CN109840183B - Data center grading early warning method and device and storage medium - Google Patents
Data center grading early warning method and device and storage medium Download PDFInfo
- Publication number
- CN109840183B CN109840183B CN201811479955.4A CN201811479955A CN109840183B CN 109840183 B CN109840183 B CN 109840183B CN 201811479955 A CN201811479955 A CN 201811479955A CN 109840183 B CN109840183 B CN 109840183B
- Authority
- CN
- China
- Prior art keywords
- early warning
- risk
- risk event
- information
- level
- 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.)
- Active
Links
Images
Classifications
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention belongs to the technical field of machine room management and discloses a data center grading early warning method, which comprises the following steps: constructing a risk event database; crawling risk event information; acquiring a correlated risk event of a data center, classifying the correlated risk event through a classifier, and acquiring a risk level of the correlated risk event according to the risk event database; obtaining a characteristic value of the associated risk event according to the risk level of the associated risk event; acquiring an early warning level corresponding to the characteristic value according to the risk event database; and sending early warning information to the associated users of the associated risk events according to the early warning level. The invention also discloses an electronic device and a computer readable storage medium. According to the invention, the risk event is comprehensively monitored by crawling risk event information, and the early warning is given to the user by setting the risk level and the early warning level, so that the early warning informing personnel has pertinence, and the early warning accuracy of the risk event is improved.
Description
Technical Field
The invention relates to the technical field of machine room management, in particular to a data center grading early warning method and device and a storage medium.
Background
The machine room is a data center for placing server equipment, runs various services, and is very important for ensuring normal operation of the machine room. Networks, services, environments, operations and the like related in the machine room are very easily affected by conditions such as major conferences, sports events, social risks, emergencies, extreme weather, natural disasters, major public health and the like, so that the risk events need to be monitored, the influence degree of the risk events on the machine room needs to be pre-warned, countermeasures are taken in time, the probability of machine room equipment affected and failed is reduced, and normal operation of the machine room is guaranteed. At present, risk events are difficult to be monitored comprehensively, an early warning grade mechanism is lacked, and early warning informing personnel lack pertinence, so that early warning is easy to occur untimely, and emergency events are difficult to be found and processed in time.
Disclosure of Invention
The invention provides a data center grading early warning method, a data center grading early warning device and a storage medium, which are used for solving the problem that early warning is not timely due to incomplete monitoring of risk events and lack of an early warning grade mechanism, and carrying out grading early warning on a data center to timely discover and process emergency events.
In order to achieve the above object, an aspect of the present invention provides a data center hierarchical warning method, including:
constructing a risk event database;
crawling risk event information;
acquiring an associated risk event of a data center from the crawled risk event information, classifying the associated risk event through a trained classifier, inquiring the risk event database according to the category of the associated risk event, and acquiring the risk level of the associated risk event;
obtaining a characteristic value of the associated risk event according to the risk level of the associated risk event;
acquiring an early warning level corresponding to the characteristic value according to the risk event database;
and sending early warning information to the associated users of the associated risk events according to the early warning level.
Preferably, the training step of the classifier comprises:
obtaining a sample set, wherein the sample set comprises a feature vector of a risk event and a category label of the risk event;
dividing the sample set into a training set and a testing set according to a proportion;
training a neural network model by using the training set to obtain the classifier;
testing the accuracy of the classifier by using the test set, and finishing training if the accuracy is greater than or equal to a preset accuracy; if the accuracy is less than the preset accuracy, continuing training.
Preferably, the classifier classifies the associated risk event information according to the attribute of the associated risk event, and obtains the risk level of each type of the associated risk event, and different early warning identifiers are adopted for different risk levels.
Preferably, the step of sending warning information to the associated user of the associated risk event according to the warning level includes: sending early warning information to an early warning platform according to the early warning level; processing the received early warning information through the early warning platform; and sending the processed early warning information to the associated user through the early warning platform.
Preferably, the step of processing the received early warning information through the early warning platform includes: grouping the early warning information according to the early warning level; and respectively setting the sending time for each group of early warning information.
Preferably, the step of sending warning information to the associated user of the associated risk event according to the warning level includes:
sending early warning information to an early warning platform according to the early warning level; determining a corresponding set of early warning notification types according to early warning information and corresponding early warning levels, wherein the set of early warning notification types comprises a plurality of different early warning notification types, each early warning notification type comprises an early warning notification mode and a plurality of notification objects which are associated with users and are divided by different priorities, and each early warning notification mode at least comprises one characteristic item; extracting a characteristic value corresponding to the characteristic item from the early warning information according to the characteristic item; and determining an early warning notification type matched with the early warning information in the set according to the extracted characteristic value, and sending the early warning information to a notification object of a first priority associated user in the early warning notification type.
