CN115827885A - Operation and maintenance knowledge graph construction method and device and electronic equipment - Google Patents
Operation and maintenance knowledge graph construction method and device and electronic equipment Download PDFInfo
- Publication number
- CN115827885A CN115827885A CN202211383421.8A CN202211383421A CN115827885A CN 115827885 A CN115827885 A CN 115827885A CN 202211383421 A CN202211383421 A CN 202211383421A CN 115827885 A CN115827885 A CN 115827885A
- Authority
- CN
- China
- Prior art keywords
- maintenance
- domain
- graph data
- content
- node
- 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
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a method and a device for constructing an operation and maintenance knowledge graph and electronic equipment, wherein the method comprises the following steps: acquiring domain knowledge content of a target domain and at least one operation and maintenance case content of the target domain, wherein the target domain is a domain to which an operation and maintenance system belongs; according to the domain knowledge content, domain graph data are constructed, the domain graph data comprise a plurality of first nodes, and any two first nodes are directly connected or indirectly connected through other first nodes; according to the operation and maintenance case content, case diagram data is constructed, the case diagram data is composed of at least one piece of sub-diagram data, the sub-diagram data are connected through a center node, the sub-diagram data comprise a plurality of second nodes, and any two second nodes are directly connected or indirectly connected through other second nodes; and carrying out fusion processing on the map data on the domain map data and the case map data to obtain an operation and maintenance knowledge map corresponding to the target domain.
Description
Technical Field
The application relates to the technical field of data processing, in particular to a method and a device for constructing an operation and maintenance knowledge graph and electronic equipment.
Background
At present, the number of business systems of each enterprise is increasing, the software and hardware architecture of each corresponding system is becoming more complex, and the related operation and maintenance work is becoming more and more complicated. With the upgrading of the system architecture, the updating of the technology model selection and the iteration of the equipment or software version, the skills needed to be mastered and the knowledge needed to be learned by the operation and maintenance personnel are more and more complicated.
In the current operation and maintenance work, most of the operation and maintenance personnel of different system modules exchange and communicate related professional knowledge through oral explanation, technical documents or experience teaching, and related knowledge service platforms are limited by webpage storage and search engines, so that accurate retrieval and query are difficult to provide for technicians in need.
Therefore, a technical solution capable of establishing a knowledge graph for operation and maintenance knowledge to facilitate query is needed.
Disclosure of Invention
In view of this, the application provides a method, an apparatus, a medium, and an electronic device for constructing an operation and maintenance knowledge map, so as to facilitate query of operation and maintenance knowledge. The following were used:
a construction method of an operation and maintenance knowledge graph comprises the following steps:
obtaining field knowledge content of a target field and at least one operation and maintenance case content of the target field, wherein the target field is a field to which an operation and maintenance system belongs;
according to the domain knowledge content, domain graph data are constructed, the domain graph data comprise a plurality of first nodes, any two first nodes are directly connected or indirectly connected through other first nodes, and the first nodes represent the domain knowledge content;
according to the operation and maintenance case content, case diagram data is constructed, the case diagram data is composed of at least one piece of sub-diagram data, the sub-diagram data are connected through a center node, the sub-diagram data comprise a plurality of second nodes, any two second nodes are directly connected or indirectly connected through other second nodes, and the second nodes represent the operation and maintenance case content to which the second nodes belong;
and carrying out image data fusion processing on the field image data and the case image data to obtain an operation and maintenance knowledge graph corresponding to the target field.
The above method, preferably, constructs the domain map data according to the domain knowledge content, including:
processing the domain knowledge content according to a preset body model architecture to obtain a domain body model corresponding to the domain knowledge content, wherein the domain body model comprises a plurality of domain bodies;
and converting the domain ontology into a first node based on graph data according to a preset mapping rule to obtain the domain graph data.
In the above method, preferably, the mapping rule includes: an ontology component in the ontology and a node storage component in the node store a translation relationship between the elements;
wherein, according to the preset mapping rule, converting the domain ontology into a first node based on graph data to obtain the domain graph data, including:
and converting the ontology structural elements in the domain ontology into node storage elements in graph data nodes according to the conversion relation so as to obtain first nodes based on the graph data, wherein the first nodes form the domain graph data.
In the method, preferably, each operation and maintenance case content corresponds to an operation and maintenance event;
wherein, the constructing case diagram data according to the operation and maintenance case content comprises:
according to the operation and maintenance case content corresponding to the operation and maintenance event, constructing sub-graph data corresponding to the operation and maintenance event; the sub-graph data corresponding to each operation and maintenance event respectively has a root node, and a second node in each sub-graph data is directly or indirectly connected to the root node;
and splicing the root nodes of all the sub-graph data through the central node to obtain case graph data.
In the above method, preferably, the operation and maintenance case content includes table record content of a corresponding operation and maintenance event, and the table record content is composed of contents of a plurality of cells;
wherein, the constructing sub-graph data corresponding to the operation and maintenance event according to the operation and maintenance case content corresponding to the operation and maintenance event includes:
and taking the cells in the table record content as nodes based on graph data, and constructing sub-graph data corresponding to the operation and maintenance event according to the content of the cells.
In the above method, preferably, the operation and maintenance case content includes a document record content of a corresponding operation and maintenance event, and the document record content includes at least one record statement;
wherein, the constructing sub-graph data corresponding to the operation and maintenance event according to the operation and maintenance case content corresponding to the operation and maintenance event includes:
extracting triples of the record statements corresponding to the operation and maintenance events to obtain a plurality of entities and association relations among the entities;
and constructing sub-graph data corresponding to the operation and maintenance event according to the entity and the incidence relation between the entities.
