Knowledge graph management method, system and device based on operation and maintenance scene, storage medium and product

Abstract

The invention discloses a knowledge graph management method, system and device based on an operation and maintenance scene, a storage medium and a product, and relates to the technical field of knowledge graphs, the method comprises the steps that an operation and maintenance knowledge graph is constructed, the operation and maintenance knowledge graph comprises knowledge agent nodes and source nodes, and the knowledge agent nodes are associated with knowledge agent elements; querying the operation and maintenance knowledge graph according to a received query request to obtain query return data; when the knowledge agent node exists in the query return data, obtaining operation and maintenance knowledge data generated in real time through a knowledge agent element; the operation and maintenance knowledge data and the query return data are fused and stored in a graph structure form, and a target knowledge graph is obtained. According to the invention, the flexibility of knowledge graph management can be improved in an application scene in which the knowledge graph and the artificial intelligence technology are fused.

Description

Technical Field

[0001] This application relates to the field of knowledge graph technology, and in particular to knowledge graph management methods, systems, equipment, storage media and products based on operation and maintenance scenarios. Background Art

[0002] With the development and widespread application of knowledge graph technology and artificial intelligence technology (including artificial intelligence and big models), a trend of integration between the two is gradually forming in the process of implementation in actual business scenarios.

[0003] Currently, in the application scenarios of the integration of knowledge graphs and artificial intelligence technologies, the construction and updating of knowledge graphs still face many limitations, which are mainly manifested in the phenomenon of delayed knowledge graph updates and difficult to control the scope of knowledge, resulting in a lack of sufficient flexibility in the management of knowledge graphs.

[0004] In summary, how to improve the flexibility of knowledge graph management in application scenarios where knowledge graphs are integrated with artificial intelligence technologies has become a technical problem that needs to be urgently solved in this field. Summary of the Invention

[0005] The main purpose of this application is to provide a knowledge graph management method, system, equipment, storage medium and product based on operation and maintenance scenarios, aiming to improve the flexibility of knowledge graph management in application scenarios where knowledge graphs are integrated with artificial intelligence technologies.

[0006] To achieve the above objectives, this application proposes a knowledge graph management method based on operation and maintenance scenarios. The knowledge graph management method based on operation and maintenance scenarios includes: Constructing an operation and maintenance knowledge graph, wherein the operation and maintenance knowledge graph includes knowledge agent nodes and source nodes, and the knowledge agent nodes are associated with knowledge agent elements; Querying the operation and maintenance knowledge graph according to the received query request to obtain query return data; When the knowledge agent node exists in the query return data, the real-time generated operation and maintenance knowledge data is acquired through the knowledge agent element; The operation and maintenance knowledge data is integrated with the query return data and stored in a graph structure to obtain a target knowledge graph.

[0007] In one embodiment, the step of constructing an operation and maintenance knowledge graph includes: Construct triple data based on the attribute data and relationship data of each preset entity; The triplet data is stored in a graph structure to obtain an operation and maintenance knowledge graph.

[0008] In one embodiment, before the step of constructing the operation and maintenance knowledge graph, the method further includes: Establish an association between the knowledge agent node and the knowledge agent element, and establish an association between the knowledge agent element and a preset operation and maintenance knowledge generation device, wherein the knowledge agent element is used to provide a knowledge pulling script, and the operation and maintenance knowledge generation device is used to provide an operation and maintenance knowledge pulling service based on the knowledge pulling script.

[0009] In one embodiment, the step of querying the operation and maintenance knowledge graph according to the received query request to obtain query return data includes: receiving a query request, and determining a query node and a query hop range according to the query request; According to the query node and the query hop range, a path from the query node to the query hop range is traversed from the operation and maintenance knowledge graph to obtain query return data.

[0010] In one embodiment, when the knowledge agent node exists in the query return data, the step of obtaining the real-time generated operation and maintenance knowledge data through the knowledge agent element includes: Detecting the knowledge agent node in the query return data; When the knowledge agent node exists in the query return data, generating script parameters according to the query request and the knowledge agent node; The knowledge agent element executes the knowledge pulling script according to the script parameters to call the operation and maintenance knowledge generating device to obtain the operation and maintenance knowledge data generated in real time.

[0011] In one embodiment, the step of executing the knowledge pulling script according to the script parameters by the knowledge proxy component to call the operation and maintenance knowledge generating device to obtain the operation and maintenance knowledge data generated in real time includes: Executing a knowledge extraction script through the knowledge proxy element to call an operation and maintenance knowledge generation device, wherein the operation and maintenance knowledge generation device has an indicator analysis service interface, an AI (Artificial Intelligence) detection service interface, and a large language model knowledge generation service interface; After the operation and maintenance knowledge generation device is successfully called, the script parameters are input into one or more of the indicator analysis service interface, the AI ​​detection service interface and the large language model knowledge generation service interface to obtain real-time generated operation and maintenance knowledge data.

[0012] In addition, to achieve the above objectives, this application also proposes a knowledge graph management system based on operation and maintenance scenarios, which includes: A knowledge graph construction module is used to construct an operation and maintenance knowledge graph, wherein the operation and maintenance knowledge graph includes knowledge agent nodes and source nodes, and the knowledge agent nodes are associated with knowledge agent elements; A knowledge graph query service module is used to query the operation and maintenance knowledge graph according to the received query request and obtain query return data; A knowledge agent and extraction module, configured to obtain real-time generated operation and maintenance knowledge data through the knowledge agent element when the knowledge agent node exists in the query return data; The knowledge graph visualization module is used to fuse the operation and maintenance knowledge data with the query return data and store them in a graph structure to obtain a target knowledge graph.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and runnable on the processor, and the computer program is configured to implement the steps of the knowledge graph management method based on the operation and maintenance scenario as described above.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the knowledge graph management method based on the operation and maintenance scenario as described above are implemented.

[0015] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the steps of the knowledge graph management method based on the operation and maintenance scenario as described above.

[0016] This application proposes a knowledge graph management method based on an operation and maintenance scenario. In this application, an operation and maintenance knowledge graph is constructed, wherein the operation and maintenance knowledge graph includes knowledge proxy nodes and source nodes, and the knowledge proxy nodes are associated with knowledge proxy elements; the operation and maintenance knowledge graph is queried according to the received query request to obtain query return data; when there is a knowledge proxy node in the query return data, the real-time generated operation and maintenance knowledge data is obtained through the knowledge proxy element; the operation and maintenance knowledge data is fused with the query return data and stored in a graph structure to obtain a target knowledge graph.

