Methods, devices, equipment, media, and software products for processing network sensing data

Abstract

This application relates to the field of data processing technology, providing a method, apparatus, device, medium, and program product for processing computing network sensing data. The method includes: analyzing the business scenarios of the computing network to obtain computing network sensing data requirements; constructing an attribute graph model for computing network sensing based on the computing network sensing data requirements; acquiring the sensing data of the computing network, and generating attribute graph instances of the sensing data based on the attribute graph model. By analyzing the business scenarios of the computing network and modeling based on attribute graphs, global sensing of the computing network is achieved from the business level, as well as the fusion processing of sensing data from the computing power domain and network domain, constructing an integrated computing network sensing system. Simultaneously, attribute graphs can more intuitively express the relationship between computing network services and computing network resources, enabling more efficient processing of associated data in the computing network and improving the global sensing and presentation capabilities of computing network sensing data.

Description

Technical Field

[0001] This application relates to the field of data processing technology, specifically to a method, apparatus, equipment, medium, and program product for processing network sensing data. Background Technology

[0002] Computing networks have gradually become the main platform for supporting business applications, providing users with independently operating and isolated computing resources. Various industries are increasingly reliant on computing networks. Currently, the computing infrastructure and network architecture of computing networks have reached a considerable scale, capable of providing different computing and network capabilities for different industries and scenarios. Service providers need to flexibly adjust network quality according to the different business scenarios of their clients, providing users with high-quality and differentiated integrated computing and networking services.

[0003] Network perception is a prerequisite for integrated network and computing services. It requires breaking down the information boundaries between the network, computing, and application domains to provide a foundation for further collaboration, scheduling, and integration. Network perception includes computing power perception, network perception, application perception, and multi-dimensional resource collaborative perception. Currently, the computing power domain and the network domain have their own unique data perception systems, which have developed independently for a long time. For example, existing network management / cloud management systems typically use ER (Entity-Relationship Model) models to model and process network and computing power domain perception data separately, and use relational databases to store the modeled perception data. The computing power network lacks a unified, global perception and presentation capability for network and computing power perception data, and there is an urgent need to build network and computing power perception capabilities, gradually integrate and unify the existing computing and network perception systems, and formulate an integrated network and computing power perception system. Summary of the Invention

[0004] This application provides a method, apparatus, device, medium, and program product for processing network sensing data, which addresses the technical problem in existing network sensing systems where the computing power domain and network domain are independent of each other, lacking the ability to perceive and present network sensing data globally.

[0005] In a first aspect, embodiments of this application provide a method for processing network sensing data, including:

[0006] Analyze the business scenarios of the computing network to obtain the computing network perception data requirements;

[0007] Construct an attribute graph model for network sensing based on the aforementioned data requirements;

[0008] The perception data of the computing power network is obtained, and an attribute graph instance of the perception data is generated based on the attribute graph model.

[0009] In one embodiment, constructing the attribute graph model for network sensing based on the network sensing data requirements includes:

[0010] The computing network resources required for the business scenario are determined based on the computing network perception data requirements, and the relationship data corresponding to the computing network resources is obtained; the relationship data includes a first relationship between the computing network resources and a second relationship between the computing network resources and the computing network services corresponding to the business scenario;

[0011] Define the computing network services and computing network resources corresponding to the business scenario as nodes, and extract the attribute information of the computing network resources;

[0012] Based on the nodes, the relational data, and the attribute information, a network-aware attribute graph model is constructed.

[0013] In one embodiment, constructing a network-aware attribute graph model based on the nodes, the relationship data, and the attribute information includes:

[0014] Generate a node set based on the aforementioned nodes;

[0015] Based on the relation data, determine the ordered node pairs in the nodes and the target relation of the ordered node pairs, and generate a relation set based on the ordered node pairs and the target relation;

[0016] The node attributes of the node and the relation attributes of the target relationship of the ordered node pairs are determined based on the attribute information, and an attribute set is generated based on the node attributes and the relation attributes.

[0017] Triples are created using the node set, the relation set, and the attribute set to obtain a network-aware attribute graph model.

[0018] In one embodiment, the sensing data includes computing network resource data and computing network relationship data; generating an attribute graph instance of the sensing data based on the attribute graph model includes:

[0019] Based on the network resource data in the perceived data, node instances of the attribute graph model are generated;

[0020] Based on the network relationship data in the perception data, generate the relationship instance corresponding to the node instance;

[0021] Based on the node instance and the relationship instance, an attribute graph instance of the perceived data is generated.