In the above method, preferably, the operation and maintenance case content includes table record content and document record content of a corresponding operation and maintenance event;
wherein, the constructing sub-graph data corresponding to the operation and maintenance event according to the operation and maintenance case content corresponding to the operation and maintenance event includes:
according to the table record content corresponding to the operation and maintenance event, constructing first graph data corresponding to the operation and maintenance event;
according to the document record content corresponding to the operation and maintenance event, second graph data corresponding to the operation and maintenance event is constructed;
aligning nodes in the first graph data and nodes in the second graph data in a semantic description;
and fusing the first graph data and the second graph data to obtain sub-graph data corresponding to the operation and maintenance event.
Preferably, the method for performing graph data fusion processing on the domain graph data and the case graph data to obtain the operation and maintenance knowledge graph corresponding to the target domain includes:
aligning nodes in the domain graph data and nodes in the case graph data on semantic description;
establishing a parent-child relationship between at least one node in the case graph data and one node in the domain graph data, so that the at least one node in the case graph data has a parent node in the domain graph data to obtain an operation and maintenance knowledge graph corresponding to the target domain;
and the respective node storage elements of the two nodes with the parent-child relationship meet the node association condition.
An operation and maintenance knowledge graph construction device, comprising:
the content obtaining unit is used for obtaining the domain knowledge content of a target domain and at least one operation and maintenance case content of the target domain, wherein the target domain is a domain to which the operation and maintenance system belongs;
the domain graph building unit is used for building domain graph data according to the domain knowledge content, the domain graph data comprises a plurality of first nodes, a connection relation exists between any first node and at least one other first node, and the first nodes represent the domain knowledge content;
the case diagram construction unit is used for constructing case diagram data according to the operation and maintenance case contents, the case diagram data is composed of at least one piece of sub-graph data, the sub-graph data are connected through a center node, the sub-graph data comprise a plurality of second nodes, a connection relation exists between any second node and at least one other second node, and the second node represents the operation and maintenance case contents to which the second node belongs;
and the graph fusion unit is used for carrying out fusion processing on the graph data on the domain graph data and the case graph data so as to obtain the operation and maintenance knowledge graph corresponding to the target domain.
An electronic device, comprising:
a memory for storing a computer program and data generated by the execution of the computer program;
a processor for executing the computer program to implement: obtaining field knowledge content of a target field and at least one operation and maintenance case content of the target field, wherein the target field is a field to which an operation and maintenance system belongs; according to the domain knowledge content, domain graph data are constructed, the domain graph data comprise a plurality of first nodes, a connection relation exists between any first node and at least one other first node, and the first nodes represent the domain knowledge content; according to the operation and maintenance case content, case diagram data are constructed, the case diagram data are composed of at least one piece of sub-diagram data, the sub-diagram data are connected through a center node, the sub-diagram data comprise a plurality of second nodes, a connection relation exists between any second node and at least one other second node, and the second nodes represent the operation and maintenance case content to which the second nodes belong; and carrying out image data fusion processing on the field image data and the case image data to obtain an operation and maintenance knowledge graph corresponding to the target field.
According to the technical scheme, in the operation and maintenance knowledge graph construction method, the operation and maintenance knowledge graph construction device and the electronic equipment, the field knowledge content and at least one operation and maintenance case content of the target field are respectively obtained aiming at the target field to which the operation and maintenance system belongs, then the field graph data and the case graph data are respectively constructed, and then the field graph data and the case graph data are fused, so that the operation and maintenance knowledge graph of the field to which the operation and maintenance system belongs is obtained. Therefore, the operation and maintenance knowledge map expressed by the map data in the corresponding field is obtained by constructing the field knowledge content and the operation and maintenance case content map data and then fusing the map data, so that the operation and maintenance knowledge map expressed by the map data in the corresponding field is conveniently inquired.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flowchart of a method for constructing an operation and maintenance knowledge graph according to an embodiment of the present application;
FIG. 2 is an exemplary diagram of domain diagram data constructed in an embodiment of the present application;
FIG. 3 is an exemplary diagram of case diagram data constructed in an embodiment of the present application;
FIG. 4 is a partial flowchart of a method for constructing an operation and maintenance knowledge graph according to an embodiment of the present application;
FIG. 5 is another partial flowchart of a method for constructing an operation and maintenance knowledge graph according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an operation and maintenance knowledge graph constructing apparatus according to a second embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to a third embodiment of the present application;
FIG. 8 is an exemplary diagram of operation and maintenance knowledge graph construction suitable for the financial enterprise business system according to the present application;
FIG. 9 is an exemplary diagram of a case knowledge graph for constructing document records in the construction of an operation and maintenance knowledge graph for a financial enterprise business system according to the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, a flowchart of an implementation of a method for constructing an operation and maintenance knowledge graph provided in an embodiment of the present application is provided, and the method may be applied to an electronic device capable of performing data processing, such as a computer or a server. The technical scheme in the embodiment is mainly used for constructing the operation and maintenance knowledge map in the field of the operation and maintenance system, so that the operation and maintenance knowledge can be conveniently inquired.
Specifically, the method in this embodiment may include the following steps:
step 101: and acquiring the domain knowledge content of the target domain and at least one operation and maintenance case content of the target domain.
The target field is the field to which the operation and maintenance system belongs. Such as the mobile phone field, the transformer substation field, the medical appliance field and the like. The domain knowledge content of the target domain refers to the inherent knowledge domain of the target domain, namely, the domain knowledge with definite storage and less update, and the knowledge content mainly comprises the following steps: the system operation and maintenance knowledge, the system upstream and downstream knowledge and the like mainly obtain the following sources: standard specifications within the industry, software technology architecture, development documentation, etc. Taking the mobile phone field as an example, the domain knowledge content of the mobile phone field may include: standard specification in the mobile phone industry, software technology architecture in the mobile phone, software and hardware development documents of the mobile phone and the like. The operation and maintenance case content in the target field is an example data field, the knowledge content mainly comprises the content of historical operation and maintenance cases, namely, the fact describing events which actually occur are stored, and the source of the knowledge content mainly comprises document record content and/or table record content and the like left by historical operation and maintenance activities, such as the table record content left by maintaining a specific mobile phone of a certain mobile phone model.
