Operation and maintenance business knowledge graph construction method and device, equipment and storage medium

Abstract

The invention relates to an operation and maintenance service knowledge graph construction method and device, equipment and a storage medium. The method comprises the steps of obtaining operation and maintenance service data provided by at least one data source; according to a service entity extraction strategy corresponding to the data type to which the operation and maintenance service data belongs, extracting at least one service entity from the operation and maintenance service data and an entity relationship between the service entities; the data type comprises a structured type and an unstructured type; and according to the at least one service entity and the entity relationship between the service entities, constructing an operation and maintenance service knowledge graph corresponding to the operation and maintenance service data. By adopting the method provided by the embodiment of the invention, the service entity related to the operation and maintenance service can be automatically extracted and mapped into the knowledge graph. Compared with a traditional manual operation and maintenance mode, the system can process mass data more intelligently, and the response speed and the operation and maintenance efficiency of the security event are remarkably improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, equipment and storage medium for constructing an operation and maintenance business knowledge graph. Background Art

[0002] With the advent of the digital age, enterprises are facing unprecedented challenges in resource management and network security operations. The continuous expansion of resource scale and the increasing complexity of the technical environment make it difficult for traditional resource management and security operations to meet current needs. In multiple links such as resource scanning, vulnerability management, host protection and security monitoring, enterprises will generate massive amounts of data. However, these data are often scattered and isolated, lacking systematic integration and association, resulting in information fragmentation and serious data islands, which brings great difficulties to resource management efficiency and problem identification in the process of security operations.

[0003] Therefore, the existing resource management methods mainly have the problem of lack of information relevance and inability to fully understand the complex dependencies between physical resources when dealing with these problems. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, equipment and storage medium for constructing an operation and maintenance business knowledge graph that can improve the comprehensiveness of the dependency relationship between entities in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for constructing an operation and maintenance business knowledge graph, including:

[0006] Obtaining operation and maintenance business data provided by at least one data source;

[0007] Extracting at least one business entity and entity relationships between business entities from the operation and maintenance business data according to a business entity extraction strategy corresponding to the data type to which the operation and maintenance business data belongs; the data type includes a structured type and an unstructured type;

[0008] Based on at least one business entity and the entity relationship between the business entities, an operation and maintenance business knowledge graph corresponding to the operation and maintenance business data is constructed.

[0009] In one embodiment, according to the business entity extraction strategy corresponding to the data type of the operation and maintenance business data, at least one business entity and the entity relationship between the business entities are extracted from the operation and maintenance business data, including:

[0010] In the case where the operation and maintenance business data is of a structured type, directly extracting at least one business entity and entity relationships between the business entities from the operation and maintenance business data;

[0011] In the case that the operation and maintenance business data is of an unstructured type, business entity annotation is performed on the operation and maintenance business data to obtain at least one business entity and entity relationships between the business entities.

[0012] In one embodiment, at least one business entity and entity relationships between business entities are directly extracted from the operation and maintenance business data, including:

[0013] Based on the business entity mapping rule, extract at least one business entity from the operation and maintenance business data; and,

[0014] Based on the entity relationship mapping rules, at least one business entity is extracted from the operation and maintenance business data.

[0015] In one embodiment, the method further comprises:

[0016] For the same business entities extracted from different operation and maintenance business data, the entity description information corresponding to the same business entities is merged.

[0017] In one embodiment, business entity annotation is performed on the operation and maintenance business data to obtain at least one business entity and entity relationships between the business entities, including:

[0018] Preprocessing the operation and maintenance business data to obtain preprocessed operation and maintenance business data; the preprocessing includes at least one of deduplication processing, standardization processing and word segmentation processing;

[0019] Perform feature encoding on the preprocessed operation and maintenance business data to obtain an operation and maintenance business vector;

[0020] The operation and maintenance business vector is labeled with business entities to obtain at least one business entity and entity relationships between the business entities.

[0021] In one embodiment, business entity labeling is performed on the operation and maintenance business vector to obtain at least one business entity and entity relationships between the business entities, including:

[0022] Based on the sequence of the operation and maintenance business vector, the operation and maintenance business vector is labeled with business entities to obtain at least one business entity and entity relationships between the business entities.