Preferably, after the step of sending the warning information to the notification object of the first priority associated user, the method further includes: judging whether the early warning platform receives feedback information of a notification object within a set time period, and if the early warning platform receives the feedback information, finishing the early warning; and if the feedback information is not received, sending early warning information to a notification object of a user associated with the next priority in the matched early warning notification type.
In order to achieve the above object, another aspect of the present invention provides an electronic device, including: a processor; a memory, wherein the memory includes a data center grading early warning program, and when executed by the processor, the data center grading early warning program implements the steps of the data center grading early warning method as described above:
constructing a risk event database;
crawling risk event information;
acquiring a relevant risk event of a data center from the crawled risk event information, classifying the relevant risk event through a trained classifier, inquiring the risk event database according to the category of the relevant risk event, and acquiring the risk level of the relevant risk event;
obtaining a characteristic value of the associated risk event according to the risk level of the associated risk event;
acquiring an early warning level corresponding to the characteristic value according to the risk event database;
and sending early warning information to the associated users of the associated risk events according to the early warning level.
Preferably, the training step of the classifier comprises:
obtaining a sample set, wherein the sample set comprises a feature vector of a risk event and a category label of the risk event;
dividing the sample set into a training set and a testing set according to a proportion;
training a neural network model by using the training set to obtain the classifier;
testing the accuracy of the classifier by using the test set, and finishing training if the accuracy is greater than or equal to a preset accuracy; if the accuracy is less than the preset accuracy, continuing training.
In order to achieve the above object, a further aspect of the present invention provides a computer-readable storage medium including a data center rating warning program, where the data center rating warning program, when executed by a processor, implements the steps of the data center rating warning method as described above.
Compared with the prior art, the invention has the following advantages and beneficial effects:
according to the method and the system, the risk events are monitored comprehensively by crawling risk event information, the risk events closely associated with the data center are filtered, different risk levels are set for different risk events, corresponding characteristic values and early warning levels are determined according to the risk levels, early warning is given to the users according to the early warning levels, so that early warning informing personnel have pertinence, the early warning accuracy and the early warning efficiency of the risk events are improved, the associated users can take corresponding countermeasures conveniently, the emergency events can be found and processed in time, and loss is reduced.
Drawings
FIG. 1 is a schematic flow chart of a data center grading early warning method according to the present invention;
fig. 2 is a schematic block diagram of a data center hierarchical warning program according to the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
The embodiments of the present invention will be described below with reference to the accompanying drawings. Those of ordinary skill in the art will recognize that the described embodiments can be modified in various different ways, or combinations thereof, without departing from the spirit and scope of the present invention. Accordingly, the drawings and description are illustrative in nature and are only intended to illustrate the invention and not to limit the scope of the claims. Furthermore, in the present description, the drawings are not to scale and like reference numerals refer to like parts.
Fig. 1 is a schematic flow chart of a data center grading early warning method according to the present invention, and as shown in fig. 1, the data center grading early warning method according to the present invention includes the following steps:
step S1, constructing a risk event database;
step S2, risk event information is crawled;
step S3, acquiring the associated risk events of the data center from the crawled risk event information, classifying the associated risk events through a trained classifier, inquiring the risk event database according to the categories of the associated risk events, and acquiring the risk levels of the associated risk events;
step S4, obtaining a characteristic value of the associated risk event according to the risk level of the associated risk event;
s5, acquiring an early warning level corresponding to the characteristic value according to the risk event database;
and step S6, sending early warning information to the associated users of the associated risk events according to the early warning levels.
According to the invention, the risk event is comprehensively monitored by crawling risk event information, the risk events closely associated with the data center are filtered out, different risk levels are set for different risk events, corresponding characteristic values and early warning levels are determined according to the risk levels, and early warning is given to the user according to the early warning levels, so that early warning informing personnel have pertinence, the early warning accuracy of the risk event and the early warning efficiency of the risk are improved, the associated user can conveniently take corresponding countermeasures, and the loss is reduced.
