CN115587188A - Operation and maintenance knowledge map acquisition and application method, device, equipment and storage medium - Google Patents

Operation and maintenance knowledge map acquisition and application method, device, equipment and storage medium Download PDF

Info

Publication number
CN115587188A
CN115587188A CN202211186399.8A CN202211186399A CN115587188A CN 115587188 A CN115587188 A CN 115587188A CN 202211186399 A CN202211186399 A CN 202211186399A CN 115587188 A CN115587188 A CN 115587188A
Authority
CN
China
Prior art keywords
maintenance
work order
knowledge
entities
maintenance knowledge
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.)
Pending
Application number
CN202211186399.8A
Other languages
Chinese (zh)
Inventor
黄苛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
CCB Finetech Co Ltd
Original Assignee
CCB Finetech Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by CCB Finetech Co Ltd filed Critical CCB Finetech Co Ltd
Priority to CN202211186399.8A priority Critical patent/CN115587188A/en
Publication of CN115587188A publication Critical patent/CN115587188A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367—Ontology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G06F16/353—Clustering; Classification into predefined classes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/02—Knowledge representation; Symbolic representation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Computational Linguistics (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Economics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Animal Behavior & Ethology (AREA)
  • Evolutionary Computation (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The disclosure provides an operation and maintenance knowledge graph obtaining and application method, device, equipment and storage medium, which can be applied to the technical field of operation and maintenance services. The method comprises the following steps: acquiring operation and maintenance resource data from a device information resource library; carrying out structured identification on the operation and maintenance resource data to obtain static operation and maintenance knowledge, wherein the static operation and maintenance knowledge comprises a plurality of first entities; acquiring real-time operation and maintenance service work order data; carrying out unstructured identification on the operation and maintenance service worksheet data by adopting a pre-trained knowledge extraction model to obtain dynamic operation and maintenance knowledge, wherein the dynamic operation and maintenance knowledge comprises a plurality of second entities; acquiring historical association relations between a plurality of first entities and a plurality of second entities; reasoning according to first similarities among the first entities, second similarities among the second entities and historical incidence relations to obtain a new incidence relation corresponding to the first entities in the operation and maintenance service work order data; and obtaining the operation and maintenance knowledge graph according to the new association relation.

Description

Operation and maintenance knowledge map acquisition and application method, device, equipment and storage medium
Technical Field
The present disclosure relates to the field of operation and maintenance services, and in particular, to an operation and maintenance knowledge graph obtaining and applying method, apparatus, device, medium, and program product.
Background
The operation and maintenance service work order records various operation and maintenance works (including but not limited to change, troubleshooting, routing inspection and the like) in the operation and maintenance process, and a large amount of precious operation and maintenance service experience is precipitated. If the part of the operation and maintenance service experience can be automatically extracted from the operation and maintenance service worksheet and automatically updated to the operation and maintenance knowledge map, the quick replication and low-cost multiplexing of the operation and maintenance service experience can be possible.
The operation and maintenance service work orders have a large number, the work orders have correlation, and the filling of text type fields (such as fault description, business influence, reason analysis, disposal scheme and the like) is different from person to person. At present, the knowledge extraction is carried out in a manual mode, the conditions of large workload, long time consumption and the like exist, and the requirement of automatic timing update of the operation and maintenance knowledge graph is difficult to meet. Moreover, the comprehension of the text type field varies from person to person, and the extraction quality of the operation and maintenance knowledge is difficult to guarantee. Or, the method completely depends on semantic analysis and machine learning, has higher requirements on computing resources and has high training cost.
Disclosure of Invention
In view of the foregoing, the present disclosure provides an operation and maintenance knowledge-graph acquisition and application method, apparatus, device, medium, and program product.
According to a first aspect of the present disclosure, there is provided an operation and maintenance knowledge graph acquisition method, including: acquiring operation and maintenance resource data from a device information resource library; carrying out structured identification on the operation and maintenance resource data to obtain static operation and maintenance knowledge, wherein the static operation and maintenance knowledge comprises a plurality of first entities; acquiring real-time operation and maintenance service work order data; carrying out unstructured identification on the operation and maintenance service worksheet data by adopting a pre-trained knowledge extraction model to obtain dynamic operation and maintenance knowledge, wherein the dynamic operation and maintenance knowledge comprises a plurality of second entities; obtaining historical association relations between a plurality of first entities and a plurality of second entities; reasoning according to first similarities among the first entities, second similarities among the second entities and historical incidence relations to obtain a new incidence relation corresponding to the first entities in the operation and maintenance service work order data; and obtaining the operation and maintenance knowledge graph according to the new association relation.
According to the embodiment of the disclosure, the operation and maintenance resource data are structurally identified, and the obtaining of the static operation and maintenance knowledge comprises the following steps: regularly pulling operation and maintenance resource data from the equipment information resource library by adopting a preset tool; carrying out entity identification, entity relationship identification and entity attribute identification on the operation and maintenance resource data to obtain relational data consisting of entities, entity relationships and entity attributes; and converting the relational data into RDF triples to obtain the static operation and maintenance knowledge.
According to the embodiment of the disclosure, the operation and maintenance knowledge map obtaining method further comprises the following steps: constructing an operation and maintenance field corpus based on static operation and maintenance knowledge and operation and maintenance service work order data; calculating a third similarity between the operation and maintenance service work order data and words in the operation and maintenance field corpus; screening out entity pairs corresponding to words with third similarity larger than a preset value; and taking sentences containing entity pairs as training samples, and training to obtain a knowledge extraction model.
According to the embodiment of the disclosure, the operation and maintenance field corpus is constructed based on the static operation and maintenance knowledge and the operation and maintenance service work order data, and the method comprises the following steps: constructing an initial operation and maintenance field corpus; outputting the relational data to an initial operation and maintenance field corpus; performing word segmentation on the operation and maintenance service work order data, removing stop words, and calculating the weighting weight of the remaining words; and outputting the words meeting the preset weight to the initial operation and maintenance field corpus to obtain the operation and maintenance field corpus.
According to an embodiment of the present disclosure, obtaining historical association relationships between a plurality of first entities and a plurality of second entities includes: acquiring a historical operation and maintenance service work order, wherein the historical operation and maintenance service work order comprises a first change application work order and an event management work order; establishing a plurality of sub work orders of a first change application work order; acquiring a first work order incidence relation between a first change application work order and a plurality of sub work orders, and a first work order resource incidence relation between the first change application work order and a plurality of first entities and a plurality of second entities contained in the first change application work order; obtaining a historical incidence relation based on the first work order incidence relation and the first work order resource incidence relation; and/or establishing a second change application work order corresponding to the event management work order; acquiring a second work order incidence relation between the event management work order and a second change application work order, and a second work order resource incidence relation between the event management work order and a plurality of first entities and a plurality of second entities contained in the event management work order; and obtaining a historical incidence relation based on the second work order incidence relation and the second work order resource incidence relation.
