CN116149885A - Method and system for predicting risk of flood IT service - Google Patents

Method and system for predicting risk of flood IT service Download PDF

Info

Publication number
CN116149885A
CN116149885A CN202310424113.3A CN202310424113A CN116149885A CN 116149885 A CN116149885 A CN 116149885A CN 202310424113 A CN202310424113 A CN 202310424113A CN 116149885 A CN116149885 A CN 116149885A
Authority
CN
China
Prior art keywords
service
ubiquitin
risk
data
flood
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202310424113.3A
Other languages
Chinese (zh)
Other versions
CN116149885B (en
Inventor
曹宏屹
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Shenzhou Bangbang Technical Service Co ltd
Original Assignee
Beijing Shenzhou Bangbang Technical Service Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Shenzhou Bangbang Technical Service Co ltd filed Critical Beijing Shenzhou Bangbang Technical Service Co ltd
Priority to CN202310424113.3A priority Critical patent/CN116149885B/en
Publication of CN116149885A publication Critical patent/CN116149885A/en
Application granted granted Critical
Publication of CN116149885B publication Critical patent/CN116149885B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/008—Reliability or availability analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
    • G06F11/3006—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3051—Monitoring arrangements for monitoring the configuration of the computing system or of the computing system component, e.g. monitoring the presence of processing resources, peripherals, I/O links, software programs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3055—Monitoring arrangements for monitoring the status of the computing system or of the computing system component, e.g. monitoring if the computing system is on, off, available, not available
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3065—Monitoring arrangements determined by the means or processing involved in reporting the monitored data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3447—Performance evaluation by modeling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367—Ontology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Quality & Reliability (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Biology (AREA)
  • Computer Hardware Design (AREA)
  • Animal Behavior & Ethology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Mathematical Physics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the technical field of intersection of a ubiquitin service and a knowledge graph, in particular to a method and a system for predicting risk of the ubiquitin service. The invention provides a method for predicting the risk of a ubiquitin service, which comprises the following steps: collecting the ubiquitin service data and constructing a ubiquitin service knowledge graph by utilizing the ubiquitin service data; obtaining the related information of the flood IT service data through the knowledge graph of the flood IT service; constructing a ubiquitin service risk prediction model by using the information related to the ubiquitin service data; and predicting the risk of the flood IT service through the flood IT service risk prediction model according to the current state of the flood IT service. The method for predicting the risk of the flood IT service can help enterprises and service providers to improve the quality and stability of the IT service, reduce potential risks and losses, and further improve the competitiveness and profitability of the enterprises or the service providers.

