenance knowledge base to obtain a second knowledge base entry specifically comprises the following steps:
inputting the new operation and maintenance event into a preset operation and maintenance knowledge base, searching related solutions or prompts, and obtaining root cause alarm data;
and determining that the root cause alarm occurs within a preset time interval, and determining a second knowledge base entry.
6. The method for updating an operation and maintenance knowledge base based on operation and maintenance events according to claim 1, wherein the step of inputting the received new operation and maintenance event into the first operation and maintenance knowledge base model to obtain a first knowledge base entry specifically comprises:
inputting the new operation and maintenance event into the first operation and maintenance knowledge base model to obtain an associated alarm title with a confidence coefficient greater than a first preset confidence coefficient;
and according to the associated alarm title, searching operation and maintenance events occurring in a preset time, marking the operation and maintenance events to the topological directed graph, and determining a plurality of first knowledge base items with confidence degrees sequenced to preset values.
7. The method for updating an operation and maintenance knowledge base based on operation and maintenance events according to claim 1, wherein the step of updating the preset operation and maintenance knowledge base according to the first knowledge base entry and the second knowledge base entry specifically comprises:
combining the first knowledge base entry and the second knowledge base entry to obtain a combined knowledge base entry;
when the confidence coefficient of any knowledge base entry in the combined knowledge base entries is greater than or equal to a second preset confidence coefficient, adding any knowledge base entry to a preset operation and maintenance knowledge base;
and deleting any one knowledge base entry in the merged knowledge base entry when the confidence coefficient of the any one knowledge base entry is smaller than a second preset confidence coefficient.
8. An operation and maintenance knowledge base updating system based on operation and maintenance events, which is characterized by comprising:
the acquisition unit is used for acquiring the operation and maintenance event data;
the first processing unit is used for carrying out correlation screening on the operation and maintenance event data to obtain a word vector training set;
the second processing unit is used for updating the historical operation and maintenance knowledge base model according to the word vector training set to obtain a first operation and maintenance knowledge base model;
the third processing unit is used for inputting the received new operation and maintenance event into the first operation and maintenance knowledge base model to obtain a first knowledge base entry, and inputting the new operation and maintenance event into a preset operation and maintenance knowledge base to obtain a second knowledge base entry;
and the fourth processing unit is used for updating the preset operation and maintenance knowledge base according to the first knowledge base entry and the second knowledge base entry.
9. An operation and maintenance knowledge base updating device based on operation and maintenance events, which is characterized by comprising:
at least one processor;
at least one memory for storing at least one program;
the at least one program, when executed by the at least one processor, causes the at least one processor to implement an operation and maintenance knowledge base updating method based on operation and maintenance events as claimed in any one of claims 1 to 7.
10. A storage medium having stored therein processor-executable instructions which, when executed by a processor, are for performing an operation and maintenance event based operation and maintenance repository updating method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311237118.1A CN117194459B (en) | 2023-09-22 | 2023-09-22 | Operation and maintenance knowledge base updating method, system, device and medium based on operation and maintenance event |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311237118.1A CN117194459B (en) | 2023-09-22 | 2023-09-22 | Operation and maintenance knowledge base updating method, system, device and medium based on operation and maintenance event |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117194459A true CN117194459A (en) | 2023-12-08 |
| CN117194459B CN117194459B (en) | 2024-05-10 |
Family
ID=89003272
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311237118.1A Active CN117194459B (en) | 2023-09-22 | 2023-09-22 | Operation and maintenance knowledge base updating method, system, device and medium based on operation and maintenance event |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117194459B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104361062A (en) * | 2014-11-03 | 2015-02-18 | 百度在线网络技术（北京）有限公司 | Associated information recommendation method and device |