A second aspect of the present disclosure provides an operation and maintenance knowledge graph application method, where an operation and maintenance knowledge graph obtained by using an operation and maintenance knowledge graph obtaining method according to any embodiment of the present disclosure includes: acquiring an operation and maintenance service work order to be processed; retrieving operation and maintenance knowledge associated with the operation and maintenance service work order to be processed in the operation and maintenance knowledge map, and calculating a fourth similarity; based on the business correlation and the fourth similarity, sorting the operation and maintenance knowledge according to the weight; and processing the operation and maintenance service work order to be processed according to the operation and maintenance knowledge with the highest weight.
According to the embodiment of the disclosure, the operation and maintenance knowledge graph application method further comprises the following steps: and updating the weight of the corresponding operation and maintenance knowledge in the operation and maintenance knowledge map according to the operation and maintenance knowledge with the highest weight.
A third aspect of the present disclosure provides an operation and maintenance knowledge graph obtaining apparatus, including: the first acquisition module is used for acquiring operation and maintenance resource data from the equipment information resource library; the first identification module is used for carrying out structured identification on the operation and maintenance resource data to obtain static operation and maintenance knowledge, and the static operation and maintenance knowledge comprises a plurality of first entities; the second acquisition module is used for acquiring real-time operation and maintenance service work order data; the second identification module is used for carrying out unstructured identification on the operation and maintenance service worksheet data by adopting a pre-trained knowledge extraction model to obtain dynamic operation and maintenance knowledge, and the dynamic operation and maintenance knowledge comprises a plurality of second entities; the third acquisition module is used for acquiring historical association relations between the plurality of first entities and the plurality of second entities; the reasoning module is used for reasoning and obtaining a new incidence relation corresponding to the first entity in the operation and maintenance service work order data according to the first similarity among the first entities, the second similarity among the second entities and the historical incidence relation; and the map acquisition module is used for acquiring the operation and maintenance knowledge map according to the new association relation.
A fourth aspect of the present disclosure provides an electronic device, comprising: one or more processors; a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the above-described operation and maintenance knowledge-graph acquisition method.
The fifth aspect of the present disclosure also provides a computer-readable storage medium, on which executable instructions are stored, and when executed by a processor, the instructions cause the processor to execute the operation and maintenance knowledge graph obtaining method.
A sixth aspect of the present disclosure also provides a computer program product comprising a computer program that, when executed by a processor, implements the operation and maintenance knowledge-graph acquisition method described above.
According to the operation and maintenance knowledge map obtaining method, device, equipment, medium and program product provided by the disclosure, static operation and maintenance knowledge is extracted from an IT equipment resource library, dynamic operation and maintenance knowledge is extracted from an operation and maintenance service work order, then entity similarity in the static operation and maintenance knowledge and the dynamic operation and maintenance knowledge is respectively calculated, based on historical associated data between static entities and dynamic entities in a historical service work order, the dynamic operation and maintenance knowledge and the static operation and maintenance knowledge can be fused and inferred to obtain a new association relation between the static entities and the historical dynamic entities corresponding to the real-time work order, and then the operation and maintenance knowledge map containing the new association relation and the related entities is obtained.
Because the change frequency of the static entity is low, and the change frequency of the dynamic entity is high, the static operation and maintenance knowledge and the dynamic operation and maintenance knowledge are extracted separately, the static operation and maintenance knowledge can be extracted by adopting a simple extraction method, the system resources are greatly saved, the knowledge extraction cost is reduced, the knowledge extraction model has knowledge expansion capability through dynamic and static knowledge fusion and reasoning, and the problem that the operation and maintenance knowledge map automatically processes similar machines (namely the static entity) can be realized, so that the problems of large workload, long time consumption and low quality of manual extraction of the operation and maintenance knowledge are at least partially solved, and the technical effect of automatically acquiring the operation and maintenance knowledge map at low cost is realized.
Drawings
The foregoing and other objects, features and advantages of the disclosure will be apparent from the following description of embodiments of the disclosure, which proceeds with reference to the accompanying drawings, in which:
FIG. 1 schematically illustrates an application scenario diagram of an operation and maintenance knowledge-graph acquisition method, apparatus, device, medium and program product according to an embodiment of the disclosure;
FIG. 2 schematically illustrates a flow chart of an operation and maintenance knowledge-graph acquisition method according to an embodiment of the disclosure;
FIG. 3 schematically illustrates a flow diagram of a method of extracting static operation and maintenance knowledge according to an embodiment of the disclosure;
FIG. 4 schematically illustrates a static operation and maintenance knowledge composition diagram according to an embodiment of the disclosure;
FIG. 5 schematically illustrates a flow diagram of a method of training a knowledge extraction model, in accordance with an embodiment of the present disclosure;
FIG. 6 is a flow chart of a method for constructing an operation and maintenance domain corpus according to an embodiment of the disclosure;
FIG. 7 schematically shows a flowchart of a method of obtaining entity associations according to an embodiment of the present disclosure;
FIG. 8 schematically illustrates a flow chart of an operation and maintenance knowledge graph application method according to an embodiment of the present disclosure;
FIG. 9 is a block diagram schematically illustrating an operation and maintenance knowledge-graph obtaining apparatus according to an embodiment of the present disclosure; and
fig. 10 schematically illustrates a block diagram of an electronic device suitable for implementing an operation and maintenance knowledge-graph acquisition method according to an embodiment of the present disclosure.
Detailed Description
Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that these descriptions are illustrative only and are not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.
Where a convention analogous to "A, B and at least one of C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include, but not be limited to, systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).
In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure, application and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations, necessary confidentiality measures are taken, and the customs of the public order is not violated.
In the technical scheme of the disclosure, the data acquisition, collection, storage, use, processing, transmission, provision, disclosure, application and other processing are all in accordance with the regulations of relevant laws and regulations, necessary security measures are taken, and the public order and good custom are not violated.
CMDB: the resource library for storing the information of the IT equipment comprises information such as IP, ports and topological relations of resources such as a physical subsystem, a deployment unit, a server, an operating system and middleware.