[0022] In one embodiment, the computing network resource data includes network resource data and computing power resource data; the node instances include network node instances and computing power node instances; the step of generating node instances of the attribute graph model based on the computing network resource data in the sensing data includes:

[0023] Based on the network resource data, network node instances of the attribute graph model are generated;

[0024] Based on the computing power resource data, a computing power node instance of the attribute graph model is generated.

[0025] In one embodiment, after generating an attribute graph instance of the perceived data based on the attribute graph model, the method further includes:

[0026] The attribute graph instance is stored in the graph database corresponding to the attribute graph model.

[0027] Secondly, embodiments of this application provide a computer network sensing data processing device, comprising:

[0028] The business analysis module is used to analyze the business scenarios of the computing network and obtain the computing network perception data requirements;

[0029] The model building module is used to build an attribute graph model for computing network sensing based on the computing network sensing data requirements;

[0030] The data processing module is used to acquire the perception data of the computing power network and generate an attribute graph instance of the perception data based on the attribute graph model.

[0031] Thirdly, embodiments of this application provide an electronic device, including a processor and a memory storing a computer program, wherein the processor executes the program to implement the steps of the computer network sensing data processing method described in the first aspect.

[0032] Fourthly, embodiments of this application provide a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the computer network sensing data processing method described in the first aspect.

[0033] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the steps of the computer network sensing data processing method described in the first aspect.

[0034] The computing network sensing data processing method, apparatus, device, medium, and program products provided in this application analyze the business scenarios of the computing power network to obtain the computing network sensing data requirements, construct an attribute graph model for computing network sensing, acquire the sensing data of the computing power network, and generate attribute graph instances of the sensing data based on the constructed attribute graph model. By analyzing the business scenarios of the computing power network and modeling based on the attribute graph, global sensing of the computing power network is achieved from the business level, as well as the fusion processing of sensing data from the computing power domain and the network domain, constructing an integrated computing network sensing system. Simultaneously, the attribute graph can more intuitively express the relationship between computing network services and computing network resources, more efficiently process related data in the computing network, and improve the global sensing and presentation capabilities of computing network sensing data. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 This is a flowchart illustrating the data processing method for computer network sensing provided in an embodiment of this application;

[0037] Figure 2 This is a schematic diagram of the attribute graph model provided in the embodiments of this application;

[0038] Figure 3 This is a schematic diagram of an example of an attribute graph provided in an embodiment of this application;

[0039] Figure 4 This is a schematic diagram of the structure of the computer network sensing data processing device provided in the embodiments of this application;

[0040] Figure 5 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0042] It should be noted that in the description of this invention, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. The terms "upper," "lower," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Unless otherwise expressly specified and limited, the terms "installed," "connected," and "linked" should be interpreted broadly, for example, as a fixed connection, a detachable connection, or an integral connection; a mechanical connection or an electrical connection; a direct connection or an indirect connection through an intermediate medium; or a connection within two elements. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0043] The terms "first," "second," etc., used in this invention are used to distinguish similar objects, not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class, without limiting the number of objects; for example, a first object can be one or more. Furthermore, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0044] The computing network encompasses a wide variety of services, a vast number of resource categories and quantities, and complex relationships between resources. When the perception data of the computing power domain and the network domain are independent, it is difficult to fully explore the correlations between them. This hinders the global collaborative perception and scheduling of multi-dimensional computing network resources, impeding the realization of integrated computing network services. In this context, using a graph model to model and process the computing network perception data can more intuitively represent the relationships between computing network services and resources, enabling efficient processing of correlated data, especially for deep relationship queries and analysis. Compared to relational databases, this approach offers a significant performance improvement in terms of scale, facilitating the storage, querying, and mining of computing network perception data.

[0045] Based on this, this application provides a method for processing network perception data. Based on attribute graph modeling, the method defines nodes, relationships and attributes in the attribute graph model according to the network business and perception data requirements, constructs an attribute graph model for perception data oriented towards network business scenarios, and then generates corresponding attribute graph instances based on the attribute graph model after obtaining network perception data, thereby realizing the fusion processing of perception data in the computing power domain and network domain, and constructing an integrated network perception system.