[0017] In summary, this application constructs an operation and maintenance knowledge graph containing knowledge proxy nodes and source nodes, and designs knowledge proxy node-associated knowledge proxy elements, thereby realizing intelligent identification of knowledge proxy nodes when receiving query requests, and triggering real-time knowledge pulling and knowledge fusion, so that the knowledge graph is updated in a timely manner and the scope of pulled knowledge is controllable, thereby improving the flexibility of knowledge graph management. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0020] Figure 1 A flowchart of the first embodiment of the knowledge graph management method based on the operation and maintenance scenario of this application is provided; Figure 2 A schematic diagram of the target knowledge graph formation process provided in Example 1 of the knowledge graph management method based on operation and maintenance scenarios of this application; Figure 3 A schematic diagram of the target operation and maintenance knowledge graph provided in Example 1 of the knowledge graph management method based on operation and maintenance scenarios of this application; Figure 4 A schematic diagram of the operation and maintenance knowledge graph storage process provided in Example 2 of the knowledge graph management method based on the operation and maintenance scenario of this application; Figure 5 A query flow diagram provided for Example 2 of the knowledge graph management method based on operation and maintenance scenarios of this application; Figure 6 A schematic diagram of the knowledge extraction process provided in Example 2 of the knowledge graph management method based on operation and maintenance scenarios of this application; Figure 7 This is a diagram of graph management provided in Example 2 of the knowledge graph management method based on operation and maintenance scenarios of this application; Figure 8 This is a schematic diagram of an example of an operation and maintenance knowledge graph provided in Example 2 of the knowledge graph management method based on an operation and maintenance scenario of this application; Figure 9 This is a schematic diagram of an example of a target operation and maintenance knowledge graph provided in Example 2 of the knowledge graph management method based on operation and maintenance scenarios of this application; Figure 10 This is a schematic diagram of another target operation and maintenance knowledge graph example provided in Example 2 of the knowledge graph management method based on operation and maintenance scenarios of this application; Figure 11 This is a schematic diagram of the module structure of the knowledge graph management system based on the operation and maintenance scenario in an embodiment of the present application; Figure 12 This is a schematic diagram of the device structure of the hardware operating environment involved in the knowledge graph management method based on the operation and maintenance scenario in the embodiment of the present application.

[0021] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0022] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0023] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0024] With the development and widespread application of knowledge graph technology and artificial intelligence technology (including artificial intelligence and big models), a trend of integration between the two is gradually forming in the process of implementation in actual business scenarios.

[0025] Currently, in the application scenarios of the integration of knowledge graphs and artificial intelligence technologies, the construction and updating of knowledge graphs still face many limitations, which are mainly manifested in the phenomenon of delayed knowledge graph updates and difficult to control the scope of knowledge, resulting in a lack of sufficient flexibility in the management of knowledge graphs.

[0026] For example, while supplementing knowledge graphs with historical accident emergency data can enable structured reasoning, the scale and completeness of knowledge supplementation are difficult to control and updates are not timely. Constructing graphs based on unstructured data relies on large language models to extract entity relationships, but the scope and scale of graph knowledge are difficult to control. Constructing operation and maintenance knowledge graphs using historical fault data has the problem that the frequency of graph updates directly restricts the timeliness of operation and maintenance knowledge. Although the construction method based on structured data and expert experience is domain-specific, it is limited by manual processes, resulting in delayed knowledge updates and insufficient domain expansion capabilities. These methods generally have common technical difficulties such as the lack of dynamic update mechanisms and insufficient scale expansion flexibility. It is urgent to establish a comprehensive knowledge graph management system based on operation and maintenance scenarios that takes into account both structured and unstructured data processing capabilities, supports real-time knowledge incremental updates, and has adaptive expansion features.

[0027] In summary, how to improve the flexibility of knowledge graph management in application scenarios where knowledge graphs are integrated with artificial intelligence technologies has become a technical problem that needs to be urgently solved in this field.

[0028] The main solution of the embodiment of the present application is: constructing an operation and maintenance knowledge graph, wherein the operation and maintenance knowledge graph includes knowledge proxy nodes and source nodes, and the knowledge proxy nodes are associated with knowledge proxy elements; querying the operation and maintenance knowledge graph according to the received query request to obtain query return data; when there is a knowledge proxy node in the query return data, obtaining real-time generated operation and maintenance knowledge data through the knowledge proxy element; fusing the operation and maintenance knowledge data with the query return data and storing them in a graph structure form to obtain a target knowledge graph.

[0029] The embodiment of the present application provides a solution. By constructing an operation and maintenance knowledge graph including knowledge proxy nodes and source nodes, and designing knowledge proxy elements to associate knowledge proxy nodes, it realizes intelligent identification of knowledge proxy nodes when receiving query requests, and triggers real-time knowledge pulling and knowledge fusion, so that the knowledge graph is updated in a timely manner and the scope of pulled knowledge is controllable, thereby improving the flexibility of knowledge graph management.

[0030] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a server, computer, personal computer, etc., or an electronic device capable of implementing the above functions. The following uses a knowledge graph management terminal based on an operation and maintenance scenario as an example, hereinafter referred to as the management terminal, to illustrate this embodiment and the following embodiments.

[0031] Based on this, the embodiment of the present application provides a knowledge graph management method based on operation and maintenance scenarios, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the knowledge graph management method based on operation and maintenance scenarios of this application.