Description

Method and system for predicting risk of flood IT service
Technical Field
The invention relates to the technical field of intersection of a ubiquitin service and a knowledge graph, in particular to a method and a system for predicting risk of the ubiquitin service.
Background
IT services have become an important part of various industries in the society today, and stability and reliability of IT services directly affect operation efficiency and business development of enterprises. However, due to the complexity and uncertainty of IT services, IT service providers face a variety of risks in the service process, such as hardware device failures, network security problems, human negligence, and the like. These risks often lead to problems such as service interruption, data loss, traffic blocking, etc., and thus have serious impact on the normal operation and development of enterprises. Currently, enterprises often face the following problems when managing the risk of flood IT services: the data source is complex, the data association is difficult, the prediction model is difficult to establish, and the timeliness is low. Therefore, in order to improve the quality and stability of IT services for enterprises, IT is important to predict the risk of the flood IT services.
With the continuous development of technology, knowledge graph technology is receiving more and more attention as a brand new knowledge representation and calculation method. The knowledge graph technology is based on semantic network theory, utilizes a large amount of structured and semi-structured data to construct a knowledge graph, and utilizes a graph database to store and inquire. Knowledge graph can realize knowledge management and analysis of cross-domain and cross-data sources, and can help users deeply mine knowledge and relevance behind data, thereby helping enterprises, government and other fields to solve various problems. Currently, there is a need for a method for predicting the risk of a generic IT service by applying a knowledge graph technology to the risk prediction of the generic IT service, so as to identify and manage various risks in the IT service, thereby improving the quality and efficiency of the IT service and reducing the potential risks and losses.
Disclosure of Invention
Aiming at the defects of the prior art, in a first aspect, the invention provides a method for predicting the risk of the flood IT service, which aims to apply a knowledge graph technology to the method for predicting the risk of the flood IT service in the prediction of the risk of the flood IT service so as to realize the identification and management of various risks in the IT service, further improve the quality and efficiency of the IT service and reduce the potential risks and losses. The method for predicting the risk of the ubiquitin service comprises the following steps: collecting the ubiquitin service data and constructing a ubiquitin service knowledge graph by utilizing the ubiquitin service data; obtaining the related information of the flood IT service data through the knowledge graph of the flood IT service; constructing a ubiquitin service risk prediction model by using the information related to the ubiquitin service data; and predicting the risk of the flood IT service through the flood IT service risk prediction model according to the current state of the flood IT service. According to the method for predicting the risk of the ubiquitin service, disclosed by the invention, the knowledge graph technology is used for establishing the knowledge graph of the ubiquitin service to obtain the related information of the ubiquitin service data, so that various related data in the ubiquitin service are more comprehensively understood and analyzed, and potential risk factors are identified; meanwhile, through the construction and application of the flood IT service risk prediction model, various risks possibly occurring in IT service are predicted more accurately, and preventive and measures are taken timely to avoid service interruption and loss. The method for predicting the risk of the flood IT service can help enterprises and service providers to improve the quality and stability of the IT service, reduce potential risks and losses, and further improve the competitiveness and profitability of the enterprises or the service providers.
Optionally, the method for predicting the risk of the ubiquitin service further comprises the following steps: formulating a general IT service risk management strategy; and utilizing the ubiquitin service risk management strategy to cope with the ubiquitin service risk predicted by the ubiquitin service risk prediction model.
Optionally, the building the ubiquitin service knowledge graph by using the ubiquitin service data includes the following steps: preprocessing the flood IT service data; entity identification and extraction are carried out on the preprocessed ubiquitin service data; utilizing the recognition entity recognition and extraction results to construct a general IT service knowledge graph; and optimizing the ubiquitin service knowledge graph.
Optionally, the obtaining the information related to the ubiquitin service data through the knowledge graph of the ubiquitin service includes the following steps: determining the type of the to-be-analyzed ubiquitin service data; obtaining an entity and a relationship corresponding to the type of the ubiquitin service data through the ubiquitin service knowledge graph; and obtaining the information related to the general IT service data of the general IT service data type by utilizing the entity and the relation.
Optionally, the building the ubiquitin service risk prediction model by using the information related to the ubiquitin service data comprises the following steps: determining the type of the flood IT service risk; and building a general IT service risk prediction model by combining the general IT service data association information corresponding to the general IT service risk type.
Further optionally, the ubiquitin service risk prediction model includes the following formula:
Figure SMS_1
，
wherein ,
Figure SMS_5
data value representing the type of ubiquitin service data to be entered,/->
Figure SMS_8
Data value +.>
Figure SMS_11
Predictive value of corresponding ubiquitin service risk type,/-for>
Figure SMS_3
,/>
Figure SMS_7
Historical data sequence representing the type of the ubiquitin service data, < >>
Figure SMS_10
Indicate->
Figure SMS_13
History data of individual general IT service data types, < >>
Figure SMS_2
，
Figure SMS_6
Representing the amount of data in the historical data sequence, +.>
Figure SMS_9
Variable parameter representing a history data sequence, +.>
Figure SMS_12
Data value representing the type of the ubiquitin service data to be entered and +.>
Figure SMS_4
The time difference between the data values.
Optionally, the predicting the risk of the ubiquitin service according to the current state of the ubiquitin service through the risk prediction model of the ubiquitin service comprises the following steps: collecting state information of the type of the currently-to-be-analyzed ubiquitin service data; converting the format of the state information; and inputting the state information after format conversion into the ubiquitin service risk prediction model to obtain a risk prediction result of the type of the ubiquitin service data to be analyzed.
Optionally, the making of the ubiquitin service risk management policy includes the following steps: by classifying and evaluating the predicted risk; according to the risk assessment result, a corresponding risk management strategy is formulated; and integrating the risk management strategy with the actual service requirement to ensure the normal operation of the actual service.