Step 102: and constructing the domain map data according to the domain knowledge content.
The domain map data refers to map data corresponding to domain knowledge content. The domain graph data includes a plurality of first nodes, and any one of the first nodes has a connection relationship with at least one other first node, as shown in fig. 2, any two of the first nodes are directly connected or indirectly connected through another first node, that is, any one of the first nodes may be connected to any one of the first nodes through one or more first nodes in the domain graph data. And the first node and the corresponding connection relation thereof can represent the domain knowledge content.
In an implementation manner, in this embodiment, a triple extraction may be performed on the domain knowledge content, for example, a relationship between an entity and an entity is identified, and then domain map data is constructed based on the extracted triple.
Step 103: and constructing case diagram data according to the operation and maintenance case contents.
The case diagram data refers to diagram data corresponding to the operation and maintenance case content. The case graph data is composed of at least one piece of sub graph data, the sub graph data are connected through a center node, the sub graph data can include a plurality of second nodes, and any one second node has a connection relation with at least one other second node, as shown in fig. 3, any two second nodes are directly connected or indirectly connected through other second nodes, that is, in each piece of sub graph data, any one second node can be connected to any one second node through one or more second nodes in the sub graph data. And the second node and the corresponding connection relation thereof can represent the operation and maintenance case content.
It should be noted that the execution sequence between step 102 and step 103 may not be limited to the execution sequence in fig. 1, and step 103 may be executed first and then step 102 is executed, or step 102 and step 103 are executed simultaneously, and different technical solutions are all within the scope of the present application.
Step 104: and carrying out fusion processing on the map data on the domain map data and the case map data to obtain an operation and maintenance knowledge map corresponding to the target domain.
The operation and maintenance knowledge graph corresponding to the target field can be understood as graph data corresponding to the target field, and the operation and maintenance knowledge graph is composed of field graph data and case graph data.
Specifically, in step 104, graph data fusion may be implemented in the following manner to obtain the operation and maintenance knowledge graph:
firstly, aligning nodes in the field graph data and nodes in the case graph data on semantic description, for example, unifying the first node and the second node on storage elements such as node names, node attributes, node relationships and the like, so that the node names corresponding to the same node are consistent, the attribute names corresponding to the same node attribute are consistent, and the like;
and then, establishing a parent-child relationship between at least one node in the case diagram data and one node in the domain diagram data, so that the at least one node in the case diagram data has a parent node in the domain diagram data, and obtaining the operation and maintenance knowledge graph corresponding to the target domain. For example, for each first node in the case graph data, a second node is respectively found in the domain graph data to establish a parent-child relationship between the first node and the second node, the second node is used as a parent node and the first node is used as a child node, and therefore fusion between the domain graph data and the case graph data is achieved by establishing the parent-child relationship between the nodes.
And the respective node storage elements of the two nodes with the parent-child relationship satisfy the node association condition. For example, the description similarity between the first node and the second node with the parent-child relationship in the element such as the node attribute is greater than or equal to the similarity threshold, and/or the first node and the second node with the parent-child relationship have a logical relationship in the element such as the node relationship, such as a causal logical relationship, a front-back logical relationship, a parallel logical relationship, or a top-bottom logical relationship.
According to the technical scheme, in the construction method of the operation and maintenance knowledge graph provided by the embodiment of the application, for the target field to which the operation and maintenance system belongs, the field knowledge content and at least one operation and maintenance case content of the target field are respectively obtained, so that the field graph data and the case graph data are respectively constructed, and then the field graph data and the case graph data are fused, so that the operation and maintenance knowledge graph in the field to which the operation and maintenance system belongs is obtained. Therefore, in the embodiment, the operation and maintenance knowledge graph expressed by the graph data in the corresponding field is obtained by constructing the field knowledge content and the operation and maintenance case content graph data respectively and then performing graph data fusion, so that the operation and maintenance knowledge graph expressed by the graph data in the corresponding field is more comprehensive and complete, and the operation and maintenance knowledge can be conveniently inquired.
In one implementation, when the domain map data is constructed according to the domain knowledge content in step 101, the following steps may be specifically implemented, as shown in fig. 4:
step 401: and processing the domain knowledge content according to a preset body model architecture to obtain a domain body model corresponding to the domain knowledge content.
Wherein, the domain ontology model comprises a plurality of domain ontologies. The domain ontology includes ontology components such as attributes, relationships, classes, instances, functions, and restrictions.
Specifically, the ontology model architecture may be configured by the staff in advance according to the target domain, such as a star architecture, a ring architecture, or a tree architecture, to represent the composition architecture between the domain ontologies.
Based on this, in this embodiment, according to a preset ontology model architecture, data in the domain knowledge content is analyzed and extracted, and then a domain ontology model under the ontology model architecture is constructed, a composition architecture between domain ontologies in the domain ontology model is matched with the ontology model architecture, and the domain ontology in the domain ontology model and a relationship between the domain ontologies represent the domain knowledge content.
For example, in this embodiment, a corresponding ontology model building tool such as Prot g may be used to process the domain knowledge content under the ontology model structure, so as to obtain the domain ontology model corresponding to the domain knowledge content.
Step 402: and converting the domain ontology model into a first node based on the graph data according to a preset mapping rule to obtain the domain graph data.
Based on the mapping rule, the domain ontology in the domain ontology model is converted into the first node based on the graph data according to the mapping rule in the embodiment, and then the domain graph data composed of the first node is obtained.
Specifically, the mapping rule may include: the ontology in the ontology stores the transformation relationships between the elements and the nodes in the nodes. Based on this, step 402 can be implemented by:
and converting the ontology structural elements in the domain ontology into node storage elements in the corresponding graph data nodes according to the conversion relation, so that the domain ontology is converted into the graph data nodes, and thus obtaining first nodes based on the graph data, wherein the first nodes form the domain graph data.