ITSM: the operation and maintenance service work order usually records, reviews and follows up the operation and maintenance service work in a work order mode in daily operation and maintenance work, including daily inspection, fault handling, upgrading and changing and other operation and maintenance work, and a large amount of precious operation and maintenance experience is accumulated in the operation and maintenance work order.
Operation and maintenance knowledge map: the knowledge graph in the IT operation and maintenance field generally stores IT entities (servers, hosts, databases, cabinets, service modules, service processes, and the like) and pairwise relationships between the entities in a triple manner. The operation and maintenance knowledge graph with reasonable design can enable the quick multiplexing and low-cost multiplexing of the operation and maintenance service experience to be possible.
Fig. 1 schematically shows an application scenario diagram of an operation and maintenance knowledge graph acquisition method according to an embodiment of the present disclosure.
As shown in fig. 1, the application scenario 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have installed thereon various communication client applications, such as shopping-like applications, web browser applications, search-like applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 105 may be a server providing various services, such as a background management server (for example only) providing support for websites browsed by users using the terminal devices 101, 102, 103. The background management server, for example, an operation and maintenance management server, may analyze and process data such as the received user request, and feed back a processing result (for example, a webpage, information, or data obtained or generated according to the user request) to the terminal device.
It should be noted that the operation and maintenance knowledge graph obtaining method provided by the embodiment of the present disclosure may be generally executed by the server 105. Accordingly, the operation and maintenance knowledge map acquisition device provided by the embodiment of the present disclosure may be generally disposed in the server 105. The operation and maintenance knowledge graph acquisition method provided by the embodiment of the present disclosure may also be executed by a server or a server cluster that is different from the server 105 and is capable of communicating with the terminal devices 101, 102, 103 and/or the server 105. Accordingly, the operation and maintenance knowledge graph obtaining apparatus provided by the embodiment of the present disclosure may also be disposed in a server or a server cluster that is different from the server 105 and is capable of communicating with the terminal devices 101, 102, 103 and/or the server 105.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
The operation and maintenance knowledge graph acquisition method of the disclosed embodiment will be described in detail below with reference to fig. 2 to 7 based on the scenario described in fig. 1.
Fig. 2 schematically shows a flowchart of an operation and maintenance knowledge-graph acquisition method according to an embodiment of the present disclosure.
As shown in fig. 2, the operation and maintenance knowledge graph acquiring method of the embodiment includes operations S210 to S270.
In operation S210, operation and maintenance resource data is acquired from the device information resource library.
According to an embodiment of the present disclosure, the device information repository is, for example, a CMDB (repository storing IT device information). The operation and maintenance resource data in the CMDB can be pulled regularly by Pull ETL or calling openAPI, for example.
Specifically, the Pull ETL program calls an openAPI (application programming interface) of the CMDB through python, for example, and pulls and analyzes the operation and maintenance resource data according to the ETL rule. Compared with the service work order data, the operation and maintenance resource change frequency in the equipment information resource libraries such as the physical subsystem, the deployment unit, the host, the storage, the database, the middleware and the like is low, so that the periodic timing pulling is only needed.
In operation S220, the operation and maintenance resource data is structurally identified to obtain static operation and maintenance knowledge, where the static operation and maintenance knowledge includes a plurality of first entities.
According to the embodiment of the disclosure, the operation and maintenance resource data is less efficient in change compared with the service work order data, so that the part of operation and maintenance knowledge belongs to static knowledge. Because the part of data is structured data, a D2RQ Mapping file can be written, the operation and maintenance resource data is abstracted into static operation and maintenance knowledge according to entities, attributes and relations through a D2R tool, and meanwhile, the static operation and maintenance knowledge can be stored in a knowledge base in an RDF format in a triple form. The plurality of first entities are entities of hardware information such as representative equipment extracted from the operation and maintenance resource data.
In operation S230, real-time operation and maintenance service work order data is acquired.
According to the embodiment of the disclosure, the operation and maintenance service work order data pushed by the ITSM (operation and maintenance service work order) can be obtained in real time through Push ETL or by calling open API, for example.
Specifically, the operation and maintenance service work order data in the ITSM may be pushed to the message queue through the Push ETL program, and the message queue subscribes to the part of the message to receive the operation and maintenance service work order data in real time. The operation and maintenance service work order bears event management work orders such as fault handling, emergency handling and the like and operation and maintenance service work orders such as data backup, disk capacity expansion and the like in the operation and maintenance process of the production environment, and information such as the incidence relation among the work orders, the work order content and the like can change along with the progress of the operation and maintenance service flow, so that the information needs to be obtained in real time.
In operation S240, unstructured identification is performed on the operation and maintenance service work order data by using a pre-trained knowledge extraction model to obtain dynamic operation and maintenance knowledge, where the dynamic operation and maintenance knowledge includes a plurality of second entities.
According to the embodiment of the disclosure, since the operation and maintenance service work order data belongs to semi-structured data, for example, the operation and maintenance service work order data includes fault description, production reason and solution in the event management work order, and unstructured text information such as change content, change reason, change risk and change control table in the change service work order, knowledge extraction can be performed on the part of text by adopting a remote supervision method, for example. Similarly, the extracted dynamic operation and maintenance knowledge also includes a plurality of second entities, such as fault descriptions, reasons for generation, solutions, follow-up measures, emergency disposal scripts, and the like.
In operation S250, historical association relationships between the plurality of first entities and the plurality of second entities are obtained.
According to the embodiment of the disclosure, the operation and maintenance service work order includes both the entities in the static operation and maintenance knowledge of the hardware types such as the equipment and the entities in the dynamic operation and maintenance knowledge such as the fault description and the solution. The historical association relationship may be, for example, a correspondence between a known machine entity in the historical operation and maintenance service work order and the relevant problem solution that the machine entity solves.
In operation S260, a new association relationship corresponding to the first entity in the operation and maintenance service work order data is obtained through inference according to the first similarities among the plurality of first entities, the second similarities among the plurality of second entities, and the historical association relationship.
According to the embodiment of the disclosure, for example, the fusion of the operation and maintenance static knowledge and the dynamic knowledge can be performed based on the operation and maintenance entity unique identifier (such as a physical address, a work order ID, and the like). The static operation and maintenance knowledge includes, for example, a static operation and maintenance entity of a plurality of devices, and the dynamic operation and maintenance knowledge includes, for example, a dynamic operation and maintenance entity of a plurality of fault descriptions, and a fault C occurring in a certain device a and a corresponding fault handling scheme can be known from a known operation and maintenance service work order, that is, an association relationship exists between the device and the fault and handling scheme. And extracting another device B and a fault D of the other device from the obtained real-time operation and maintenance service work order, wherein at the moment, the similarity between the device B and the device A and the similarity between the fault D and the fault C are calculated, assuming that the device B is a device similar to the device A through the similarity calculation and the fault D is a fault similar to the fault C, a new association relation equivalent to the device B and the fault C can be obtained through reasoning based on the association relation between the device A and the fault C, so that an operation and maintenance knowledge map containing the new association relation and related entities is obtained, and a processing scheme of the fault D is automatically generated through the operation and maintenance knowledge map.