Further optionally, classifying and evaluating the predicted risk further comprises classifying and evaluating the predicted risk using a risk classification model, the risk classification model satisfying the following formula:
Figure SMS_14
，
wherein ,
Figure SMS_21
data value +.>
Figure SMS_20
Corresponding risk class, when->
Figure SMS_25
When the risk level is low; />
Figure SMS_22
The risk level is medium; />
Figure SMS_23
The risk level is stronger and is->
Figure SMS_26
When the risk level is strong; />
Figure SMS_30
Data value +.>
Figure SMS_17
A predictive value of a corresponding type of ubiquitin service risk,
Figure SMS_27
,/>
Figure SMS_15
historical data sequence representing the type of the ubiquitin service data, < >>
Figure SMS_28
Indicate->
Figure SMS_18
History data of individual general IT service data types, < >>
Figure SMS_24
，/>
Figure SMS_16
Representing the amount of data in the historical data sequence; />
Figure SMS_29
Maximum history in the history sequence representing the type of ubiquitin service data,/for example>
Figure SMS_19
The smallest of the largest histories in the sequence of histories representing the type of the ubiquitin service data.
Further optionally, the data sources of the pan IT service data include a service data source, a log data source, a monitoring data source, and a customer feedback data source; wherein the service data source comprises a service level agreement and a service level target; the log data source comprises a log recorded by an IT service provider; the monitoring data source comprises operation condition data of the IT system collected by an IT service provider by using a monitoring tool; the customer feedback data source includes customer feedback data to an IT service provider. The general IT service data is obtained through the combination of various data sources, and risk information with different dimensions, including service problems, system anomalies, customer feedback and the like, so that the risk situation of the general IT service is more comprehensively known, comprehensive, accurate and timely information support is further provided for general IT service risk management, and the improvement of the risk management efficiency and service quality is facilitated.
In order to better execute the ubiquitin service risk prediction method, in a second aspect, the invention also provides a ubiquitin service risk prediction system. The flood IT service risk prediction system comprises one or more processors; the system comprises one or more input devices, one or more output devices and a memory, wherein the processor, the input devices, the output devices and the memory are connected through a bus, the memory is used for storing a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the ubiquitin service risk prediction method provided by the first aspect of the invention. The system for predicting the risk of the flood IT service provided by the invention has the advantages of compact structure and stable performance, and can be used for efficiently and accurately implementing the method for predicting the risk of the flood IT service.
Drawings
FIG. 1 is a flowchart of a method for predicting risk of a flood IT service according to an embodiment of the present invention;
fig. 2 is a knowledge graph of the pan IT service constructed in the present embodiment;
FIG. 3 is a flowchart of a method for predicting risk of a flood IT service according to an embodiment of the present invention;
fig. 4 is a structural diagram of a system for predicting risk of a ubiquitin service according to an embodiment of the present invention.
Detailed Description
Specific embodiments of the invention will be described in detail below, it being noted that the embodiments described herein are for illustration only and are not intended to limit the invention. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, it will be apparent to one of ordinary skill in the art that: no such specific details are necessary to practice the invention. In other instances, well-known circuits, software, or methods have not been described in detail in order not to obscure the invention.
Throughout the specification, references to "one embodiment," "an embodiment," "one example," or "an example" mean: a particular feature, structure, or characteristic described in connection with the embodiment or example is included within at least one embodiment of the invention. Thus, the appearances of the phrases "in one embodiment," "in an embodiment," "one example," or "an example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, the particular features, structures, or characteristics may be combined in any suitable combination and/or sub-combination in one or more embodiments or examples. Moreover, those of ordinary skill in the art will appreciate that the illustrations provided herein are for illustrative purposes and that the illustrations are not necessarily drawn to scale.
In an alternative embodiment, please refer to fig. 1, fig. 1 is a flowchart of a method for predicting risk of a pan IT service according to an embodiment of the present invention. As shown in fig. 1, the method for predicting the risk of the ubiquitin service comprises the following steps:
and S01, collecting the ubiquitin service data, and constructing a ubiquitin service knowledge graph by utilizing the ubiquitin service data.
IT should be understood that the risk of the flood IT service refers to various risks faced when an enterprise uses an external IT service provider (such as cloud computing, software as a service, etc.), mainly including service interruption, data security, compliance, etc., which typically require negotiation and management between the enterprise and the service provider. Thus, the flood IT service risk management needs to consider the service provider's perspective and build a closer partnership to jointly solve the risk problem. In order to enrich the data association information contained in the knowledge graph of the flood IT service, the flood IT service data needs to be acquired from a plurality of data sources when the flood IT service data is collected. The information of different aspects contained by the data sources is integrated into one general IT service data knowledge graph, so that the general appearance of the general IT service can be better understood, and the risk assessment of the general IT service is facilitated. Better may help us better.
Further, the plurality of data sources includes a service data source, a log data source, a monitoring data source, and a customer feedback data source. Wherein the service data source comprises a service level agreement and a service level objective, the service level agreement and the service level objective refer to a contract between a service provider and a client, wherein the contract prescribes the service level promise of the service provider, and the service data source also comprises indexes such as availability, performance, response time and the like of the service. The log data sources include a wide variety of logs recorded by IT service providers, such as network traffic, server logs, application logs, database logs, and the like. The data in the log data source records events and activities in the IT system, and the side surface represents the running condition of the system. The monitoring data sources are operational status data of the IT system collected by the IT service provider using various monitoring tools including server load, network bandwidth usage, application performance, etc. The customer feedback data sources include customer feedback data to the IT service provider, further including customer satisfaction and demand for IT services, and some problems in the IT system.