[0023] In a second aspect, the present application also provides a device for constructing an operation and maintenance business knowledge graph, including:

[0024] A data acquisition module, used to acquire operation and maintenance business data provided by at least one data source;

[0025] An entity extraction module is used to extract at least one business entity and entity relationships between business entities from the operation and maintenance business data according to a business entity extraction strategy corresponding to the data type to which the operation and maintenance business data belongs; the data type includes a structured type and an unstructured type;

[0026] The graph construction module is used to construct an operation and maintenance business knowledge graph corresponding to the operation and maintenance business data based on at least one business entity and the entity relationship between the business entities.

[0027] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0028] Obtaining operation and maintenance business data provided by at least one data source;

[0029] Extracting at least one business entity and entity relationships between business entities from the operation and maintenance business data according to a business entity extraction strategy corresponding to the data type to which the operation and maintenance business data belongs; the data type includes a structured type and an unstructured type;

[0030] Based on at least one business entity and the entity relationship between the business entities, an operation and maintenance business knowledge graph corresponding to the operation and maintenance business data is constructed.

[0031] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0032] Obtaining operation and maintenance business data provided by at least one data source;

[0033] Extracting at least one business entity and entity relationships between business entities from the operation and maintenance business data according to a business entity extraction strategy corresponding to the data type to which the operation and maintenance business data belongs; the data type includes a structured type and an unstructured type;

[0034] Based on at least one business entity and the entity relationship between the business entities, an operation and maintenance business knowledge graph corresponding to the operation and maintenance business data is constructed.

[0035] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0036] Obtaining operation and maintenance business data provided by at least one data source;

[0037] Extracting at least one business entity and entity relationships between business entities from the operation and maintenance business data according to a business entity extraction strategy corresponding to the data type to which the operation and maintenance business data belongs; the data type includes a structured type and an unstructured type;

[0038] Based on at least one business entity and the entity relationship between the business entities, an operation and maintenance business knowledge graph corresponding to the operation and maintenance business data is constructed.

[0039] The above-mentioned operation and maintenance business knowledge graph construction method, device, equipment and storage medium obtain operation and maintenance business data provided by at least one data source; extract at least one business entity and the entity relationship between each business entity from the operation and maintenance business data according to the business entity extraction strategy corresponding to the data type to which the operation and maintenance business data belongs; the data type includes structured type and unstructured type; according to at least one business entity and the entity relationship between each business entity, construct an operation and maintenance business knowledge graph corresponding to the operation and maintenance business data. This embodiment automatically extracts business entities related to the operation and maintenance business and maps them to the knowledge graph. Compared with the traditional operation and maintenance method that relies on manual labor, the system can process massive data more intelligently and significantly improve the response speed and operation and maintenance efficiency of security incidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 An application environment diagram of a method for constructing an operation and maintenance business knowledge graph provided in this embodiment;

[0042] Figure 2 A schematic diagram of a process for constructing an operation and maintenance business knowledge graph provided in this embodiment;

[0043] Figure 3 A schematic diagram of entity relationship provided for this embodiment;

[0044] Figure 4 A structural block diagram of a device for constructing an operation and maintenance business knowledge graph provided in this embodiment;

[0045] Figure 5 An internal structure diagram of a computer device provided in this embodiment;

[0046] Figure 6 This is a diagram of the internal structure of a computer device provided in this embodiment. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0048] The operation and maintenance business knowledge graph construction method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The computer device obtains the operation and maintenance business data provided by at least one data source; according to the business entity extraction strategy corresponding to the data type of the operation and maintenance business data, at least one business entity and the entity relationship between the business entities are extracted from the operation and maintenance business data; the data type includes structured type and unstructured type; according to at least one business entity and the entity relationship between the business entities, the operation and maintenance business knowledge graph corresponding to the operation and maintenance business data is constructed. Among them, the computer device can be both a terminal and a server. The terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0049] In an exemplary embodiment, Figure 2 As shown in the figure, a method for constructing an operation and maintenance business knowledge graph is provided, and the method is applied to Figure 1 The computer device in the example is used to illustrate, including the following steps 201 to 203. Among them:

[0050] Step 201: Acquire operation and maintenance business data provided by at least one data source.