For example, the mapping rules may be as shown in table 1:
TABLE 1 mapping rules
Based on this, in this embodiment, the domain ontology is converted into the graph data node according to the above mapping relationship, so as to obtain the domain graph data.
In one implementation, each operation and maintenance case content corresponds to an operation and maintenance event, which may be tagged with an event identification, such as an event ID. Based on this, when the case diagram data is constructed according to the operation and maintenance case content in step 103, the following steps may be specifically implemented, as shown in fig. 5:
step 501: and constructing sub-graph data corresponding to the operation and maintenance event according to the operation and maintenance case content corresponding to the operation and maintenance event.
The subgraph data corresponding to each operation and maintenance event respectively has a root node, and the second node in each subgraph data is directly or indirectly connected to the root node.
That is to say, in this embodiment, for each operation and maintenance event, the corresponding operation and maintenance case content may be processed respectively to construct the sub-graph data corresponding to each operation and maintenance event, and the number of the operation and maintenance events determines the number of the sub-graph data.
Step 502: and splicing the root nodes of all the sub-graph data through the central node to obtain case graph data.
The central node may be a node representing a target domain. Based on this, in this embodiment, the root node of each sub-graph data is connected to the central node, so as to obtain complete case graph data.
In a specific implementation, the operation and maintenance case content corresponding to each operation and maintenance event may be table record content, or may be document record content, or may have both table record content and document record content. The table record content is composed of the contents of a plurality of cells, and the document record content comprises at least one record statement.
In an implementation manner, when the operation and maintenance case content corresponding to the operation and maintenance event only includes table record content, in this embodiment, when constructing the sub-graph data corresponding to the operation and maintenance event, cells in the table record content are used as nodes based on the graph data, and the sub-graph data corresponding to the operation and maintenance event is constructed according to the content of the cells. For example, a second node included in the sub-graph data is initialized according to a cell in the table record content, and then a node storage element of the second node is set according to the content of the cell, so that complete and accurate sub-graph data is obtained.
In an implementation manner, under the condition that the operation and maintenance case content corresponding to the operation and maintenance event only includes document record content, in the embodiment, when the sub-graph data corresponding to the operation and maintenance event is constructed, triple extraction is performed on record statements corresponding to the operation and maintenance event to obtain a plurality of entities and an association relationship between the entities; and then, constructing sub-graph data corresponding to the operation and maintenance event according to the entities and the incidence relation among the entities.
Specifically, in this embodiment, the document record content may be converted into a format of a text document, then word serialization processing is performed on the text document, then entity recognition is performed on the serialized words, after an entity is recognized and extracted, a corresponding association relationship is extracted, then a second node in the sub-graph data is constructed according to the entity, and a node storage element of the second node is constructed according to the association relationship between the entities, so that complete and accurate sub-graph data is obtained.
In an implementation manner, under the condition that the operation and maintenance case content corresponding to the operation and maintenance event includes table record content and document record content, when constructing the sub-graph data corresponding to the operation and maintenance event in this embodiment, first graph data corresponding to the operation and maintenance event may be constructed according to the table record content corresponding to the operation and maintenance event, and the manner of constructing the first graph data may refer to corresponding content in the foregoing; moreover, according to the document record content corresponding to the operation and maintenance event, second graph data corresponding to the operation and maintenance event is constructed, and the way of constructing the second graph data can refer to the corresponding content in the foregoing; based on the semantic description, aligning the nodes in the first graph data and the nodes in the second graph data, wherein the aligning mode can refer to corresponding contents in the preceding text; and finally, fusing the first graph data and the second graph data, for example, taking any graph data in the first graph data and the second graph data as a reference, and optimizing the reference graph data by using the other graph data, thereby obtaining complete and accurate sub-graph data.
Referring to fig. 6, a schematic structural diagram of an operation and maintenance knowledge graph constructing apparatus provided in the second embodiment of the present application is provided, where the apparatus may be applied to an electronic device capable of performing data processing, such as a computer or a server. The technical scheme in the embodiment is mainly used for constructing the operation and maintenance knowledge map in the field of operation and maintenance systems, so that operation and maintenance knowledge query is facilitated.
Specifically, the apparatus in this embodiment may include the following units:
a content obtaining unit 601, configured to obtain domain knowledge content of a target domain and at least one operation and maintenance case content of the target domain, where the target domain is a domain to which an operation and maintenance system belongs;
a domain graph constructing unit 602, configured to construct domain graph data according to the domain knowledge content, where the domain graph data includes a plurality of first nodes, and any first node has a connection relationship with at least one other first node, and the first node represents the domain knowledge content;
the case diagram constructing unit 603 is configured to construct case diagram data according to the operation and maintenance case content, where the case diagram data is composed of at least one piece of sub-graph data, the sub-graph data is connected with each other through a central node, the sub-graph data includes a plurality of second nodes, a connection relationship exists between any one of the second nodes and at least one other second node, and the second node represents the operation and maintenance case content to which the second node belongs;
and a graph fusion unit 604, configured to perform graph data fusion processing on the domain graph data and the case graph data to obtain an operation and maintenance knowledge graph corresponding to the target domain.
According to the technical scheme, in the construction device of the operation and maintenance knowledge graph provided by the second embodiment of the application, for the target field to which the operation and maintenance system belongs, the field knowledge content and at least one operation and maintenance case content of the target field are respectively obtained, so that the field graph data and the case graph data are respectively constructed, and then the field graph data and the case graph data are fused, so that the operation and maintenance knowledge graph in the field to which the operation and maintenance system belongs is obtained. Therefore, in the embodiment, the operation and maintenance knowledge graph expressed by the graph data in the corresponding field is obtained by constructing the field knowledge content and the operation and maintenance case content graph data respectively and then performing graph data fusion, so that the operation and maintenance knowledge graph expressed by the graph data in the corresponding field is more comprehensive and complete, and the operation and maintenance knowledge can be conveniently inquired.