The knowledge graph technology is based on semantic network theory, utilizes a large amount of structured and semi-structured data to construct a knowledge graph, and utilizes a graph database to store and inquire. In an alternative embodiment, the building a knowledge graph of the ubiquitin service using the ubiquitin service data in step S01 includes the following steps:
s011, preprocessing the ubiquitin service data. In step S011, the collected pan IT service data is subjected to preprocessing such as cleaning, deduplication, format conversion, and the like, so as to be subjected to subsequent processing.
S012, entity identification and extraction are carried out on the preprocessed ubiquitin service data. In step S012, the entity-entity relationship in the pre-processed ubiquitin service data is obtained through entity identification and extraction. Further, entity recognition and extraction may use natural language processing techniques to perform entity recognition and relationship extraction on the pre-processed ubiquitin service text data.
S013, utilizing the recognition entity recognition and extraction results to construct a ubiquitin service knowledge graph. Step S013 stores the entity and the relation between the entities extracted from the preprocessed ubiquitin service data into a ubiquitin service knowledge graph database to construct a corresponding ubiquitin service knowledge graph. Further, the building of the ubiquitin service knowledge graph can use an open source knowledge graph building tool to store the relationship between the entities as nodes and edges, and establish corresponding indexes so as to obtain the ubiquitin service knowledge graph. The knowledge graph construction tools of the source comprise a Neo4j graph construction tool, an OrientDB graph construction tool and the like.
And S014, optimizing the ubiquitin service knowledge graph. Specifically, step S014 optimizes the constructed generic IT service knowledge graph by removing duplicate nodes, merging similar nodes, adding nodes and relationship attributes, and the like, so as to improve the efficiency and accuracy of the generic IT service knowledge graph.
In this embodiment, the collected ubiquitin service data constructs a ubiquitin service knowledge graph through steps S011 to S014. The finally constructed ubiquitin service knowledge graph is a large-scale structured data graph, wherein entities, attributes and relations are stored as nodes and edges, and rapid query and analysis can be performed through a graph database.
In yet another alternative embodiment, please refer to fig. 2, fig. 2 is a generic IT service knowledge graph constructed in this embodiment. As shown in fig. 2, in the generic IT service knowledge graph provided in this embodiment, an entity includes an IT service, an application program, a network device, a virtual machine, a host, and a storage device; the entity relationship comprises a deployment relationship between an IT service and an application program, a deployment relationship between the application program and a host, a deployment relationship between a virtual machine and the host and a connection relationship between the host and a storage device; meanwhile, different entities have respective corresponding attributes, specifically, fig. 2 includes an operation state of an IT service, a version number of an application program, and an operating system of a host; the relationship between different entities also has specific properties, specifically, the connection relationship between the host and the storage device in fig. 2 includes the transmission rate and bandwidth information. In the knowledge graph of the generic IT service provided in this embodiment, IT service is used as a center, and is connected with entities such as an application program, a network device, a virtual machine, a host, and a storage device through different relationships, so as to form a complex relationship network. Through the knowledge graph of the ubiquitin service, the correlation among different entities in the ubiquitin service can be deeply mined, so that potential risks possibly existing in the ubiquitin service can be discovered, and risk prediction and management can be performed.
S02, obtaining the related information of the ubiquitin service data through the knowledge graph of the ubiquitin service.
The IT service data association information in step S02 is data and association information related to the type of the generic IT service data to be analyzed. Further, the generic IT service data association information includes an entity of the generic IT service data type to be analyzed and interactions and dependencies between the entity and the remaining entities. These interactions and dependencies facilitate the construction of subsequent flood IT service risk prediction models so that the flood IT service risk prediction models can more accurately predict risk. At the same time, it also facilitates risk checking, for example, if a service fails, it can be detected quickly to check other services related to the service, thereby reducing risk.
In an optional embodiment, the obtaining the information related to the ubiquitin service data through the knowledge graph of the ubiquitin service in step S02 includes the following steps: s021, determining the type of the to-be-analyzed pan IT service data. The general IT service data types comprise network flow, log data, system performance data and other data types. S022, obtaining the entity and the relation corresponding to the type of the ubiquitin service data through the knowledge graph of the ubiquitin service. S023 obtains the information related to the general IT service data of the general IT service data type by utilizing the entity and the relation.
In this embodiment, the type of the pan IT service data to be analyzed determined in step S021 is network traffic data; therefore, in step S022, entities and relationships corresponding to the network traffic data are obtained through the generic IT service knowledge graph, wherein the entities include servers, switches and routers, and the relationships include connections and traffic; step S023 obtains corresponding information related to the general IT service data by inquiring the general IT service knowledge graph again according to the entities and the relations, wherein the information related to the general IT service data comprises connection information between a certain server and a switch, flow data of the certain server in a certain period of time and the like.
S03, constructing a ubiquitin service risk prediction model by utilizing the information related to the ubiquitin service data.
IT should be understood that in step S03, the ubiquitin service risk prediction model needs to be constructed in combination with the information related to the ubiquitin service data acquired in step 2. The accuracy and predictive effectiveness of the flood IT service risk prediction model depends on the rationality of the selected metrics, the quality of the data, and the merits of the algorithm. Therefore, in practical application, the indexes, data and algorithms in the ubiquitin service risk prediction model are required to be continuously optimized and adjusted according to the data updated in real time.
In an alternative embodiment, the building a generic IT service risk prediction model by using the generic IT service data association information in step S03 includes the following steps:
s031, determining the type of the general IT service risk. In a flood IT service, there may be multiple risk types, such as performance problems, data problems, system problems, etc. The type of the ubiquitin service risk to be predicted needs to be determined first so as to construct a corresponding prediction model. Thus, a generic IT service risk type is first determined, further including performance risk, data risk, and system risk. The type of the flood IT service risk can be determined by methods such as domain expert, historical data analysis and the like.
S032, building a general IT service risk prediction model by combining the general IT service data associated information corresponding to the general IT service risk type. And selecting a proper machine learning algorithm for modeling according to the type of the risk of the flood IT service, the type of the flood IT service data and the actual data condition to be predicted. For example, for certain ubiquitin service risk types, supervised learning algorithms (e.g., decision trees, support vector machines, neural networks, etc.) may be used for modeling; for some ubiquitin service risk types, an unsupervised learning algorithm (e.g., cluster analysis, anomaly detection, etc.) may be used for modeling.
Further, the selection of the type of the generic IT service risk in step S031 involves specific business scenario and data situation, which cannot be summarized. In step S032, the corresponding generic IT service risk prediction model is constructed, and in general, the supervised learning algorithm is applied to explicitly labeled data, such as the generic IT service data that has been labeled as normal and abnormal, and classification algorithms (e.g., decision tree, support vector machine, neural network, etc.) may be used to construct the risk prediction model; for data which is not explicitly marked, an unsupervised learning algorithm (such as cluster analysis, anomaly detection and the like) can be used for modeling, and by clustering or anomaly detection on the ubiquitin service data, rules and anomaly points in the data are found, so that potential risks are identified.
In an alternative embodiment, the generic IT service risk prediction model in step S032 includes the following formula:
Figure SMS_31
，
wherein ,
Figure SMS_33
data value representing the type of ubiquitin service data to be entered, further +.>
Figure SMS_39
Is obtained by the related information of the flood IT service data corresponding to the flood IT service data type>
Figure SMS_42
Data value +.>
Figure SMS_34
Predictive value of corresponding ubiquitin service risk type,/-for>
Figure SMS_37
The larger value indicates that the degree of risk of the ubiquitin service corresponding to the input type of the ubiquitin service data is higher, +.>
Figure SMS_40
,/>
Figure SMS_44
A historical data sequence representing a generic IT service data type,
Figure SMS_32
indicate->
Figure SMS_38
History data of individual general IT service data types, < >>
Figure SMS_43
，/>
Figure SMS_45
Representing the amount of data in the historical data sequence, +.>
Figure SMS_35
Variable parameter representing a history data sequence, +.>
Figure SMS_36
Data value representing the type of the ubiquitin service data to be entered and +.>
Figure SMS_41
The time difference between the data values. The risk prediction model of the ubiquitin service provided by the embodiment performs risk prediction by depending on the data value of the type of the ubiquitin service data to be input and the data in the historical data sequence, and the risk prediction model is easy to realize, good in generalization capability, strong in instantaneity and wide in application range.
S04, predicting the risk of the ubiquitin service through the risk prediction model of the ubiquitin service according to the current state of the ubiquitin service.
IT should be understood that, in the step of performing risk prediction according to the current state of the ubiquitin service in step S04, state information of the current ubiquitin service, such as performance index, log information, use condition, etc., needs to be acquired, and these information are converted into the numerical feature vector required by the ubiquitin service risk prediction model. And then, inputting the feature vectors into corresponding ubiquitin service risk prediction models to obtain corresponding risk prediction results. In particular, classification models or regression models in supervised learning algorithms may be used to accomplish the prediction tasks. The classification model is suitable for discrete risk type prediction, such as high risk, medium risk, low risk and the like; the regression model is suitable for continuous risk value prediction, such as risk score, risk grade, etc. During model training, the historical data set can be used for training, model performance is optimized by means of adjusting model parameters, selecting a proper characteristic engineering method and the like, and accuracy and reliability of the ubiquitin service risk prediction are improved.
In an alternative embodiment, the step S04 of predicting the risk of the ubiquitin service according to the current state of the ubiquitin service through the ubiquitin service risk prediction model includes the following steps:
s041, collecting state information of the type of the currently-to-be-analyzed ubiquitin service data.
IT should be understood that the type of the flood IT service data to be analyzed described in step S041 is consistent with the type of the flood IT service data described in step S021. Specifically, the flood IT service data types may include CPU usage, memory usage, network bandwidth, disk space usage, and the like; and state information of the type of the ubiquitin service data to be analyzed needs to be collected, including but not limited to: the value of the current generic IT service data type, timestamp, data type, etc. The manner of collection may be based on the particular circumstances, such as by way of sensors, API interfaces, manual inputs, etc. In practice, the data collection may be performed using a relational library (e.g., requests, sensors) in the Python programming language. For example, assuming that a server CPU load condition of a certain company needs to be analyzed, current CPU load data can be acquired through an API interface and used as state information of a type of the ubiquitin service data to be analyzed.
S042, carrying out format conversion on the state information.
I.e. step S042 converts the status information into an input format of the ubiquitin service risk prediction model to conform to the input format of the ubiquitin service risk prediction model. The specific format conversion method can be determined according to the selected ubiquitin service risk prediction model. For example, if the model selected requires a one-dimensional vector to be input, then the parameters in the state information need to be translated into a one-dimensional vector. In practice, format conversion may be performed using a relational library (e.g., numpy) in the Python programming language.
S043, inputting the state information after format conversion into the ubiquitin service risk prediction model to obtain a risk prediction result of the type of the ubiquitin service data to be analyzed.
In step S043, the state information after format conversion in step S042 is input into the selected ubiquitin service risk prediction model, and a risk prediction result of the type of the ubiquitin service data to be analyzed is obtained. Further, in actual operation, the model may be invoked using a relational library (e.g., sklearn) in the Python programming language.