[0046] Specifically, Figure 1 This is a flowchart illustrating the data processing method for computer network sensing provided in this application. (Refer to...) Figure 1 The data processing method for computer network sensing provided in this application embodiment may include:

[0047] Step 100: Analyze the business scenarios of the computing network to obtain the computing network perception data requirements;

[0048] Step 200: Construct an attribute graph model for network sensing based on the network sensing data requirements;

[0049] Step 300: Obtain the perception data of the computing power network, and generate an attribute graph instance of the perception data based on the attribute graph model.

[0050] First, the business scenarios of the computing power network are analyzed to obtain the network awareness data requirements. These business scenarios correspond to network services, and the network awareness data requirements include the network resources needed for those services. Different business scenarios correspond to different network services, or different business scenarios correspond to different types of network services; different network services require different network resources, or different types of network services require different network resources.

[0051] It is understandable that computing network services generally involve both the computing power domain and the network domain of the computing power network. Analyzing the business scenarios of the computing power network, that is, analyzing the computing network services of the computing power network, can achieve unified perception of the computing power domain and the network domain from the business level.

[0052] Based on the analyzed data requirements for network perception, an attribute graph model for network perception is constructed. Attribute graphs, also known as labeled attribute graphs (LPGs), represent entities with nodes and relationships between entities with edges. Nodes and edges can be associated with attributes and attribute values ​​of any amount of data through key-value pairs. Based on the data requirements for network perception, the network resources required by different services, the relationships between different network resources, and the relationships between network resources and services can be determined. Network services and network resources, as entities, can serve as nodes in the attribute graph model. The relationships between network resources, and the relationships between network resources and network services, constitute the relationships between nodes, thus constructing the attribute graph model for network perception.

[0053] When constructing the attribute graph model, one can first build an attribute graph model for a specific computing network service, and then gradually build attribute graph models for other computing network services based on this, thus obtaining the attribute graph model of the entire computing power network. Alternatively, one can build a corresponding attribute graph model for each computing network service in the computing power network, and then integrate the attribute graph models under different computing network services to obtain the attribute graph model of the entire computing power network. After constructing the attribute graph model of the computing power network, when a new computing network service is added, an attribute graph model for the corresponding service scenario is built based on the attribute graph model of the computing power network and integrated to obtain the attribute graph model for all computing network services in the computing power network.

[0054] Acquire perception data for the future computing network. This perception data is the perception result of the computing power network, mainly including the resource usage of each computing network service in the computing power network. Based on the constructed attribute graph model, generate attribute graph instances of the perception data.

[0055] In this embodiment, by analyzing the business scenarios of the computing power network, the data requirements for computing power network perception are obtained, and an attribute graph model for computing power network perception is constructed. Then, the perception data of the computing power network is acquired, and attribute graph instances of the perception data are generated based on the constructed attribute graph model. By analyzing the business scenarios of the computing power network and modeling based on attribute graphs, global perception of the computing power network is achieved from the business level, as well as the fusion processing of perception data from the computing power domain and the network domain, thus constructing an integrated computing power network perception system. Simultaneously, attribute graphs can more intuitively express the relationship between computing power network services and computing power network resources, enabling more efficient processing of related data in the computing power network and improving the global perception and presentation capabilities of computing power network perception data.

[0056] In one embodiment, by analyzing the business scenarios of the computing power network, the resulting computing network perception data requirements include the objects to be perceived (perceived objects) and the metrics that these objects need to perceive (perceived metrics). The perceived objects are computing network resources or computing network services, and the perceived metrics include the service quality of computing network services, the resource type of computing network resources, resource allocation, and resource usage. Taking the "Eastern Data, Western Storage" business as an example, this business scenario focuses on the needs of intelligent hierarchical data storage, building a data sharing service network, scheduling "western" storage resources to support "eastern" data archiving and backup, and providing users with location-insensitive distributed off-site data storage services. During business operation, it is necessary to perceive the usage of storage resources and network bandwidth occupancy in real time, and automatically adjust link bandwidth based on business data migration needs, providing users with location-insensitive data storage services with bandwidth adjusted on demand. In this business scenario, the computing network perception data requirements obtained through analysis are specifically manifested as follows: the perceived objects in the computing power domain include computing power nodes, distributed storage pools, and object storage services; the perceived objects in the network domain include intelligent leased lines and SRv6 tunnels. Furthermore, the perception metrics for computing power nodes include resource pool, availability zone, storage type, resource type, total object storage capacity, used object storage capacity, network bandwidth, and object storage capacity utilization; the perception metrics for distributed storage pools include total storage pool capacity, used storage pool capacity, and storage capacity utilization; the perception metrics for object storage services include storage utilization, number of buckets, number of files, download / upload bandwidth, download / upload traffic, number of GET / PUT requests, average latency of total requests, and request success rate; the perception metrics for intelligent leased lines include the source and destination network elements and ports of the leased line service, as well as the traffic / latency / packet loss rate of the leased line service; the perception metrics for SRv6 tunnels include the source and destination network elements and IP addresses of the SRv6 service, as well as the traffic / latency / packet loss rate of the SRv6 service.