In an implementation manner, the domain graph constructing unit 602 is specifically configured to: processing the domain knowledge content according to a preset body model architecture to obtain a domain body model corresponding to the domain knowledge content, wherein the domain body model comprises a plurality of domain bodies; and converting the domain ontology into a first node based on graph data according to a preset mapping rule to obtain the domain graph data.
In an optional implementation manner, the mapping rule includes: an ontology component in the ontology and a node storage component in the node store a translation relationship between the elements;
when the domain ontology is converted into the first node based on the graph data, the domain graph constructing unit 602 may specifically be implemented in the following manner: and converting the ontology structural elements in the domain ontology into node storage elements in graph data nodes according to the conversion relation so as to obtain first nodes based on the graph data, wherein the first nodes form the domain graph data.
In one implementation, each operation and maintenance case content corresponds to an operation and maintenance event; the case diagram constructing unit 603 is specifically configured to: according to the operation and maintenance case content corresponding to the operation and maintenance event, constructing sub-graph data corresponding to the operation and maintenance event; the sub-graph data corresponding to each operation and maintenance event respectively has a root node, and a second node in each sub-graph data is directly or indirectly connected to the root node; and splicing the root nodes of all the sub-graph data through the central node to obtain case graph data.
In an optional implementation manner, the operation and maintenance case content includes table record content of a corresponding operation and maintenance event, and the table record content is composed of contents of a plurality of cells;
when the case graph constructing unit 603 constructs sub-graph data corresponding to the operation and maintenance event according to the operation and maintenance case content corresponding to the operation and maintenance event, the sub-graph data can be implemented in the following manner: and taking the cells in the table record content as nodes based on graph data, and constructing sub-graph data corresponding to the operation and maintenance event according to the content of the cells.
In an optional implementation manner, the operation and maintenance case content includes a document record content of a corresponding operation and maintenance event, and the document record content includes at least one record statement;
when the case graph constructing unit 603 constructs sub-graph data corresponding to the operation and maintenance event according to the operation and maintenance case content corresponding to the operation and maintenance event, the sub-graph data can be implemented in the following manner: extracting triples of the recorded sentences corresponding to the operation and maintenance events to obtain a plurality of entities and the incidence relation among the entities; and constructing sub-graph data corresponding to the operation and maintenance event according to the entity and the incidence relation between the entities.
In an optional implementation manner, the operation and maintenance case content includes table record content and document record content of a corresponding operation and maintenance event;
when the case graph constructing unit 603 constructs sub-graph data corresponding to the operation and maintenance event according to the operation and maintenance case content corresponding to the operation and maintenance event, the sub-graph data corresponding to the operation and maintenance event can be implemented in the following manner: according to the table record content corresponding to the operation and maintenance event, constructing first graph data corresponding to the operation and maintenance event; according to the document record content corresponding to the operation and maintenance event, second graph data corresponding to the operation and maintenance event is constructed; aligning nodes in the first graph data and nodes in the second graph data in a semantic description; and fusing the first graph data and the second graph data to obtain sub-graph data corresponding to the operation and maintenance event.
In one implementation, the graph fusing unit 604 is specifically configured to: aligning nodes in the domain graph data and nodes in the case graph data on semantic description; establishing a parent-child relationship between at least one node in the case graph data and one node in the domain graph data, so that the at least one node in the case graph data has a parent node in the domain graph data to obtain an operation and maintenance knowledge graph corresponding to the target domain; and the respective node storage elements of the two nodes with the parent-child relationship meet the node association condition.
It should be noted that, for the specific implementation of each unit in the present embodiment, reference may be made to the corresponding content in the foregoing, and details are not described here.
Referring to fig. 7, a schematic structural diagram of an electronic device according to a third embodiment of the present application, where the electronic device is a computer or a server capable of performing data processing, specifically, the electronic device may include the following structure:
a memory 701 for storing a computer program and data generated by the computer program;
a processor 702 for executing the computer program to implement: obtaining field knowledge content of a target field and at least one operation and maintenance case content of the target field, wherein the target field is a field to which an operation and maintenance system belongs; according to the domain knowledge content, domain graph data are constructed, the domain graph data comprise a plurality of first nodes, a connection relation exists between any first node and at least one other first node, and the first nodes represent the domain knowledge content; according to the operation and maintenance case content, case diagram data are constructed, the case diagram data are composed of at least one piece of sub-diagram data, the sub-diagram data are connected through a center node, the sub-diagram data comprise a plurality of second nodes, a connection relation exists between any second node and at least one other second node, and the second nodes represent the operation and maintenance case content to which the second nodes belong; and carrying out fusion processing on the map data on the domain map data and the case map data to obtain an operation and maintenance knowledge map corresponding to the target domain.
According to the technical scheme, in the electronic device provided by the third embodiment of the application, for the target field to which the operation and maintenance system belongs, the field knowledge content and at least one operation and maintenance case content of the target field are respectively obtained, so that the field diagram data and the case diagram data are respectively constructed, and then the field diagram data and the case diagram data are fused, so that the operation and maintenance knowledge diagram in the field to which the operation and maintenance system belongs is obtained. Therefore, in the embodiment, the operation and maintenance knowledge graph expressed by the graph data in the corresponding field is obtained by constructing the field knowledge content and the operation and maintenance case content graph data respectively and then performing graph data fusion, so that the operation and maintenance knowledge graph expressed by the graph data in the corresponding field is more comprehensive and complete, and the operation and maintenance knowledge can be conveniently inquired.