[0032] In this embodiment, the knowledge graph management method based on the operation and maintenance scenario includes steps S10 to S40: Step S10: constructing an operation and maintenance knowledge graph, wherein the operation and maintenance knowledge graph includes knowledge agent nodes and source nodes, and the knowledge agent nodes are associated with knowledge agent elements; It should be noted that the operation and maintenance knowledge graph is an operation and maintenance knowledge base stored in the form of a graph structure, which is used to store, manage and query relevant knowledge of operation and maintenance scenarios. The operation and maintenance scenario refers to the full life cycle management scenario for monitoring, maintenance, optimization and troubleshooting of operation and maintenance objects (such as hosts, services, components, indicators, etc.); the knowledge agent node is a knowledge extension logic unit predefined in the operation and maintenance knowledge graph, which can pull external knowledge into the operation and maintenance knowledge graph through the knowledge agent element; the source node is the basic data unit in the operation and maintenance knowledge graph, representing the specific entities or concepts in the operation and maintenance scenario, such as hosts, services, components, indicators and other operation and maintenance objects; the knowledge agent element is an executable logic unit pre-stored in a preset storage space (such as a knowledge agent element library), which is associated with the knowledge agent node through a unique identifier and is used to provide script information for accessing or generating knowledge, including script identification, script path, script description, knowledge retrieval script, etc.

[0033] In this embodiment, an operation and maintenance knowledge graph is constructed, which includes knowledge agent nodes and source nodes, and the knowledge agent nodes are associated with knowledge agent elements.

[0034] It is worth mentioning that for this operation and maintenance knowledge graph, the management terminal has the ability to manage knowledge graph graph spaces (knowledge graphs used to distinguish specific application fields or topics) (graph space creation, graph space deletion, graph space usage, graph space details, etc.), knowledge graph pattern management (including the addition, modification, and deletion of point types, the addition, modification, and deletion of edge types, etc.), knowledge graph point management (the insertion, deletion, and modification of points, etc.), and knowledge graph edge management (the insertion, deletion, and modification of edges, etc.). Among them, knowledge graph pattern management can cover entities, relationships, attributes, etc. in the knowledge graph, mainly including the name of the entity and other attributes of the entity. For example, the person entity includes two attributes, name and age, with a structure of ("namestring, ageint"); the has relationship includes a single attribute, name, with a structure of ("namestring").

[0035] A new KA (KnowledgeAgent) node has been added to the knowledge graph construction. KA attributes include the knowledge agent component name and the knowledge agent component identifier. The specific structure is (kanamestring,kaunitstring), where kaunit corresponds to the knowledge agent component identifier. For example, a business-impacting golden metric node, ka_metrics_001, is defined. It belongs to both the knowledge agent (KA) and metric (metrics) entity types. ka_metrics_001 attributes include the knowledge agent component name, knowledge agent component identifier, metric name, metric value, and whether it is abnormal. The specific structure is as follows: "ka_metrics-001": {"kaunit_name":"component name","kaunit_id":"ka_unit_1001","name":"metric name","value":"","ex_rst":""}. When performing knowledge graph Q&A or queries, the configured knowledge agent component retrieves the specific knowledge information of ka_metrics_001. The retrieved knowledge can be one or more pieces, depending on the operation and maintenance business scenario.

[0036] In a feasible embodiment, step S10 may include step A10: Step A10, establish an association between the knowledge agent node and the knowledge agent element, and establish an association between the knowledge agent element and the preset operation and maintenance knowledge generation device, wherein the knowledge agent element is used to provide a knowledge pulling script, and the operation and maintenance knowledge generation device is used to provide an operation and maintenance knowledge pulling service based on the knowledge pulling script.

[0037] It should be noted that the operation and maintenance knowledge generation device is an intelligent virtual device that integrates multiple operation and maintenance capabilities. It has operation and maintenance capabilities such as indicator analysis services, AI detection services, and large language model knowledge generation services, and can generate knowledge data for operation and maintenance scenarios in real time.

[0038] Establish an association between the knowledge agent node and the knowledge agent element, and establish an association between the knowledge agent element and the preset operation and maintenance knowledge generation device, that is, establish an application association between the knowledge agent node, the knowledge agent element and the operation and maintenance knowledge generation device, that is, establish an automatic call chain between the knowledge agent node and the knowledge agent element, and the operation and maintenance knowledge generation device through the association relationship. Through the association establishment, the knowledge agent node can identify and call the corresponding knowledge agent element, and then call the operation and maintenance knowledge generation device through the knowledge agent element, so as to realize the dynamic acquisition and update of operation and maintenance knowledge.

[0039] It's worth noting that the metadata of knowledge agent components is pre-stored in a pre-set knowledge agent component library. The management terminal can manage knowledge agent components (including adding, modifying, deleting, and uploading component scripts), and also provides query services for knowledge agent components. The main attributes of a knowledge agent component include the knowledge agent component identifier, knowledge agent component name, knowledge agent component file path, knowledge agent component description, knowledge agent component creation time, knowledge agent component update time, knowledge agent component creator, knowledge agent component updater, knowledge agent component reference count, knowledge agent component execution server IP (Internet Protocol Address), knowledge agent component execution user, and knowledge agent component status.

[0040] For example, the storage data of the golden indicator knowledge agent component information of the operation and maintenance object is shown in Table 1: Table 1

[0041] Among them, the number of references to the knowledge proxy component is the cumulative number of references to the knowledge proxy component by the knowledge proxy nodes. When deleting a knowledge proxy component, it is necessary to determine the number of times the knowledge proxy component has been referenced. When the number of references to the knowledge proxy component is greater than zero, the knowledge proxy component cannot be deleted, and the knowledge proxy node that references the knowledge proxy component in the graph must be deleted first.

[0042] When building the operation and maintenance knowledge graph, it is necessary to call the query service interface of the knowledge agent component library to query and verify. If the configured knowledge agent component is in the knowledge agent component library, the verification passes, and the knowledge agent component is called in subsequent knowledge graph queries to obtain operation and maintenance knowledge to create knowledge agent instance points and edges; otherwise, the verification fails and it cannot be added to the operation and maintenance knowledge graph, prompting a graph construction exception.

[0043] Step S20: query the operation and maintenance knowledge graph according to the received query request to obtain query return data; It should be noted that operation and maintenance scenarios include service health assessment scenarios and alarm diagnosis scenarios, etc. The query request can be a knowledge graph-based inspection query service request initiated by the operation and maintenance troubleshooting device in the service health assessment scenario, or it can be a knowledge graph-based fault troubleshooting query service initiated by the operation and maintenance troubleshooting device in the alarm diagnosis scenario when a fault alarm information occurs, or it can be a query request submitted by the user, etc. In this embodiment, there is no specific limitation on the source of the query request.