It is understood that the above-mentioned devices a, B, C and D are only schematic codes, and the correspondence between the devices and between the faults is not clear before the similarity is calculated. The historical operation and maintenance service work order comprises a plurality of static operation and maintenance entities and a plurality of dynamic operation and maintenance entities, and the equipment A similar to the equipment B and the fault C similar to the fault D can be found by calculating the similarity between each entity in the real-time operation and maintenance service work order and each entity in the historical operation and maintenance service work order. Besides the failure, the dynamic operation and maintenance entity may also be a change, such as replacement of a server disk, migration of a machine room address, and the like.
Specifically, for example, a relationship R1 exists between the Linux server ED1 and an entity ST1 in the implemented volume expansion service work order, the head entity is the static operation and maintenance entity ED1, the tail entity is the dynamic operation and maintenance entity ST1, an entity ST2 in the non-implemented volume expansion service work order, and an implementation object of ST2 is another Linux server ED2, and a similar relationship exists between the static operation and maintenance entity ED2 and the dynamic operation and maintenance entity ST1 is inferred according to the high similarity between ST2 and ST1 and the high similarity between ED2 and ED1, that is, the change risk, the change control table, the change script, and the verification script in ST1 are applicable to the volume expansion service work order of ED 2.
In operation S270, an operation and maintenance knowledge graph is obtained according to the new association relationship.
According to the embodiment of the disclosure, after the operation and maintenance knowledge graph is obtained, the operation and maintenance knowledge graph obtained by fusion and inference of the static operation and maintenance entity and the dynamic operation and maintenance entity can be updated into the graph database and expressed to be in accordance with a mode of machine processing, so that the operation and maintenance knowledge graph can be conveniently applied subsequently. The method and the device have the advantages that the operation and maintenance knowledge acquisition cost is reduced based on the JSON format semi-structured data acquired by the operation and maintenance service work order interface, and meanwhile, the automatic extraction of the operation and maintenance knowledge and the automatic updating of the operation and maintenance knowledge map are realized.
FIG. 3 is a flow chart of a method for extracting static operation and maintenance knowledge according to an embodiment of the disclosure.
According to an embodiment of the present disclosure, as shown in fig. 3, the static operation and maintenance knowledge is extracted through steps S221 to S223, for example.
Step S221, a preset tool is adopted to pull the operation and maintenance resource data from the equipment information resource library at regular time.
According to an embodiment of the present disclosure, the preset tool is, for example, a Pull ETL program. And actively pulling the operation and maintenance resource data from the CMDB through Pull ETL periodically. Before pulling the data, for example, a python editor pycharm may be installed, the python version is, for example, 3.8.8, and modules such as requests, json, jieba, word2vec, and the like may be installed. And applying for a network environment capable of calling the operation and maintenance service work order query interface. Wherein, the requests module: the operation and maintenance work order data acquisition module is used for calling an openAPI interface to acquire operation and maintenance work order data; a json module: mainly formatting the obtained JSON data; a jieba module: the method is mainly used for segmenting words of the text and removing stop words; word2Vec module: named entity recognition and relationship extraction.
Step S222, carrying out entity identification, entity relationship identification and entity attribute identification on the operation and maintenance resource data to obtain relational data consisting of entities, entity relationships and entity attributes.
According to the embodiment of the disclosure, by identifying the structured operation and maintenance resource data, static knowledge entities (e.g., physical subsystems, deployment units, storage, databases, processes, middleware, etc.), entity attributes (e.g., IP, ports, etc.), entity relationships (e.g., inclusion, composition, connection, etc.) can be obtained, and these interrelated static knowledge entities, entity attributes, and entity relationships together form relational data.
And step S223, converting the relational data into RDF triples to obtain the static operation and maintenance knowledge.
FIG. 4 schematically illustrates a static operation and maintenance knowledge composition diagram according to an embodiment of the disclosure.
According to an embodiment of the present disclosure, as shown in fig. 4, by converting the above-mentioned relational data into RDF triples, abstracted static operation and maintenance knowledge can be obtained. The physical subsystem 1 includes, for example, n deployment units, each deployment unit includes, for example, two linux servers, and the two linux servers are connected to one NFS shared memory. The static operation and maintenance knowledge with low update frequency and the dynamic operation and maintenance knowledge related to the service are extracted separately by a simple extraction method of structured recognition and format conversion, so that the task amount of high-frequency operation and maintenance management such as service change, fault treatment and the like is greatly reduced, and the operation and maintenance management cost is reduced.
FIG. 5 schematically illustrates a flow diagram of a method of training a knowledge extraction model, in accordance with an embodiment of the disclosure.
According to an embodiment of the present disclosure, as shown in FIG. 5, the knowledge extraction model is trained, for example, by steps S241-S244.
And step S241, constructing an operation and maintenance field corpus based on the static operation and maintenance knowledge and the operation and maintenance service work order data.
According to the embodiment of the disclosure, the operation and maintenance domain corpus is a set of high-quality static operation and maintenance knowledge and high-similarity dynamic operation and maintenance knowledge. By constructing the operation and maintenance field corpus and training the dynamic operation and maintenance knowledge extraction model based on the operation and maintenance field corpus, the extraction accuracy of the dynamic operation and maintenance knowledge is improved. The operation and maintenance service work order is, for example, a manual processing work order obtained by continuous precipitation, and due to the fact that a high-quality operation and maintenance field corpus is constructed, only a part of the work order can be extracted to serve as a training sample, so that the training efficiency is improved, the training cost is reduced, meanwhile, the accuracy of dynamic operation and maintenance knowledge extraction is also guaranteed based on the semi-structured data type of the operation and maintenance service work order and the high-quality operation and maintenance field corpus.
Step S242, calculate a third similarity between the operation and maintenance service work order data and the words in the operation and maintenance field corpus.
In step S243, the entity pair corresponding to the word with the third similarity greater than the preset value is screened out.