According to the method for predicting the risk of the ubiquitin service, disclosed by the invention, the knowledge graph technology is used for establishing the knowledge graph of the ubiquitin service to obtain the related information of the ubiquitin service data, so that various related data in the ubiquitin service are more comprehensively understood and analyzed, and potential risk factors are identified; meanwhile, through the construction and application of the flood IT service risk prediction model, various risks possibly occurring in IT service are predicted more accurately, and preventive and measures are taken timely to avoid service interruption and loss. The method for predicting the risk of the flood IT service can help enterprises and service providers to improve the quality and stability of the IT service, reduce potential risks and losses, and further improve the competitiveness and profitability of the enterprises or the service providers.
In order to further reduce or avoid the influence of risks on enterprises, in yet another alternative embodiment, please refer to fig. 3, fig. 3 is a flowchart complementary to the method for predicting risk of the flood IT service according to an embodiment of the present invention. Based on the flowchart of the method for predicting the risk of the ubiquitin service shown in fig. 1, the method for predicting the risk of the ubiquitin service shown in fig. 2 further comprises the following steps:
s05, formulating a general IT service risk management strategy.
In step S05, the predicted risk is first classified and evaluated, and the degree of influence and occurrence probability thereof are determined. Then, corresponding risk management strategies including aspects of risk prevention, risk alleviation, risk transfer, risk acceptance and the like need to be formulated. Finally, the risk management strategy and the actual service requirement are integrated, so that the implemented risk management measures can be ensured to the greatest extent to ensure the normal operation of the service. Further, the making of the flood IT service risk management policy in step S05 includes the following steps:
s051 by classifying and evaluating the predicted risk. I.e. by classifying and evaluating the predicted risks, it is possible to determine which risks have the greatest influence on the business and the probability of occurrence of these risks. In yet another alternative embodiment, the generic IT service risk prediction model provided by the above embodiment is based on:
Figure SMS_46
, wherein ,/>
Figure SMS_47
Data value +.>
Figure SMS_48
Predictive value of corresponding ubiquitin service risk type, and +.>
Figure SMS_49
The larger the value is, the higher the degree of risk of the ubiquitin service corresponding to the input type of the ubiquitin service data is. Thus, step S051 is passed +.>
Figure SMS_50
Risk classification and assessment of the size of (a), in particular, by comparison of the size of (a) in step S051Classifying and evaluating the predicted risk further comprises classifying and evaluating the predicted risk using a risk classification model that satisfies the following formula:
Figure SMS_53
, wherein ,/>
Figure SMS_55
Data value +.>
Figure SMS_59
Corresponding risk class, when->
Figure SMS_52
When the risk level is low; />
Figure SMS_56
The risk level is medium; />
Figure SMS_58
The risk level is stronger and is->
Figure SMS_61
When the risk level is strong; />
Figure SMS_51
Data value +.>
Figure SMS_54
A predictive value of a corresponding ubiquitin service risk type; />
Figure SMS_57
Maximum history in the history sequence representing the type of ubiquitin service data,/for example>
Figure SMS_60
The smallest of the largest histories in the sequence of histories representing the type of the ubiquitin service data.
S052, according to the risk assessment result, formulating a corresponding risk management strategy. Specific measures may include enhancing data backup and recovery, enhancing network security, periodically updating hardware devices, enhancing employee training, and the like.
S053, integrating the risk management strategy with the actual service requirement to ensure the normal operation of the actual service. This includes taking into account business requirements, the impact of risk counter measures on business, etc. when formulating risk management policies.
S06, using the ubiquitin service risk management strategy to cope with the ubiquitin service risk predicted by the ubiquitin service risk prediction model.
IT will be appreciated that this step is important in dealing with predicted risk of flood IT services according to established risk management policies. Because IT is only practical and effective to implement the corresponding risk management policies, IT service risks can be effectively reduced and avoided. Further, the processing of the ubiquitin service risk predicted by the ubiquitin service risk prediction model by using the ubiquitin service risk management policy in step S06 includes the following steps:
and S061, implementing corresponding measures according to the formulated risk management strategy, and ensuring that the risks are effectively controlled and managed.
And S062, monitoring and evaluating risks of the general IT service regularly, timely finding risk changes, and taking corresponding measures.
In the embodiment, by making the risk management policy of the ubiquitin service, the enterprise can reasonably avoid or mitigate the risk, thereby ensuring the security and stability of the ubiquitin service. Meanwhile, according to the formulated ubiquitin service risk management strategy, timely coping is performed for the predicted risk, and the possibility of risk occurrence and the influence on enterprises are reduced.
In order to better execute the above-mentioned method for predicting the risk of the ubiquitin service, in an alternative embodiment, please refer to fig. 4, fig. 4 is a block diagram of a system for predicting the risk of the ubiquitin service according to an embodiment of the present invention. As shown in fig. 4, the system for predicting the risk of the flood IT service provided by the present invention includes one or more processors; the system comprises one or more input devices, one or more output devices and a memory, wherein the processor, the input devices, the output devices and the memory are connected through a bus, the memory is used for storing a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the ubiquitin service risk prediction method provided by the invention. The system for predicting the risk of the flood IT service provided by the invention has the advantages of compact structure and stable performance, and can be used for efficiently and accurately implementing the method for predicting the risk of the flood IT service.
In yet another alternative embodiment, the processor 401 may be a central processing unit (Central Processing Unit, CPU), which may also be other general purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The input device 402 may be used to input collected pan IT service data. The output device 403 may display information about the risk of the flood IT service predicted by the method of the present invention. The memory 404 may include read only memory and random access memory and provide instructions and data to the processor 401. A portion of memory 404 may also include non-volatile random access memory. For example, memory 404 may also store information of device type.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention, and are intended to be included within the scope of the appended claims and description.

