CN112801434A - Method, device, equipment and storage medium for monitoring performance index health degree - Google Patents
Method, device, equipment and storage medium for monitoring performance index health degree Download PDFInfo
- Publication number
- CN112801434A CN112801434A CN201911106724.3A CN201911106724A CN112801434A CN 112801434 A CN112801434 A CN 112801434A CN 201911106724 A CN201911106724 A CN 201911106724A CN 112801434 A CN112801434 A CN 112801434A
- Authority
- CN
- China
- Prior art keywords
- monitored
- index
- target
- score
- degree score
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Mathematical Optimization (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Algebra (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Debugging And Monitoring (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application provides a method, a device, equipment and a storage medium for monitoring the health degree of performance indexes, wherein the method comprises the following steps: acquiring an actual value of an index to be monitored at a target moment; determining the deviation degree score and the abnormality persistence degree score of the index to be monitored at the target moment according to the parameter of the abnormality monitoring model obtained by pre-training and the actual value; and determining a first health degree score of the index to be monitored at the target moment according to the deviation degree score and the abnormal persistence degree score. The method reduces the labor cost and improves the accuracy of the monitoring result.
Description
Technical Field
The application relates to the field of communication, in particular to a method, a device, equipment and a storage medium for monitoring the health degree of a performance index.
Background
As an important infrastructure in the information age, a communication network system needs to ensure continuous and stable operation to meet communication needs in every day, business, public service and the like of society. Therefore, equipment developers design various performance indexes, and network operation and maintenance personnel can monitor the operation states of all components of the network and the network conveniently. Operation and maintenance personnel can quickly deduce the current network or the operation state of a certain component according to the health degree of the performance index, thereby being beneficial to finding out network faults in time and carrying out fault recovery. However, in the conventional method, the detection threshold of each performance index needs to be manually set, and as the network system becomes more complex, it is difficult to manually set the threshold for a large number of performance indexes, which results in higher labor cost and lower accuracy of the monitoring result.
Disclosure of Invention
The application provides a monitoring method, a monitoring device, monitoring equipment and a storage medium for performance index health degree.
The embodiment of the application provides a method for monitoring the health degree of performance indexes, which comprises the following steps:
acquiring an actual value of an index to be monitored at a target moment;
determining a deviation degree score and an abnormal duration score of the index to be monitored at the target time according to a parameter of an abnormal monitoring model obtained by pre-training and the actual value, wherein the deviation degree score is used for representing the deviation degree of the actual value relative to a predicted value of the index to be monitored at the target time, and the abnormal duration score is used for representing the proportion of the actual value of the index to be monitored as an abnormal value in a preset time window containing the target time;
and determining a first health degree score of the index to be monitored at the target moment according to the deviation degree score and the abnormal persistence degree score.
The embodiment of the application provides a monitoring devices of healthy degree of performance index, includes:
the first acquisition module is used for acquiring the actual value of the index to be monitored at the target moment;
the first determination module is used for determining a deviation degree score and an abnormal duration score of the index to be monitored at the target time according to a parameter of an abnormal monitoring model obtained through pre-training and the actual value, wherein the deviation degree score is used for representing the deviation degree of the actual value relative to a predicted value of the index to be monitored at the target time, and the abnormal duration score is used for representing the proportion of the actual value of the index to be monitored to the abnormal value in a preset time window containing the target time;
and the second determination module is used for determining a first health degree score of the index to be monitored at the target moment according to the deviation degree score and the abnormal persistence degree score.
The embodiment of the present application provides a computer device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements any one of the methods in the embodiment of the present application when executing the computer program.
The embodiment of the present application provides a storage medium, which stores a computer program, and the computer program realizes any one of the methods in the embodiment of the present application when being executed by a processor.
According to the performance index health degree monitoring method, the performance index health degree monitoring device, the performance index health degree monitoring equipment and the storage medium, computer equipment obtains an actual value of an index to be monitored at a target moment, determines deviation degree grading and abnormal continuity degree grading of the index to be monitored at the target moment according to a parameter of an abnormal monitoring model obtained through pre-training and the actual value, and determines a first health degree grading of the index to be monitored at the target moment according to the deviation degree grading and the abnormal continuity degree grading. The anomaly monitoring model for determining the deviation degree score and the anomaly persistence degree score of the index to be monitored is obtained by pre-training, namely the parameter of the anomaly monitoring model is obtained by pre-training, namely the parameter equivalent to the detection threshold value of the index to be monitored is not manually set, so that manual participation is reduced, the labor cost is reduced, and the accuracy of the monitoring result is improved. Meanwhile, the first health degree score of the index to be monitored is obtained in the two aspects of comprehensive deviation degree score and abnormal persistence degree score, and reference factors are comprehensive, so that the accuracy of the monitoring result is further improved.
Drawings
Fig. 1 is a schematic flow chart of a method for monitoring health of performance indicators according to an embodiment;
fig. 2 is a block diagram of a communication system according to an embodiment;
FIG. 3 is a schematic flow chart of a method for monitoring health of performance indicators according to another embodiment;
FIG. 4 is a schematic diagram of an internal structure of an embodiment of a device for monitoring health of performance indicators;
fig. 5 is a schematic internal structural diagram of a computer device according to an embodiment.
Detailed Description
To make the objects, technical solutions and advantages of the present application more apparent, embodiments of the present application will be described in detail below with reference to the accompanying drawings. It should be noted that the embodiments and features of the embodiments in the present application may be arbitrarily combined with each other without conflict.
It should be noted that the execution subject of the method embodiments described below may be a device for monitoring the performance index health degree, and the device may be implemented as part of or all of the computer device by software, hardware, or a combination of software and hardware. The method embodiments described below are described by way of example with the execution subject being a computer device.
Fig. 1 is a schematic flow chart of a method for monitoring a performance index health degree according to an embodiment. The embodiment relates to a specific process of how the computer device determines the health degree score of the index to be monitored at the target moment. As shown in fig. 1, the method may include:
s101, obtaining an actual value of an index to be monitored at a target moment.
The index to be monitored is any performance index needing to be monitored in the communication system. Taking the communication system as a Long Term Evolution (LTE) wireless network system as an example, as shown in fig. 2, a typical LTE wireless network system includes a plurality of base stations, and one base station is logically divided into several cells (e.g., cell 1, cell 2, and cell 3 in fig. 2). Under each cell, a plurality of terminals (such as mobile phone users) access to carry out mobile communication activities such as wireless communication, internet surfing, video watching and the like. Some Key Performance indicators (KPIs, Key Performance indicators), such as Radio Resource Control (RRC) drop rate, RRC connection establishment success rate, uplink and downlink average traffic, may reflect an operation state of the network system. The real-time health degree detection is carried out on the KPIs, so that operation and maintenance personnel can be assisted to manage the network system.
S102, determining the deviation degree score and the abnormality persistence degree score of the index to be monitored at the target moment according to the parameter of the abnormality monitoring model obtained through pre-training and the actual value.
Optionally, the parameters of the anomaly monitoring model may include a predicted value, an upper normal value limit, and a lower normal value limit of the to-be-monitored indicator at each time, the deviation score is used to represent a deviation degree of the actual value relative to the predicted value of the to-be-monitored indicator at the target time, and the anomaly duration score is used to represent a ratio that the actual value of the to-be-monitored indicator is an abnormal value within a preset time window including the target time.
The anomaly monitoring model is obtained by training historical data of indexes to be monitored in advance, and in practical application, a training period of the anomaly monitoring model can be set according to the overall running state of the network. For example, when the overall operation state of the network is relatively stable, the training period of the anomaly monitoring model may be set to be longer, when the overall operation state of the network fluctuates, the training period of the anomaly monitoring model may be set to be shorter, and the model may be trained using the historical data of a time period relatively close to the target time. In addition, these historical data used for training are also normal data obtained after preprocessing. The abnormal monitoring model obtained by training can comprise three parameters which are respectively a predicted value, a normal value upper limit and a normal value lower limit of the index to be monitored at each moment. Therefore, the computer equipment can read the actual value of the index to be monitored at the target moment in real time, and determine the deviation degree of the actual value of the index to be monitored at the target moment relative to the predicted value at the target moment according to the three parameters contained in the anomaly monitoring model, so as to obtain the deviation degree score of the index to be monitored at the target moment; and determining the abnormal condition of the actual value of the index to be monitored at the target moment according to the upper limit parameter and the lower limit parameter of the normal value of the index to be monitored at each moment, which are contained in the abnormal monitoring model, and obtaining the abnormal duration grade of the index to be monitored at the target moment by combining the abnormal condition of the actual value of the index to be monitored in a preset time window.
Optionally, the process of determining the offset degree score of the to-be-monitored index at the target time according to the parameter of the abnormal monitoring model obtained through pre-training and the actual value may be: and determining the deviation degree score of the index to be monitored at the target moment according to a predicted value parameter, a normal value upper limit parameter, a normal value lower limit parameter and the actual value of the index to be monitored at the target moment, which are contained in an abnormal monitoring model obtained by pre-training.
Specifically, the computer device may determine the offset score s of the to-be-monitored index at the target time according to the following formula 1 and formula 2d。
Equation 1:
equation 2:
wherein a and b are parameters greater than zero, respectively, y is the actual value,
yupperand ylowerThe parameters of the model are monitored for abnormalities obtained by pre-training, an
Is the predicted value y of the index to be monitored at the target moment tupperIs the upper limit of the normal value of the index to be monitored at the target moment t, ylowerAnd the lower limit of the normal value of the index to be monitored at the target moment t is defined.
Optionally, the process of determining the abnormal duration degree score of the to-be-monitored index at the target time according to the parameter of the abnormal monitoring model obtained through pre-training and the actual value may be: determining a first probability that the actual value is an abnormal value according to a normal value upper limit parameter and a normal value lower limit parameter of the index to be monitored at the target moment, which are contained in an abnormal monitoring model obtained through pre-training; acquiring second probabilities of the index to be monitored at each historical moment in a preset time window, wherein the second probabilities are used for representing the probability that the actual value of the index to be monitored at the target historical moment is an abnormal value; and determining the abnormal persistence degree score of the index to be monitored at the target moment according to the first probability and the second probability.
Specifically, the computer device determines that the actual value of the index to be monitored at the target time is greater than the upper limit of the normal value at the target time or is less than the lower limit of the normal value at the target time, determines that the first probability that the actual value is the abnormal value is 1, and determines that the first probability that the actual value is the abnormal value is 0 when the actual value of the index to be monitored at the target time is determined to be between the lower limit of the normal value and the upper limit of the normal value at the target time. And meanwhile, the computer equipment determines the abnormal persistence degree score of the index to be monitored at the target moment according to the first probability and the second probability of the index to be monitored at each historical moment in the preset time window. Wherein, predetermine the time window and can carry out corresponding setting according to actual demand. Taking the preset time window as 5 moments as an example, assuming that the starting moment is the 1 st moment and the target moment is the 5 th moment, the computer device needs to determine a first probability that the actual value of the to-be-monitored index at the 5 th moment is an abnormal value, and in combination with a second probability that the actual values of the to-be-monitored index at the 1 st moment, the 2 nd moment, the 3 rd moment and the 4 th moment are abnormal values, the abnormal duration score of the to-be-monitored index at the 5 th moment can be determined based on the arithmetic mean value of the first probability and the second probability. When the actual values of the indexes to be monitored in the whole preset time window are all abnormal values, the abnormal persistence degree of the indexes to be monitored at the target moment is determined to be scored as 1; and when the actual values of the indexes to be monitored in the whole preset time window are normal values, the abnormal persistence degree of the determined indexes to be monitored at the target moment is scored as 0.
It should be noted that, in the determination process of the second probability that the actual value of the to-be-monitored indicator at the 1 st time, the 2 nd time, the 3 rd time, and the 4 th time is the abnormal value, reference may be made to the determination process of the first probability that the actual value of the to-be-monitored indicator at the 5 th time is the abnormal value, and details of this embodiment are not repeated herein. In practical application, the computer device stores the second probabilities that the actual values of the index to be monitored at the 1 st moment, the 2 nd moment, the 3 rd moment and the 4 th moment are abnormal values, and directly reads the stored corresponding values to calculate when determining the abnormal duration score of the index to be monitored at the 5 th moment.
S103, determining a first health degree score of the index to be monitored at the target moment according to the deviation degree score and the abnormal persistence degree score.
Specifically, the computer device may combine the obtained deviation degree score and the abnormal persistence degree score, so as to obtain a first health degree score of the index to be monitored at the target time. The first health degree score can reflect the running state of the equipment, and the higher the first health degree score of the index to be monitored is, the more normal the running state of the equipment is. Optionally, the computer device may determine the first health score s of the to-be-monitored index at the target time according to the following formula 3h。
Equation 3: sh＝1-(ωa*sa+ωd*sd)，
Wherein, ω isaScoring the degree of deviation saOccupied weight, ωdScoring the abnormality persistence sdOccupied weight, ωa∈[0，1]ωd∈[0，1]，ωaAnd omegadThe sum is equal to 1, and the sum can be adjusted to omega according to actual requirementsaAnd ωdAnd carrying out corresponding setting. From the above formula, the higher the deviation score and the abnormality duration score of the index to be monitored are, the higher the first health score s thereof ishThe lower.
In order to improve the intelligence of the human-computer interaction, optionally, after the first health score of the index to be monitored is obtained, the method may further include: and determining a target state of the index to be monitored at the target moment according to the first health degree score and a preset state mapping relation, and outputting the target state, wherein the state mapping relation comprises a corresponding relation between the first health degree score and the index state.
Specifically, the preset state mapping relation can grade the first health degree score by four grades, such as normal (0.75-1.0), sub-health (0.5-0.75), early warning (0.25-0.5) and fault state (0-0.25). Therefore, the computer equipment can determine the target state of the index to be monitored at the target moment according to the obtained first health degree score and the state mapping relation, and output the target state. Meanwhile, different colors can be used for marking and distinguishing aiming at different target states. For example, when the target state is a fault, the target state is marked by using 'red', when the target state is an early warning, the target state is marked by using 'blue', and when the target state is sub-healthy, the target state is marked by using 'yellow'. Of course, the obtained target state may also be sent to a terminal of the operation and maintenance personnel to attract the attention of the operation and maintenance personnel.
According to the monitoring method of the health degree of the performance index, computer equipment acquires an actual value of the index to be monitored at a target moment, determines the deviation degree score and the abnormal continuity degree score of the index to be monitored at the target moment according to a parameter of an abnormal monitoring model obtained through pre-training and the actual value, and determines the first health degree score of the index to be monitored at the target moment according to the deviation degree score and the abnormal continuity degree score. The abnormity monitoring model for determining the deviation degree score and the abnormity duration score of the index to be monitored is obtained by pre-training, namely the parameter of the abnormity monitoring model is obtained by pre-training, namely, the parameter equivalent to the detection threshold value of the index to be monitored is not manually set, so that the manual participation is reduced, the labor cost is reduced, and the accuracy of the monitoring result is improved. Meanwhile, the first health degree score of the index to be monitored is obtained in the two aspects of comprehensive deviation degree score and abnormal persistence degree score, and reference factors are comprehensive, so that the accuracy of the monitoring result is further improved.
In an embodiment, there is further provided an acquiring process of the anomaly monitoring model, and optionally, as shown in fig. 3, before the step S101, the method may further include:
s201, obtaining historical data of indexes to be monitored.
In order to enable the trained anomaly monitoring model to be more suitable for the recent actual state of the index to be monitored, historical data of a time period closer to the target time can be selected. The RRC call drop rate with the index to be monitored as a certain base station is assumed as an analysis object, the acquisition time of the RRC call drop rate is 30 days, and the acquisition granularity is 15 minutes. The abnormal monitoring model for monitoring the health degree of the RRC call drop rate on the 16 th day can be trained by reading the RRC call drop rate data on the 1 st to 15 th days. With the lapse of time, when the 17 th day is reached, an abnormal detection model for monitoring the health degree of the RRC call drop rate of the 17 th day can be trained by reading the RRC call drop rate data of the 2 nd to 16 th days, and so on. Of course, when the overall operation state of the network is relatively stable, the training period of the anomaly monitoring model can be set to be larger. For example, two days or more.
Optionally, the acquired historical data of the index to be monitored may be preprocessed, for example, the historical data is denoised, so that the historical data used for training the abnormal monitoring model parameter belongs to normal data.
S202, determining the data type of the historical data.
The computer device may determine whether the data type of the historical data has a periodic type by using a Discrete Fourier Transform (DFT) algorithm, and certainly, may also determine whether the data type of the historical data has randomness, trend, and the like by using other algorithms.
S203, determining a target basic model to be trained according to the data type and a preset model mapping relation, wherein the model mapping relation comprises a corresponding relation between the data type and the basic model.
When the data type of the historical data is judged to be a periodic type, a cubic exponential smoothing (Holt-Winters) model can be selected as a target basic model to be trained, when the data type of the historical data is judged to be a random type, a nuclear density estimation algorithm can be selected as the target basic model to be trained, and when the data type of the historical data is judged to be other types, a corresponding modeling algorithm is selected as the target basic model to be trained.
And S204, training the target basic model according to the historical data to obtain an abnormal monitoring model.
Optionally, the parameters of the trained anomaly monitoring model may include a predicted value, an upper normal value limit, and a lower normal value limit of the index to be monitored at each next time.
In this embodiment, in the process of obtaining the anomaly monitoring model, the computer device may select a target base model corresponding to the data type of the historical data as the model to be trained, and obtain the anomaly monitoring model for determining the deviation score and the anomaly persistence score of the index to be monitored by combining the determined target base model and the historical data, so as to improve the accuracy of the parameters of the anomaly monitoring model, and further improve the accuracy of the monitoring result using the parameters of the anomaly monitoring model as the monitoring reference.
In practical application, a plurality of performance indexes need to be comprehensively analyzed to obtain the health degree score of the same component. Optionally, on the basis of the foregoing embodiment, the method may further include: acquiring a first health degree score of each index to be monitored corresponding to a target component; and combining the first health degree scores of all the indexes to be monitored to obtain a second health degree score of the target component at the target moment.
Specifically, the meaning of the component may be physical or logical, and taking the LTE wireless network system shown in fig. 2 as an example, one base station may be regarded as one component; the wireless performance indexes are many in number, and generally can be classified into an access class, a maintenance class, a sensing class, mobility and the like according to service logic, and are used for representing system operation states in different aspects.
The target component is any component in the communication system which needs to be monitored. The target component may include a plurality of performance indexes, each of the performance indexes is an index to be monitored, and the process of acquiring the first health degree score of the plurality of indexes to be monitored included in the target component may refer to the process of the above embodiment. After obtaining the first health degree score of each index to be monitored included in the target component, the computer device may combine the first health degree scores of each index to be monitored according to the following formula 4 to obtain a second health degree score s of the target component at the target time.
Equation 4:
wherein m is the number of indexes to be monitored included in the target component, siA first health score, ω, for the ith index to be monitored of the target componentiThe weight coefficient, omega, of the ith index to be monitored of the target componenti∈[0，1]The sum of the weight coefficients of the indexes to be monitored is equal to 1.
Of course, the computer device may also obtain the second health degree score of the target component at the target time by merging the deviation degree scores of the indexes to be monitored included in the target component, merging the abnormality persistence degree scores of the indexes to be monitored, and performing comprehensive calculation based on the merged deviation degree score and the merged abnormality persistence degree score.
Optionally, after the second health degree score of the target component is obtained, the target state of the target component may be determined according to the second health degree score of the target component, and the determined target state is output, that is, the overall health degree score of the target component is subjected to hierarchical grading processing.
In practical applications, it is also necessary to perform a comprehensive analysis on a plurality of components to obtain a health score of the communication system. Optionally, on the basis of the foregoing embodiment, the method may further include: acquiring a second health degree score of each component corresponding to the target system; and combining the second health degree scores of the components to obtain a third health degree score of the target system at the target moment.
Specifically, the target system is a communication system that needs to be monitored, and the target system may include a plurality of components, and the health degree score of the target system may be obtained by performing a comprehensive analysis on the health degree scores of the plurality of components. For each component in each component, the process of obtaining the second health degree score of each component may refer to the process of obtaining the second health degree score of the target component, which is not described herein again. After obtaining the second health scores of the components included in the target system, the computer device may combine the second health scores of the components according to the following formula 5 to determine a third health score s of the target system at the target timec。
Equation 5:
wherein n is the number of target components included in the target system, sjSecond health score, ω, for jth target component of target systemjIs the weight coefficient, ω, of the jth target component of the target systemj∈[0，1]The sum of the weight coefficients of the respective target components is equal to 1.
Of course, the computer device may also obtain a third health score of the target system at the target time by merging the deviation scores of the components included in the target system, merging the abnormality duration scores of the components, and performing comprehensive calculation based on the merged deviation score and the merged abnormality duration score.
Optionally, after the third health degree score of the target system is obtained, the target state of the target system may be determined according to the third health degree score of the target system, and the determined target state is output, that is, the overall health degree score of the target system is subjected to hierarchical grading processing.
In practical application, a part of indexes to be monitored have an association relationship, the part of indexes to be monitored may be in the same component and the same system, or may be in a cross-component and cross-system, for example, for a communication system, the part of indexes to be monitored may include an access index, a maintenance index, a perception index and a mobility index, these different types of indexes may not belong to the same component, some belong to an access-side index, and some belong to a core-side index, but their health degree scores may reflect the health degree scores of the whole communication system, that is, there is an association relationship between these various indexes to be monitored. Even if the indexes to be monitored of the same component, such as the access indexes, may include the access indexes of the access side and the access indexes of the core side, the health degree score of the access indexes of the access side and the health degree score of the access indexes of the core side may reflect the health degree score of the access indexes together, that is, the access indexes of the core side and the access indexes of the access side have an association relationship, and the association relationship is not listed one by one. Therefore, it is also necessary to perform comprehensive analysis on a plurality of indexes to be monitored having correlation relationships to obtain a health score of the correlation index. Optionally, on the basis of the foregoing embodiment, the method may further include: acquiring a first health degree score of each index to be monitored with an incidence relation; and combining the first health degree scores of all the indexes to be monitored to obtain a fourth health degree score of the associated index at the target moment.
Specifically, the association relationship may be set manually or automatically by a computer device through an association algorithm. The computer device may combine the first health degree scores of the various to-be-monitored indexes included in the associated index by using the following formula 6 to determine a fourth health degree score s of the associated index at the target momentd。
Equation 6:
wherein k is the number of indexes to be monitored included in the associated indexes, slA first health score, ω, for the first index to be monitored of the associated indexlThe weight coefficient, omega, of the first index to be monitored as a correlation indexl∈[0，1]The sum of the weight coefficients of the indexes to be monitored is equal to 1.
Of course, the computer device may also obtain the fourth health degree score of the correlation index at the target time by merging the deviation degree scores of the indexes to be monitored included in the correlation index, merging the abnormality persistence degree scores of the indexes to be monitored, and performing comprehensive calculation based on the merged deviation degree score and the merged abnormality persistence degree score.
Optionally, after the fourth health degree score of the correlation index is obtained, the target state of the correlation index may be determined according to the fourth health degree score of the correlation index, and the determined target state is output, that is, the overall health degree score of the correlation index is subjected to hierarchical grading processing.
In this embodiment, the computer equipment can carry out health degree fusion score and score to the health degree fusion of a plurality of subassemblies to a plurality of performance index of same subassembly, conveniently monitors communication system's state from a plurality of dimensions such as single subassembly and entire system, is favorable to the running state of the more comprehensive monitored control system of fortune dimension personnel to the intelligence of control has been improved.
Fig. 4 is a schematic diagram of an internal structure of an embodiment of a device for monitoring a performance index of health, as shown in fig. 4, the device may include: a first obtaining module 10, a first determining module 11 and a second determining module 12.
Specifically, the first obtaining module 10 is configured to obtain an actual value of an index to be monitored at a target time;
the first determining module 11 is configured to determine, according to a parameter of an anomaly monitoring model obtained through pre-training and the actual value, an offset degree score and an anomaly duration score of the to-be-monitored indicator at the target time, where the offset degree score is used to represent an offset degree of the actual value relative to a predicted value of the to-be-monitored indicator at the target time, and the anomaly duration score is used to represent a ratio of the actual value of the to-be-monitored indicator to an abnormal value within a preset time window including the target time;
the second determining module 12 is configured to determine a first health degree score of the to-be-monitored indicator at the target time according to the deviation degree score and the abnormality duration score.
According to the monitoring device for the health degree of the performance indexes, computer equipment acquires actual values of indexes to be monitored at a target moment, and determines deviation degree grading and abnormal duration degree grading of the indexes to be monitored at the target moment according to parameters of an abnormal monitoring model obtained through pre-training and the actual values, and determines that the indexes to be monitored are at a first health degree grading of the target moment according to the deviation degree grading and the abnormal duration degree grading. The abnormity monitoring model for determining the deviation degree score and the abnormity duration score of the index to be monitored is obtained by pre-training, namely the parameter of the abnormity monitoring model is obtained by pre-training, namely, the parameter equivalent to the detection threshold value of the index to be monitored is not manually set, so that the manual participation is reduced, the labor cost is reduced, and the accuracy of the monitoring result is improved. Meanwhile, the first health degree score of the index to be monitored is obtained in the two aspects of comprehensive deviation degree score and abnormal persistence degree score, and reference factors are comprehensive, so that the accuracy of the monitoring result is further improved.
Optionally, on the basis of the above embodiment, the apparatus further includes: the device comprises a second obtaining module, a third determining module, a fourth determining module and a training module.
Specifically, the second obtaining module is configured to obtain historical data of the index to be monitored before the first obtaining module obtains the actual value of the index to be monitored at the target time;
the third determination module is used for determining the data type of the historical data;
the fourth determination module is used for determining a target basic model to be trained according to the data type and a preset model mapping relation, wherein the model mapping relation comprises a corresponding relation between the data type and the basic model;
and the training module is used for training the target basic model according to the historical data to obtain an abnormal monitoring model.
Optionally, on the basis of the above embodiment, the apparatus further includes: the device comprises a third acquisition module and a first merging module.
Specifically, the third obtaining module is used for obtaining a first health degree score of each index to be monitored corresponding to the target component;
the first merging module is used for merging the first health degree scores of the indexes to be monitored to obtain a second health degree score of the target component at the target moment.
Optionally, on the basis of the above embodiment, the apparatus further includes: the device comprises a fourth acquisition module and a second merging module.
Specifically, the fourth obtaining module is configured to obtain a second health degree score of each component corresponding to the target system;
and the second merging module is used for merging the second health degree scores of the components to obtain a third health degree score of the target system at the target moment.
Optionally, on the basis of the above embodiment, the apparatus further includes: a fifth acquiring module and a third combining module.
Specifically, the fifth obtaining module is configured to obtain a first health degree score of each index to be monitored, which has an association relationship;
and the third merging module is used for merging the first health degree scores of all the indexes to be monitored to obtain a fourth health degree score of the associated index at the target moment.
Optionally, on the basis of the above embodiment, the apparatus further includes: and a processing module.
Specifically, the processing module is configured to determine a target state of the to-be-monitored indicator at the target time according to the first health degree score and a preset state mapping relationship, and output the target state, where the state mapping relationship includes a corresponding relationship between the first health degree score and the indicator state.
Optionally, on the basis of the above embodiment, the first determining module is specifically configured to determine, according to a predicted value parameter, a normal value upper limit parameter, a normal value lower limit parameter, and the actual value of the to-be-monitored index at the target time, which are included in the abnormality monitoring model obtained through pre-training, an offset score of the to-be-monitored index at the target time.
Optionally, on the basis of the above embodiment, the first determining module is specifically configured to determine, according to a normal value upper limit parameter and a normal value lower limit parameter of the to-be-monitored indicator at the target time, which are included in an anomaly monitoring model obtained through pre-training, a first probability that the actual value is an abnormal value; acquiring second probabilities of the index to be monitored at each historical moment in a preset time window, wherein the second probabilities are used for representing the probability that the actual value of the index to be monitored at the target historical moment is an abnormal value; and determining the abnormal persistence degree score of the index to be monitored at the target moment according to the first probability and the second probability.
Optionally, the parameters of the anomaly monitoring model include a predicted value, an upper normal value limit, and a lower normal value limit of the index to be monitored at each time.
In one embodiment, a computer device is provided, the internal structure of which may be as shown in FIG. 5. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing data in the monitoring process of the health degree of the performance index. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method for monitoring health of a performance indicator.
Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring an actual value of an index to be monitored at a target moment;
determining a deviation degree score and an abnormal duration score of the index to be monitored at the target time according to a parameter of an abnormal monitoring model obtained by pre-training and the actual value, wherein the deviation degree score is used for representing the deviation degree of the actual value relative to a predicted value of the index to be monitored at the target time, and the abnormal duration score is used for representing the proportion of the actual value of the index to be monitored as an abnormal value in a preset time window containing the target time;
and determining a first health degree score of the index to be monitored at the target moment according to the deviation degree score and the abnormal persistence degree score.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring historical data of an index to be monitored; determining a data type of the historical data; determining a target basic model to be trained according to the data type and a preset model mapping relation, wherein the model mapping relation comprises a corresponding relation between the data type and the basic model; and training the target basic model according to the historical data to obtain an abnormal monitoring model.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring a first health degree score of each index to be monitored corresponding to a target component; and combining the first health degree scores of all the indexes to be monitored to obtain a second health degree score of the target component at the target moment.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring a second health degree score of each component corresponding to the target system; and combining the second health degree scores of the components to obtain a third health degree score of the target system at the target moment.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring a first health degree score of each index to be monitored with an incidence relation; and combining the first health degree scores of all the indexes to be monitored to obtain a fourth health degree score of the associated index at the target moment.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and determining a target state of the index to be monitored at the target moment according to the first health degree score and a preset state mapping relation, and outputting the target state, wherein the state mapping relation comprises a corresponding relation between the first health degree score and the index state.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and determining the deviation degree score of the index to be monitored at the target moment according to a predicted value parameter, a normal value upper limit parameter, a normal value lower limit parameter and the actual value of the index to be monitored at the target moment, which are contained in an abnormal monitoring model obtained by pre-training.
In one embodiment, the processor, when executing the computer program, further performs the steps of: determining a first probability that the actual value is an abnormal value according to a normal value upper limit parameter and a normal value lower limit parameter of the index to be monitored at the target moment, which are contained in an abnormal monitoring model obtained through pre-training; acquiring second probabilities of the index to be monitored at each historical moment in a preset time window, wherein the second probabilities are used for representing the probability that the actual value of the index to be monitored at the target historical moment is an abnormal value; and determining the abnormal persistence degree score of the index to be monitored at the target moment according to the first probability and the second probability.
Optionally, the parameters of the anomaly monitoring model include a predicted value, an upper normal value limit, and a lower normal value limit of the index to be monitored at each time.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring an actual value of an index to be monitored at a target moment;
determining a deviation degree score and an abnormal duration score of the index to be monitored at the target time according to a parameter of an abnormal monitoring model obtained by pre-training and the actual value, wherein the deviation degree score is used for representing the deviation degree of the actual value relative to a predicted value of the index to be monitored at the target time, and the abnormal duration score is used for representing the proportion of the actual value of the index to be monitored as an abnormal value in a preset time window containing the target time;
and determining a first health degree score of the index to be monitored at the target moment according to the deviation degree score and the abnormal persistence degree score.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring historical data of an index to be monitored; determining a data type of the historical data; determining a target basic model to be trained according to the data type and a preset model mapping relation, wherein the model mapping relation comprises a corresponding relation between the data type and the basic model; and training the target basic model according to the historical data to obtain an abnormal monitoring model.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring a first health degree score of each index to be monitored corresponding to a target component; and combining the first health degree scores of all the indexes to be monitored to obtain a second health degree score of the target component at the target moment.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring a second health degree score of each component corresponding to the target system; and combining the second health degree scores of the components to obtain a third health degree score of the target system at the target moment.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring a first health degree score of each index to be monitored with an incidence relation; and combining the first health degree scores of all the indexes to be monitored to obtain a fourth health degree score of the associated index at the target moment.
In one embodiment, the computer program when executed by the processor further performs the steps of: and determining a target state of the index to be monitored at the target moment according to the first health degree score and a preset state mapping relation, and outputting the target state, wherein the state mapping relation comprises a corresponding relation between the first health degree score and the index state.
In one embodiment, the computer program when executed by the processor further performs the steps of: and determining the deviation degree score of the index to be monitored at the target moment according to a predicted value parameter, a normal value upper limit parameter, a normal value lower limit parameter and the actual value of the index to be monitored at the target moment, which are contained in an abnormal monitoring model obtained by pre-training.
In one embodiment, the computer program when executed by the processor further performs the steps of: determining a first probability that the actual value is an abnormal value according to a normal value upper limit parameter and a normal value lower limit parameter of the index to be monitored at the target moment, which are contained in an abnormal monitoring model obtained through pre-training; acquiring second probabilities of the index to be monitored at each historical moment in a preset time window, wherein the second probabilities are used for representing the probability that the actual value of the index to be monitored at the target historical moment is an abnormal value; and determining the abnormal persistence degree score of the index to be monitored at the target moment according to the first probability and the second probability.
Optionally, the parameters of the anomaly monitoring model include a predicted value, an upper normal value limit, and a lower normal value limit of the index to be monitored at each time.
The performance index health degree monitoring device, the computer device and the storage medium provided in the above embodiments may execute the performance index health degree monitoring method provided in any embodiment of the present application, and have corresponding functional modules and beneficial effects for executing the method. For technical details that are not described in detail in the above embodiments, reference may be made to the method for monitoring the health of the performance index provided in any embodiment of the present application.
The above description is only exemplary embodiments of the present application, and is not intended to limit the scope of the present application.
In general, the various embodiments of the application may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. For example, some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device, although the application is not limited thereto.
Embodiments of the application may be implemented by a data processor of the fault injection testing apparatus executing computer program instructions, for example in a processor entity, or by hardware, or by a combination of software and hardware. The computer program instructions may be assembly instructions, Instruction Set Architecture (ISA) instructions, machine related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages.
Any logic flow block diagrams in the figures of this application may represent program steps, or may represent interconnected logic circuits, modules, and functions, or may represent a combination of program steps and logic circuits, modules, and functions. The computer program may be stored on a memory. The memory may be of any type suitable to the local technical environment and may be implemented using any suitable data storage technology, such as, but not limited to, Read Only Memory (ROM), Random Access Memory (RAM), optical storage devices and systems (digital versatile disks, DVDs, or CD discs), etc. The computer readable medium may include a non-transitory storage medium. The data processor may be of any type suitable to the local technical environment, such as but not limited to general purpose computers, special purpose computers, microprocessors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), programmable logic devices (FGPAs), and processors based on a multi-core processor architecture.
The foregoing has provided by way of exemplary and non-limiting examples a detailed description of exemplary embodiments of the present application. Various modifications and adaptations to the foregoing embodiments may become apparent to those skilled in the relevant arts in view of the drawings and the following claims without departing from the scope of the invention. Accordingly, the proper scope of the application is to be determined according to the claims.
Claims (12)
1. A method for monitoring the health degree of performance indexes is characterized by comprising the following steps:
acquiring an actual value of an index to be monitored at a target moment;
determining a deviation degree score and an abnormal duration score of the index to be monitored at the target time according to a parameter of an abnormal monitoring model obtained by pre-training and the actual value, wherein the deviation degree score is used for representing the deviation degree of the actual value relative to a predicted value of the index to be monitored at the target time, and the abnormal duration score is used for representing the proportion of the actual value of the index to be monitored as an abnormal value in a preset time window containing the target time;
and determining a first health degree score of the index to be monitored at the target moment according to the deviation degree score and the abnormal persistence degree score.
2. The method according to claim 1, wherein before the obtaining the actual value of the index to be monitored at the target time, the method further comprises:
acquiring historical data of an index to be monitored;
determining a data type of the historical data;
determining a target basic model to be trained according to the data type and a preset model mapping relation, wherein the model mapping relation comprises a corresponding relation between the data type and the basic model;
and training the target basic model according to the historical data to obtain an abnormal monitoring model.
3. The method of claim 1, further comprising:
acquiring a first health degree score of each index to be monitored corresponding to a target component;
and combining the first health degree scores of all the indexes to be monitored to obtain a second health degree score of the target component at the target moment.
4. The method of claim 1, further comprising:
acquiring a second health degree score of each component corresponding to the target system;
and combining the second health degree scores of the components to obtain a third health degree score of the target system at the target moment.
5. The method of claim 1, further comprising:
acquiring a first health degree score of each index to be monitored with an incidence relation;
and combining the first health degree scores of all the indexes to be monitored to obtain a fourth health degree score of the associated index at the target moment.
6. The method of claim 1 or 2, further comprising:
and determining a target state of the index to be monitored at the target moment according to the first health degree score and a preset state mapping relation, and outputting the target state, wherein the state mapping relation comprises a corresponding relation between the first health degree score and the index state.
7. The method according to any one of claims 1 to 5, wherein the determining the deviation degree score of the index to be monitored at the target time according to the parameter of the abnormality monitoring model obtained by pre-training and the actual value comprises:
and determining the deviation degree score of the index to be monitored at the target moment according to a predicted value parameter, a normal value upper limit parameter, a normal value lower limit parameter and the actual value of the index to be monitored at the target moment, which are contained in an abnormal monitoring model obtained by pre-training.
8. The method according to any one of claims 1 to 5, wherein the determining the abnormality duration score of the index to be monitored at the target time according to the parameters of the abnormality monitoring model obtained by pre-training and the actual values comprises:
determining a first probability that the actual value is an abnormal value according to a normal value upper limit parameter and a normal value lower limit parameter of the index to be monitored at the target moment, which are contained in an abnormal monitoring model obtained through pre-training;
acquiring second probabilities of the index to be monitored at each historical moment in a preset time window, wherein the second probabilities are used for representing the probability that the actual value of the index to be monitored at the target historical moment is an abnormal value;
and determining the abnormal persistence degree score of the index to be monitored at the target moment according to the first probability and the second probability.
9. The method according to any one of claims 1 to 5, wherein the parameters of the abnormality monitoring model include a predicted value, an upper normal value limit, and a lower normal value limit of the index to be monitored at each time.
10. A monitoring device of performance index health degree, characterized by includes:
the first acquisition module is used for acquiring the actual value of the index to be monitored at the target moment;
the first determination module is used for determining a deviation degree score and an abnormal duration score of the index to be monitored at the target time according to a parameter of an abnormal monitoring model obtained through pre-training and the actual value, wherein the deviation degree score is used for representing the deviation degree of the actual value relative to a predicted value of the index to be monitored at the target time, and the abnormal duration score is used for representing the proportion of the actual value of the index to be monitored to the abnormal value in a preset time window containing the target time;
and the second determination module is used for determining a first health degree score of the index to be monitored at the target moment according to the deviation degree score and the abnormal persistence degree score.
11. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method according to any of claims 1-9 when executing the computer program.
12. A storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any one of claims 1-9.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911106724.3A CN112801434A (en) | 2019-11-13 | 2019-11-13 | Method, device, equipment and storage medium for monitoring performance index health degree |
| PCT/CN2020/127672 WO2021093715A1 (en) | 2019-11-13 | 2020-11-10 | Performance index health monitoring method, device and apparatus, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911106724.3A CN112801434A (en) | 2019-11-13 | 2019-11-13 | Method, device, equipment and storage medium for monitoring performance index health degree |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112801434A true CN112801434A (en) | 2021-05-14 |
Family
ID=75803254
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911106724.3A Pending CN112801434A (en) | 2019-11-13 | 2019-11-13 | Method, device, equipment and storage medium for monitoring performance index health degree |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112801434A (en) |
| WO (1) | WO2021093715A1 (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113593142A (en) * | 2021-07-26 | 2021-11-02 | 中国工商银行股份有限公司 | Automatic Teller Machine (ATM) patrolling method and device |
| CN114323725A (en) * | 2022-01-26 | 2022-04-12 | 深圳市信润富联数字科技有限公司 | Health degree detection method, device and equipment for dispenser and storage medium |
| CN114896024A (en) * | 2022-03-28 | 2022-08-12 | 同方威视技术股份有限公司 | Method and device for detecting running state of virtual machine based on kernel density estimation |
| WO2023185358A1 (en) * | 2022-03-28 | 2023-10-05 | 同方威视技术股份有限公司 | Kernel density estimation-based virtual machine running state detection method and apparatus |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10595788B2 (en) * | 2016-05-31 | 2020-03-24 | Stmicroelectronics S.R.L. | Method for the detecting electrocardiogram anomalies and corresponding system |
| CN106571627A (en) * | 2016-10-12 | 2017-04-19 | 中国南方电网有限责任公司 | Secondary device health state evaluation method based on on-line monitoring information |
| CN106368816B (en) * | 2016-10-27 | 2018-09-25 | 中国船舶工业系统工程研究院 | A kind of online method for detecting abnormality of marine low speed diesel engine based on baseline offset |
| CN107766299B (en) * | 2017-10-24 | 2021-05-18 | 携程旅游信息技术（上海）有限公司 | Data index abnormity monitoring method and system, storage medium and electronic equipment |
-
2019
- 2019-11-13 CN CN201911106724.3A patent/CN112801434A/en active Pending
-
2020
- 2020-11-10 WO PCT/CN2020/127672 patent/WO2021093715A1/en active Application Filing
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113593142A (en) * | 2021-07-26 | 2021-11-02 | 中国工商银行股份有限公司 | Automatic Teller Machine (ATM) patrolling method and device |
| CN114323725A (en) * | 2022-01-26 | 2022-04-12 | 深圳市信润富联数字科技有限公司 | Health degree detection method, device and equipment for dispenser and storage medium |
| CN114896024A (en) * | 2022-03-28 | 2022-08-12 | 同方威视技术股份有限公司 | Method and device for detecting running state of virtual machine based on kernel density estimation |
| CN114896024B (en) * | 2022-03-28 | 2022-11-22 | 同方威视技术股份有限公司 | Method and device for detecting running state of virtual machine based on kernel density estimation |
| WO2023185358A1 (en) * | 2022-03-28 | 2023-10-05 | 同方威视技术股份有限公司 | Kernel density estimation-based virtual machine running state detection method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021093715A1 (en) | 2021-05-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113780691B (en) | Data testing method and device, electronic equipment and storage medium | |
| CN112801434A (en) | Method, device, equipment and storage medium for monitoring performance index health degree | |
| CN110457175B (en) | Service data processing method and device, electronic equipment and medium | |
| CN112419268A (en) | Method, device, equipment and medium for detecting image defects of power transmission line | |
| CN112632179A (en) | Model construction method and device, storage medium and equipment | |
| CN111007452A (en) | Fault diagnosis method and device of data acquisition system | |
| CN113242213A (en) | Power communication backbone network node vulnerability diagnosis method | |
| CN116743637A (en) | Abnormal flow detection method and device, electronic equipment and storage medium | |
| CN116227911A (en) | Risk monitoring and early warning method, device, equipment and medium for fault power failure event | |
| CN111935279B (en) | Internet of things network maintenance method based on block chain and big data and computing node | |
| CN114760190A (en) | Service-oriented converged network performance anomaly detection method | |
| CN114443738A (en) | Abnormal data mining method, device, equipment and medium | |
| CN110413482B (en) | Detection method and device | |
| CN109558258B (en) | Method and device for positioning root fault of distributed system | |
| CN111679924A (en) | Component software system reliability simulation method and device and electronic equipment | |
| CN116149971B (en) | Equipment fault prediction method and device, electronic equipment and storage medium | |
| CN115001997B (en) | Extreme value theory-based smart city network equipment performance abnormal threshold evaluation method | |
| CN117132176B (en) | Runoff forecasting model construction and runoff forecasting method based on forecasting factor screening | |
| CN113052509B (en) | Model evaluation method, model evaluation device, electronic apparatus, and storage medium | |
| CN112434178B (en) | Image classification method, device, electronic equipment and storage medium | |
| CN117667311A (en) | Container cluster monitoring and alarming method and device | |
| CN116975590A (en) | Data processing method, apparatus, program product, computer device, and medium | |
| CN117389788A (en) | Big data platform operation and maintenance method, device and medium | |
| CN117853087A (en) | Data analysis system of power equipment | |
| CN115170315A (en) | Monitoring report generation method and device, storage medium and electronic equipment |
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 |