According to the embodiment of the disclosure, the words similar to the words of the operation and maintenance field corpus in the operation and maintenance service work order data are screened out to obtain the entity pairs, and the similarity is larger and closer. If the cosine similarity of the word vector is calculated, the range is [0,1], and calculation similarity larger than 0.8 is generally considered. If the quality requirement is high, the threshold can be adjusted up to 0.85. The entity pair is, for example, a resource entity pair, such as a disk and a server in "disk mount to server", a room and an address in "room migrated from address a to address B".
Step S244, the sentence containing the entity pair is used as a training sample, and a knowledge extraction model is obtained through training.
According to an embodiment of the present disclosure, the knowledge extraction model is, for example, a supervised learning model. After word segmentation, for example, based on a constructed high-quality operation and maintenance field corpus, sentences containing the entity pairs are extracted from unstructured texts in operation and maintenance service work order data to serve as training samples, a supervised learning model is trained, dynamic entity recognition, attribute recognition and relationship recognition are carried out, the extracted dynamic operation and maintenance entities, entity attributes and entity relationships are supplemented into the operation and maintenance field corpus to serve as sample data of the next batch of training, and the supervised learning model is iteratively optimized. The operation and maintenance field corpus and the knowledge extraction model are both in continuous dynamic optimization, so that the accuracy of dynamic knowledge extraction is further ensured.
Fig. 6 schematically shows a flowchart of a method for constructing an operation and maintenance domain corpus according to an embodiment of the present disclosure.
According to an embodiment of the present disclosure, as shown in fig. 6, the knowledge extraction model is trained, for example, through steps S2411-S2414.
Step S2411, constructing an initial operation and maintenance domain corpus.
Step S2412, outputting the relational data to the initial operation and maintenance domain corpus.
According to an embodiment of the present disclosure, the relational data is, for example, the above-mentioned static knowledge entities (e.g., physical subsystems, deployment units, storage, databases, processes, middleware, etc.), entity attributes (e.g., IP, ports, etc.), entity relationships (e.g., inclusion, composition, connection, etc.).
Step S2413, performing word segmentation on the operation and maintenance service work order data, removing stop words, and calculating the weighting weight of the remaining words.
According to an embodiment of the disclosure, a weighted weight of the remaining words in the operation and maintenance service work order data after the stop words are removed is calculated, for example, through a TF-IDF algorithm.
Step S2414, outputting the words meeting the preset weight to the initial operation and maintenance field corpus to obtain the operation and maintenance field corpus.
According to the embodiment of the present disclosure, the value threshold of the TF-IDF is theoretically [0, positive infinity), and the larger the value is, the more important the value is, so that topN is generally taken to add into the thesaurus, and in this scenario, for example, top5 may be taken to add into the operation and maintenance domain corpus. The word mining in the operation and maintenance service work order is based on an operation and maintenance field corpus, for example, words obtained by mining are input into the operation and maintenance field corpus, namely, the word input from the operation and maintenance service work order to the operation and maintenance field corpus is a dynamic circulating process, and the word input source of static operation and maintenance knowledge is combined, so that the word breadth of the operation and maintenance field corpus is ensured, the screening of the word weight is realized, and the word accuracy is also improved.
Fig. 7 schematically shows a flowchart of a method for obtaining an entity association relationship according to an embodiment of the present disclosure.
According to the embodiment of the present disclosure, as shown in fig. 7, the entity association relationship is obtained, for example, through steps S251 to S257.
Step S251, obtaining a historical operation and maintenance service work order, wherein the historical operation and maintenance service work order comprises a first change application work order and an event management work order.
According to the embodiment of the disclosure, before the static operation and maintenance knowledge and the dynamic operation and maintenance knowledge are fused and inferred, the association relationship between the work order and the association relationship between the work order and each entity included in the work order need to be obtained. Then, by establishing the work order incidence relation between the static operation and maintenance entities such as the physical subsystem, the deployment unit and the host and the dynamic operation and maintenance entities such as the change type, the change content, the change risk, the change control table, the fault type and the solution, carrying out knowledge reasoning according to the static operation and maintenance entity type and the work order incidence relation, simultaneously converting the vector of the entities in the static knowledge map (obtained by static operation and maintenance knowledge vectorization) by using the relation vector, and defining each triple according to the similarity degree between the converted head entity and the tail entity, thereby obtaining the required operation and maintenance knowledge map.
Step S252 is to create a plurality of sub-work orders of the first change application work order.
According to the embodiment of the present disclosure, the first change application form is, for example, an independent change application form obtained from a change cause due to a non-failure such as a service change. For the changed application work order, if a plurality of implementation stages or a plurality of implementation steps are changed at a time, a corresponding sub-work order needs to be established so as to finely follow the implementation situation. For example, a machine resource on-line application establishes a corresponding machine power-on service work order, an operating system installation work order, a network debugging work order and a service component deployment work order according to an implementation link, and the changed work orders have a relationship with a resource entity and an association relationship between the work orders.
Step S253, a first work order association relationship between the first change application work order and the plurality of sub work orders and a first work order resource association relationship between the first change application work order and the plurality of first entities and the plurality of second entities included therein are obtained.
According to the embodiment of the disclosure, the first work order incidence relation is, for example, an incidence relation between the total change application work order and each sub-work order. The first work order resource association relationship is, for example, an association relationship between the total change application work order and each static operation and maintenance entity and each dynamic operation and maintenance entity included in the total change application work order.
And step S254, obtaining a historical incidence relation based on the first work order incidence relation and the first work order resource incidence relation. And/or the presence of a gas in the gas,
step S255, a second change application work order corresponding to the event management work order is created.
According to the embodiment of the disclosure, for event management, besides filling information such as fault description and severity level in the event management work order, there is also a corresponding change application work order, that is, a second change application work order. For example, because an Oracle fault (corresponding to the event management work order ST 3) caused by insufficient table space requires an increase of the corresponding table space after the completion of the event analysis, there is a change application work order (corresponding to the change application work order ST 4) with "capacity expansion of the table space", and there is an association between the event management work order ST3 and the change application work order ST 4.
Step S256, a second work order association relationship between the event management work order and the second change application work order, and a second work order resource association relationship between the event management work order and the plurality of first entities and the plurality of second entities included therein are obtained.
According to the embodiment of the present disclosure, the second work order resource association relationship is, for example, an association relationship between the event management work order and each of the static operation and maintenance entities and the dynamic operation and maintenance entities included in the event management work order.
Step S257, a historical association is obtained based on the second work order association and the second work order resource association.