In the present invention, a risk event refers to an event that may have a significant impact on the network, business, environment, operation, etc. involved in the data center, and includes, but is not limited to, events such as major conferences, sporting events, social risks, emergency events, extreme weather, natural disasters, major public health, etc. The risk event database comprises the attributes, the categories, the risk levels, the early warning levels, the associated users and the like of risk events, wherein the risk events are classified according to the attributes of the risk events, each category of risk events corresponds to a plurality of risk levels (for example, the risk levels can comprise outage, network operation prohibition and the like), each risk level corresponds to a plurality of early warning levels (for example, the risk levels can be divided into first-level early warning, second-level early warning, third-level early warning and the like, the first-level early warning represents that the influence time is 1-6 hours, the second-level early warning represents that the influence time is 6-12 hours, the third-level early warning represents that the influence time is 12-24 hours and the like), the early warning levels respectively correspond to different characteristic value threshold ranges, the corresponding early warning levels can be obtained according to the sizes of the characteristic values, and early warning is performed on the associated users of the associated risk events. The different types of risk events have different standards for setting risk levels, and the corresponding early warning levels are different. In the present invention, only some examples of risk levels and warning levels are listed, and the present invention is not limited thereto.
According to the method, the risk event information is crawled through channels such as a meteorological data station, a portal medium, a work and trust department, a public security department, a health department, an emergency early warning platform and the like, and the crawled events are filtered to obtain the associated risk event information related to a data center.
In the invention, the classifier is used for classifying the associated risk events so as to determine the risk level according to the category of the associated risk events, thereby determining the early warning level according to the risk level. Preferably, the training step of the classifier comprises:
acquiring a sample set, wherein the sample set comprises a characteristic vector and a category label of a risk event, extracting a corresponding characteristic vector from each risk event, and determining the category label of the risk event according to the attribute of the risk event;
dividing the sample set into a training set and a test set according to a proportion, wherein the division proportion of the training set and the test set is actually determined according to the number of samples in the sample set;
training a neural network model by using the training set to obtain the classifier;
in order to ensure the accuracy of the classifier for classifying the risk events, the accuracy of the classifier needs to be verified, the accuracy of the classifier is tested by using the test set, and if the accuracy is greater than or equal to the preset accuracy, the training is finished; if the accuracy is less than the preset accuracy, continuing training, wherein the preset accuracy can be 90% or 95%.
And inputting the associated risk events into a classifier, obtaining the probability of each class label corresponding to the associated risk events, and selecting the class label with the highest probability as the class label of the associated risk events so as to determine the class of the associated risk events.
For different types of risk events, the risk events have different influences, the standards for setting the risk levels are different, and the corresponding early warning levels are also different. For example, in the event of a natural disaster, a sports event, or the like, the risk level set is different depending on the influence on the user, and in the event of a natural disaster, it may be necessary to perform power outage and network disconnection for a long time to maintain the server device or the like, whereas in the event of a sports event, it is sufficient to perform power outage and network disconnection for a short time.
In an embodiment of the present invention, the classifier classifies the associated risk event information according to the attribute of the associated risk event, and obtains the risk level of each type of the associated risk event, and different early warning identifiers are used for different risk levels, so that the risk level of the risk event can be identified by the early warning identifier.
In the invention, various modes of sending the early warning information according to the early warning level are provided. In one embodiment, the step of sending warning information to the associated user of the associated risk event according to the warning level includes: sending early warning information to an early warning platform according to the early warning level; receiving early warning information through the early warning platform; processing the received early warning information through the early warning platform; and sending the processed early warning information to the associated user through the early warning platform. All the early warning information is sent and received through the same early warning platform, and the early warning information is processed in a unified mode, so that the accuracy of early warning is improved, and repeated early warning is avoided.
Further, the step of processing the received early warning information through the early warning platform includes: grouping the early warning information according to the early warning level; and respectively setting sending time for each group of early warning information so as to send the early warning information to the associated user within the preset sending time and decompose the information transmission pressure of the early warning platform. The sending time can be determined according to the risk level and the emergency degree of the early warning information, and therefore the processing is carried out in sequence according to the emergency degree of the early warning.
In an embodiment of the present invention, the data center grading early warning method further includes: and acquiring the association degree of the associated risk event and the user, determining the priority of the associated user according to the association degree, and sending the early warning information according to the priority so as to avoid mistaken sending or missed sending of the early warning information. For example, a user in a certain area range is determined as a related user according to the place of the risk event, the degree of association between the risk event and the user is measured according to the distance between the place of the risk event and the location of the related user, and the smaller the distance is, the greater the degree of association is. For example, if a major conference is opened in beijing, users in areas around beijing (such as tianjin and corridor) are associated users, the closer to beijing, the greater the association degree, and the users in areas such as guangdong and shenzhen are non-associated users.