[0051] Among them, data sources include asset management systems, vulnerability management tools, log monitoring systems, incident response platforms, etc. Operation and maintenance business data can be log data and business operation data generated during the network security operation and maintenance process in the historical period, including but not limited to: asset scanning, vulnerability management, host protection, security monitoring, API interface management, etc.

[0052] Among them, asset scanning records the asset's IP, security partition, device name, operating system, open ports, and other structured data, as well as text unstructured data of port usage descriptions. Vulnerability management includes structured data fields such as the IP of the asset with vulnerabilities, port number, vulnerability name, and risk level, as well as text fields such as vulnerability lifespan and reinforcement suggestions. The host security protection system includes the IP of the system equipment, security services, and protected systems. API interface management includes the system name of the API interface, its major, interface type, interface address, and unstructured text data.

[0053] Specifically, the computer device obtains operation and maintenance business data from at least one data source.

[0054] Step 202: extract at least one business entity and entity relationships between business entities from the operation and maintenance business data according to a business entity extraction strategy corresponding to the data type to which the operation and maintenance business data belongs.

[0055] Among them, data types include structured types and unstructured types. Business entities may include asset entities, vulnerability entities, security service entities, network security issue entities, and business execution entities. Asset entities are used to describe asset information involved in security operation and maintenance. Its attribute information includes asset IP, security zone, asset type, asset name, and assigns a unique identifier to each asset. Vulnerability entities are used to describe vulnerabilities discovered during the security operation and maintenance process. They include vulnerability numbers, vulnerability announcement time, vulnerability discovery time, vulnerability hazard level, and the system / software where the vulnerability is located. Security service entities are used to describe security devices and security services currently deployed by the enterprise, such as firewall services, IPS services, etc. They include security system names, deployment time, service names, and security device locations. Network security issue entities describe problems encountered and solved in security operation and maintenance services, such as vulnerabilities, weak passwords, sensitive information leaks, etc. They include problem names, problem hazard scope, problem solving suggestions, problem solving records, etc. Business entities include the subject of business execution, the purpose of the business, the time of business execution, the business number, the status of business execution, etc. For example, Figure 3 The entity relationship diagram shown, for example, the asset (xx.xx.xx.xx) has a security issue (exists a vulnerability) involving a vulnerability (CVE-xxxxx), and the business (business order number) is used to solve the above problem.

[0056] In one embodiment, at least one business entity and the entity relationship between the business entities are extracted from the operation and maintenance business data according to a business entity extraction strategy corresponding to the data type of the operation and maintenance business data, including: when the operation and maintenance business data is of a structured type, directly extracting at least one business entity and the entity relationship between the business entities from the operation and maintenance business data; when the operation and maintenance business data is of an unstructured type, business entity annotation is performed on the operation and maintenance business data to obtain at least one business entity and the entity relationship between the business entities.

[0057] Step 203: construct an operation and maintenance business knowledge graph corresponding to the operation and maintenance business data based on at least one business entity and the entity relationship between the business entities.

[0058] Specifically, according to at least one business entity and the entity relationship between each business entity, an operation and maintenance business knowledge graph corresponding to the operation and maintenance business data is constructed, and at least one business entity and the entity relationship between each business entity are stored in the form of triples (such as server A, existence, vulnerability B), and a CSV file is used to import at least one business entity and the entity relationship between each business entity (for example, a node CSV file contains entities and their types, and a CSV file contains the relationship between entities), and a processed CSV file is obtained. The CSV file is imported into a Neo4j database to realize data storage, visualization of network security operation and maintenance business data, and association relationship query.