According to the embodiment of the disclosure, the historical incidence relation comprises the incidence relation between the work order and the incidence relation between the work order and the entity in the work order. By changing the work order incidence relation and the work order entity incidence relation in the application work order data, the knowledge graph related to change application disposal can be perfected. Through the work order incidence relation and the work order entity relation in the event management work order, the knowledge graph related to the event attribution link and the fault disposal can be perfected.
According to the embodiment of the disclosure, the association relationship between the operation and maintenance service work order obtained in real time and the static operation and maintenance entity and the dynamic operation and maintenance entity in the historical operation and maintenance service work order can be realized based on the historical association relationship.
The change application work order includes, but is not limited to, the following information, as shown in table 1:
TABLE 1 Change application work order
Figure BDA0003866062010000141
Figure BDA0003866062010000151
And further, the relation between dynamic operation and maintenance entities such as change content, change reasons, change schemes, change plans and change control tables and static operation and maintenance entities such as physical subsystems, deployment units and hosts can be established. The event management work order includes, for example, but is not limited to, the following information, as shown in table 2:
TABLE 2 event management work order
Figure BDA0003866062010000152
And then, the relation between dynamic operation and maintenance entities such as fault description, generation reasons, solutions, follow-up measures and emergency disposal scripts and static operation and maintenance entities such as physical subsystems, deployment units and hosts can be established. And extracting fault entities and causal relations, and establishing a fault attribution link, so that the operation and maintenance knowledge graph can be conveniently called in the later stage to be applied to fault prediction. The method and the system establish the relation between the static operation and maintenance entity and the dynamic operation and maintenance entities such as fault description, solution, emergency disposal script and the like, and facilitate the later-stage calling of the operation and maintenance knowledge map for fault emergency disposal.
Fig. 8 schematically shows a flowchart of an operation and maintenance knowledge-graph application method according to an embodiment of the present disclosure.
Based on the operation and maintenance knowledge graph obtained by the operation and maintenance knowledge graph obtaining method, the invention also provides an operation and maintenance knowledge graph application method, which comprises the following steps:
and S810, acquiring the operation and maintenance service work order to be processed.
According to the embodiment of the disclosure, for example, dynamic operation and maintenance entities such as operation and maintenance service work order types and work order titles and static operation and maintenance entities such as physical subsystems, deployment units, hosts and the like in the operation and maintenance service work orders are obtained.
S820, retrieving the operation and maintenance knowledge associated with the operation and maintenance service work order to be processed in the operation and maintenance knowledge map, and calculating a fourth similarity.
According to the embodiment of the disclosure, the associated operation and maintenance knowledge is retrieved from the operation and maintenance knowledge map according to the dynamic operation and maintenance entity and the static operation and maintenance entity, such as the operation and maintenance service work order type, the work order title, and the like.
And S830, sorting the operation and maintenance knowledge according to the weight based on the business relevance and the fourth similarity.
According to the embodiment of the disclosure, for example, the operation and maintenance knowledge similarity weights are sorted in a reverse order according to the retrieved operation and maintenance knowledge similarity weights, the recommendation result is transmitted to the operation and maintenance service work order system through an interface, and an operation and maintenance engineer selects the disposal process with the highest correlation according to the business.
And S840, processing the operation and maintenance service work order to be processed according to the operation and maintenance knowledge with the highest weight.
According to the embodiment of the disclosure, after the operation and maintenance knowledge with the highest weight is obtained, the weight of the corresponding operation and maintenance knowledge in the operation and maintenance knowledge map can be updated, so that the accuracy of the operation and maintenance knowledge map and the recommendation accuracy of a recommendation system recommending the operation and maintenance knowledge map are further improved. The operation and maintenance knowledge graph is applied to operation and maintenance services, for example, operation and maintenance tools including but not limited to event intelligent handling, operation and maintenance service work order intelligent handling and the like, and operation and maintenance efficiency and operation and maintenance quality are improved.
In particular, a low risk operation and maintenance service work order may be automatically implemented, for example, after a certain degree of accuracy is reached. For example, the operation and maintenance service work order ST5 expanded by the server is received, the server changed and implemented in ST5 is obtained, the attribute of the operating system of the server is Linux, and the change risk (low), the change control table, the change script and the verification script of the operation and maintenance service work order ST5 are retrieved from the operation and maintenance knowledge graph according to the entity attribute and the entity correlation, so that the server initiating the request is automatically expanded, and the verification result is returned to the control table and fed back to the operation and maintenance engineer.
Based on the operation and maintenance knowledge map acquisition method, the disclosure also provides an operation and maintenance knowledge map acquisition device. The apparatus will be described in detail below with reference to fig. 9.
Fig. 9 schematically shows a block diagram of an operation and maintenance knowledge map acquisition apparatus according to an embodiment of the present disclosure.
As shown in fig. 8, the operation and maintenance knowledge map acquisition apparatus 900 of this embodiment includes, for example: a first acquisition module 910, a first identification module 920, a second acquisition module 930, a second identification module 940, a third acquisition module 950, an inference module 960, and a map acquisition module 970.
The first obtaining module 910 is configured to obtain operation and maintenance resource data from a device information resource library. In an embodiment, the first obtaining module 910 may be configured to perform the operation S210 described above, which is not described herein again.
The first identification module 920 is configured to perform structured identification on the operation and maintenance resource data to obtain static operation and maintenance knowledge, where the static operation and maintenance knowledge includes a plurality of first entities. In an embodiment, the first identifying module 920 may be configured to perform the operation S220 described above, which is not described herein again.
The second obtaining module 930 is configured to obtain real-time operation and maintenance service work order data. In an embodiment, the second obtaining module 930 may be configured to perform the operation S230 described above, and is not described herein again.
The second identification module 940 is configured to perform unstructured identification on the operation and maintenance service work order data by using a pre-trained knowledge extraction model to obtain dynamic operation and maintenance knowledge, where the dynamic operation and maintenance knowledge includes a plurality of second entities. In an embodiment, the second identifying module 940 may be configured to perform the operation S240 described above, which is not described herein again.
The third obtaining module 950 is configured to obtain historical association relationships between the plurality of first entities and the plurality of second entities. In an embodiment, the third obtaining module 950 may be configured to perform the operation S250 described above, and is not described herein again.
The inference module 960 is configured to infer a new association relationship corresponding to a first entity in the operation and maintenance service work order data according to a first similarity between multiple first entities, a second similarity between multiple second entities, and a historical association relationship. In an embodiment, the inference module 960 may be configured to perform the operation S260 described above, which is not described herein again.