[0057] In step 200, an attribute graph model for network sensing is constructed based on the analyzed data requirements, specifically including:

[0058] Step 210: Determine the computing network resources required for the business scenario based on the computing network perception data requirements, and obtain the relationship data corresponding to the computing network resources; the relationship data includes the first relationship between the computing network resources and the second relationship between the computing network resources and the computing network services corresponding to the business scenario;

[0059] Step 220: Define the computing network service corresponding to the business scenario and the computing network resource as nodes, and extract the attribute information of the computing network resource;

[0060] Step 230: Based on the nodes, the relationship data, and the attribute information, construct a network-aware attribute graph model.

[0061] When constructing the attribute graph model, the first step is to determine the computing network resources required for the business scenarios of the computing power network based on the computing network awareness data requirements, and then obtain the relationship data corresponding to the computing network resources. This relationship data includes the first relationship between different resources among the required computing network resources, and the second relationship between the computing network services corresponding to the business scenarios and the required computing network resources. The computing network services corresponding to the business scenarios of the computing power network, and the computing network resources required by the computing network services, are defined as nodes in the attribute graph model. The attribute information of the computing network resources is extracted as node attributes. Based on the defined nodes, the obtained relationship data, and the extracted attribute information, the attribute graph model for computing network awareness is constructed.

[0062] In one embodiment, a type of sensing object in the sensing data requirement corresponds to a type of computing network service or computing network resource. A type of computing network resource can be defined as a type of node, and the key attributes of the computing network resource can be extracted as node attributes. Different types of computing network resources are distinguished by different type identifiers, and different types of nodes are also distinguished by different node identifiers. Since there are relationships between computing network resources and between computing network resources and computing network services, different relationships are distinguished by different relationship identifiers.

[0063] In a computing network, computing services are implemented using various computing resources. Different computing services rely on significantly different computing resources; therefore, each type of computing service is defined as a type of node. During the design and orchestration phases of computing services, it can be determined which computing resources constitute a service, thus establishing the relationship between that service and those resources. In the attribute graph model, computing services and resources are used as nodes. Various types of relationships exist between nodes, including one-to-many "inclusion" relationships, one-to-one "connection" relationships, and many-to-one "composed of..." relationships.

[0064] Furthermore, in step 230, constructing the attribute graph model for network awareness based on the defined nodes, acquired relational data, and extracted attribute information may further include:

[0065] Step 231: Generate a node set based on the nodes;

[0066] Step 232: Determine the ordered node pairs in the nodes and the target relation of the ordered node pairs based on the relation data, and generate a relation set based on the ordered node pairs and the target relation;

[0067] Step 233: Determine the node attributes of the node and the relation attributes of the target relationship of the ordered node pairs based on the attribute information, and generate an attribute set based on the node attributes and the relation attributes;

[0068] Step 234: Create triples using the node set, the relation set, and the attribute set to obtain the attribute graph model of the computing network.

[0069] In the attribute graph model, information is stored in nodes containing sources and entities, as well as edges containing relationships between nodes. Nodes and edges in the attribute graph are identified by their internal structure, including unique identifiers and attributes. Any node or edge can contain attributes that represent data attributes as key-value pairs. The attribute graph model GM can be described using triples: GM :=<N,R,L> Let N = {n1, n2, ..., nt} be a non-empty finite set of nodes, where the t elements in N are called t nodes. Let R = {r1, r2, ..., rs} be a set of relations consisting of ordered pairs (ni, nj) of nodes in node set N, where the s elements in R are called s relations, and satisfy the following conditions: L is a set of attributes consisting of node attributes and relation attributes.