[0044] Receive a query request, and perform precise matching and retrieval on the operation and maintenance knowledge graph based on the query request to generate query return data. The query request usually carries information about the query node and the query hop range, that is, the knowledge graph range of the query can be determined according to the query request. The query return data includes information about each point and edge within the knowledge graph range of the query. The returned point data includes point identifier, point type (such as knowledge agent type KA and other entity types such as metrics) and point attribute information (such as name, age, etc. If it is a knowledge agent node, the name and knowledge agent component identifier kaunit attribute are returned); edge data mainly includes edge type identifier, edge attributes, edge source node identifier, edge destination node identifier, etc. The returned data is similar to the following structure: (<edge type name>-><source node identifier>-><destination node identifier>).

[0045] Step S30: when there is a knowledge agent node in the query return data, the real-time generated operation and maintenance knowledge data is obtained through the knowledge agent component; When parsing query return data, if the existence of a knowledge agent node is identified, the knowledge agent component is automatically triggered to obtain the latest generated operation and maintenance knowledge data in real time to ensure the timeliness and accuracy of the knowledge.

[0046] Specifically, for the knowledge agent node information returned in the query return data, that is, if the knowledge agent node exists, the knowledge agent component name, knowledge agent component file path, execution environment (server IP, user name) information, etc. are queried, and the entity type and identification (such as host and IP), time information, etc. of the source node are used as parameters to pull the operation and maintenance knowledge data.

[0047] For example, for the golden indicators of a host's impact on business, the golden indicator query capability and the indicator anomaly detection AI capability are invoked. Operation and maintenance knowledge data returns the attribute information of the indicator entity in JSON (JavaScript Object Notation, a data format), mainly including the indicator name, indicator value, anomaly detection conclusion, etc. If there are multiple golden indicators, the list data of the golden indicators is returned. The returned example is as follows: { [“name”:”cpu_pused”,”value”:”50%”,”ex_rst”:”normal”], ["name":"mem_pused","value":"40%","ex_rst":"normal"] } Among them, name indicates the name of the indicator, namely cpu_pused (Central Processing Unit_pused, central processing unit usage) and mem_pused (Memory_pused, memory usage); value indicates the specific value of the indicator, CPU usage is 50%, and memory usage is 40%; ex_rst indicates that the status of the indicator is normal.

[0048] Step S40: The operation and maintenance knowledge data is integrated with the query return data and stored in a graph structure to obtain a target knowledge graph.

[0049] The acquired operation and maintenance knowledge data is intelligently integrated with the original query return data, and the integrated data is stored in a graph structure to form a target knowledge graph.

[0050] For example, in a feasible implementation, the process of forming the target knowledge graph is as follows: Figure 2 As shown, the details are as follows: First, create an empty knowledge graph object to save the object data of the knowledge graph; Then, traverse the knowledge graph query return data (including operation and maintenance knowledge data and original query return data), and perform the following operations for each entity and relationship: Create a point object using the entity's properties and add the point to the graph object; Create an edge object using the relationship's properties and add the edge to the graph object; After the addition is completed, a complete graph object is generated, loaded, rendered and displayed to the user.

[0051] An example of the target operation and maintenance knowledge graph displayed after rendering is as follows: Figure 3As shown in the figure, the host's IP address is 127.0.0.1, and its host name is "hostname". The host has multiple monitoring metrics, including "cpu_pused" (50%, normal) and "mem_pused" (40%, normal).

[0052] This embodiment provides a knowledge graph management method based on operation and maintenance scenarios, constructs an operation and maintenance knowledge graph including knowledge proxy nodes and source nodes, and designs knowledge proxy elements to associate knowledge proxy nodes. When a query request is received, the operation and maintenance knowledge graph is queried according to the query request to obtain query return data; when there is a knowledge proxy node in the query return data, the real-time generated operation and maintenance knowledge data is obtained through the knowledge proxy element. At this time, the knowledge proxy element only pulls knowledge related to the function of the knowledge proxy node associated with it, avoiding unnecessary knowledge pulling. At the same time, due to the use of a real-time knowledge pulling mechanism, when the data in the operation and maintenance scenario changes, the query return data can obtain the latest knowledge in time, so that the knowledge graph is updated in time and the scope of the pulled knowledge is controllable, thereby improving the flexibility of knowledge graph management.

[0053] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction and will not be repeated hereafter. On this basis, step S10 can include steps S101~S102: Step S101, constructing triple data based on the attribute data and relationship data of each preset entity; It should be noted that triple data is a data structure composed of three elements. In the construction of the operation and maintenance knowledge graph, triples are used to express the attribute relationships and association relationships of each preset entity. The form can be <source entity, relationship, target entity> or <entity, attribute, attribute value>; preset entity refers to the entity type with specific attributes and relationships that has been defined before the construction of the operation and maintenance knowledge graph.

[0054] It is worth mentioning that for knowledge proxy points and edges, the factual data generated by the operation and maintenance knowledge generation device to complete the knowledge is not saved. On the one hand, it improves the flexibility of operation and maintenance knowledge fusion and dynamically adjusts the operation and maintenance knowledge suitable for different operation and maintenance scenarios; on the other hand, it can compress the scale of the knowledge graph and improve the performance of graph query.

[0055] Triple data is constructed based on the attribute data and relationship data of each preset entity. These preset entities include source entities and knowledge agent entities, so as to clearly express the intrinsic attributes of each preset entity and the relationship between them in the form of triples, providing a basis for subsequent graph construction.

[0056] Step S102: Store the triplet data in a graph structure to obtain an operation and maintenance knowledge graph.

[0057] These triple data are stored in the form of a graph structure to form a complete operation and maintenance knowledge graph. In the graph, knowledge agent entities are represented as knowledge agent nodes, source entities are represented as source nodes, and the nodes also include information such as the attributes of each entity. The relationship between each preset entity is reflected through the edges in the graph.

[0058] The operation and maintenance knowledge graph is stored in a preset graph database, which can be Neo4j (a graph database), NebulaGraph (a graph database), etc. Specifically, the operation and maintenance knowledge graph storage process is as follows: Figure 4 As shown in the figure, after the knowledge graph is constructed, it is adapted to the graph database through the preset graph data operation adaptation interface (such as data operation driver, client API (Application Programming Interface), etc.), and the constructed knowledge graph is stored in the graph database storage layer through the graph database service layer. The stored data includes pattern layer data (i.e. graph style) and fact data (i.e. triple data).

[0059] Therefore, in this embodiment, when the knowledge graph is constructed, a knowledge proxy node is added to the knowledge graph. When the knowledge graph is saved, only the proxy entity's points and related edge information are saved. The execution of the knowledge proxy component script is not triggered (i.e., the factual data pulled by the knowledge proxy is not saved in the knowledge graph). When a user asks a question based on the knowledge graph, the knowledge proxy component script is triggered to execute, pulling the operation and maintenance knowledge generated by the operation and maintenance knowledge generation device, merging it to form a resultant knowledge graph, ensuring the freshness of the merged knowledge.

[0060] In a feasible embodiment, step S20 may include steps S201 and S202: Step S201: receiving a query request and determining a query node and a query hop range according to the query request; It should be noted that the query node is an entity node in the operation and maintenance knowledge graph that is directly related to the query request. It serves as the starting point or key point of the query operation and is used to locate the information of interest to the query request; the query hop range refers to the maximum number of hops allowed when traversing along the edges in the operation and maintenance knowledge graph, starting from the query node (i.e., the number of edges passed through). It is used to control the complexity of the query and the scale of the returned data, to avoid performance degradation caused by excessive traversal or returning too much irrelevant information.

[0061] Receive a query request and intelligently determine the query node and query hop range based on the content of the request.

[0062] Step S202: According to the query node and the query hop range, traverse the path from the query node to the query hop range in the operation and maintenance knowledge graph to obtain the query return data.

[0063] Based on the determined query node and query hop range, path traversal is performed in the operation and maintenance knowledge graph. During this process, starting from the query node, the edges in the operation and maintenance knowledge graph are gradually expanded to all reachable nodes within the specified hop range. Finally, the relevant information on these paths is collected and organized to form the query return data.

[0064] For example, the query process for the operation and maintenance knowledge graph is as follows: Figure 5 As shown, according to the operation and maintenance business needs, the subgraph information and alarm time of the n-hop range of the specified node (i.e., the query node) are queried, and the management terminal queries the specified operation and maintenance knowledge graph data according to the knowledge graph query request; for the knowledge agent node returned in the query result (it can be set whether to automatically execute the knowledge agent), the knowledge agent component information is determined according to the knowledge agent component identifier, and the knowledge agent component is further called to execute the knowledge pulling script to call the ability of the operation and maintenance knowledge generation device to generate operation and maintenance knowledge, and construct a knowledge graph based on the operation and maintenance knowledge, that is, generate a target operation and maintenance knowledge graph, and then return the target operation and maintenance knowledge graph object for rendering and display.

[0065] In a feasible embodiment, step S30 may include steps S301 to S303: Step S301, detecting knowledge agent nodes in query return data; It should be noted that the knowledge agent node detection is the prerequisite for triggering the knowledge pulling mechanism, which determines whether it is necessary to call the operation and maintenance knowledge generation device to obtain the latest operation and maintenance knowledge data.

[0066] Check whether there is a knowledge agent node in the query return data.

[0067] Step S302: When a knowledge agent node exists in the query return data, script parameters are generated according to the query request and the knowledge agent node; After confirming the existence of a knowledge proxy node in the query return data, the corresponding script parameters are generated according to the specific content of the query request and the characteristics of the knowledge proxy node, such as source node type, source node identifier, edge type, alarm time, query hop count, etc. These parameters will be used to guide the execution of the knowledge retrieval script to ensure that the operation and maintenance knowledge generation device can be accurately called and the required knowledge data can be obtained.

[0068] Step S303: executing the knowledge extraction script according to the script parameters through the knowledge agent component to call the operation and maintenance knowledge generation device to obtain the operation and maintenance knowledge data generated in real time.

[0069] It should be noted that the knowledge extraction script is a piece of program code embedded in the knowledge agent element, which is used to call the operation and maintenance knowledge generation device to obtain the real-time generated operation and maintenance knowledge data when executed.

[0070] The knowledge extraction script is executed according to the generated script parameters. By calling the operation and maintenance knowledge generation device, the latest operation and maintenance knowledge data is obtained in real time and prepared to be integrated into the knowledge graph, thereby realizing the dynamic update and knowledge fusion of the knowledge graph.

[0071] In a feasible embodiment, step S303 may include steps S3031 and S3032: Step S3031: Execute a knowledge extraction script through the knowledge proxy component to call an operation and maintenance knowledge generation device. The operation and maintenance knowledge generation device has an indicator analysis service interface, an AI detection service interface, and a large language model knowledge generation service interface. It should be noted that the indicator analysis service interface is an interface for receiving and processing indicator data. It can conduct in-depth analysis of operation and maintenance indicators, extract valuable information, and help discover potential problems and optimization points in the operation and maintenance process; the AI ​​detection service interface is an interface that uses artificial intelligence technology to provide detection services. For example, through the application of machine learning, deep learning and other algorithms, it detects and analyzes performance indicator data in the operation and maintenance knowledge graph, and outputs future operation and maintenance status prediction results, thereby realizing automatic identification and prediction of operation and maintenance trends, and providing more accurate knowledge support; the large language model knowledge generation service interface is an interface for generating knowledge using a large language model. It can generate natural and fluent knowledge descriptions based on input parameters, making the generated knowledge easier to understand and apply.

[0072] Step S3032: After the operation and maintenance knowledge generation device is successfully called, the script parameters are input into one or more of the indicator analysis service interface, the AI ​​detection service interface, and the large language model knowledge generation service interface to obtain real-time generated operation and maintenance knowledge data.

[0073] After the operation and maintenance knowledge generation device is successfully called, the knowledge pulling script is executed according to the pre-generated script parameters. The execution of the script will trigger the call of the operation and maintenance knowledge generation device, and generate comprehensive and accurate operation and maintenance knowledge data through the indicator analysis service interface, AI detection service interface and large language model knowledge generation service interface integrated in the operation and maintenance knowledge generation device.

[0074] For example, the execution process of knowledge extraction is as follows: Figure 6As shown, first, when there is a knowledge agent node in the query return data, the knowledge agent is started, and the knowledge pulling script corresponding to the knowledge agent element is executed on the execution server of the knowledge agent element according to the knowledge agent element information to call the capabilities provided by the operation and maintenance knowledge generation device, including AI capabilities, data service capabilities and LLM (Large Language Model, large language model) capabilities, to extract and construct knowledge, generate relevant operation and maintenance knowledge data, and organize and return the knowledge data in JSON format.