The early warning platform determines different early warning modes according to different early warning information, for example, different early warning notification modes (including short message service notification, mail notification, and the like) are set, notification objects (associated users are divided into different priorities according to different job responsibilities of workers, and the notification objects are short message clients, WeChat clients, mail clients, and the like) are set, notification frequency (different notification frequencies are set according to the early warning levels, and the higher the early warning level is, the higher the notification frequency is, for example, notification is performed once every 1 hour or two hours, and the like) is set, and the like. Preferably, the step of sending warning information to the associated user of the associated risk event according to the warning level includes: sending early warning information to an early warning platform according to the early warning level; determining a corresponding set of early warning notification types according to early warning information and corresponding early warning levels, wherein the set of early warning notification types comprises a plurality of different early warning notification types, each early warning notification type comprises an early warning notification mode and a plurality of notification objects which are associated with users and are divided by different priorities, and each early warning notification mode at least comprises one characteristic item; extracting a characteristic value corresponding to the characteristic item from the early warning information according to the characteristic item; judging whether the early warning information is matched with the early warning notification types in the set or not according to the extracted characteristic value; and determining the matched early warning notification type, and sending early warning information to a notification object of a first priority associated user in the early warning notification type.
Further, preferably, after the step of sending the warning information to the notification object of the first priority associated user, the method further includes: judging whether the early warning platform receives feedback information of a notification object within a set time period, and if the early warning platform receives the feedback information, finishing the early warning; and if the feedback information is not received, sending early warning information to a notification object of a next priority associated user in the matched early warning notification type so as to ensure that the notification object can obtain the early warning information and relevant personnel can take measures in time according to the early warning information. For example, if the early warning platform does not receive the feedback information of the first priority associated user, the early warning platform sends early warning information to a notification object of a second priority associated user, which is next to the first priority, and if the early warning platform does not receive the feedback information of the second priority associated user, the early warning platform continues to send early warning information to a notification object of a third priority associated user, which is next to the second priority, and so on until the early warning platform receives the feedback information, or until the early warning platform sends early warning information to the notification objects of all associated users in the early warning notification type.
Preferably, the early warning information includes one or more of early warning time, early warning identification, early warning reason and early warning level.
The data center grading early warning method is applied to an electronic device, and the electronic device can be a television, a smart phone, a tablet personal computer, a computer and other terminal equipment.
The electronic device includes: a processor; the processor executes the data center grading early warning program to realize the following steps of the data center grading early warning method:
constructing a risk event database;
crawling risk event information;
acquiring a relevant risk event of a data center from the crawled risk event information, classifying the relevant risk event through a trained classifier, inquiring the risk event database according to the category of the relevant risk event, and acquiring the risk level of the relevant risk event;
obtaining a characteristic value of the associated risk event according to the risk level of the associated risk event;
acquiring an early warning level corresponding to the characteristic value according to the risk event database;
and sending early warning information to the associated users of the associated risk events according to the early warning level.
The electronic device further comprises a network interface, a communication bus and the like. The network interface may include a standard wired interface and a standard wireless interface, and the communication bus is used for realizing connection and communication among the components.
The memory includes at least one type of readable storage medium, which may be a non-volatile storage medium such as a flash memory, a hard disk, an optical disk, etc., or a plug-in hard disk, etc., and is not limited thereto, and may be any device that stores instructions or software and any associated data files in a non-transitory manner and provides instructions or software programs to the processor to enable the processor to execute the instructions or software programs. In the invention, the software program stored in the memory comprises a data center grading early warning program and can provide the data center grading early warning program for the processor, so that the processor can execute the data center grading early warning program to realize the steps of the data center grading early warning method.
The processor may be a central processing unit, a microprocessor or other data processing chip, etc., and may run a stored program in the memory, for example, to execute the data center hierarchical warning program in the present invention.
The electronic device may further comprise a display, which may also be referred to as a display screen or display unit. In some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an Organic Light-Emitting Diode (OLED) touch panel, or the like. The display is used for displaying information processed in the electronic device and for displaying a visual work interface, for example, warning information may be displayed.
The electronic device may further comprise a user interface which may comprise an input unit, such as a keyboard, a speech output device, such as a sound, a headset, etc.