[0059] The above-mentioned operation and maintenance business knowledge graph construction method obtains operation and maintenance business data provided by at least one data source; extracts at least one business entity and the entity relationship between each business entity from the operation and maintenance business data according to the business entity extraction strategy corresponding to the data type to which the operation and maintenance business data belongs; the data type includes structured type and unstructured type; according to at least one business entity and the entity relationship between each business entity, constructs an operation and maintenance business knowledge graph corresponding to the operation and maintenance business data. This embodiment automatically extracts business entities related to the operation and maintenance business and maps them to the knowledge graph. Compared with the traditional operation and maintenance method that relies on manual labor, the system can process massive data more intelligently and significantly improve the response speed and operation and maintenance efficiency of security incidents.

[0060] In one embodiment, at least one business entity and the entity relationship between the business entities are directly extracted from the operation and maintenance business data, including: extracting at least one business entity from the operation and maintenance business data based on business entity mapping rules; and extracting at least one business entity from the operation and maintenance business data based on entity relationship mapping rules.

[0061] Specifically, according to the entities, attributes and relationships defined in the ontology architecture, the fields of different data sources are mapped to the relevant entities and attributes of the knowledge graph; using the defined rules, the corresponding field information is matched in the business data of different structures, and the mapped entity type and entity attributes are determined; according to the defined entity-relationship mapping rules, the fields in the data source are mapped to the relationships between entities.

[0062] In one embodiment, the method further includes: for the same business entities extracted from different operation and maintenance business data, integrating entity description information corresponding to the same business entities.

[0063] Specifically, the same entity may exist in multiple data sources, such as a server appearing in asset management and vulnerability management systems. Deduplication and data fusion are needed to avoid redundancy. During the fusion process, if different data sources of the same entity provide the same or similar attribute information, the attribute data is deduplicated based on rules and priorities.

[0064] In this embodiment, at least one business entity is extracted from the operation and maintenance business data based on the business entity mapping rules; and at least one business entity is extracted from the operation and maintenance business data based on the entity relationship mapping rules. By constructing a knowledge graph, this embodiment can quickly locate and retrieve information related to specific assets or events, such as the security status of assets, historical change records, etc. The knowledge graph is based on the association of entities and relationships, which significantly improves the speed and accuracy of data queries and provides strong support for security operation and maintenance decisions.

[0065] In one embodiment, business entity labeling is performed on operation and maintenance business data to obtain at least one business entity and entity relationships between business entities, including: preprocessing the operation and maintenance business data to obtain preprocessed operation and maintenance business data; feature encoding the preprocessed operation and maintenance business data to obtain an operation and maintenance business vector; and business entity labeling is performed on the operation and maintenance business vector to obtain at least one business entity and entity relationships between business entities.

[0066] Among them, preprocessing includes at least one of removing irrelevant information (such as HTML tags, special characters, useless stop words, etc.), deduplication processing, standardization processing (for example, unifying "firewall" and "firewall system" into "firewall", etc.) and word segmentation processing.

[0067] Specifically, the training strategy of RoBERTa is used, and a 12-layer Transformer encoder is selected, with a hidden layer size of 768, 12 multi-head attention heads, a middle layer size of 3072, and a maximum sequence length of 512. All operation and maintenance business data are processed, the operation and maintenance business data are segmented, and a corresponding dictionary is constructed. The dictionary contains special fields in operation and maintenance, such as IP, URL, registry key values, etc. All texts are mapped to numbers using the dictionary, randomly embedded into the vector space and input into the model for training. The pre-training task uses the mask prediction task, that is, some words are randomly masked in the input text, and the model predicts the masked words based on the context.

[0068] In one embodiment, business entity labeling is performed on the operation and maintenance business vector to obtain at least one business entity and entity relationships between the business entities, including: based on the sequence of the operation and maintenance business vector, business entity labeling is performed on the operation and maintenance business vector to obtain at least one business entity; and association relationships between entities are established according to entity types to determine entity relationships between the business entities.

[0069] Specifically, BiLSTM-CRF is added to the output of the pre-trained model, and the text is annotated using the BIO annotation format (B-Entity, I-Entity, O) based on the entities, relationships, and attribute types defined in the network security operation and maintenance business knowledge graph ontology; in order to perform fine-tuning training for named entity recognition, the CRF loss function is used, which calculates the difference between the predicted label sequence and the true label sequence, and takes into account the dependency between labels.