The embodiment of the present application further provides a computer-readable medium, on which a computer program is stored, where the computer program is executed by a processor to implement the method for constructing an operation and maintenance knowledge graph according to the foregoing embodiment.
The embodiment of the application further provides a processor, and the processor is used for running the program, wherein the method for constructing the operation and maintenance knowledge graph described in the above method embodiments is implemented when the program runs.
The embodiment of the present application further provides a computer program product, which, when executed on a data processing device, enables the data processing device to implement the method for constructing the operation and maintenance knowledge graph described in the above method embodiments.
Taking an operation and maintenance system as an example of a business system of a financial enterprise, in order to construct a knowledge graph of the operation and maintenance system, based on the technical scheme described in the foregoing, the application is directed to the problems of complicated knowledge system, insufficient structuralization and the like existing in the operation and maintenance work of the current system, and the operation and maintenance knowledge (including domain knowledge and operation and maintenance cases) of the operation and maintenance system is induced, expressed and stored by using graph data as a key technology. The basic scheme is as follows: the method comprises the steps of carrying out ontology modeling, element mapping and graph data embedding on operation and maintenance field knowledge (namely field knowledge content in the text) of a business system, carrying out triple extraction and graph data embedding on operation and maintenance case knowledge (namely operation and maintenance case content in the text) of the business system, and completing construction of an operation and maintenance knowledge base after graph data fusion, thereby providing a more convenient and efficient knowledge retrieval interface for technicians and operation and maintenance personnel.
Specifically, the knowledge graph construction scheme based on the graph database is provided, and knowledge graph modeling is carried out by adopting the knowledge graph. The operation and maintenance knowledge graph of the application is divided into two parts: domain knowledge graphs (i.e., domain graph data in the foregoing) and case knowledge graphs (i.e., case graph data in the foregoing). The domain knowledge map is an inherent knowledge domain, namely, the domain knowledge which is determined by storage and is less updated is stored, the knowledge mainly comprises system operation and maintenance knowledge, system upstream and downstream knowledge and the like, and the main acquisition sources are standard specifications, software technical architectures, development documents and the like in the industry. The case knowledge graph is an example data domain, the knowledge mainly comprises historical operation and maintenance cases, namely, events which describe facts and actually occur are stored, and the knowledge source is mainly characters and table records left by historical operation and maintenance activities.
From the knowledge-graph perspective, most of the domain knowledge-graphs exist in the form of classes, representing concepts that have been abstracted from concrete things, while most of the case knowledge-graphs exist in the form of instances, i.e., each node represents only one thing. Because the stored information has different meanings and sources, the construction method and the process are respectively introduced as follows:
the construction scheme of the knowledge graph provided by the application is oriented to operation and maintenance of a business system, and the constructed technical route is shown in fig. 8.
Firstly, because the operation and maintenance of the business system involve many aspects and the amount of related knowledge is huge, the staff needs to sort and summarize the related knowledge in advance to form the original domain knowledge content. Before constructing the domain knowledge graph, the domain of the knowledge graph needs to be determined according to the direction of application. The model layer design of the domain knowledge graph is mainly expressed in an ontology mode and mainly comprises concepts (nodes) and relations (connecting lines between the nodes), the purpose is to abstract concrete domain knowledge into a knowledge expression framework, the ontology modeling of the application can be completed in the Prot g, and for the storage and fusion part of the complete knowledge graph, the ontology modeling is performed in a graph database, wherein the mapping from the ontology to the graph database is related. The method comprises the following specific steps:
(1) Ontology modeling
In the process of modeling the domain ontology, determining the professional domain and category of the domain ontology, sorting and listing out important terms in the domain related to the ontology, extracting concepts and classifying concept hierarchies, and defining relationships among concepts are important links in the domain ontology modeling process, as shown in fig. 1. In the application, a worker can adopt a deduction and induction combined strategy, and firstly performs deduction from top to bottom according to a plurality of divided domains; secondly, combing and summarizing actual domain knowledge by adopting a bottom-up summary; then, iterative adjustment is carried out on the top-down method and the bottom-up method, and a final domain ontology is obtained. The tool mainly used in the method is a project, wherein the import of concepts, instances and relationships, and the definition of constraints and attributes are completed, and finally a domain ontology (namely, the domain ontology model in the foregoing) is constructed.
(2) Mapping rules
The present application describes a mesh structure of an ontology by means of graph characteristics possessed by a graph database, and defines a mapping rule between basic constituent elements of the ontology and node storage elements of nodes in the graph database, as shown in table 1.
According to the mapping rule shown in table 1, in the present application, the own representation method (i.e., the domain ontology) of the ontology model can be embedded and stored in the graph database (the domain graph data is output through Neo4 j), so that the initial construction of the domain knowledge base (i.e., the domain graph data) is completed.
The main content of the case knowledge graph is the historical operation and maintenance cases, so the case knowledge graph is different from the construction idea of the field knowledge graph, the requirements on a mode layer are low, the requirements on an instance layer are high, and the description of a knowledge graph form needs to be carried out on one operation and maintenance event.
Because the constituent elements of the case knowledge graph are mostly 'events', each event is modeled as a 'community' of a graph structure, wherein a central node is needed, and the central node is similar to a 'primary key' of a relational database (due to the heterogeneity of data sources, the definition of the central node of each event is different, but the model structure is similar), and the node directly generating the relationship with the central node represents the relevant operation and maintenance information of the event, such as the fault phenomenon, the fault reason and the final processing measure of the secondary event.
The source of case knowledge maps is mainly in two forms: table records and document records. The data recorded in the form of a table mainly summarizes a series of operation and maintenance activities, and is characterized by being structured, easy to import into a graph database, but limited in expressed information; the data recorded by the document is mainly detailed records from beginning to end of each fault event, and is characterized in that the expressed semantic information is extremely rich, the expert operation and maintenance experience can be deeply embodied, but the data is unstructured.