In the invention, the classifier is used for classifying the associated risk events so as to determine the risk level according to the category of the associated risk events, thereby determining the early warning level according to the risk level. Preferably, the training step of the classifier comprises:
acquiring a sample set, wherein the sample set comprises a characteristic vector and a category label of a risk event, extracting a corresponding characteristic vector from each risk event, and determining the category label of the risk event according to the attribute of the risk event;
dividing the sample set into a training set and a test set according to a proportion, wherein the division proportion of the training set and the test set is actually determined according to the number of samples in the sample set;
training a neural network model by using the training set to obtain the classifier;
in order to ensure the accuracy of the classifier for classifying the risk events, the accuracy of the classifier needs to be verified, the accuracy of the classifier is tested by using the test set, and if the accuracy is greater than or equal to the preset accuracy, the training is finished; if the accuracy is less than the preset accuracy, continuing training, wherein the preset accuracy can be 90% or 95%.
And inputting the associated risk events into a classifier, obtaining the probability of each class label corresponding to the associated risk events, and selecting the class label with the highest probability as the class label of the associated risk events so as to determine the class of the associated risk events.
For different types of risk events, the risk events have different influences, the standards for setting the risk levels are different, and the corresponding early warning levels are also different. For example, in the event of a natural disaster, a sports event, or the like, the risk level set is different depending on the influence on the user, and in the event of a natural disaster, it may be necessary to perform power outage and network disconnection for a long time to maintain the server device or the like, whereas in the event of a sports event, it is sufficient to perform power outage and network disconnection for a short time.
In an embodiment of the present invention, the classifier classifies the associated risk event information according to the attribute of the associated risk event, and obtains the risk level of each type of the associated risk event, and different early warning identifiers are used for different risk levels, so that the risk level of the risk event can be identified by the early warning identifier.
In the invention, the electronic device sends the early warning information according to the early warning level in various ways. In one embodiment, the step implemented by the electronic device of sending alert information to the associated user of the associated risk event according to the alert level comprises: sending early warning information to an early warning platform according to the early warning level; receiving early warning information through the early warning platform; processing the received early warning information through the early warning platform; and sending the processed early warning information to the associated user through the early warning platform. All the early warning information is sent through the same early warning platform, and the early warning information is processed in a unified mode, so that the accuracy of early warning is improved, and repeated early warning is avoided.
Further, the step of processing the received early warning information through the early warning platform includes: grouping the early warning information according to the early warning level; and respectively setting sending time for each group of early warning information so as to send the early warning information to the associated user within the preset sending time and decompose the information transmission pressure of the early warning platform. The sending time can be determined according to the risk level and the emergency degree of the early warning information, so that risks are sequentially processed according to the emergency degree of the early warning.
In an embodiment of the present invention, the processor executing the data center line hierarchical warning program may further implement the following steps of the data center hierarchical warning method: and acquiring the association degree of the associated risk event and the user, determining the priority of the associated user according to the association degree, and sending early warning information according to the priority so as to avoid mistaken sending or missed sending of the early warning information. For example, a user in a certain area range is determined as a related user according to the place of the risk event, the degree of association between the risk event and the user is measured according to the distance between the place of the risk event and the location of the related user, and the smaller the distance is, the greater the degree of association is. For example, if a major conference is opened in beijing, users in areas around beijing are related users, the closer to beijing, the greater the degree of association, and users in areas such as guangdong and shenzhen are unrelated users.
The early warning platform determines different early warning modes according to different early warning information, for example, different early warning notification modes (including short message service notification, mail notification, and the like) are set, notification objects (associated users are divided into different priorities according to different job responsibilities of workers, and the notification objects are short message clients, WeChat clients, mail clients, and the like) are set, notification frequency (different notification frequencies are set according to the early warning levels, and the higher the early warning level is, the higher the notification frequency is, for example, notification is performed once every 1 hour or two hours, and the like) is set, and the like. Preferably, the step of sending, by the electronic device, the warning information to the associated user of the associated risk event according to the warning level includes: sending early warning information to an early warning platform according to the early warning level; receiving early warning information and corresponding early warning levels through an early warning platform; determining a corresponding set of early warning notification types according to early warning information and corresponding early warning levels, wherein the set of early warning notification types comprises a plurality of different early warning notification types, each early warning notification type comprises an early warning notification mode and a plurality of notification objects which are associated with users and are divided by different priorities, and each early warning notification mode at least comprises one characteristic item; extracting a characteristic value corresponding to the characteristic item from the early warning information according to the characteristic item; judging whether the early warning information is matched with the early warning notification types in the set or not according to the extracted characteristic value; and determining the matched early warning notification type, and sending early warning information to a notification object of a first priority associated user in the early warning notification type.