[0075] In summary, in this embodiment, according to the entity type in the operation and maintenance knowledge graph, a knowledge proxy node is added to the operation and maintenance knowledge graph, and the knowledge generated by the operation and maintenance knowledge generation device is pulled through the knowledge proxy and merged into the operation and maintenance knowledge graph. First, the scope of pulled knowledge is controllable to avoid the knowledge scope being too large caused by knowledge push, which affects the availability of the knowledge graph; second, the scale of pulled knowledge is controllable, and knowledge proxy nodes are only set for nodes that need to be expanded, and the type of node is set as needed; finally, the scalability of knowledge graph knowledge is enhanced through knowledge pulling, and the scope of knowledge is adjusted through the optimization of the capabilities of the operation and maintenance knowledge generation device based on the operation and maintenance scenario, so that the knowledge graph is updated in a timely manner and the scope of pulled knowledge is controllable, thereby improving the flexibility of operation and maintenance knowledge graph management.

[0076] For example, in order to help understand the implementation process of the knowledge graph management method based on the operation and maintenance scenario obtained by combining this embodiment with the above embodiments, this embodiment provides a brief flow chart of the knowledge graph management method based on the operation and maintenance scenario, as shown in FIG. Figure 7As shown, specifically, the device modules involved in the knowledge graph management process based on the operation and maintenance scenario include a knowledge graph construction module, a knowledge graph storage module, a knowledge agent component library module, a knowledge graph query service module, a knowledge agent and extraction module, and a knowledge graph visualization module. Among them, the knowledge graph construction module adds a knowledge agent ontology in addition to the commonly used ontologies (host, service, component, indicator, etc.), and the corresponding entity attributes save the entity name and the component identifier of the knowledge agent component library; the knowledge graph storage module stores the triple data of the knowledge graph, including <source entity, relationship, target entity> or <entity, attribute, attribute value>. The knowledge agent class ontology is extended in the knowledge graph storage module to store knowledge agent class entity triples; the knowledge agent component library module stores the knowledge agent components corresponding to the knowledge graph, and the knowledge agent components are used to provide script information for accessing or generating knowledge, that is, the knowledge pulling script, which may specifically include script identifier, script path, script description, knowledge pulling script, etc.; the knowledge graph query service module provides knowledge query services, receives external query requests, queries knowledge graph information from the knowledge graph storage module, calls the knowledge agent and extraction module for the knowledge agent node to pull external operation and maintenance knowledge information, and then uses the pulled operation and maintenance knowledge information to complete the knowledge graph and return the visualized knowledge graph to the requester; the knowledge agent and extraction module executes the knowledge pulling script in the execution environment according to the source node identifier and knowledge agent component identifier provided by the knowledge graph query service module, and the knowledge is returned in JSON format. The specific data structure is generated by the knowledge agent component; the knowledge graph visualization module receives the knowledge graph data returned by the knowledge query service module and displays the knowledge graph information in a graphical manner. At this time, the knowledge agent node has been replaced with the knowledge of specific points and edges, and the target operation and maintenance knowledge graph is obtained.

[0077] Through the interaction between the above modules, the knowledge graph is able to pull operation and maintenance knowledge and automatically integrate and construct it, comprehensively displaying expert knowledge, AI capability knowledge, and LLM-generated knowledge, and assisting in the end-to-end troubleshooting of operation and maintenance faults.

[0078] The process of this embodiment can be used in two main scenarios. The first is in the alarm diagnosis scenario, that is, when an alarm is generated by an existing monitoring alarm device, the operation and maintenance troubleshooting device queries the system n-hop range knowledge graph subgraph information of the alarm convergence, and the associated knowledge agent integrates the knowledge generated by the operation and maintenance knowledge generation device to assist in the investigation of the alarm propagation path. The other is in the service health assessment scenario, which refers to the periodic inspection based on the system knowledge graph, integrating indicator data, AI anomaly detection knowledge, and LLM generalized knowledge to assist in the health assessment of equipment, services, components, and application systems.

[0079] For example, the troubleshooting scenario corresponding to the first case is as follows: When hadoopdatanodedn_1 (the name of a data node) generates a fault alarm at 2024-6-21 15:01:00, the operation and maintenance troubleshooting device initiates a knowledge graph-based fault troubleshooting query service to query the knowledge graph subgraph information within a three-hop range related to the dn_1 node.

[0080] Assume that the operation and maintenance knowledge graph constructed by the knowledge graph construction module (edge ​​attributes are omitted) is as follows Figure 8 As shown in the figure, it includes the golden indicator knowledge agent node, the belonging knowledge agent (ka) and the golden indicator (metrics) entity type. The knowledge graph query service module receives the knowledge graph subgraph query request and calls the knowledge graph storage module to query the knowledge graph information. The query logic is: start querying the subgraph from the point dn_1 in the knowledge graph; query the points and edges in the knowledge graph that are connected to the dn_1 point within 0-3 hops; the edge type is owned, carried, and heartbeat, including in-degree and out-degree; the datanode type point can only contain the dn_1 point.

[0081] For the returned knowledge proxy points, knowledge needs to be pulled to complete. The knowledge graph query service module calls the knowledge proxy and extraction module. The knowledge proxy and extraction module executes the knowledge pulling script according to the input parameters (source point information, edge information, knowledge proxy component information, alarm time, etc.), and returns the specific golden indicators and anomaly detection information of each knowledge proxy node in the subgraph. The knowledge graph query service module completes the points and edges of the subgraph based on the returned knowledge. The main logic of the call is as follows: the knowledge graph query service module prepares parameters and calls the knowledge proxy and extraction module; the knowledge proxy component calls the operation and maintenance knowledge generation device capability, and the alarm time is 2024-6-2115:01:00. The indicator query and anomaly analysis range is determined based on this time; the knowledge proxy and extraction module returns the pulled operation and maintenance knowledge, which is the golden indicator information in this example; the knowledge graph query service completes the knowledge graph subgraph based on the pulled operation and maintenance knowledge and returns it to the requester; The knowledge graph visualization module receives the subgraph data queried by the knowledge graph query service module, traverses the points and edges in the returned data, generates graph objects and displays them. The displayed results are as follows: Figure 9 shown.