[0070] Based on this, when constructing the attribute graph model for network awareness, a node set is generated based on the defined nodes. Then, according to the acquired relational data, ordered node pairs in each node and the target relations of each ordered node pair are determined. A relation set is generated based on the ordered node pairs and their target relations. Based on the extracted attribute information, the node attributes of each node and the relational attributes of the target relations of each ordered node pair are determined. An attribute set is generated based on the node attributes and relational attributes. Using the generated node set, relation set, and attribute set, triples are created to describe the attribute graph model, thus obtaining the attribute graph model for network awareness.

[0071] Taking the aforementioned "Eastern Data Storage in Western Regions" business as an example, the constructed attribute graph model is as follows: Figure 2As shown, the "Eastern Data to Western Storage" service and its required network resources are used as nodes to construct an attribute graph model containing Eastern Data to Western Storage service nodes, intelligent leased line nodes, SRv6 tunnel nodes, object storage service nodes, network element nodes, port nodes, distributed storage pool nodes, and computing power nodes. The relationships between Eastern Data to Western Storage service nodes and intelligent leased line nodes, Eastern Data to Western Storage service nodes and SRv6 tunnel nodes, Eastern Data to Western Storage service nodes and object storage service nodes, SRv6 tunnel nodes and network element nodes, and intelligent leased line nodes and port nodes are all "composed of..." relationships, indicating that the Eastern Data to Western Storage service consists of intelligent leased lines, SRv6 tunnels, and object storage services; intelligent leased lines are composed of ports; and SRv6 tunnels are composed of network elements. The relationships between network element nodes and port nodes, object storage service nodes and distributed storage pool nodes, and computing power nodes and distributed storage pool nodes are all inclusion relationships, indicating that network elements contain ports, computing power nodes contain distributed storage pools, and distributed storage pools contain object storage services. The connection between computing power nodes and port nodes is bidirectional.

[0072] It should be noted that nodes and the relationships between them can have multiple attributes, and each different type of node or relationship can be distinguished by a different ID. There can be multiple different relationships between nodes, which can be unidirectional or bidirectional, and the number of attributes can also be dynamically expanded.

[0073] In another embodiment, the acquired sensing data includes computing network resource data and computing network relationship data. In step 300, based on the constructed attribute graph model, an attribute graph instance of the sensing data is generated, including:

[0074] Step 310: Based on the computing network resource data in the perceived data, generate node instances of the attribute graph model;

[0075] Step 320: Based on the network relationship data in the perception data, generate a relationship instance corresponding to the node instance;

[0076] Step 330: Generate an attribute graph instance of the perceived data based on the node instance and the relationship instance.

[0077] Based on the computing network resource data in the sensing data, node instances in the attribute graph model are generated. Based on the computing network relationship data in the acquired sensing data, the relationships between each node instance are determined, thereby generating the relationship instances corresponding to each node instance. Based on the generated node instances and relationship instances, the attribute graph instances of the acquired sensing data are generated.

[0078] In one embodiment, the computing network resource data includes network resource data and computing power resource data, and the generated node instances include computing power node instances and network node instances. Step 310, based on the computing network resource data in the acquired sensing data, generates node instances for the attribute graph model, specifically further including:

[0079] Step 311: Based on the network resource data, generate network node instances of the attribute graph model;

[0080] Step 312: Based on the computing power resource data, generate computing power node instances of the attribute graph model.

[0081] When generating node instances, network node instances in the attribute graph model are generated based on network resource data in the computing network resource data, and computing power node instances in the attribute graph model are generated based on computing power resource data in the computing network resource data.

[0082] The generation of network node instances and computing power node instances can be performed in parallel or sequentially, without specific limitations. In one embodiment, network resource data and relationship data between network resources are periodically synchronized from the network management system and converted into network node instances and corresponding node relationship instances in the attribute graph model; computing power resource data and relationship data between computing power resources are periodically synchronized from the cloud management system and converted into computing power resource node instances and corresponding relationship instances in the attribute graph model. After the computing network service is activated, the network management / cloud management system returns the allocated computing network resource instances to the service layer, converts the newly activated computing network service and the newly allocated computing network resource into corresponding node instances, and converts the relationships between allocated computing network resources and the relationships between computing network services and computing network resources into relationship instances between nodes, thereby generating attribute graph instances.