Further, preferably, after the step of sending the warning information to the notification object of the first priority associated user, the method further includes: judging whether the early warning platform receives feedback information of a notification object within a set time period, and if the early warning platform receives the feedback information, finishing the early warning; and if the feedback information is not received, sending early warning information to a notification object of a next priority associated user in the matched early warning notification type so as to ensure that the notification object can obtain the early warning information and relevant personnel can take measures in time according to the early warning information. For example, if the early warning platform does not receive the feedback information of the first priority associated user, the early warning platform sends early warning information to a notification object of a second priority associated user, which is next to the first priority, and if the early warning platform does not receive the feedback information of the second priority associated user, the early warning platform continues to send early warning information to a notification object of a third priority associated user, which is next to the second priority, and so on until the early warning platform receives the feedback information, or until the early warning platform sends early warning information to the notification objects of all associated users in the early warning notification type.
Preferably, the early warning information includes one or more of early warning time, early warning identification, early warning reason and early warning level.
In other embodiments, the data center hierarchical early warning program may also be partitioned into one or more modules, which are stored in the memory and executed by the processor to implement the present invention. The modules referred to herein are referred to as a series of computer program instruction segments capable of performing specified functions.
Fig. 2 is a schematic block diagram of a hierarchical early warning program of a data center according to the present invention, and as shown in fig. 2, the hierarchical early warning program of the data center may be divided into: the system comprises a database construction module 1, a crawling module 2, a risk level determination module 3, a characteristic value extraction module 4, an early warning level determination module 5 and a sending module 6. The functions or operation steps implemented by the modules are similar to those of the above, and are not detailed here, for example, where:
the database construction module 1 is used for constructing a risk event database;
the crawling module 2 is used for crawling risk event information;
the risk level determining module 3 is used for acquiring the associated risk events of the data center from the crawled risk event information, classifying the associated risk events through a trained classifier, inquiring the risk event database according to the categories of the associated risk events, and acquiring the risk levels of the associated risk events;
the characteristic value extraction module 4 is used for obtaining the characteristic value of the associated risk event according to the risk level of the associated risk event;
the early warning level determining module 5 is used for acquiring an early warning level corresponding to the characteristic value according to the risk event database;
and the sending module 6 is used for sending early warning information to the associated users of the associated risk events according to the early warning levels.
In one embodiment of the invention, a computer readable storage medium may be any tangible medium that can contain, or store a program or instructions, where the program can be executed to implement corresponding functions via hardware associated with stored program instructions. For example, the computer readable storage medium may be a computer diskette, hard disk, random access memory, read only memory, or the like. The invention is not so limited and can be any means that stores the instructions or software and any associated data files or data structures in a non-transitory manner and that can be provided to a processor to cause the processor to execute the programs or instructions therein. The computer readable storage medium comprises a data center grading early warning program, and when the data center grading early warning program is executed by a processor, the data center grading early warning method is realized as follows:
constructing a risk event database;
crawling risk event information;
acquiring a relevant risk event of a data center from the crawled risk event information, classifying the relevant risk event through a trained classifier, inquiring the risk event database according to the category of the relevant risk event, and acquiring the risk level of the relevant risk event;
obtaining a characteristic value of the associated risk event according to the risk level of the associated risk event;
acquiring an early warning level corresponding to the characteristic value according to the risk event database;
and sending early warning information to the associated users of the associated risk events according to the early warning level.
The specific implementation of the computer-readable storage medium of the present invention is substantially the same as the above-mentioned data center hierarchical warning method and the electronic device, and will not be described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments. Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (5)
1. A data center grading early warning method is applied to an electronic device and is characterized by comprising the following steps:
constructing a risk event database; the risk event database comprises the attributes, the categories, the risk levels, the early warning levels and associated users of risk events, wherein the risk events are classified according to the attributes of the risk events, each category of risk events corresponds to a plurality of risk levels, each risk level corresponds to a plurality of early warning levels, the early warning levels correspond to different characteristic value threshold ranges respectively, and the corresponding early warning levels can be obtained according to the sizes of the characteristic values; the different types of risk events have different standards for setting risk levels, and the corresponding early warning levels are different;
crawling risk event information;
acquiring an associated risk event of a data center from the crawled risk event information, classifying the associated risk event through a trained classifier, inquiring the risk event database according to the category of the associated risk event, and acquiring the risk level of the associated risk event; the classifier classifies the associated risk event information according to the attributes of the associated risk events, obtains the risk level of each type of the associated risk events, and adopts different early warning identifications for different risk levels;
the training step of the classifier comprises the following steps:
obtaining a sample set, wherein the sample set comprises a feature vector of a risk event and a category label of the risk event; dividing the sample set into a training set and a testing set according to a proportion; training a neural network model by using the training set to obtain the classifier; testing the accuracy of the classifier by using the test set, and finishing training if the accuracy is greater than or equal to a preset accuracy; if the accuracy is less than the preset accuracy, continuing training; the preset accuracy is 90% or 95%;
obtaining a characteristic value of the associated risk event according to the risk level of the associated risk event;
acquiring an early warning level corresponding to the characteristic value according to the risk event database;
sending early warning information to the associated users of the associated risk events according to the early warning level; the step of sending early warning information to the associated user of the associated risk event according to the early warning level comprises:
sending early warning information to an early warning platform according to the early warning level;
processing the received early warning information through the early warning platform;
sending the processed early warning information to the associated user through the early warning platform; or
The step of sending early warning information to the associated user of the associated risk event according to the early warning level comprises:
sending early warning information to an early warning platform according to the early warning level;
determining a corresponding set of early warning notification types according to early warning information and corresponding early warning levels, wherein the set of early warning notification types comprises a plurality of different early warning notification types, each early warning notification type comprises an early warning notification mode and a plurality of notification objects which are associated with users and are divided by different priorities, and each early warning notification mode at least comprises one characteristic item;
extracting a characteristic value corresponding to the characteristic item from the early warning information according to the characteristic item;
and determining an early warning notification type matched with the early warning information in the set according to the extracted characteristic value, and sending the early warning information to a notification object of a first priority associated user in the early warning notification type.
2. The hierarchical pre-warning method for the data center according to claim 1, wherein the step of processing the received pre-warning information through the pre-warning platform comprises: grouping the early warning information according to the early warning level; and respectively setting the sending time for each group of early warning information.
3. The data center grading early warning method according to claim 2, wherein after the step of sending early warning information to the notification object of the first priority associated user, the method further comprises: judging whether the early warning platform receives feedback information of a notification object within a set time period, and if the early warning platform receives the feedback information, finishing the early warning; and if the feedback information is not received, sending early warning information to a notification object of a user associated with the next priority in the matched early warning notification type.
4. An electronic device, comprising:
a processor;
a memory, wherein the memory includes a data center grading early warning program, and the data center grading early warning program, when executed by the processor, implements the following steps of the data center grading early warning method:
constructing a risk event database; the risk event database comprises the attributes, the categories, the risk levels, the early warning levels and associated users of risk events, wherein the risk events are classified according to the attributes of the risk events, each category of risk events corresponds to a plurality of risk levels, each risk level corresponds to a plurality of early warning levels, the early warning levels correspond to different characteristic value threshold ranges respectively, and the corresponding early warning levels can be obtained according to the sizes of the characteristic values; the different types of risk events have different standards for setting risk levels, and the corresponding early warning levels are different;
crawling risk event information;
acquiring an associated risk event of a data center from the crawled risk event information, classifying the associated risk event through a trained classifier, inquiring the risk event database according to the category of the associated risk event, and acquiring the risk level of the associated risk event; the classifier classifies the associated risk event information according to the attributes of the associated risk events, obtains the risk level of each type of the associated risk events, and adopts different early warning identifications for different risk levels;
the training step of the classifier comprises the following steps:
obtaining a sample set, wherein the sample set comprises a feature vector of a risk event and a category label of the risk event; dividing the sample set into a training set and a testing set according to a proportion; training a neural network model by using the training set to obtain the classifier; testing the accuracy of the classifier by using the test set, and finishing training if the accuracy is greater than or equal to a preset accuracy; if the accuracy is less than the preset accuracy, continuing training; the preset accuracy is 90% or 95%;
obtaining a characteristic value of the associated risk event according to the risk level of the associated risk event;
acquiring an early warning level corresponding to the characteristic value according to the risk event database;
sending early warning information to the associated users of the associated risk events according to the early warning level; the step of sending early warning information to the associated user of the associated risk event according to the early warning level comprises:
sending early warning information to an early warning platform according to the early warning level;
processing the received early warning information through the early warning platform;
sending the processed early warning information to the associated user through the early warning platform; or
The step of sending early warning information to the associated user of the associated risk event according to the early warning level comprises:
sending early warning information to an early warning platform according to the early warning level;
determining a corresponding set of early warning notification types according to early warning information and corresponding early warning levels, wherein the set of early warning notification types comprises a plurality of different early warning notification types, each early warning notification type comprises an early warning notification mode and a plurality of notification objects which are associated with users and are divided by different priorities, and each early warning notification mode at least comprises one characteristic item;
extracting a characteristic value corresponding to the characteristic item from the early warning information according to the characteristic item;
and determining an early warning notification type matched with the early warning information in the set according to the extracted characteristic value, and sending the early warning information to a notification object of a first priority associated user in the early warning notification type.