| CN108073711A (en) * | 2017-12-21 | 2018-05-25 | 北京大学深圳研究生院 | A kind of Relation extraction method and system of knowledge based collection of illustrative plates |
| CN108874783A (en) * | 2018-07-12 | 2018-11-23 | 国网福建省电力有限公司 | Power information O&M knowledge model construction method |
| CN109063048A (en) * | 2018-07-18 | 2018-12-21 | 哈尔滨工业大学 | A kind of matched data cleaning method of knowledge based library figure and device |
| CN112163422A (en) * | 2020-09-25 | 2021-01-01 | 和美（深圳）信息技术股份有限公司 | Method and system for generating word vector based on dictionary |
| CN113627148A (en) * | 2021-05-19 | 2021-11-09 | 中国银行股份有限公司 | Automatic association method and device for knowledge in knowledge base |
| WO2022007108A1 (en) * | 2020-07-07 | 2022-01-13 | 南京邮电大学 | Deep learning-based network alarm positioning method |
| CN114064855A (en) * | 2021-11-10 | 2022-02-18 | 国电南瑞南京控制系统有限公司 | Information retrieval method and system based on transformer knowledge base |
-
2023
- 2023-09-22 CN CN202311237118.1A patent/CN117194459B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104361062A (en) * | 2014-11-03 | 2015-02-18 | 百度在线网络技术（北京）有限公司 | Associated information recommendation method and device |
| CN108073711A (en) * | 2017-12-21 | 2018-05-25 | 北京大学深圳研究生院 | A kind of Relation extraction method and system of knowledge based collection of illustrative plates |
| CN108874783A (en) * | 2018-07-12 | 2018-11-23 | 国网福建省电力有限公司 | Power information O&M knowledge model construction method |
| CN109063048A (en) * | 2018-07-18 | 2018-12-21 | 哈尔滨工业大学 | A kind of matched data cleaning method of knowledge based library figure and device |
| WO2022007108A1 (en) * | 2020-07-07 | 2022-01-13 | 南京邮电大学 | Deep learning-based network alarm positioning method |
| CN112163422A (en) * | 2020-09-25 | 2021-01-01 | 和美（深圳）信息技术股份有限公司 | Method and system for generating word vector based on dictionary |
| CN113627148A (en) * | 2021-05-19 | 2021-11-09 | 中国银行股份有限公司 | Automatic association method and device for knowledge in knowledge base |
| CN114064855A (en) * | 2021-11-10 | 2022-02-18 | 国电南瑞南京控制系统有限公司 | Information retrieval method and system based on transformer knowledge base |
Non-Patent Citations (2)
| Title |
|---|
| JIAN DANG 等: "Construction of knowledge graph of electrical equipment based on sentence-BERT", 《2021 INTERNATIONAL CONFERENCE ON ADVANCED ELECTRICAL EQUIPMENT AND RELIABLE OPERATION》, 16 January 2022 (2022-01-16), pages 1 - 2 * |
| 罗婉丽 等: "结合拓扑势与TextRank算法的关键词提取方法", 《计算机应用与软件》, vol. 39, no. 1, 12 January 2022 (2022-01-12), pages 334 - 338 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117194459B (en) | 2024-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3964976A1 (en) | Cloud inference system | |
| CN201402459Y (en) | Test case management device | |
| CN109947729B (en) | Real-time data analysis method and device | |
| CN112148733A (en) | Method, device, electronic device and computer readable medium for determining fault type | |
| US20230315727A1 (en) | Cost-based query optimization for untyped fields in database systems | |
| CN112083812A (en) | Associative word determining method and device, storage medium and electronic equipment | |
| CN113254630A (en) | Domain knowledge map recommendation method for global comprehensive observation results | |
| CN111125213A (en) | Data acquisition method, device and system | |
| CN107851098A (en) | Concatenated data set | |
| CN102654879B (en) | Search method and device | |
| CN117194459B (en) | Operation and maintenance knowledge base updating method, system, device and medium based on operation and maintenance event | |
| CN116303628B (en) | Alarm data query method, system and equipment based on elastic search | |
| CN103365778B (en) | A kind of method and apparatus testing control | |
| CN117609153A (en) | Electronic archive management method and device based on multi-source heterogeneous | |
| CN115221119A (en) | File searching method and device, storage medium and electronic equipment | |
| EP3625703A1 (en) | System and method for enabling related searches for live events in data streams | |
| CN111143582B (en) | Multimedia resource recommendation method and device for updating association words in double indexes in real time | |
| CN108614818B (en) | Data storage, updating and query method and device | |
| CN113505142A (en) | Data query method and device and server | |
| CN113627148A (en) | Automatic association method and device for knowledge in knowledge base | |
| CN104572879A (en) | Method and device for updating index table and method and device for searching based on index table | |
| CN115391355B (en) | Data processing method, device, equipment and storage medium | |
| CN117909301B (en) | Index-based object query method, device, equipment and medium | |
| CN116226231B (en) | Data segmentation method and related device | |
| CN109905475B (en) | Method for outputting cloud computing monitoring data in specified format based on SQL |
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 |