[0070] Specifically, use NER annotation tools (such as LabelStudio, Prodigy, etc.) to annotate the business text with named entities. During the annotation process, various entities in the text are classified and annotated according to the entity types, attributes and relationships defined in the above-mentioned network security operation and maintenance business knowledge graph framework. This embodiment uses the BIO tag format (for example, given text data: the server was attacked by SQL injection, it is labeled: B-asset, OB-vulnerability, I-vulnerability, O); then, load the previously pre-trained RoBERTa model, and add BiLSTM-CRF to it to realize the knowledge extraction task; finally, use the annotated data to train the model, so as to extract the named entities in the power grid security operation and maintenance business, and provide support for the construction of the knowledge graph.

[0071] This embodiment can effectively integrate scattered data, establish relationships between entities such as assets, vulnerabilities, and security incidents, and break the limitations of traditional information isolation. With the help of the relationship network of the knowledge graph, enterprises can fully understand the interdependence of various entities, thereby more accurately identifying potential security risks and improving the grasp of multi-dimensional relationships in complex systems.

[0072] In one embodiment, this embodiment provides an optional method for constructing an operation and maintenance business knowledge graph, and takes the method applied to a server as an example for illustration. The method includes the following steps:

[0073] Step 301: Acquire operation and maintenance business data provided by at least one data source.

[0074] Step 302: if the operation and maintenance business data is of a structured type, extract at least one business entity from the operation and maintenance business data based on a business entity mapping rule; and extract at least one business entity from the operation and maintenance business data based on an entity relationship mapping rule.

[0075] Step 303, when the operation and maintenance business data is of an unstructured type, preprocess the operation and maintenance business data to obtain preprocessed operation and maintenance business data; feature encode the preprocessed operation and maintenance business data to obtain an operation and maintenance business vector; and perform business entity labeling on the operation and maintenance business vector to obtain at least one business entity and entity relationships between the business entities.

[0076] Step 304: construct an operation and maintenance business knowledge graph corresponding to the operation and maintenance business data based on at least one business entity and the entity relationship between the business entities.

[0077] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0078] Based on the same inventive concept, the embodiment of the present application also provides an operation and maintenance business knowledge graph construction device for implementing the above-mentioned operation and maintenance business knowledge graph construction method. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above-mentioned method, so the specific limitations in one or more operation and maintenance business knowledge graph construction device embodiments provided below can refer to the limitations of the operation and maintenance business knowledge graph construction method above, and will not be repeated here.

[0079] In an exemplary embodiment, Figure 4As shown, a device for constructing an operation and maintenance business knowledge graph is provided, comprising: a data acquisition module 10, an entity extraction module 11 and a graph construction module 12, wherein:

[0080] A data acquisition module 10 is used to acquire operation and maintenance business data provided by at least one data source;

[0081] The entity extraction module 11 is used to extract at least one business entity and the entity relationship between the business entities from the operation and maintenance business data according to the business entity extraction strategy corresponding to the data type to which the operation and maintenance business data belongs; the data type includes structured type and unstructured type;

[0082] The graph construction module 12 is used to construct an operation and maintenance business knowledge graph corresponding to the operation and maintenance business data based on at least one business entity and the entity relationship between the business entities.

[0083] In one embodiment, the entity extraction module 11 further includes:

[0084] A structure type processing unit, used to directly extract at least one business entity and entity relationships between business entities from the operation and maintenance business data when the operation and maintenance business data belongs to a structured type;

[0085] The unstructured type processing unit is used to perform business entity labeling on the operation and maintenance business data when the operation and maintenance business data is of an unstructured type, so as to obtain at least one business entity and entity relationships between the business entities.

[0086] In one embodiment, the structure type processing unit is used to extract at least one business entity from the operation and maintenance business data based on the business entity mapping rule; and to extract at least one business entity from the operation and maintenance business data based on the entity relationship mapping rule.