[0082] For example, the service health assessment scenario corresponding to the second case is as follows: When the operation and maintenance personnel conduct a health assessment of the cluster service in the most recent period, they initiate a knowledge graph-based inspection query service through the operation and maintenance troubleshooting device to complete the health assessment knowledge agent information of the entity in the knowledge graph.

[0083] Assume that the knowledge graph constructed by the knowledge graph construction module (the attributes of the edges are omitted) is as follows Figure 8As shown in the figure, the included knowledge agent nodes belong to the knowledge agent and health check entity types. The knowledge graph query service module receives the knowledge graph query request, calls the knowledge graph storage module to query the knowledge graph information, and returns the knowledge graph vertex and edge information. The returned knowledge agent node attributes include name, knowledge agent component identifier, health score (null), health description (null), etc.

[0084] For the returned knowledge proxy points, operational knowledge needs to be pulled in for completion. The knowledge graph query service module calls the knowledge proxy and extraction module. The knowledge proxy and extraction module executes the knowledge proxy component script based on the input parameters (source point type and identifier, edges, knowledge proxy component information, etc.), returning the specific health assessment knowledge (including the entity's health assessment score and health assessment description) for each knowledge proxy node in the graph. The knowledge graph query service module completes the points and edges of the knowledge graph based on the returned operational knowledge.

[0085] The knowledge graph visualization module receives the graph data queried by the knowledge graph query service module, traverses the points and edges in the returned data, generates graph objects and displays them. The displayed results are as follows: Figure 10 shown.

[0086] It should be noted that the above examples are only used to understand this application and do not constitute a limitation on the knowledge graph management method based on operation and maintenance scenarios of this application. More simple transformations based on this technical concept are all within the scope of protection of this application.

[0087] This application also provides a knowledge graph management system based on operation and maintenance scenarios. Figure 11 The knowledge graph management system based on operation and maintenance scenarios includes: The knowledge graph construction module 10 is used to construct an operation and maintenance knowledge graph, wherein the operation and maintenance knowledge graph includes knowledge agent nodes and source nodes, and the knowledge agent nodes are associated with knowledge agent elements; The knowledge graph query service module 20 is used to query the operation and maintenance knowledge graph according to the received query request and obtain query return data; The knowledge agent and extraction module 30 is used to obtain the real-time generated operation and maintenance knowledge data through the knowledge agent component when there is a knowledge agent node in the query return data; The knowledge graph visualization module 40 is used to fuse the operation and maintenance knowledge data with the query return data and store them in a graph structure to obtain a target knowledge graph.

[0088] Optionally, the knowledge graph construction module 10 includes a knowledge graph storage module (not shown), which is used to: Construct triple data based on the attribute data and relationship data of each preset entity; The triple data is stored in a graph structure to obtain the operation and maintenance knowledge graph.

[0089] Optionally, the knowledge graph construction module 10 includes a knowledge agent component library module (not shown), which is used to: Establish an association between the knowledge agent node and the knowledge agent element, and establish an association between the knowledge agent element and the preset operation and maintenance knowledge generation device, wherein the knowledge agent element is used to provide a knowledge pulling script, and the operation and maintenance knowledge generation device is used to provide an operation and maintenance knowledge pulling service based on the knowledge pulling script.

[0090] Optionally, the knowledge graph query service module 20 is further configured to: Receive a query request and determine a query node and a query hop range according to the query request; According to the query node and query hop range, the path from the query node to the query hop range is traversed from the operation and maintenance knowledge graph to obtain the query return data.

[0091] Optionally, the knowledge agent and extraction module 30 is further configured to: Detecting knowledge agent nodes in query return data; When there is a knowledge agent node in the query return data, script parameters are generated according to the query request and the knowledge agent node; The knowledge pulling script is executed according to the script parameters by the knowledge agent component to call the operation and maintenance knowledge generating device to obtain the operation and maintenance knowledge data generated in real time.

[0092] Optionally, the knowledge agent and extraction module 30 is further configured to: Execute the knowledge extraction script through the knowledge agent component to call the operation and maintenance knowledge generation device, which has an indicator analysis service interface, an AI detection service interface, and a large language model knowledge generation service interface; After the operation and maintenance knowledge generation device is successfully called, the script parameters are input into one or more of the indicator analysis service interface, AI detection service interface and large language model knowledge generation service interface to obtain real-time generated operation and maintenance knowledge data.

[0093] The knowledge graph management system based on the operation and maintenance scenario provided in the embodiment of the present application adopts the knowledge graph management method based on the operation and maintenance scenario in the above embodiment, which can improve the flexibility of knowledge graph management in the application scenario where the knowledge graph is integrated with artificial intelligence technology. Compared with the prior art, the beneficial effects of the knowledge graph management system based on the operation and maintenance scenario provided in the embodiment of the present application are the same as the beneficial effects of the knowledge graph management method based on the operation and maintenance scenario provided in the above embodiment, and the other technical features in the knowledge graph management system based on the operation and maintenance scenario are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0094] An embodiment of the present application provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the knowledge graph management method based on the operation and maintenance scenario in the above-mentioned embodiment one.

[0095] Reference below Figure 12 , which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present application. The electronic device in the embodiments of the present application may include but is not limited to complete devices such as multimedia interactive all-in-one devices, touch all-in-one devices, etc. Figure 12 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0096] like Figure 12 As shown, the electronic device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory 1002 or programs loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the electronic device. The processing device 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems may be connected to the input / output interface 1006: an input device 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; a storage device 1003 including, for example, a magnetic tape or hard disk; and a communication device 1009. The communication device 1009 may allow the electronic device to communicate with other devices wirelessly or wired to exchange data. Although the figures show electronic devices with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0097] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are performed.

[0098] The electronic device provided in the embodiment of the present application adopts the knowledge graph management method based on operation and maintenance scenarios in the above embodiment, which can efficiently extract and display knowledge from massive multi-source data. Compared with the prior art, the beneficial effects of the electronic device provided in the embodiment of the present application are the same as the beneficial effects of the knowledge graph management method based on operation and maintenance scenarios provided in the above embodiment, and the other technical features of the electronic device are the same as the features disclosed in the knowledge graph management method based on operation and maintenance scenarios in the previous embodiment, which will not be repeated here.