For the structured data of the tabular records, the features of each column can be used as relationship names in the knowledge graph, and each cell can be imported into the graph database as a node of one event element. For unstructured data of the document record, preprocessing needs to be performed by using Natural Language Processing (NLP) technology, and a main technical route is shown in fig. 9. Firstly, converting an original document into a text document (word 2txt, namely converting the original document in the word format into the text document in the txt format), then performing triple extraction (including three subtasks of word serialization, entity identification and relation extraction) through a natural language processing model based on a language representation model BERT (bidirectional Encode representation from Transformers), and storing the triple extraction into a graph database (namely sub-graph data corresponding to each operation and maintenance event stored in the graph database) after manual verification.
After the case knowledge graph (namely the sub-graph data corresponding to each operation and maintenance event) of each event is obtained, the case knowledge graph is subjected to knowledge graph fusion, and the same concepts in the case knowledge graph are subjected to entity alignment to form a final case knowledge graph.
Finally, the domain knowledge graph and the case knowledge graph are independently constructed, so that the domain knowledge graph and the case knowledge graph need to be further fused. Because the domain knowledge graph is designed with more emphasis on the mode layer, all the instances in the operation and maintenance records belong to a certain class through the deduction from top to bottom, all the entities in the case knowledge graph only need to be summarized from bottom to top, and are classified together, and the relationships of the instances and the concepts in the domain knowledge graph are generated, so that the whole system operation and maintenance domain knowledge base is formed.
In summary, the technical solution proposed by the present application has the following advantages:
first, the present application employs a knowledge management method. Compared with other knowledge representation methods, the knowledge graph is stored in a graph structure, the storage structure is more visual, the relation query efficiency is higher, the semantic expression capability is stronger, and the knowledge query efficiency can be improved.
Secondly, the method for constructing the knowledge base is adopted. The top-down deduction and the bottom-up deduction are combined, so that the knowledge graph has a rigorous and complete mode layer and a rich and diverse data layer, and the knowledge system can lose information as little as possible in the structured storage process.
Finally, the present application employs a knowledge storage tool. Compared with a relational database, the relational query of a graph database is more efficient, and semantic expression is supported. Therefore, the fault diagnosis is carried out by using the knowledge map, and the historical operation and maintenance process and the expert experience can be applied to the operation and maintenance process, so that the fault location and the operation and maintenance decision become more 'intelligent'.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A construction method of an operation and maintenance knowledge graph is characterized by comprising the following steps:
obtaining field knowledge content of a target field and at least one operation and maintenance case content of the target field, wherein the target field is a field to which an operation and maintenance system belongs;
according to the domain knowledge content, domain graph data are constructed, the domain graph data comprise a plurality of first nodes, any two first nodes are directly connected or indirectly connected through other first nodes, and the first nodes represent the domain knowledge content;
according to the operation and maintenance case content, case diagram data is constructed, the case diagram data is composed of at least one piece of sub-diagram data, the sub-diagram data are connected through a center node, the sub-diagram data comprise a plurality of second nodes, any two second nodes are directly connected or indirectly connected through other second nodes, and the second nodes represent the operation and maintenance case content to which the second nodes belong;
and carrying out fusion processing on the map data on the domain map data and the case map data to obtain an operation and maintenance knowledge map corresponding to the target domain.
2. The method of claim 1, wherein constructing domain graph data based on the domain knowledge content comprises:
processing the domain knowledge content according to a preset body model architecture to obtain a domain body model corresponding to the domain knowledge content, wherein the domain body model comprises a plurality of domain bodies;
and converting the domain ontology into a first node based on graph data according to a preset mapping rule to obtain the domain graph data.
3. The method of claim 2, wherein the mapping rule comprises: the conversion relation between the ontology constituent elements in the ontology and the node storage elements in the nodes;
wherein, according to the preset mapping rule, converting the domain ontology into a first node based on graph data to obtain the domain graph data, including:
and converting the ontology structural elements in the domain ontology into node storage elements in graph data nodes according to the conversion relation so as to obtain first nodes based on the graph data, wherein the first nodes form the domain graph data.
4. The method according to claim 1 or 2, wherein each operation and maintenance case content corresponds to an operation and maintenance event;
wherein, the constructing case diagram data according to the operation and maintenance case content comprises:
according to the operation and maintenance case content corresponding to the operation and maintenance event, constructing sub-graph data corresponding to the operation and maintenance event; the sub-graph data corresponding to each operation and maintenance event respectively has a root node, and a second node in each sub-graph data is directly or indirectly connected to the root node;
and splicing the root nodes of all the sub-graph data through the central node to obtain case graph data.
5. The method of claim 4, wherein the operation and maintenance case content comprises table record content of the corresponding operation and maintenance event, and the table record content is composed of contents of a plurality of cells;
wherein, the constructing sub-graph data corresponding to the operation and maintenance event according to the operation and maintenance case content corresponding to the operation and maintenance event includes:
and taking the cells in the table record content as nodes based on graph data, and constructing sub-graph data corresponding to the operation and maintenance event according to the content of the cells.
6. The method of claim 4, wherein the operation and maintenance case content comprises documentary content of a corresponding operation and maintenance event, and the documentary content comprises at least one documentary statement;
wherein, the constructing sub-graph data corresponding to the operation and maintenance event according to the operation and maintenance case content corresponding to the operation and maintenance event includes:
extracting triples of the record statements corresponding to the operation and maintenance events to obtain a plurality of entities and association relations among the entities;
and constructing sub-graph data corresponding to the operation and maintenance event according to the entity and the incidence relation between the entities.