Claims (10)

1. The method for predicting the risk of the ubiquitin service is characterized by comprising the following steps of:
collecting the ubiquitin service data and constructing a ubiquitin service knowledge graph by utilizing the ubiquitin service data;
obtaining the related information of the flood IT service data through the knowledge graph of the flood IT service;
constructing a ubiquitin service risk prediction model by using the information related to the ubiquitin service data;
and predicting the risk of the flood IT service through the flood IT service risk prediction model according to the current state of the flood IT service.
2. The method for predicting the risk of a flood IT service according to claim 1, further comprising the steps of:
formulating a general IT service risk management strategy;
and utilizing the ubiquitin service risk management strategy to cope with the ubiquitin service risk predicted by the ubiquitin service risk prediction model.
3. The method for predicting the risk of the ubiquitin service according to claim 1, wherein the constructing a knowledge graph of the ubiquitin service by using the ubiquitin service data comprises the following steps:
preprocessing the flood IT service data;
entity identification and extraction are carried out on the preprocessed ubiquitin service data;
utilizing the recognition entity recognition and extraction results to construct a general IT service knowledge graph;
and optimizing the ubiquitin service knowledge graph.
4. The method for predicting risk of a flood IT service according to claim 1, wherein the obtaining the association information of the flood IT service data through the knowledge graph of the flood IT service comprises the following steps:
determining the type of the to-be-analyzed ubiquitin service data;
obtaining an entity and a relationship corresponding to the type of the ubiquitin service data through the ubiquitin service knowledge graph;
and obtaining the information related to the general IT service data of the general IT service data type by utilizing the entity and the relation.
5. The method for predicting risk of a flood IT service according to claim 1, wherein the building of the flood IT service risk prediction model using the association information of the flood IT service data comprises the steps of:
determining the type of the flood IT service risk;
and building a general IT service risk prediction model by combining the general IT service data association information corresponding to the general IT service risk type.
6. The method of claim 5, wherein the ubiquitin service risk prediction model comprises the following formula:
Figure QLYQS_1
，
wherein ,
Figure QLYQS_4
data value representing the type of ubiquitin service data to be entered,/->
Figure QLYQS_7
Data value representing a type of ubiquitin service data
Figure QLYQS_11
Predictive value of corresponding ubiquitin service risk type,/-for>
Figure QLYQS_3
,/>
Figure QLYQS_8
Representing ubiquitin service dataType of history data sequence,/->
Figure QLYQS_10
Indicate->
Figure QLYQS_13
History data of individual general IT service data types, < >>
Figure QLYQS_2
，/>
Figure QLYQS_6
Representing the amount of data in the historical data sequence, +.>
Figure QLYQS_9
Variable parameter representing a history data sequence, +.>
Figure QLYQS_12
Data value representing the type of the ubiquitin service data to be entered and +.>
Figure QLYQS_5
The time difference between the data values.
7. The method for predicting the risk of the ubiquitin service according to claim 4, wherein the step of predicting the risk of the ubiquitin service according to the current state of the ubiquitin service through the model for predicting the risk of the ubiquitin service comprises the following steps:
collecting state information of the type of the currently-to-be-analyzed ubiquitin service data;
converting the format of the state information;
and inputting the state information after format conversion into the ubiquitin service risk prediction model to obtain a risk prediction result of the type of the ubiquitin service data to be analyzed.
8. The method for predicting the risk of the flood IT service according to claim 2, wherein the step of formulating the risk management policy of the flood IT service comprises the steps of:
by classifying and evaluating the predicted risk;
according to the risk assessment result, a corresponding risk management strategy is formulated;
and integrating the risk management strategy with the actual service requirement to ensure the normal operation of the actual service.
9. The method of claim 1-8, wherein the data sources of the flood IT service data include a service data source, a log data source, a monitoring data source, and a customer feedback data source;
wherein the service data source comprises a service level agreement and a service level target;
the log data source comprises a log recorded by an IT service provider;
the monitoring data source comprises operation condition data of the IT system collected by an IT service provider by using a monitoring tool;
the customer feedback data source includes customer feedback data to an IT service provider.
10. A ubiquitin service risk prediction system, wherein the ubiquitin service risk prediction system comprises one or more processors; one or more input devices, one or more output devices and a memory, said processor, said input devices, said output devices and said memory being connected by a bus, said memory being for storing a computer program, said computer program comprising program instructions, said processor being configured for invoking said program instructions for performing the ubiquitin service risk prediction method according to any of claims 1-9.
CN202310424113.3A 2023-04-20 2023-04-20 Method and system for predicting risk of flood IT service Active CN116149885B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310424113.3A CN116149885B (en) 2023-04-20 2023-04-20 Method and system for predicting risk of flood IT service