[0087] In one embodiment, the structure type processing unit is used to merge entity description information corresponding to the same business entity extracted from different operation and maintenance business data.

[0088] In one embodiment, the non-structural type processing unit is used to preprocess the operation and maintenance business data to obtain preprocessed operation and maintenance business data; the preprocessing includes at least one of deduplication processing, standardization processing and word segmentation processing; feature encoding is performed on the preprocessed operation and maintenance business data to obtain an operation and maintenance business vector; business entity labeling is performed on the operation and maintenance business vector to obtain at least one business entity and the entity relationship between the business entities.

[0089] In one embodiment, the non-structural type processing unit is used to perform business entity labeling on the operation and maintenance business vector based on the sequence of the operation and maintenance business vector to obtain at least one business entity and entity relationships between the business entities.

[0090] Each module in the above-mentioned operation and maintenance business knowledge graph construction device can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0091] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for constructing an operation and maintenance business knowledge graph is implemented.

[0092] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 6As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for constructing an operation and maintenance business knowledge graph is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0093] Those skilled in the art will understand that Figure 5 and Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0094] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0095] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0096] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0097] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0098] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0099] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0100] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for constructing an operation and maintenance business knowledge graph, characterized in that: The method comprises: Obtaining operation and maintenance business data provided by at least one data source; Extracting at least one business entity and entity relationships between business entities from the operation and maintenance business data according to a business entity extraction strategy corresponding to a data type to which the operation and maintenance business data belongs; the data type includes a structured type and an unstructured type; Based on at least one business entity and the entity relationship between the business entities, an operation and maintenance business knowledge graph corresponding to the operation and maintenance business data is constructed.

2. The method according to claim 1, characterized in that: The extracting at least one business entity and the entity relationship between the business entities from the operation and maintenance business data according to the business entity extraction strategy corresponding to the data type to which the operation and maintenance business data belongs includes: In the case where the operation and maintenance business data is of a structured type, directly extracting at least one business entity and entity relationships between the business entities from the operation and maintenance business data; In the case that the operation and maintenance business data is of an unstructured type, business entity annotation is performed on the operation and maintenance business data to obtain at least one business entity and entity relationships between the business entities.

3. The method according to claim 2, characterized in that The step of directly extracting at least one business entity and entity relationships between the business entities from the operation and maintenance business data includes: extracting at least one business entity from the operation and maintenance business data based on a business entity mapping rule; and, Based on entity relationship mapping rules, at least one business entity is extracted from the operation and maintenance business data.

4. The method according to claim 3, characterized in that The method further comprises: For the same business entities extracted from different operation and maintenance business data, the entity description information corresponding to the same business entities is merged.

5. The method according to claim 2, characterized in that: The operation and maintenance business data is annotated with business entities to obtain at least one business entity and entity relationships between the business entities, including: Preprocessing the operation and maintenance business data to obtain preprocessed operation and maintenance business data; the preprocessing includes at least one of deduplication processing, standardization processing and word segmentation processing; Performing feature encoding on the preprocessed operation and maintenance service data to obtain an operation and maintenance service vector; Business entity labeling is performed on the operation and maintenance business vector to obtain at least one business entity and entity relationships between the business entities.

6. The method according to claim 5, characterized in that The step of labeling the operation and maintenance business vector with business entities to obtain at least one business entity and entity relationships between the business entities includes: Based on the sequence of the operation and maintenance business vectors, the operation and maintenance business vectors are labeled with business entities to obtain at least one business entity and entity relationships between the business entities.

7. A device for constructing an operation and maintenance business knowledge graph, characterized in that: The device comprises: A data acquisition module, used to acquire operation and maintenance business data provided by at least one data source; An entity extraction module, used to extract at least one business entity and entity relationships between business entities from the operation and maintenance business data according to a business entity extraction strategy corresponding to a data type to which the operation and maintenance business data belongs; the data type includes a structured type and an unstructured type; The graph construction module is used to construct an operation and maintenance business knowledge graph corresponding to the operation and maintenance business data based on at least one business entity and the entity relationship between the business entities.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images