7. The method of claim 4, wherein the operation and maintenance case content comprises table record content and document record content of the corresponding operation and maintenance event;
wherein, the constructing sub-graph data corresponding to the operation and maintenance event according to the operation and maintenance case content corresponding to the operation and maintenance event includes:
according to the table record content corresponding to the operation and maintenance event, constructing first graph data corresponding to the operation and maintenance event;
according to the document record content corresponding to the operation and maintenance event, second graph data corresponding to the operation and maintenance event is constructed;
aligning nodes in the first graph data and nodes in the second graph data in a semantic description;
and fusing the first graph data and the second graph data to obtain sub-graph data corresponding to the operation and maintenance event.
8. The method according to claim 1 or 2, wherein the fusing of the map data between the domain map data and the case map data to obtain the operation and maintenance knowledge graph corresponding to the target domain comprises:
aligning nodes in the domain graph data and nodes in the case graph data on semantic description;
establishing a parent-child relationship between at least one node in the case graph data and one node in the domain graph data, so that the at least one node in the case graph data has a parent node in the domain graph data to obtain an operation and maintenance knowledge graph corresponding to the target domain;
and the respective node storage elements of the two nodes with the parent-child relationship meet the node association condition.
9. An operation and maintenance knowledge graph construction device, which is characterized by comprising:
the content obtaining unit is used for obtaining the domain knowledge content of a target domain and at least one operation and maintenance case content of the target domain, wherein the target domain is a domain to which the operation and maintenance system belongs;
the domain graph building unit is used for building domain graph data according to the domain knowledge content, the domain graph data comprises a plurality of first nodes, a connection relation exists between any first node and at least one other first node, and the first nodes represent the domain knowledge content;
the case diagram construction unit is used for constructing case diagram data according to the operation and maintenance case contents, the case diagram data is composed of at least one piece of sub-graph data, the sub-graph data are connected through a center node, the sub-graph data comprise a plurality of second nodes, a connection relation exists between any second node and at least one other second node, and the second node represents the operation and maintenance case contents to which the second node belongs;
and the graph fusion unit is used for carrying out fusion processing on the graph data on the domain graph data and the case graph data so as to obtain the operation and maintenance knowledge graph corresponding to the target domain.
10. An electronic device, comprising:
a memory for storing a computer program and data generated by the execution of the computer program;
a processor for executing the computer program to implement: obtaining field knowledge content of a target field and at least one operation and maintenance case content of the target field, wherein the target field is a field to which an operation and maintenance system belongs; according to the domain knowledge content, domain graph data are constructed, the domain graph data comprise a plurality of first nodes, a connection relation exists between any first node and at least one other first node, and the first nodes represent the domain knowledge content; constructing case diagram data according to the operation and maintenance case contents, wherein the case diagram data comprises at least one sub-graph data, the sub-graph data are connected through a center node, the sub-graph data comprise a plurality of second nodes, a connection relation exists between any second node and at least one other second node, and the second node represents the operation and maintenance case contents to which the second node belongs; and carrying out image data fusion processing on the field image data and the case image data to obtain an operation and maintenance knowledge graph corresponding to the target field.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211383421.8A CN115827885A (en) | 2022-11-07 | 2022-11-07 | Operation and maintenance knowledge graph construction method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211383421.8A CN115827885A (en) | 2022-11-07 | 2022-11-07 | Operation and maintenance knowledge graph construction method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115827885A true CN115827885A (en) | 2023-03-21 |
Family
ID=85526785
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211383421.8A Pending CN115827885A (en) | 2022-11-07 | 2022-11-07 | Operation and maintenance knowledge graph construction method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115827885A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116150929A (en) * | 2023-04-17 | 2023-05-23 | 中南大学 | Construction method of railway route selection knowledge graph |
-
2022
- 2022-11-07 CN CN202211383421.8A patent/CN115827885A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116150929A (en) * | 2023-04-17 | 2023-05-23 | 中南大学 | Construction method of railway route selection knowledge graph |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111428053B (en) | Construction method of tax field-oriented knowledge graph | |
| CN111708773B (en) | Multi-source scientific and creative resource data fusion method | |
| WO2021103492A1 (en) | Risk prediction method and system for business operations | |
| CN111488465A (en) | Knowledge graph construction method and related device | |
| CN106407208B (en) | A kind of construction method and system of city management ontology knowledge base | |
| CN110941612A (en) | Autonomous data lake construction system and method based on associated data | |
| WO2020010834A1 (en) | Faq question and answer library generalization method, apparatus, and device | |
| US10924551B2 (en) | IRC-Infoid data standardization for use in a plurality of mobile applications | |
| US20120078969A1 (en) | System and method to extract models from semi-structured documents | |
| CN111967761A (en) | Monitoring and early warning method and device based on knowledge graph and electronic equipment | |
| WO2023124191A1 (en) | Depth map matching-based automatic classification method and system for medical data elements | |
| CN111061679A (en) | Method and system for rapid configuration of technological innovation policy based on rete and drools rules | |
| CN114218472A (en) | Intelligent search system based on knowledge graph | |
| Kamalabalan et al. | Tool support for traceability of software artefacts | |
| CN112613611A (en) | Tax knowledge base system based on knowledge graph | |
| CN115438199A (en) | Knowledge platform system based on smart city scene data middling platform technology | |
| Schorlemmer et al. | Institutionalising ontology-based semantic integration | |
| CN116561264A (en) | Knowledge graph-based intelligent question-answering system construction method | |
| CN115827885A (en) | Operation and maintenance knowledge graph construction method and device and electronic equipment | |
| CN111159427A (en) | Knowledge graph construction method and system based on crowdsourcing | |
| CN114911893A (en) | Method and system for automatically constructing knowledge base based on knowledge graph | |
| CN113610626A (en) | Bank credit risk identification knowledge graph construction method and device, computer equipment and computer readable storage medium | |
| CN113220951A (en) | Medical clinical support method and system based on intelligent content | |
| CN112883202A (en) | Knowledge graph-based multi-component modeling method and system | |
| CN106933844B (en) | Construction method of reachability query index facing large-scale RDF data |
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 |