[0083] In one embodiment, based on Figure 2 The attribute graph model of the "Eastern Data Storage in Western Regions" service shown above generates an example of the attribute graph of the perceived data for the "Eastern Data Storage in Western Regions" service. Figure 3 As shown. In Figure 3 In this context, the computing network resources allocated for the East-to-West data storage service include Intelligent Leased Line 1, SRv6 Tunnel 1, Object Storage Service 1, and Object Storage Service 2. Specifically, Intelligent Leased Line 1 consists of Port A and Port Z, where Port A contains network element X and Port B contains network element Y; SRv6 Tunnel 1 consists of network element A and Network element Z, where Network element A contains Port X and Network element Z contains Port Y; Computing Node 1 contains Distributed Storage Pool 1, Computing Node 2 contains Distributed Storage Pool 2, Distributed Storage Pool 1 further contains Object Storage Service 1, and Distributed Storage Pool 2 further contains Object Storage Service 2; Computing Node 1 is bidirectionally connected to Port Y, and Computing Node 2 is bidirectionally connected to Port X.

[0084] Furthermore, after generating attribute graph instances of the acquired perceptual data based on the attribute graph model, it may also include:

[0085] Step 400: Store the attribute graph instance in the graph database corresponding to the attribute graph model.

[0086] The generated attribute graph instances are stored in the corresponding graph database for querying and retrieval, enabling the storage of network perception data and facilitating its querying and retrieval. Network perception data based on attribute graph models can be stored in graph databases that support attribute graphs. Most graph databases support data import methods, allowing for easy import of network resource data obtained from network management / cloud management systems. Taking Neo4j graph database as an example, this database supports three data import methods:

[0087] 1. “Cypher create” statement: Each piece of data corresponds to a create operation command, which is suitable for the scenario of opening up computing network services. After the computing network service is opened, it creates the corresponding node instances and relationship instances of computing network services, object storage services, intelligent leased lines and SRv6 tunnels.

[0088] 2. The “Cyphe load csv” statement: Converts data into CSV format. The “LOAD CSV” command is used to read the data. It is suitable for scenarios where computing network resource data is synchronized on a regular basis. Most network management systems use the “FTP+CSV” method to synchronize computing network resource data. The “LOAD CSV” command statement can be used to read CSV format resource files and import the corresponding computing network resource data into the graph database.

[0089] 3. Loading directly from JDBC to Neo4j: Suitable for scenarios where relational data is directly converted into graph data, and can be used for historical data migration.

[0090] After storing the generated attribute graph instances in the graph database, data analysis can be performed using the stored attribute graph instances. Based on the intuitive and unified presentation of the computing network sensing data using the attribute graph instances, the computing network sensing data can be mined, thereby enabling fault analysis and location of the computing network, resource trend prediction, and optimization of global resource scheduling and allocation strategies.

[0091] In this embodiment, by analyzing the perception data requirements of the business scenario, nodes, relationships, and attributes in the attribute graph model are defined to construct a computing network perception attribute graph model. In practical applications, the computing network perception data can be stored in a graph database that supports attribute graphs based on the constructed attribute graph model. The graph query capabilities of the graph data enable unified presentation and in-depth relationship query analysis of the computing network perception data, achieving efficient computation on large-scale graph data.

[0092] Furthermore, based on the perception foundation of computing networks, unified and global computing network perception data can be collected, perceived, and presented intuitively, providing data support for the intelligent orchestration and integrated operation and maintenance of computing network services.

[0093] The following describes the computer network sensing data processing device provided in the embodiments of this application. The computer network sensing data processing device described below and the computer network sensing data processing method described above can be referred to in correspondence.

[0094] Reference Figure 4 The computer network sensing data processing device provided in this application embodiment includes:

[0095] Business analysis module 10 is used to analyze the business scenarios of the computing network and obtain the computing network perception data requirements;

[0096] The model building module 20 is used to build an attribute graph model of the computing network sensing according to the computing network sensing data requirements;

[0097] The data processing module 30 is used to acquire the perception data of the computing power network and generate an attribute graph instance of the perception data based on the attribute graph model.