The map acquisition module 970 is used for acquiring the operation and maintenance knowledge map according to the new association relationship. In an embodiment, the map obtaining module 970 may be configured to perform the operation S270 described above, and is not described herein again.
According to the embodiment of the present disclosure, any plurality of the first obtaining module 910, the first identifying module 920, the second obtaining module 930, the second identifying module 940, the third obtaining module 950, the reasoning module 960, and the map obtaining module 970 may be combined into one module to be implemented, or any one of them may be split into a plurality of modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the first obtaining module 910, the first identifying module 920, the second obtaining module 930, the second identifying module 940, the third obtaining module 950, the reasoning module 960 and the atlas obtaining module 970 may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented by hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or implemented by any one of three implementations of software, hardware and firmware, or in a suitable combination of any of them. Alternatively, at least one of the first obtaining module 910, the first identifying module 920, the second obtaining module 930, the second identifying module 940, the third obtaining module 950, the reasoning module 960 and the map obtaining module 970 may be at least partially implemented as a computer program module, which when executed, may perform corresponding functions.
Fig. 10 schematically illustrates a block diagram of an electronic device suitable for implementing an operation and maintenance knowledge-graph acquisition method according to an embodiment of the present disclosure.
As shown in fig. 10, an electronic device 1000 according to an embodiment of the present disclosure includes a processor 1001 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 1002 or a program loaded from a storage section 1008 into a Random Access Memory (RAM) 1003. Processor 1001 may include, for example, a general purpose microprocessor (e.g., CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., application Specific Integrated Circuit (ASIC)), among others. The processor 1001 may also include onboard memory for caching purposes. The processor 1001 may include a single processing unit or multiple processing units for performing different actions of a method flow according to embodiments of the present disclosure.
In the RAM1003, various programs and data necessary for the operation of the electronic apparatus 1000 are stored. The processor 1001, ROM 1002, and RAM1003 are connected to each other by a bus 1004. The processor 1001 performs various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM 1002 and/or the RAM 1003. Note that the programs may also be stored in one or more memories other than the ROM 1002 and the RAM 1003. The processor 1001 may also perform various operations of the method flows according to embodiments of the present disclosure by executing programs stored in the one or more memories.
Electronic device 1000 may also include an input/output (I/O) interface 1005, input/output (I/O) interface 1005 also connected to bus 1004, according to an embodiment of the present disclosure. Electronic device 900 may also include one or more of the following components connected to I/O interface 1005: an input portion 1006 including a keyboard, a mouse, and the like; an output section 1007 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 1008 including a hard disk and the like; and a communication section 1009 including a network interface card such as a LAN card, a modem, or the like. The communication section 1009 performs communication processing via a network such as the internet. The driver 1010 is also connected to the I/O interface 1005 as necessary. A removable medium 1011 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 1010 as necessary, so that a computer program read out therefrom is mounted into the storage section 1008 as necessary.
The present disclosure also provides a computer-readable storage medium, which may be contained in the apparatus/device/system described in the above embodiments; or may exist separately and not be assembled into the device/apparatus/system. The computer readable storage medium carries one or more programs which, when executed, implement the operation and maintenance knowledge graph acquisition method according to the embodiments of the present disclosure.
According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, a computer-readable storage medium may include the ROM 1002 and/or the RAM1003 described above and/or one or more memories other than the ROM 1002 and the RAM 1003.
Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the method illustrated in the flow chart. When the computer program product runs in a computer system, the program code is used for causing the computer system to realize the operation and maintenance knowledge graph acquisition method provided by the embodiment of the disclosure.
The computer program performs the above-described functions defined in the system/apparatus of the embodiments of the present disclosure when executed by the processor 1001. The systems, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.
In one embodiment, the computer program may be hosted on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed in the form of a signal over a network medium, downloaded and installed via the communication part 1009, and/or installed from the removable medium 1011. The computer program containing program code may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
In such an embodiment, the computer program may be downloaded and installed from a network through the communication part 1009 and/or installed from the removable medium 1011. The computer program performs the above-described functions defined in the system of the embodiment of the present disclosure when executed by the processor 1001. The systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.
In accordance with embodiments of the present disclosure, program code for executing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, these computer programs may be implemented using high level procedural and/or object oriented programming languages, and/or assembly/machine languages. The programming language includes, but is not limited to, programming languages such as Java, C + +, python, the "C" language, or the like. The program code may execute entirely on the user computing device, partly on the user device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. 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 involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Those skilled in the art will appreciate that various combinations and/or combinations of features recited in the various embodiments and/or claims of the present disclosure can be made, even if such combinations or combinations are not expressly recited in the present disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present disclosure may be made without departing from the spirit or teaching of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.
The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used advantageously in combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the present disclosure, and such alternatives and modifications are intended to be within the scope of the present disclosure.

Claims (11)

1. An operation and maintenance knowledge graph acquisition method comprises the following steps:
acquiring operation and maintenance resource data from a device information resource library;
carrying out structured identification on the operation and maintenance resource data to obtain static operation and maintenance knowledge, wherein the static operation and maintenance knowledge comprises a plurality of first entities;
acquiring real-time operation and maintenance service work order data;
carrying out unstructured identification on the operation and maintenance service work order data by adopting a pre-trained knowledge extraction model to obtain dynamic operation and maintenance knowledge, wherein the dynamic operation and maintenance knowledge comprises a plurality of second entities;
acquiring historical association relations between the plurality of first entities and the plurality of second entities;
reasoning and obtaining a new incidence relation corresponding to the first entity in the operation and maintenance service work order data according to the first similarity among the first entities, the second similarity among the second entities and the historical incidence relation;
and obtaining the operation and maintenance knowledge graph according to the new incidence relation.
2. The operation and maintenance knowledge graph acquisition method according to claim 1, wherein the operation and maintenance resource data are structurally identified, and obtaining static operation and maintenance knowledge comprises:
regularly pulling the operation and maintenance resource data from the equipment information resource library by adopting a preset tool;
carrying out entity identification, entity relationship identification and entity attribute identification on the operation and maintenance resource data to obtain relationship type data consisting of entities, entity relationships and entity attributes;
and converting the relational data into RDF triples to obtain the static operation and maintenance knowledge.
3. The operation and maintenance knowledge graph acquisition method according to claim 2, further comprising:
constructing an operation and maintenance field corpus based on the static operation and maintenance knowledge and the operation and maintenance service work order data;
calculating a third similarity between the operation and maintenance service work order data and words in the operation and maintenance field corpus;
screening out entity pairs corresponding to the words with the third similarity larger than a preset value;
and taking sentences containing the entity pairs as training samples, and training to obtain the knowledge extraction model.