[0099] It should be understood that the various parts disclosed in the embodiments of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any appropriate manner in any one or more embodiments or examples.

[0100] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0101] An embodiment of the present application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, and the computer-readable program instructions are used to execute the knowledge graph management method based on the operation and maintenance scenario in the above embodiment.

[0102] The computer-readable storage medium provided in the embodiments of the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium can be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0103] The computer-readable storage medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0104] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by an electronic device, the electronic device: constructs an operation and maintenance knowledge graph, wherein the operation and maintenance knowledge graph contains knowledge agent nodes and source nodes, and the knowledge agent nodes are associated with knowledge agent elements; queries the operation and maintenance knowledge graph according to the received query request to obtain query return data; when there is a knowledge agent node in the query return data, obtains the real-time generated operation and maintenance knowledge data through the knowledge agent element; merges the operation and maintenance knowledge data with the query return data and stores them in a graph structure to obtain the target knowledge graph.

[0105] The computer program code for performing the operations of the embodiments of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, through the Internet using an Internet service provider).

[0106] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0107] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0108] The computer-readable storage medium provided in the embodiments of this application is a computer-readable storage medium. The computer-readable storage medium stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned knowledge graph management method for operation and maintenance scenarios. This computer-readable storage medium is capable of efficiently extracting and displaying knowledge from massive amounts of multi-source data. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in the embodiments of this application are the same as those of the knowledge graph management method for operation and maintenance scenarios provided in the aforementioned embodiments, and are not further elaborated here.

[0109] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned knowledge graph management method based on operation and maintenance scenarios.

[0110] The computer program product provided in the embodiments of this application is capable of mining effective information from data generated by information technology systems. Compared with the prior art, the beneficial effects of the computer program product provided in the embodiments of this application are the same as the beneficial effects of the knowledge graph management method based on operation and maintenance scenarios provided in the above embodiments, and will not be repeated here.

[0111] The above are only some embodiments of the present application and are not intended to limit the patent scope of the present application. All equivalent structural transformations made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A knowledge graph management method based on operation and maintenance scenarios, characterized in that: The knowledge graph management method based on operation and maintenance scenarios includes: Constructing an operation and maintenance knowledge graph, wherein the operation and maintenance knowledge graph includes knowledge agent nodes and source nodes, and the knowledge agent nodes are associated with knowledge agent elements; Querying the operation and maintenance knowledge graph according to the received query request to obtain query return data; When the knowledge agent node exists in the query return data, the real-time generated operation and maintenance knowledge data is acquired through the knowledge agent element; The operation and maintenance knowledge data is integrated with the query return data and stored in a graph structure to obtain a target knowledge graph.

2. The knowledge graph management method based on operation and maintenance scenarios according to claim 1 is characterized in that: The steps of constructing the operation and maintenance knowledge graph include: Construct triple data based on the attribute data and relationship data of each preset entity; The triplet data is stored in a graph structure to obtain an operation and maintenance knowledge graph.

3. The knowledge graph management method based on operation and maintenance scenarios according to claim 1 is characterized in that: Before the step of constructing the operation and maintenance knowledge graph, the following steps are also included: Establish an association between the knowledge agent node and the knowledge agent element, and establish an association between the knowledge agent element and a preset operation and maintenance knowledge generation device, wherein the knowledge agent element is used to provide a knowledge pulling script, and the operation and maintenance knowledge generation device is used to provide an operation and maintenance knowledge pulling service based on the knowledge pulling script.

4. The knowledge graph management method based on operation and maintenance scenarios according to claim 1 is characterized in that: The step of querying the operation and maintenance knowledge graph according to the received query request to obtain query return data includes: receiving a query request, and determining a query node and a query hop range according to the query request; According to the query node and the query hop range, a path from the query node to the query hop range is traversed from the operation and maintenance knowledge graph to obtain query return data.

5. The knowledge graph management method based on operation and maintenance scenarios according to claim 1 is characterized in that: When the knowledge agent node exists in the query return data, the step of obtaining the real-time generated operation and maintenance knowledge data through the knowledge agent element includes: Detecting the knowledge agent node in the query return data; When the knowledge agent node exists in the query return data, generating script parameters according to the query request and the knowledge agent node; The knowledge agent element executes the knowledge pulling script according to the script parameters to call the operation and maintenance knowledge generating device to obtain the operation and maintenance knowledge data generated in real time.

6. The knowledge graph management method based on operation and maintenance scenarios according to claim 5 is characterized in that: The step of executing the knowledge pulling script according to the script parameters by the knowledge proxy component to call the operation and maintenance knowledge generating device to obtain the operation and maintenance knowledge data generated in real time includes: Executing a knowledge extraction script through the knowledge proxy element to call an operation and maintenance knowledge generation device, wherein the operation and maintenance knowledge generation device has an indicator analysis service interface, an AI detection service interface, and a large language model knowledge generation service interface; After the operation and maintenance knowledge generation device is successfully called, the script parameters are input into one or more of the indicator analysis service interface, the AI ​​detection service interface and the large language model knowledge generation service interface to obtain real-time generated operation and maintenance knowledge data.

7. A knowledge graph management system based on operation and maintenance scenarios, characterized in that: The knowledge graph management system based on operation and maintenance scenarios includes: A knowledge graph construction module is used to construct an operation and maintenance knowledge graph, wherein the operation and maintenance knowledge graph includes knowledge agent nodes and source nodes, and the knowledge agent nodes are associated with knowledge agent elements; A knowledge graph query service module is used to query the operation and maintenance knowledge graph according to the received query request and obtain query return data; A knowledge agent and extraction module, configured to obtain real-time generated operation and maintenance knowledge data through the knowledge agent element when the knowledge agent node exists in the query return data; The knowledge graph visualization module is used to fuse the operation and maintenance knowledge data with the query return data and store them in a graph structure to obtain a target knowledge graph.

8. An electronic device, characterized in that: The electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the knowledge graph management method based on operation and maintenance scenarios as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the knowledge graph management method based on the operation and maintenance scenario as described in any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product includes a computer program, which, when executed by a processor, implements the steps of the knowledge graph management method based on operation and maintenance scenarios as described in any one of claims 1 to 6.

Images