[0098] In one embodiment, the model building module 20 is further configured to:

[0099] The computing network resources required for the business scenario are determined based on the computing network perception data requirements, and the relationship data corresponding to the computing network resources is obtained; the relationship data includes a first relationship between the computing network resources and a second relationship between the computing network resources and the computing network services corresponding to the business scenario;

[0100] Define the computing network services and computing network resources corresponding to the business scenario as nodes, and extract the attribute information of the computing network resources;

[0101] Based on the nodes, the relational data, and the attribute information, a network-aware attribute graph model is constructed.

[0102] In one embodiment, the model building module 20 is further configured to:

[0103] Generate a node set based on the aforementioned nodes;

[0104] Based on the relation data, determine the ordered node pairs in the nodes and the target relation of the ordered node pairs, and generate a relation set based on the ordered node pairs and the target relation;

[0105] The node attributes of the node and the relation attributes of the target relationship of the ordered node pairs are determined based on the attribute information, and an attribute set is generated based on the node attributes and the relation attributes.

[0106] Triples are created using the node set, the relation set, and the attribute set to obtain a network-aware attribute graph model.

[0107] In one embodiment, the sensing data includes computing network resource data and computing network relationship data; the data processing module 30 is further configured to:

[0108] Based on the network resource data in the perceived data, node instances of the attribute graph model are generated;

[0109] Based on the network relationship data in the perception data, generate the relationship instance corresponding to the node instance;

[0110] Based on the node instance and the relationship instance, an attribute graph instance of the perceived data is generated.

[0111] In one embodiment, the computing network resource data includes network resource data and computing power resource data; the node instance includes network node instance and computing power node instance; the data processing module 30 is further configured to:

[0112] Based on the network resource data, network node instances of the attribute graph model are generated;

[0113] Based on the computing power resource data, a computing power node instance of the attribute graph model is generated.

[0114] In one embodiment, the computer network sensing data processing device further includes a data storage module, used for:

[0115] The attribute graph instance is stored in the graph database corresponding to the attribute graph model.

[0116] Figure 5 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 5 As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530, and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other via the communication bus 540. The processor 510 can call a computer program in the memory 530 to execute the steps of the network sensing data processing method, such as including:

[0117] Analyze the business scenarios of the computing network to obtain the computing network perception data requirements;

[0118] Construct an attribute graph model for network sensing based on the aforementioned data requirements;

[0119] The perception data of the computing power network is obtained, and an attribute graph instance of the perception data is generated based on the attribute graph model.

[0120] Furthermore, the logical instructions in the aforementioned memory 530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0121] On the other hand, embodiments of this application also provide a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can perform the steps of the network sensing data processing method provided in the above embodiments, such as including:

[0122] Analyze the business scenarios of the computing network to obtain the computing network perception data requirements;

[0123] Construct an attribute graph model for network sensing based on the aforementioned data requirements;

[0124] The perception data of the computing power network is obtained, and an attribute graph instance of the perception data is generated based on the attribute graph model.

[0125] On the other hand, embodiments of this application also provide a processor-readable storage medium storing a computer program, the computer program being used to cause a processor to execute the steps of the network sensing data processing method provided in the above embodiments, for example including:

[0126] Analyze the business scenarios of the computing network to obtain the computing network perception data requirements;

[0127] Construct an attribute graph model for network sensing based on the aforementioned data requirements;

[0128] The perception data of the computing power network is obtained, and an attribute graph instance of the perception data is generated based on the attribute graph model.

[0129] The processor-readable storage medium can be any available medium or data storage device that the processor can access, including but not limited to magnetic memory (e.g., floppy disk, hard disk, magnetic tape, magneto-optical disk (MO)), optical memory (e.g., CD, DVD, BD, HVD), and semiconductor memory (e.g., ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)).