4. The operation and maintenance knowledge graph obtaining method according to claim 3, wherein the constructing an operation and maintenance field corpus based on the static operation and maintenance knowledge and the operation and maintenance service work order data comprises:
constructing an initial operation and maintenance field corpus;
outputting the relational data to the initial operation and maintenance domain corpus; and the number of the first and second groups,
performing word segmentation on the operation and maintenance service work order data, removing stop words, and calculating the weighting weight of the remaining words;
and outputting words meeting preset weight to the initial operation and maintenance field corpus to obtain the operation and maintenance field corpus.
5. The operation and maintenance knowledge graph acquisition method according to claim 1, wherein the acquiring of the historical association relationship between the plurality of first entities and the plurality of second entities comprises:
acquiring a historical operation and maintenance service work order, wherein the historical operation and maintenance service work order comprises a first change application work order and an event management work order;
establishing a plurality of sub-work orders of the first change application work order;
acquiring a first work order incidence relation between the first change application work order and the plurality of sub work orders, and a first work order resource incidence relation between the first change application work order and the plurality of first entities and the plurality of second entities contained in the first change application work order;
obtaining the historical incidence relation based on the first work order incidence relation and the first work order resource incidence relation; and/or the presence of a gas in the atmosphere,
establishing a second change application work order corresponding to the event management work order;
acquiring a second work order incidence relation between the event management work order and the second change application work order, and a second work order resource incidence relation between the event management work order and the plurality of first entities and the plurality of second entities contained in the event management work order;
and obtaining the historical incidence relation based on the second work order incidence relation and the second work order resource incidence relation.
6. An operation and maintenance knowledge graph application method, which adopts an operation and maintenance knowledge graph obtained by the operation and maintenance knowledge graph obtaining method based on any one of claims 1 to 5, comprises the following steps:
acquiring an operation and maintenance service work order to be processed;
retrieving operation and maintenance knowledge associated with the operation and maintenance service work order to be processed in the operation and maintenance knowledge map, and calculating a fourth similarity;
sorting the operation and maintenance knowledge by weight based on the business relevance and the fourth similarity;
and processing the operation and maintenance service work order to be processed according to the operation and maintenance knowledge with the highest weight.
7. The operation and maintenance knowledge-graph application method of claim 6, further comprising:
and updating the weight of the corresponding operation and maintenance knowledge in the operation and maintenance knowledge map according to the operation and maintenance knowledge with the highest weight.
8. An operation and maintenance knowledge map acquisition device, comprising:
the first acquisition module is used for acquiring operation and maintenance resource data from the equipment information resource library;
the first identification module is used for carrying out structured identification on the operation and maintenance resource data to obtain static operation and maintenance knowledge, and the static operation and maintenance knowledge comprises a plurality of first entities;
the second acquisition module is used for acquiring real-time operation and maintenance service work order data;
the second identification module is used for carrying out unstructured identification on the operation and maintenance service work order data by adopting a pre-trained knowledge extraction model to obtain dynamic operation and maintenance knowledge, and the dynamic operation and maintenance knowledge comprises a plurality of second entities;
a third obtaining module, configured to obtain historical association relationships between the multiple first entities and the multiple second entities;
the reasoning module is used for reasoning and obtaining a new incidence relation corresponding to the first entity in the operation and maintenance service work order data according to the first similarity among the first entities, the second similarity among the second entities and the historical incidence relation; and
and the map acquisition module is used for acquiring the operation and maintenance knowledge map according to the new association relation.
9. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the operation and maintenance knowledge-graph acquisition method of any one of claims 1-5.
10. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the operation and maintenance knowledge-graph acquisition method according to any one of claims 1 to 5.
11. A computer program product comprising a computer program which, when executed by a processor, implements an operation and maintenance knowledge-graph acquisition method according to any one of claims 1 to 5.
CN202211186399.8A 2022-09-27 2022-09-27 Operation and maintenance knowledge map acquisition and application method, device, equipment and storage medium Pending CN115587188A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211186399.8A CN115587188A (en) 2022-09-27 2022-09-27 Operation and maintenance knowledge map acquisition and application method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211186399.8A CN115587188A (en) 2022-09-27 2022-09-27 Operation and maintenance knowledge map acquisition and application method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN115587188A true CN115587188A (en) 2023-01-10

Family

ID=84772714

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211186399.8A Pending CN115587188A (en) 2022-09-27 2022-09-27 Operation and maintenance knowledge map acquisition and application method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN115587188A (en)

Similar Documents

Publication Publication Date Title
US11604798B2 (en) Techniques for ranking content item recommendations
US20190278787A1 (en) Personalized content delivery system
US10983789B2 (en) Systems and methods for automating and monitoring software development operations
JP2021534493A (en) Techniques for building knowledge graphs within a limited knowledge domain
US11726840B2 (en) Flexible and scalable artificial intelligence and analytics platform with advanced content analytics and data ingestion
US20160162476A1 (en) Methods and systems for modeling complex taxonomies with natural language understanding
WO2023124029A1 (en) Deep learning model training method and apparatus, and content recommendation method and apparatus
US20220043874A1 (en) Systems and methods for intelligent content filtering and persistence
US20190244146A1 (en) Elastic distribution queuing of mass data for the use in director driven company assessment
CN113986864A (en) Log data processing method and device, electronic equipment and storage medium
US20200042593A1 (en) Dynamic configuration of document portions via machine learning
CN114254389A (en) Message desensitization method, device, electronic equipment and medium
US20200110815A1 (en) Multi contextual clustering
CN116225848A (en) Log monitoring method, device, equipment and medium
CN115952258A (en) Generation method of government affair label library, and label determination method and device of government affair text
KR20230059364A (en) Public opinion poll system using language model and method thereof
CN115587188A (en) Operation and maintenance knowledge map acquisition and application method, device, equipment and storage medium
CN111368036B (en) Method and device for searching information
CN112329429A (en) Text similarity learning method, device, equipment and storage medium
US11868737B2 (en) Method and server for processing text sequence for machine processing task
CN116561258A (en) Information management method, device, equipment, medium and product
CN113918584A (en) Metadata updating method and device, electronic equipment and storage medium
CN114661878A (en) Text processing method and device, electronic equipment and computer readable storage medium
CN115689263A (en) Information generation method, device, equipment and storage medium
CN116266184A (en) Method for providing interface service, electronic device and storage medium

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