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310424113.3A CN116149885B (en) 2023-04-20 2023-04-20 Method and system for predicting risk of flood IT service

Publications (2)

Publication Number Publication Date
CN116149885A true CN116149885A (en) 2023-05-23
CN116149885B CN116149885B (en) 2023-06-20

Family

ID=86362186

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310424113.3A Active CN116149885B (en) 2023-04-20 2023-04-20 Method and system for predicting risk of flood IT service

Country Status (1)

Country Link
CN (1) CN116149885B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170293853A1 (en) * 2016-04-07 2017-10-12 Fujitsu Limited Behavior prediction
CN108596439A (en) * 2018-03-29 2018-09-28 北京中兴通网络科技股份有限公司 A kind of the business risk prediction technique and system of knowledge based collection of illustrative plates
CN110717816A (en) * 2019-07-15 2020-01-21 上海氪信信息技术有限公司 Artificial intelligence technology-based global financial risk knowledge graph construction method
CN110889556A (en) * 2019-11-28 2020-03-17 福建亿榕信息技术有限公司 Enterprise operation risk prediction method and system
CN112365171A (en) * 2020-11-16 2021-02-12 广州杰赛科技股份有限公司 Risk prediction method, device and equipment based on knowledge graph and storage medium
CN113537796A (en) * 2021-07-22 2021-10-22 大路网络科技有限公司 Enterprise risk assessment method, device and equipment

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170293853A1 (en) * 2016-04-07 2017-10-12 Fujitsu Limited Behavior prediction
CN108596439A (en) * 2018-03-29 2018-09-28 北京中兴通网络科技股份有限公司 A kind of the business risk prediction technique and system of knowledge based collection of illustrative plates
CN110717816A (en) * 2019-07-15 2020-01-21 上海氪信信息技术有限公司 Artificial intelligence technology-based global financial risk knowledge graph construction method
CN110889556A (en) * 2019-11-28 2020-03-17 福建亿榕信息技术有限公司 Enterprise operation risk prediction method and system
CN112365171A (en) * 2020-11-16 2021-02-12 广州杰赛科技股份有限公司 Risk prediction method, device and equipment based on knowledge graph and storage medium
CN113537796A (en) * 2021-07-22 2021-10-22 大路网络科技有限公司 Enterprise risk assessment method, device and equipment

Also Published As

Publication number Publication date
CN116149885B (en) 2023-06-20

Similar Documents

Publication Publication Date Title
US10296912B2 (en) System and methods for dynamic digital threat mitigation
US11777963B2 (en) Analytics for processing information system data
US11558272B2 (en) Methods and systems for predicting time of server failure using server logs and time-series data
US9942103B2 (en) Predicting service delivery metrics using system performance data
JP7038143B2 (en) How to estimate the deleteability of a data object
US10581667B2 (en) Method and network node for localizing a fault causing performance degradation of a service
US11449798B2 (en) Automated problem detection for machine learning models
CN116680459B (en) Foreign trade content data processing system based on AI technology
US11663329B2 (en) Similarity analysis for automated disposition of security alerts
WO2019125445A1 (en) Automated fault detecting control system
Zhou et al. Recommending ticket resolution using feature adaptation
CN116438553A (en) Machine learning model for probability prediction of success of operators in PAAS cloud environments
Prakash et al. Big data preprocessing for modern world: opportunities and challenges
US20230396638A1 (en) Adaptive system for network and security management
CN116149885B (en) Method and system for predicting risk of flood IT service
CN111797942A (en) User information classification method and device, computer equipment and storage medium
US20230199006A1 (en) Systems and methods for machine learning-based detection of an automated fraud attack or an automated abuse attack
Mijumbi et al. MAYOR: machine learning and analytics for automated operations and recovery
Ghosh et al. Dependency Aware Incident Linking in Large Cloud Systems
CN117527622B (en) Data processing method and system of network switch
CN117978545B (en) Network security risk assessment method, system, equipment and medium based on large model
US11887126B2 (en) Systems and methods for generating a probationary automated-decisioning workflow in a machine learning-task oriented digital threat or digital abuse mitigation system
CN116707834B (en) Distributed big data evidence obtaining and analyzing platform based on cloud storage
Abdelkhalki et al. Incident prediction through logging management and machine learning
US20240073229A1 (en) Real time behavioral alert processing in computing environments

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant