CN117714453A - Intelligent device management method and system based on Internet of things card - Google Patents
Intelligent device management method and system based on Internet of things card Download PDFInfo
- Publication number
- CN117714453A CN117714453A CN202410160659.7A CN202410160659A CN117714453A CN 117714453 A CN117714453 A CN 117714453A CN 202410160659 A CN202410160659 A CN 202410160659A CN 117714453 A CN117714453 A CN 117714453A
- Authority
- CN
- China
- Prior art keywords
- fault
- server
- service
- management
- servers
- 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
Links
- 238000007726 management method Methods 0.000 title claims abstract description 141
- 238000012795 verification Methods 0.000 claims abstract description 78
- 238000012544 monitoring process Methods 0.000 claims abstract description 44
- 238000000034 method Methods 0.000 claims abstract description 24
- 238000004364 calculation method Methods 0.000 claims abstract description 15
- 230000003213 activating effect Effects 0.000 claims abstract description 11
- 238000012360 testing method Methods 0.000 claims description 70
- 230000002159 abnormal effect Effects 0.000 claims description 55
- 238000013507 mapping Methods 0.000 claims description 22
- 238000011156 evaluation Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 12
- 230000004927 fusion Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 238000012512 characterization method Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 7
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000005856 abnormality Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
- H04L67/1008—Server selection for load balancing based on parameters of servers, e.g. available memory or workload
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0677—Localisation of faults
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/16—Threshold monitoring
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses an intelligent device management method and system based on an Internet of things card, and relates to the field of artificial intelligence, wherein the method comprises the following steps: traversing M servers to perform fault pre-verification, and activating a system monitoring module of an enterprise management platform of the Internet of things card to obtain M service request sets corresponding to the M servers when a fault pre-verification result is passed; according to the load degree analyzer, carrying out service load degree identification on M servers through M service request sets and M device feature sets to obtain M service load degrees; performing overload duty ratio calculation on M service load degrees based on M load degree constraints to obtain an overload coefficient; and if the overload factor is greater than/equal to the preset overload factor, executing server addition management of the target enterprise according to the addition service instruction. The technical problems of poor server management effect of enterprises caused by low management adaptability and poor accuracy of the server additionally arranged for the enterprises in the prior art are solved.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to an intelligent device management method and system based on an Internet of things card.
Background
Servers are one of the important devices of modern enterprises. The server can provide stable, efficient and reliable calculation and service support for enterprises, so that the enterprises are helped to improve the working efficiency, and meanwhile, the data security of the enterprises is ensured, the business process of the enterprises is optimized, and the collaborative office capacity of the enterprises is improved.
In the prior art, the technical problems of poor management effect of the server of the enterprise caused by low management adaptability and poor accuracy of the server additionally arranged to the enterprise exist.
Disclosure of Invention
The application provides an intelligent device management method and system based on an Internet of things card. The technical problems of poor server management effect of enterprises caused by low management adaptability and poor accuracy of the server additionally arranged for the enterprises in the prior art are solved. The method and the device have the advantages that the server adding management adaptability and accuracy of an enterprise are improved, meanwhile, the request switching timeliness of the enterprise server is improved, the communication service availability of the enterprise is effectively guaranteed, and the server management quality of the enterprise is improved.
In view of the above problems, the present application provides an intelligent device management method and system based on an internet of things card.
In a first aspect, the present application provides an intelligent device management method based on an internet of things card, where the method is applied to an intelligent device management system based on an internet of things card, and the method includes: the resource management module of the internet of things card enterprise management platform is interacted to obtain M device feature sets corresponding to M servers of a target enterprise, wherein M is a positive integer greater than 1; traversing the M servers to perform fault pre-verification based on a pre-constructed fault pre-verifier to obtain a fault pre-verification result; when the failure pre-verification result is passed, obtaining a request mapping instruction; based on the request mapping instruction, activating a system monitoring module of the internet of things card enterprise management platform to obtain M service request sets corresponding to the M servers; constructing a load degree analyzer based on a pre-constructed network evaluation function; according to the load degree analyzer, carrying out service load degree identification on the M servers through the M service request sets and the M device feature sets to obtain M service load degrees; obtaining M load degree constraints corresponding to the M servers, and performing overload duty ratio calculation on the M service load degrees based on the M load degree constraints to obtain an overload coefficient; judging whether the overload factor is smaller than a preset overload factor or not; and if the overload factor is greater than or equal to the preset overload factor, obtaining an additional service instruction, and executing server additional management of the target enterprise according to the additional service instruction.
In a second aspect, the present application further provides an intelligent device management system based on an internet of things card, where the system includes: the device feature interaction module is used for interacting the resource management module of the internet of things card enterprise management platform to obtain M device feature sets corresponding to M servers of a target enterprise, wherein M is a positive integer greater than 1; the fault pre-checking module is used for traversing the M servers to perform fault pre-checking based on a pre-constructed fault pre-checker to obtain a fault pre-checking result; the mapping instruction generation module is used for obtaining a request mapping instruction when the failure pre-verification result is passing; the service request acquisition module is used for activating a system monitoring module of the internet of things card enterprise management platform based on the request mapping instruction to acquire M service request sets corresponding to the M servers; the construction module is used for constructing a load degree analyzer based on a pre-constructed network evaluation function; the service load degree identification module is used for carrying out service load degree identification on the M servers through the M service request sets and the M device feature sets according to the load degree analyzer to obtain M service load degrees; the overload duty ratio calculation module is used for obtaining M load degree constraints corresponding to the M servers, and carrying out overload duty ratio calculation on the M service load degrees based on the M load degree constraints to obtain an overload coefficient; the judging module is used for judging whether the overload coefficient is smaller than a preset overload coefficient or not; and the additionally-arranged management module is used for obtaining an additionally-arranged service instruction if the overload coefficient is greater than/equal to the preset overload coefficient, and executing server additionally-arranged management of the target enterprise according to the additionally-arranged service instruction.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
obtaining M device feature sets corresponding to M servers of a target enterprise through a resource management module of an enterprise management platform of the internet of things card; traversing M servers to perform fault pre-verification to obtain a fault pre-verification result; when the failure pre-verification result is passed, activating a system monitoring module of an enterprise management platform of the Internet of things card to obtain M service request sets corresponding to M servers; according to the load degree analyzer, obtaining M service load degrees by carrying out service load degree identification on M service request sets and M device feature sets; performing overload duty ratio calculation on M service load degrees based on M load degree constraints to obtain an overload coefficient; if the overload factor is greater than/equal to the preset overload factor, obtaining an additional service instruction, and executing server additional management of the target enterprise according to the additional service instruction. The method and the device have the advantages that the server adding management adaptability and accuracy of an enterprise are improved, meanwhile, the request switching timeliness of the enterprise server is improved, the communication service availability of the enterprise is effectively guaranteed, and the server management quality of the enterprise is improved.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
In order to more clearly illustrate the technical solution of the embodiments of the present invention, the following description will briefly explain the drawings of the embodiments of the present invention. It is apparent that the figures in the following description relate only to some embodiments of the invention and are not limiting of the invention.
Fig. 1 is a flow chart of an intelligent device management method based on an internet of things card.
Fig. 2 is a schematic flow chart of generating an equalization switching instruction in the intelligent device management method based on the internet of things card.
Fig. 3 is a schematic structural diagram of an intelligent device management system based on an internet of things card.
Detailed Description
The application provides an intelligent device management method and system based on an Internet of things card. The technical problems of poor server management effect of enterprises caused by low management adaptability and poor accuracy of the server additionally arranged for the enterprises in the prior art are solved. The method and the device have the advantages that the server adding management adaptability and accuracy of an enterprise are improved, meanwhile, the request switching timeliness of the enterprise server is improved, the communication service availability of the enterprise is effectively guaranteed, and the server management quality of the enterprise is improved.
Example 1
Referring to fig. 1, the present application provides an intelligent device management method based on an internet of things card, wherein the method is applied to an intelligent device management system based on an internet of things card, the system is in communication connection with an internet of things card enterprise management platform, and the method specifically includes the following steps:
and interacting the resource management module of the enterprise management platform of the Internet of things card to obtain M device feature sets corresponding to M servers of a target enterprise, wherein M is a positive integer greater than 1.
An intelligent device management system based on an Internet of things card is in communication connection with an Internet of things card enterprise management platform. The internet of things card enterprise management platform is a comprehensive internet of things card management platform for operators and large enterprises. The internet of things card enterprise management platform supports direct docking of interface parameter forms, can realize functions of unified access, inquiry, card state management, charging statistics and the like of internet of things cards of different operators, and realizes efficient management and control through role authority and organization architecture functions. The enterprise management platform of the internet of things card comprises a resource management module, a communication management module, a fund management module, a system management module and a system monitoring module. The resource management module has the functions of carrying out the management of the operator channels, the configuration of channel access, the configuration of charging rules and the like on the users. The communication management module has the functions of carrying out information management, data operation management, batch inquiry management, data updating and the like on the card of the Internet of things for the user. The fund management module has the functions of price management, charging rule configuration, bill report form, data export and the like for the user. The system management module has the functions of user management, role management, menu management, department management and the like for users. The system monitoring module has the functions of performance monitoring, log management and the like.
The resource management module also has the functions of data storage and data query. And carrying out parameter query on M servers of the target enterprise through a resource management module to obtain M device feature sets. The target enterprise can use any enterprise of the internet of things card enterprise management platform. M is a positive integer greater than 1. Each equipment characteristic set comprises parameter information such as a model number, CPU frequency, CPU cache, main board parameters, internal hard disk digits, CD-ROM parameters, network controller parameters, power and the like corresponding to each server.
And traversing the M servers to perform fault pre-verification based on a pre-constructed fault pre-verifier to obtain a fault pre-verification result.
And carrying out random numbering on the M servers to obtain a first server and a second server … M-th server, wherein M is a positive integer, and M belongs to M.
And performing fault verification on the first server to obtain a first fault verification result.
And carrying out real-time state monitoring on the first server based on the system monitoring module to obtain a first state monitoring set.
And carrying out abnormal state identification on the first state monitoring set to obtain a first state abnormal coefficient.
And judging whether the first state anomaly coefficient is smaller than a preset anomaly coefficient.
If the first state anomaly coefficient is smaller than the preset anomaly coefficient, the obtained first fault checking result is passed.
If the first state abnormal coefficient is greater than or equal to the preset abnormal coefficient, the obtained first fault checking result is not passed.
And carrying out random numbering on the M servers to obtain a first server and a second server … mth server. And M is a positive integer, and M is M. And then, the system monitoring module also has the function of monitoring the server in real time. And carrying out real-time state monitoring on the first server through the system monitoring module to obtain a first state monitoring set. The first state monitoring set comprises a server real-time temperature, a server real-time noise, a server real-time operation parameter corresponding to the first server, a real-time environment temperature, a real-time environment humidity and the like corresponding to the first server.
And obtaining a first state anomaly coefficient by carrying out anomaly state identification on the first state monitoring set. The first state anomaly coefficient is data information for characterizing the degree of anomaly of the first state monitoring set. The greater the degree of abnormality of the first state monitoring set, the greater the degree of abnormality of the corresponding first server, and the greater the corresponding first state abnormality coefficient. For example, when the first state monitoring set is subjected to abnormal state identification, historical data query is performed according to the first state monitoring set, and an abnormal state identification library is obtained. The abnormal state identification library includes a plurality of sets of abnormal state identification data. Each group of abnormal state identification data comprises a historical state monitoring set and a historical state abnormal coefficient corresponding to the historical state monitoring set. And inputting the first state monitoring set into an abnormal state identification library, and carrying out abnormal coefficient matching on the first state monitoring set through the abnormal state identification library to obtain a first state abnormal coefficient.
Further, whether the first state anomaly coefficient is smaller than a preset anomaly coefficient is judged. The preset abnormal coefficient comprises a state abnormal coefficient threshold value preset and determined by the intelligent device management system based on the Internet of things card. If the first state anomaly coefficient is smaller than the preset anomaly coefficient, the obtained first fault checking result is passing. In contrast, if the first state anomaly coefficient is greater than/equal to the preset anomaly coefficient, the obtained first fault verification result is not passed.
And continuing to perform fault verification on the mth server of the second server … to obtain a second fault verification result … mth fault verification result.
The fault pre-verifier is constructed, wherein the fault pre-verifier comprises a fault pre-verifier, the fault pre-verifier is that when the first fault verification result and the second fault verification result … are all passed, the obtained fault pre-verifier is that the fault pre-verifier is passed, and when any one of the first fault verification result and the second fault verification result … is that the fault pre-verifier is not passed, the obtained fault pre-verifier is that the fault pre-verifier is not passed.
And inputting the first fault checking result, the second fault checking result … and the mth fault checking result into the fault pre-checker to generate the fault pre-checking result.
And continuing to perform fault verification on the m-th server of the second server … to obtain a second fault verification result … m-th fault verification result. And in the m-th fault verification result of the second fault verification result …, each fault verification result is pass/fail. The "failure check for the m-th server of the second server …" is the same as the "failure check for the first server", and will not be described here again.
Further, the first fault verification result and the second fault verification result … are input into a fault pre-verifier to generate a fault pre-verification result. Wherein the fault pre-verifier comprises a fault pre-verifier operator. The fault pre-checking operator is used for obtaining a fault pre-checking result which is passed when the first fault checking result and the m-th fault checking result of the second fault checking result … are all passed; when any one of the first fault checking result and the second fault checking result … mth fault checking result is failed, the obtained fault pre-checking result is failed. The failure pre-check results in pass/fail.
As shown in fig. 2, after generating the failure pre-verification result, the method further includes:
and when the failure pre-checking result is that the failure pre-checking result is not passed, generating an abnormal positioning instruction.
And based on the abnormal positioning instruction, performing abnormal positioning on the M servers according to the fault pre-verification result to obtain an abnormal server positioning result.
And generating an equalization switching instruction based on the abnormal server positioning result, and carrying out mapping switching of a load equalizer on the abnormal server positioning result according to the equalization switching instruction.
And when the failure pre-verification result is that the failure pre-verification result is not passed, the intelligent equipment management system based on the Internet of things card automatically generates an abnormal positioning instruction. The abnormal positioning instruction is instruction information used for representing that the obtained failure pre-verification result is failed and that M servers of a target enterprise need to be switched. And then, according to the abnormal positioning instruction, performing abnormal positioning on the M servers according to the failure pre-verification result, namely, when the failure pre-verification result is failed, setting the failed failure verification result as an abnormal failure verification result in the first failure verification result and the second failure verification result … mth failure verification result corresponding to the failure pre-verification result, and setting the server corresponding to the abnormal failure verification result as an abnormal server positioning result.
When an abnormal server positioning result is obtained, the intelligent device management system based on the Internet of things card automatically generates an equalization switching instruction, and service request switching is performed on the abnormal server positioning result through a load balancer according to the equalization switching instruction. Therefore, timeliness and timeliness of request switching of the enterprise server are improved, communication service availability of a target enterprise is guaranteed, server management quality of the enterprise is improved, and server extension analysis reliability of the enterprise is improved. The load balancer is a hardware device, and can be used for distributing service requests to M servers or balancing the service requests so as to improve the performance and response speed of the servers. The balancing switching instruction is instruction information for characterizing that a service request of an abnormal server positioning result needs to be switched to another server by the load balancer.
And when the failure pre-checking result is passing, obtaining a request mapping instruction.
And activating a system monitoring module of the enterprise management platform of the internet of things card based on the request mapping instruction to obtain M service request sets corresponding to the M servers.
When the failure pre-checking result is passed, obtaining a request mapping instruction, and activating a system monitoring module of the Internet of things card enterprise management platform according to the request mapping instruction to obtain M service request sets corresponding to the M servers. The request mapping instruction is instruction information used for representing that the failure pre-verification result is passing and service request acquisition needs to be carried out on M servers. The system monitoring module also has the function of collecting service requests of the M servers. Each service request set includes a plurality of real-time service requests corresponding to each server. For example, the plurality of real-time service requests include a real-time file storage request, a real-time file sharing request, a real-time data backup request, a real-time Web service request, a real-time communication service request, and the like.
And constructing a load degree analyzer based on a pre-constructed network evaluation function.
And obtaining a sample service load degree identification record library, and executing random division on the sample service load degree identification record library to obtain a first training data sequence and a first test data sequence.
And training a first service load degree identification network based on the first training data sequence.
And testing the first service load degree identification network according to the first test data sequence to obtain a plurality of test accuracy rates and a plurality of test error loss rates.
Based on big data, a plurality of groups of sample service load degree identification records are collected, and a sample service load degree identification record library is obtained. The sample service load degree identification record library comprises a plurality of groups of sample service load degree identification records. Each group of sample service load degree identification records comprise a history service request set, a history equipment characteristic set and a history service load degree corresponding to the history server. Then, the service load degree identification record base is randomly divided, for example, 80% of the random data information in the service load degree identification record base is divided into a first training data sequence, and 20% of the random data information in the service load degree identification record base is divided into a first test data sequence.
Further, cross-monitoring training is carried out on the first training data sequence according to the fully-connected neural network, and a first service load degree identification network is obtained. The fully-connected neural network is a feedforward neural network consisting of an input layer, a hidden layer and an output layer. The first service load degree identification network comprises an input layer, a hidden layer and an output layer. The first test data sequence then includes a plurality of sets of sample service load identification records randomly divided. And recording a plurality of groups of sample service load degree identification records in the first test data sequence as a plurality of test data groups. And respectively marking a history service request set and a history equipment characteristic set in each test data set as test input information, and marking the history service load degree in the test data set corresponding to the test input information as standard test output information. And inputting the test input information into a first service load degree identification network to obtain the predicted service load degree corresponding to the test input information predicted by the first service load degree identification network. And further, the absolute value of the difference value between the standard test output information and the predicted service load degree corresponding to the test input information is recorded as a test error, the ratio between the test error and the standard test output information is output as a test error loss rate corresponding to the test input information, and the difference value between 1 and the test error loss rate is recorded as a test accuracy rate corresponding to the test input information. Therefore, a plurality of test accuracy rates and a plurality of test error loss rates corresponding to the plurality of test data sets are obtained.
And constructing the network evaluation function.
Wherein the network evaluation function is:
；
；
wherein f (X) characterizes a first network confidence accuracy, X n Characterizing an nth test feature accuracy, N being a positive integer, and N being the number of test groups within the first test data sequence, PRE n Characterization of nth test accuracy, LRE n And characterizing an nth test error loss rate.
And inputting the plurality of test accuracy rates and the plurality of test error loss rates into the network evaluation function to obtain a first network confidence accuracy.
And judging whether the first network confidence accuracy meets a preset network confidence accuracy constraint.
And if the first network confidence accuracy meets the preset network confidence accuracy constraint, integrating the first service load degree identification network into the load degree analyzer.
And inputting the multiple test accuracy rates and the multiple test error loss rates into a network evaluation function to obtain the first network confidence accuracy. The network evaluation function is:
；
；
wherein f (X) is the output first network confidence accuracy, X n For the nth test feature accuracy, N is a positive integer, N is N, N is the number of test groups in the first test data sequence, the number of test groups is the number of a plurality of test data groups, PRE n For the n-th test accuracy of input, LRE n The n-th test error loss rate is input.
Further, a determination is made as to whether the first network confidence accuracy meets a preset network confidence accuracy constraint. The preset network confidence accuracy constraint comprises a network confidence accuracy range preset and determined by the intelligent device management system based on the Internet of things card. If the first network confidence accuracy meets the preset network confidence accuracy constraint, a first service load level identification network is added to the load level analyzer. The load analyzer includes a first service load identification network that satisfies a preset network confidence accuracy constraint. If the first network confidence accuracy does not meet the preset network confidence accuracy constraint, continuing to train the first service load degree identification network until the first service load degree identification network meeting the preset network confidence accuracy constraint is obtained.
By means of the network evaluation function, a high-precision load degree analyzer is built, accuracy of service load degree identification of M servers is improved, and accordingly server extension fitness of enterprises is improved.
And carrying out service load degree identification on the M servers through the M service request sets and the M device feature sets according to the load degree analyzer to obtain M service load degrees.
Obtaining M load degree constraints corresponding to the M servers, and performing overload duty ratio calculation on the M service load degrees based on the M load degree constraints to obtain an overload coefficient.
And inputting the M service request sets and the M device feature sets into a load degree analyzer, and carrying out service load degree matching on the M service request sets and the M device feature sets by a first service load degree identification network in the load degree analyzer to obtain M service load degrees. The processing power of the different servers is different, but the processing power of each server is limited. When a server receives a set of service requests, it needs to allocate processing power (e.g., computing power) to the set of service requests. If the request amount of the service request set exceeds the processing capacity of the server, the load of the server may increase, resulting in a slow response time of the server or a crash of the server. Service load level is data information used to characterize the load level of a server. The higher the load level of the server, the greater the corresponding service load level.
Further, each load degree constraint comprises a service load degree threshold value of each server which is preset and determined by the intelligent device management system based on the Internet of things card. And performing overload duty ratio calculation on the M service load degrees based on the M load degree constraints, namely respectively judging whether each service load degree is larger than the corresponding load degree constraint. If the service load level is greater than the corresponding load level constraint, the service load level is noted as an identification overload level. And outputting the overload coefficient by the ratio of the number of the identified overload degrees to M.
And judging whether the overload coefficient is smaller than a preset overload coefficient or not.
And if the overload factor is greater than or equal to the preset overload factor, obtaining an additional service instruction, and executing server additional management of the target enterprise according to the additional service instruction.
And obtaining an additional record library of the server.
And based on the knowledge graph, carrying out data fusion on the server additionally-arranged record library to obtain an additionally-arranged management graph.
And executing the addition analysis of the overload coefficient based on the addition management map to obtain an addition scheme, and executing server addition management of the target enterprise according to the addition scheme.
And carrying out server additional record inquiry based on the big data to obtain a server additional record base. The server add record library includes a plurality of server add records. Each server additionally-arranged record comprises a historical overload coefficient and a historical additionally-arranged scheme corresponding to the historical overload coefficient. The history adding scheme comprises data information such as the number of the history server adding corresponding to the history overload coefficient, the type of the history server adding and the like.
Further, based on the knowledge graph, data fusion is performed on the server addition record library, that is, in the server addition record library, a plurality of historical overload coefficients in a plurality of server addition records are recorded as a plurality of addition analysis input features, a plurality of historical overload coefficients in a plurality of addition analysis input features are recorded as a plurality of addition analysis output features, and the plurality of addition analysis input features and the plurality of addition analysis output features are added to the addition management graph. The knowledge graph is a multidisciplinary fusion theory, and describes and displays knowledge and the development process and structural relationship thereof in a visual mode. The knowledge graph can visually express knowledge resources and carriers thereof, thereby helping people to understand and master knowledge more intuitively. The additional management atlas includes multiple additional analysis input features and multiple additional analysis output features.
Further, whether the overload factor is smaller than a preset overload factor is judged. If the overload factor is greater than/equal to the preset overload factor, the intelligent device management system based on the Internet of things card automatically generates an additional service instruction. And then, inputting the overload coefficient into an additionally-arranged management map according to the additionally-arranged service instruction, additionally-arranging analysis output characteristic matching on the overload coefficient by using the additionally-arranged management map to obtain an additionally-arranged scheme, and additionally-arranging and managing the servers of the target enterprise according to the additionally-arranged scheme, so that the additionally-arranged management effect of the servers of the enterprise is improved. The preset overload factor comprises an overload factor threshold preset and determined by the intelligent device management system based on the Internet of things card. The additional service instruction is instruction information for representing that the overload factor is greater than/equal to a preset overload factor and that additional management of the server is required for the target enterprise. The additional scheme comprises data information such as the additional number of servers, the additional type of the servers and the like corresponding to the overload factor which is larger than/equal to the preset overload factor.
In summary, the intelligent device management method based on the internet of things card provided by the application has the following technical effects:
1. Obtaining M device feature sets corresponding to M servers of a target enterprise through a resource management module of an enterprise management platform of the internet of things card; traversing M servers to perform fault pre-verification to obtain a fault pre-verification result; when the failure pre-verification result is passed, activating a system monitoring module of an enterprise management platform of the Internet of things card to obtain M service request sets corresponding to M servers; according to the load degree analyzer, obtaining M service load degrees by carrying out service load degree identification on M service request sets and M device feature sets; performing overload duty ratio calculation on M service load degrees based on M load degree constraints to obtain an overload coefficient; if the overload factor is greater than/equal to the preset overload factor, obtaining an additional service instruction, and executing server additional management of the target enterprise according to the additional service instruction. The method and the device have the advantages that the server adding management adaptability and accuracy of an enterprise are improved, meanwhile, the request switching timeliness of the enterprise server is improved, the communication service availability of the enterprise is effectively guaranteed, and the server management quality of the enterprise is improved.
2. By means of the network evaluation function, a high-precision load degree analyzer is built, accuracy of service load degree identification of M servers is improved, and accordingly server extension fitness of enterprises is improved.
Example two
Based on the same inventive concept as the intelligent device management method based on the internet of things card in the foregoing embodiment, the invention also provides an intelligent device management system based on the internet of things card, please refer to fig. 3, the system includes:
the device feature interaction module is used for interacting the resource management module of the internet of things card enterprise management platform to obtain M device feature sets corresponding to M servers of a target enterprise, and M is a positive integer greater than 1.
The fault pre-checking module is used for traversing the M servers to perform fault pre-checking based on a pre-constructed fault pre-checker to obtain a fault pre-checking result.
And the mapping instruction generation module is used for obtaining a request mapping instruction when the failure pre-verification result is passing.
The service request obtaining module is used for activating a system monitoring module of the internet of things card enterprise management platform based on the request mapping instruction to obtain M service request sets corresponding to the M servers.
The construction module is used for constructing the load degree analyzer based on a pre-constructed network evaluation function.
And the service load degree identification module is used for carrying out service load degree identification on the M servers through the M service request sets and the M device feature sets according to the load degree analyzer to obtain M service load degrees.
And the overload duty ratio calculation module is used for obtaining M load degree constraints corresponding to the M servers, and carrying out overload duty ratio calculation on the M service load degrees based on the M load degree constraints to obtain an overload coefficient.
And the judging module is used for judging whether the overload coefficient is smaller than a preset overload coefficient or not.
And the additionally-arranged management module is used for obtaining an additionally-arranged service instruction if the overload coefficient is greater than/equal to the preset overload coefficient, and executing server additionally-arranged management of the target enterprise according to the additionally-arranged service instruction.
Further, the system further comprises:
and the numbering module is used for carrying out random numbering on the M servers to obtain a first server and a second server … mth server, wherein M is a positive integer and belongs to M.
The first fault checking module is used for performing fault checking on the first server to obtain a first fault checking result.
And the second fault checking module is used for continuously performing fault checking on the m-th server of the second server … to obtain a second fault checking result … m-th fault checking result.
The first execution module is used for constructing the fault pre-verifier, wherein the fault pre-verifier comprises a fault pre-verifier, the fault pre-verifier is a fault pre-verifier which is obtained when the first fault verification result and the second fault verification result … are all passed, the fault pre-verifier is obtained when any one of the first fault verification result and the second fault verification result … is failed, and the fault pre-verifier is obtained when the fault pre-verifier is not passed.
And the second execution module is used for inputting the first fault checking result and the second fault checking result … into the fault pre-checker and generating the fault pre-checking result.
Further, the system further comprises:
the real-time state monitoring module is used for monitoring the real-time state of the first server based on the system monitoring module to obtain a first state monitoring set.
The abnormal state identification module is used for carrying out abnormal state identification on the first state monitoring set to obtain a first state abnormal coefficient.
The abnormal coefficient judging module is used for judging whether the first state abnormal coefficient is smaller than a preset abnormal coefficient or not.
And the third execution module is used for obtaining the first fault verification result if the first state abnormal coefficient is smaller than the preset abnormal coefficient.
And the fourth execution module is used for obtaining a first fault check result which is not passed if the first state abnormal coefficient is larger than/equal to the preset abnormal coefficient.
Further, the system further comprises:
and the positioning instruction generation module is used for generating an abnormal positioning instruction when the failure pre-verification result is that the failure pre-verification result does not pass.
And the server abnormality positioning module is used for carrying out abnormality positioning on the M servers according to the fault pre-verification result based on the abnormality positioning instruction to obtain an abnormality server positioning result.
And the mapping switching module is used for generating an equalization switching instruction based on the abnormal server positioning result and carrying out the mapping switching of the load equalizer on the abnormal server positioning result according to the equalization switching instruction.
Further, the system further comprises:
the sample dividing module is used for obtaining a sample service load degree identification record base, and executing random division on the sample service load degree identification record base to obtain a first training data sequence and a first test data sequence.
And the network training module is used for training the first service load degree identification network based on the first training data sequence.
And the network test module is used for testing the first service load degree identification network according to the first test data sequence to obtain a plurality of test accuracy rates and a plurality of test error loss rates.
And the function construction module is used for constructing the network evaluation function.
The confidence accuracy obtaining module is used for inputting the plurality of test accuracy rates and the plurality of test error loss rates into the network evaluation function to obtain a first network confidence accuracy.
And the fifth execution module is used for judging whether the first network confidence accuracy meets the preset network confidence accuracy constraint.
And the sixth execution module is used for integrating the first service load degree identification network into the load degree analyzer if the first network confidence accuracy meets the preset network confidence accuracy constraint.
Wherein the network evaluation function is:
；
；
wherein f (X) characterizes a first network confidence accuracy, X n Characterizing an nth test feature accuracy, N being a positive integer, and N being the number of test groups within the first test data sequence, PRE n Characterization of nth test accuracy, LRE n And characterizing an nth test error loss rate.
Further, the system further comprises:
and the seventh execution module is used for obtaining the server additionally-arranged record library.
And the record fusion module is used for carrying out data fusion on the server additionally-arranged record library based on the knowledge graph to obtain an additionally-arranged management graph.
And the addition scheme obtaining module is used for carrying out addition analysis of the overload coefficient based on the addition management map, obtaining an addition scheme and carrying out server addition management of the target enterprise according to the addition scheme.
The intelligent device management system based on the Internet of things card provided by the embodiment of the invention can execute the intelligent device management method based on the Internet of things card provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
All the included modules are only divided according to the functional logic, but are not limited to the above-mentioned division, so long as the corresponding functions can be realized; in addition, the specific names of the functional modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present invention.
The application provides an intelligent device management method based on an Internet of things card, wherein the method is applied to an intelligent device management system based on the Internet of things card, and the method comprises the following steps: obtaining M device feature sets corresponding to M servers of a target enterprise through a resource management module of an enterprise management platform of the internet of things card; traversing M servers to perform fault pre-verification to obtain a fault pre-verification result; when the failure pre-verification result is passed, activating a system monitoring module of an enterprise management platform of the Internet of things card to obtain M service request sets corresponding to M servers; according to the load degree analyzer, obtaining M service load degrees by carrying out service load degree identification on M service request sets and M device feature sets; performing overload duty ratio calculation on M service load degrees based on M load degree constraints to obtain an overload coefficient; if the overload factor is greater than/equal to the preset overload factor, obtaining an additional service instruction, and executing server additional management of the target enterprise according to the additional service instruction. The method and the device have the advantages that the server adding management adaptability and accuracy of an enterprise are improved, meanwhile, the request switching timeliness of the enterprise server is improved, the communication service availability of the enterprise is effectively guaranteed, and the server management quality of the enterprise is improved.
Although the invention has been described in more detail by means of the above embodiments, the invention is not limited to the above embodiments, but may comprise many other equivalent embodiments without departing from the inventive concept, the scope of which is determined by the scope of the appended claims.
Claims (8)
1. The intelligent equipment management method based on the Internet of things card is characterized by being applied to an intelligent equipment management system based on the Internet of things card, wherein the system is in communication connection with an enterprise management platform of the Internet of things card, and the method comprises the following steps:
the resource management module of the internet of things card enterprise management platform is interacted to obtain M device feature sets corresponding to M servers of a target enterprise, wherein M is a positive integer greater than 1;
traversing the M servers to perform fault pre-verification based on a pre-constructed fault pre-verifier to obtain a fault pre-verification result;
when the failure pre-verification result is passed, obtaining a request mapping instruction;
based on the request mapping instruction, activating a system monitoring module of the internet of things card enterprise management platform to obtain M service request sets corresponding to the M servers;
constructing a load degree analyzer based on a pre-constructed network evaluation function;
According to the load degree analyzer, carrying out service load degree identification on the M servers through the M service request sets and the M device feature sets to obtain M service load degrees;
obtaining M load degree constraints corresponding to the M servers, and performing overload duty ratio calculation on the M service load degrees based on the M load degree constraints to obtain an overload coefficient;
judging whether the overload factor is smaller than a preset overload factor or not;
and if the overload factor is greater than or equal to the preset overload factor, obtaining an additional service instruction, and executing server additional management of the target enterprise according to the additional service instruction.
2. The method of claim 1, wherein traversing the M servers for failure pre-verification based on a pre-built failure pre-verifier, obtaining failure pre-verification results comprises:
randomly numbering the M servers to obtain a first server and a second server … M server, wherein M is a positive integer and belongs to M;
performing fault verification on the first server to obtain a first fault verification result;
continuing to perform fault verification on the m-th server of the second server … to obtain a second fault verification result … m-th fault verification result;
Constructing the fault pre-verifier, wherein the fault pre-verifier comprises a fault pre-verifier, the fault pre-verifier is that when the first fault verification result and the second fault verification result … are all passed, the obtained fault pre-verifier is that the fault pre-verifier is passed, and when any one of the first fault verification result and the second fault verification result … is that the fault pre-verifier is not passed, the obtained fault pre-verifier is that the fault pre-verifier is not passed;
and inputting the first fault checking result, the second fault checking result … and the mth fault checking result into the fault pre-checker to generate the fault pre-checking result.
3. The method of claim 2, wherein performing a fault check on the first server to obtain a first fault check result comprises:
based on the system monitoring module, carrying out real-time state monitoring on the first server to obtain a first state monitoring set;
carrying out abnormal state identification on the first state monitoring set to obtain a first state abnormal coefficient;
judging whether the first state anomaly coefficient is smaller than a preset anomaly coefficient or not;
If the first state anomaly coefficient is smaller than the preset anomaly coefficient, the obtained first fault verification result is passed;
if the first state abnormal coefficient is greater than or equal to the preset abnormal coefficient, the obtained first fault checking result is not passed.
4. The method of claim 1, further comprising, after obtaining the failure pre-verification result:
when the failure pre-checking result is that the failure pre-checking result is not passed, generating an abnormal positioning instruction;
based on the abnormal positioning instruction, performing abnormal positioning on the M servers according to the fault pre-verification result to obtain an abnormal server positioning result;
and generating an equalization switching instruction based on the abnormal server positioning result, and carrying out mapping switching of a load equalizer on the abnormal server positioning result according to the equalization switching instruction.
5. The method of claim 1, wherein building a load factor analyzer based on a pre-constructed network evaluation function comprises:
obtaining a sample service load degree identification record library, and executing random division on the sample service load degree identification record library to obtain a first training data sequence and a first test data sequence;
Training a first service load degree identification network based on the first training data sequence;
testing the first service load degree identification network according to the first test data sequence to obtain a plurality of test accuracy rates and a plurality of test error loss rates;
constructing the network evaluation function;
inputting the plurality of test accuracy rates and the plurality of test error loss rates into the network evaluation function to obtain a first network confidence accuracy;
judging whether the first network confidence accuracy meets a preset network confidence accuracy constraint;
and if the first network confidence accuracy meets the preset network confidence accuracy constraint, integrating the first service load degree identification network into the load degree analyzer.
6. The method of claim 5, wherein the network evaluation function is:
；
；
wherein f (X) characterizes a first network confidence accuracy, X n Characterizing an nth test feature accuracy, N being a positive integer, and N being the number of test groups within the first test data sequence, PRE n Characterization of nth test accuracy, LRE n And characterizing an nth test error loss rate.
7. The method of claim 1, wherein performing server addition management for the target enterprise according to the addition service instruction comprises:
Obtaining a server additionally provided with a record library;
based on the knowledge graph, carrying out data fusion on the server additionally-arranged record library to obtain an additionally-arranged management graph;
and executing the addition analysis of the overload coefficient based on the addition management map to obtain an addition scheme, and executing server addition management of the target enterprise according to the addition scheme.
8. An intelligent device management system based on an internet of things card, wherein the system is configured to perform the method of any one of claims 1 to 7, the system being communicatively connected to an internet of things card enterprise management platform, the system comprising:
the device feature interaction module is used for interacting the resource management module of the internet of things card enterprise management platform to obtain M device feature sets corresponding to M servers of a target enterprise, wherein M is a positive integer greater than 1;
the fault pre-checking module is used for traversing the M servers to perform fault pre-checking based on a pre-constructed fault pre-checker to obtain a fault pre-checking result;
the mapping instruction generation module is used for obtaining a request mapping instruction when the failure pre-verification result is passing;
The service request acquisition module is used for activating a system monitoring module of the internet of things card enterprise management platform based on the request mapping instruction to acquire M service request sets corresponding to the M servers;
the construction module is used for constructing a load degree analyzer based on a pre-constructed network evaluation function;
the service load degree identification module is used for carrying out service load degree identification on the M servers through the M service request sets and the M device feature sets according to the load degree analyzer to obtain M service load degrees;
the overload duty ratio calculation module is used for obtaining M load degree constraints corresponding to the M servers, and carrying out overload duty ratio calculation on the M service load degrees based on the M load degree constraints to obtain an overload coefficient;
the judging module is used for judging whether the overload coefficient is smaller than a preset overload coefficient or not;
and the additionally-arranged management module is used for obtaining an additionally-arranged service instruction if the overload coefficient is greater than/equal to the preset overload coefficient, and executing server additionally-arranged management of the target enterprise according to the additionally-arranged service instruction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410160659.7A CN117714453B (en) | 2024-02-05 | 2024-02-05 | Intelligent device management method and system based on Internet of things card |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410160659.7A CN117714453B (en) | 2024-02-05 | 2024-02-05 | Intelligent device management method and system based on Internet of things card |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117714453A true CN117714453A (en) | 2024-03-15 |
| CN117714453B CN117714453B (en) | 2024-04-26 |
Family
ID=90148228
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410160659.7A Active CN117714453B (en) | 2024-02-05 | 2024-02-05 | Intelligent device management method and system based on Internet of things card |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117714453B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170046254A1 (en) * | 2015-08-13 | 2017-02-16 | Spirent Communications, Inc. | Method to configure monitoring thresholds using output of load or resource loadings |
| CN111416836A (en) * | 2020-02-13 | 2020-07-14 | 中国平安人寿保险股份有限公司 | Nginx-based server maintenance method and device, computer equipment and storage medium |
| CN114185639A (en) * | 2021-11-02 | 2022-03-15 | 北京银盾泰安网络科技有限公司 | Application container extension engine platform |
| CN115102831A (en) * | 2022-07-26 | 2022-09-23 | 武汉烽火技术服务有限公司 | Method and system for deploying distributed BGP (Border gateway protocol) service |
| CN117081996A (en) * | 2023-10-16 | 2023-11-17 | 北京乐讯科技有限公司 | Flow control method based on real-time feedback and soft value of server and related equipment |
| US20230393902A1 (en) * | 2022-06-02 | 2023-12-07 | Ainnocence Technologies Llc | Data processing method, system, electronic equipment, and storage medium based on a cloud platform |
| CN117354312A (en) * | 2023-09-28 | 2024-01-05 | 中国电信股份有限公司技术创新中心 | Access request processing method, device, system, computer equipment and storage medium |
-
2024
- 2024-02-05 CN CN202410160659.7A patent/CN117714453B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170046254A1 (en) * | 2015-08-13 | 2017-02-16 | Spirent Communications, Inc. | Method to configure monitoring thresholds using output of load or resource loadings |
| CN111416836A (en) * | 2020-02-13 | 2020-07-14 | 中国平安人寿保险股份有限公司 | Nginx-based server maintenance method and device, computer equipment and storage medium |
| CN114185639A (en) * | 2021-11-02 | 2022-03-15 | 北京银盾泰安网络科技有限公司 | Application container extension engine platform |
| US20230393902A1 (en) * | 2022-06-02 | 2023-12-07 | Ainnocence Technologies Llc | Data processing method, system, electronic equipment, and storage medium based on a cloud platform |
| CN115102831A (en) * | 2022-07-26 | 2022-09-23 | 武汉烽火技术服务有限公司 | Method and system for deploying distributed BGP (Border gateway protocol) service |
| CN117354312A (en) * | 2023-09-28 | 2024-01-05 | 中国电信股份有限公司技术创新中心 | Access request processing method, device, system, computer equipment and storage medium |
| CN117081996A (en) * | 2023-10-16 | 2023-11-17 | 北京乐讯科技有限公司 | Flow control method based on real-time feedback and soft value of server and related equipment |
Non-Patent Citations (2)
| Title |
|---|
| E QIN等: "Research on Nginx Dynamic Load Balancing Algorithm", IEEE, 30 March 2020 (2020-03-30) * |
| 郭成城, 晏蒲柳: "一种异构Web服务器集群动态负载均衡算法", 计算机学报, no. 02, 12 February 2005 (2005-02-12) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117714453B (en) | 2024-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cai et al. | An under‐sampled software defect prediction method based on hybrid multi‐objective cuckoo search | |
| US10140453B1 (en) | Vulnerability management using taxonomy-based normalization | |
| Zheng et al. | Research on the design of analytical communication and information model for teaching resources with cloud‐sharing platform | |
| CN107343041B (en) | Accurate poverty alleviation management system and method based on cloud computing | |
| CN110083518B (en) | AdaBoost-Elman-based virtual machine software aging prediction method | |
| JP6847590B2 (en) | Integrated monitoring operation system and method | |
| CN112559831A (en) | Link monitoring method and device, computer equipment and medium | |
| US11972382B2 (en) | Root cause identification and analysis | |
| CN114356712B (en) | Data processing method, apparatus, device, readable storage medium, and program product | |
| CN109711849B (en) | Ether house address portrait generation method and device, electronic equipment and storage medium | |
| You et al. | A Cloud Based Network Intrusion Detection System | |
| Wu et al. | An Auxiliary Decision‐Making System for Electric Power Intelligent Customer Service Based on Hadoop | |
| Priyanka et al. | Fundamentals of wireless sensor networks using machine learning approaches: Advancement in big data analysis using Hadoop for oil pipeline system with scheduling algorithm | |
| CN115168848B (en) | Interception feedback processing method based on big data analysis interception | |
| CN117714453B (en) | Intelligent device management method and system based on Internet of things card | |
| US20230236922A1 (en) | Failure Prediction Using Informational Logs and Golden Signals | |
| CN110717192B (en) | Big data security oriented access control method based on Key-Value accelerator | |
| Zhang et al. | A security monitoring method based on autonomic computing for the cloud platform | |
| CN114490405A (en) | Resource demand determination method, device, equipment and storage medium | |
| CN113988695A (en) | Power grid layered line loss analysis method based on semantic model and multi-source data | |
| Wang | Reliability detection method of online education resource sharing based on blockchain | |
| Zhang et al. | Financial System Design for High‐Tech Enterprise Based on Cloud Service and Task Scheduling Algorithm | |
| Zhang | Application of fusion of fuzzy mathematical clustering analysis in enterprise financial management cloud platform | |
| Zhou et al. | Research on Cloud Computing Security Technology under Computer Big Data Network | |
| CN118093330B (en) | Visualization method based on CHSM management and application thereof |
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 |