[0130] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0131] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0132] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for processing network sensing data, characterized in that, include: The business scenarios of the computing network are analyzed to obtain the computing network perception data requirements; the computing network perception data requirements include perception objects and perception indicators corresponding to the perception objects; the perception objects include computing network services and computing network resources, and the perception indicators include the service quality of the computing network services, the resource type, resource allocation, and resource usage of the computing network resources; Construct an attribute graph model for network sensing based on the aforementioned data requirements; Acquire the perception data of the computing power network, and generate an attribute graph instance of the perception data based on the attribute graph model; The construction of the attribute graph model for network sensing based on the network sensing data requirements includes: The computing network resources required for the business scenario are determined based on the computing network perception data requirements, and the relationship data corresponding to the computing network resources is obtained; the relationship data includes a first relationship between the computing network resources and a second relationship between the computing network resources and the computing network services corresponding to the business scenario; The computing network services and computing network resources corresponding to the business scenario are defined as nodes, and the attribute information of the computing network resources is extracted as node attributes; there are multiple types of relationships between the nodes, including one-to-many inclusion relationships, one-to-one connection relationships, and many-to-many composition relationships; Based on the nodes, the relational data, and the attribute information, a network-aware attribute graph model is constructed. The construction of the attribute graph model for network awareness based on the nodes, the relationship data, and the attribute information includes: Generate a node set based on the aforementioned nodes; Based on the relation data, the ordered node pairs in the nodes and the target relation of the ordered node pairs are determined, and a relation set is generated based on the ordered node pairs and the target relation; the nodes and the target relation are distinguished by different IDs; The node attributes of the node and the relation attributes of the target relationship of the ordered node pairs are determined based on the attribute information, and an attribute set is generated based on the node attributes and the relation attributes. Triples are created using the node set, the relation set, and the attribute set to obtain a network-aware attribute graph model.

2. The computer network sensing data processing method according to claim 1, characterized in that, The sensing data includes computing network resource data and computing network relationship data; The step of generating an attribute graph instance of the perceived data based on the attribute graph model includes: Based on the network resource data in the perceived data, node instances of the attribute graph model are generated; Based on the network relationship data in the perception data, generate the relationship instance corresponding to the node instance; Based on the node instance and the relationship instance, an attribute graph instance of the perceived data is generated.

3. The computer network sensing data processing method according to claim 2, characterized in that, The computing network resource data includes network resource data and computing power resource data; the node instances include network node instances and computing power node instances; the node instances used to generate the attribute graph model based on the computing network resource data in the sensing data include: Based on the network resource data, network node instances of the attribute graph model are generated; Based on the computing power resource data, a computing power node instance of the attribute graph model is generated.

4. The computer network sensing data processing method according to claim 1, characterized in that, After generating the attribute graph instance of the perceived data based on the attribute graph model, the method further includes: The attribute graph instance is stored in the graph database corresponding to the attribute graph model.

5. A computer network sensing data processing device, characterized in that, include: The business analysis module is used to analyze the business scenarios of the computing network and obtain the computing network perception data requirements. The computing network perception data requirements include perception objects and perception indicators corresponding to the perception objects. The perception objects include computing network services and computing network resources. The perception indicators include the service quality of the computing network services, the resource type, resource allocation, and resource usage of the computing network resources. The model building module is used to build an attribute graph model for computing network sensing based on the computing network sensing data requirements; The data processing module is used to acquire the perception data of the computing power network and generate an attribute graph instance of the perception data based on the attribute graph model. The model building module is also used for: The computing network resources required for the business scenario are determined based on the computing network perception data requirements, and the relationship data corresponding to the computing network resources is obtained; the relationship data includes a first relationship between the computing network resources and a second relationship between the computing network resources and the computing network services corresponding to the business scenario; The computing network services and computing network resources corresponding to the business scenario are defined as nodes, and the attribute information of the computing network resources is extracted as node attributes; there are multiple types of relationships between the nodes, including one-to-many inclusion relationships, one-to-one connection relationships, and many-to-many composition relationships; Based on the nodes, the relational data, and the attribute information, a network-aware attribute graph model is constructed. The model building module is also used for: Generate a node set based on the aforementioned nodes; Based on the relation data, the ordered node pairs in the nodes and the target relation of the ordered node pairs are determined, and a relation set is generated based on the ordered node pairs and the target relation; the nodes and the target relation are distinguished by different IDs; The node attributes of the node and the relation attributes of the target relationship of the ordered node pairs are determined based on the attribute information, and an attribute set is generated based on the node attributes and the relation attributes. Triples are created using the node set, the relation set, and the attribute set to obtain a network-aware attribute graph model.

6. An electronic device comprising a processor and a memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the computer network sensing data processing method according to any one of claims 1 to 4.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the computer network sensing data processing method according to any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the computer network sensing data processing method as described in any one of claims 1 to 4.

Images