5. A computer-readable storage medium, comprising a data center rating pre-warning program, wherein the data center rating pre-warning program, when executed by a processor, implements the steps of the data center rating pre-warning method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811479955.4A CN109840183B (en) | 2018-12-05 | 2018-12-05 | Data center grading early warning method and device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811479955.4A CN109840183B (en) | 2018-12-05 | 2018-12-05 | Data center grading early warning method and device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109840183A CN109840183A (en) | 2019-06-04 |
| CN109840183B true CN109840183B (en) | 2022-07-08 |
Family
ID=66883164
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811479955.4A Active CN109840183B (en) | 2018-12-05 | 2018-12-05 | Data center grading early warning method and device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109840183B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110348806A (en) * | 2019-06-26 | 2019-10-18 | 阿里巴巴集团控股有限公司 | The method and apparatus of solution of emergent event |
| CN110855703A (en) * | 2019-11-22 | 2020-02-28 | 秒针信息技术有限公司 | Intelligent risk identification system and method and electronic equipment |
| CN111369107A (en) * | 2020-02-18 | 2020-07-03 | 平安科技（深圳）有限公司 | Object risk early warning method, management terminal and storage medium |
| CN111552857B (en) * | 2020-05-06 | 2023-09-19 | 支付宝(杭州)信息技术有限公司 | Feature event identification method and device, electronic equipment and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107070680A (en) * | 2016-12-02 | 2017-08-18 | 国家电网公司 | A kind of intelligent operational system of IT information machine rooms and method |
| CN106856508A (en) * | 2017-02-08 | 2017-06-16 | 北京百度网讯科技有限公司 | The cloud monitoring method and cloud platform of data center |
| CN107247653A (en) * | 2017-06-02 | 2017-10-13 | 郑州云海信息技术有限公司 | A kind of Fault Classification and device of data center's monitoring system |
| CN107463963A (en) * | 2017-08-10 | 2017-12-12 | 郑州云海信息技术有限公司 | A kind of Fault Classification and device |
| CN107608866A (en) * | 2017-08-22 | 2018-01-19 | 深圳企管加企业服务有限公司 | Calculator room equipment fault early warning method, device and storage medium based on Internet of Things |
-
2018
- 2018-12-05 CN CN201811479955.4A patent/CN109840183B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109840183A (en) | 2019-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109840183B (en) | Data center grading early warning method and device and storage medium | |
| CN107566358B (en) | Risk early warning prompting method, device, medium and equipment | |
| CN104346566A (en) | Method, device, terminal, server and system for detecting privacy authority risks | |
| CN112052111B (en) | Processing method, device and equipment for server abnormity early warning and storage medium | |
| CN105989144A (en) | Notification message management method, apparatus and system as well as terminal device | |
| CN106648698A (en) | Method and device for displaying message notification and electronic equipment | |
| US9418354B2 (en) | Facilitating user incident reports | |
| CN111934899A (en) | Configuration method and device of user information of Internet of things and computer equipment | |
| CN104092577A (en) | Network alarm notifying system and notifying method thereof | |
| CN112395351A (en) | Visual identification group complaint risk method, device, computer equipment and medium | |
| CN111371581A (en) | Method, device, equipment and medium for detecting business abnormity of Internet of things card | |
| CN113672475A (en) | Alarm processing method and device, computer equipment and storage medium | |
| CN106155000A (en) | The processing method and processing device of the board warning information of semiconductor board | |
| CN110009473B (en) | Data processing method, device, equipment and storage medium | |
| CN111858236A (en) | Knowledge graph monitoring method and device, computer equipment and storage medium | |
| CN107818419B (en) | Method and device for determining function test range | |
| KR101462858B1 (en) | Methods for competency assessment of corporation for global business | |
| CN110909129B (en) | Abnormal complaint event identification method and device | |
| CN114329164A (en) | Method, apparatus, device, medium and product for processing data | |
| CN110677271B (en) | Big data alarm method, device, equipment and storage medium based on ELK | |
| CN110288467B (en) | Data mining method and device, electronic equipment and storage medium | |
| CN106547679B (en) | Script management method and script management platform | |
| CN109246718B (en) | Terminal user behavior monitoring method and device | |
| CN109598485A (en) | A kind of emergency event report thing method and device | |
| CN113095788B (en) | Problem distribution method, device, electronic equipment and storage medium |
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 |