CN115617613A - Data early warning method and device, electronic equipment and storage medium - Google Patents
Data early warning method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115617613A CN115617613A CN202211327899.9A CN202211327899A CN115617613A CN 115617613 A CN115617613 A CN 115617613A CN 202211327899 A CN202211327899 A CN 202211327899A CN 115617613 A CN115617613 A CN 115617613A
- Authority
- CN
- China
- Prior art keywords
- function
- fitting
- monitored
- fitted
- early warning
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3058—Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The embodiment of the application relates to the technical field of monitoring, and provides a data early warning method, a data early warning device, electronic equipment and a storage medium, wherein a function list corresponding to an object to be monitored is obtained aiming at the object to be monitored, the function list comprises a plurality of functions to be fitted, and one function to be fitted is used for representing a variation trend of the object to be monitored; then, fitting the function to be fitted in the function list for multiple times based on the actual data value of the object to be monitored to obtain a target fitting function with the minimum deviation between the represented change trend of the object to be monitored and the actual change trend of the object to be monitored; finally, early warning is carried out on the object to be monitored by utilizing a target fitting function; therefore, accurate early warning can be carried out before a fault occurs.
Description
Technical Field
The embodiment of the application relates to the technical field of monitoring, in particular to a data early warning method, a data early warning device, electronic equipment and a storage medium.
Background
In the operation process of the information system, risk factors in various aspects such as hardware, network, software and the like need to be faced, and the factors can cause the quality of system service to be reduced and even cause system crash.
At present, in order to ensure the stable operation of a system, system operation and maintenance personnel often add a series of monitoring objects to the system after the system is on-line, for example, service delay, service success rate, and the like, and set a monitoring threshold of each monitoring object at the same time. In the running process of the system, various monitoring objects are continuously sampled, and when the data sampling value of a certain monitoring object exceeds the monitoring threshold value, an alarm is given.
However, this method can only alarm the fault that has occurred, and cannot alarm in advance before the fault occurs.
Disclosure of Invention
The embodiment of the application aims to provide a data early warning method and device, electronic equipment and a storage medium, which can perform accurate early warning before a fault occurs.
In order to achieve the above object, the embodiments of the present application adopt the following technical solutions:
in a first aspect, an embodiment of the present application provides a data early warning method, which is applied to an electronic device, and the method includes:
acquiring a function list corresponding to an object to be monitored, wherein the function list comprises a plurality of functions to be fitted, and one function to be fitted is used for representing a variation trend of the object to be monitored;
fitting the function to be fitted in the function list for multiple times based on the actual data value of the object to be monitored to obtain a target fitting function; the deviation between the variation trend of the object to be monitored represented by the target fitting function and the actual variation trend of the object to be monitored is minimum;
and early warning the object to be monitored by utilizing the target fitting function.
Optionally, the method further comprises:
periodically sampling the actual data value of the object to be monitored according to a preset sampling interval;
and aiming at each sampling period, taking the sampling period and the corresponding actual data value thereof as sampling data, and adding the sampling data into a pre-constructed sampling data set.
Optionally, the step of fitting the function to be fitted in the function list for multiple times based on the actual data value of the object to be monitored to obtain a target fitting function includes:
acquiring the last sampling data and the sampling data with the preset number from the sampling data set to obtain a plurality of candidate sampling data;
fitting each function to be fitted in the function list according to the candidate sampling data to obtain each fitting function;
verifying each fitting function and determining candidate fitting functions; the variation trend of the object to be monitored represented by the candidate fitting function is the largest in deviation with the actual variation trend of the object to be monitored;
removing the function to be fitted corresponding to the candidate fitting function from the function list;
and repeatedly executing the steps until only one function to be fitted remains in the function list, and taking a fitting function obtained by the function to be fitted in the last fitting as the target fitting function.
Optionally, the step of fitting each function to be fitted in the function list according to the multiple candidate sample data to obtain each fitting function includes:
for each function to be fitted, if the function to be fitted is a system time function, solving each coefficient in the function to be fitted by using a least square method according to the plurality of candidate sampling data to obtain the fitting function;
and if the function to be fitted is an extended time function, solving each coefficient in the function to be fitted by using a gradient descent method according to the plurality of candidate sampling data, the coefficient partial derivative function group of the extended time function and the coefficient guess value to obtain the fitting function.
Optionally, the candidate sampling data includes a candidate sampling period and its corresponding actual data value;
the step of verifying each fitting function and determining candidate fitting functions comprises:
for each fitting function, substituting the candidate sampling data into the fitting function to obtain a predicted data value corresponding to each candidate sampling period;
calculating a variance sum corresponding to the fitting function according to the predicted data value and the actual data value corresponding to each candidate sampling period, wherein the variance sum indicates the deviation between the variation trend of the object to be monitored represented by the fitting function and the actual variation trend of the object to be monitored;
calculating a fitting result weight of each fitting function according to the variance sum corresponding to each fitting function, wherein the fitting result weight represents the fitting effect of the fitting function;
and taking the fitting function with the maximum weight value of the fitting result as the candidate fitting function.
Optionally, the step of calculating a fitting result weight of each fitting function according to the variance sum corresponding to each fitting function includes:
according to the variance sum corresponding to each fitting function, utilizing a preset formula
Calculating the fitting result weight of each fitting function;
wherein, W ij Representing the fitting result weight of the ith fitting function in the jth fitting; w i(j-1) Represents the weight of the fitting result of the ith fitting function in the (j-1) th fitting, and W i(j-1) Is 0; sum ij Representing the corresponding variance sum of the ith fitting function in the jth fitting; sum total Representing the sum of the variances and sums corresponding to each of said fitting functions participating in the jth fitting,
n represents the number of said fitting functions participating in the jth fitting, and k represents the number of said fitting functions participating in the jth fitting.
Optionally, the step of performing an early warning on the object to be monitored by using the target fitting function includes:
obtaining a sampling period of the last sampling data from the sampling data set;
determining a future sampling period to be predicted according to the sampling period of the last sampling data, the sampling interval and a preset early warning time offset;
substituting the sampling period to be predicted into the target fitting function to obtain a predicted value of the object to be monitored in the sampling period to be predicted;
if the predicted value exceeds an early warning threshold value, early warning is carried out on the object to be monitored at the early warning moment;
the early warning moment is before the sampling period to be predicted, and the early warning moment and the sampling period to be predicted have the difference of the early warning time offset.
Optionally, the electronic device stores a function library, where the function library includes a plurality of system time functions and a plurality of extended time functions, and the extended time functions are customized by system operation and maintenance personnel;
the step of obtaining the function list corresponding to the object to be monitored comprises the following steps:
responding to selection operation, and acquiring a plurality of functions to be fitted from the function library to obtain the function list; wherein the function to be fitted is at least one of the system time function and the extended time function.
In a second aspect, an embodiment of the present application further provides a data early warning apparatus, which is applied to an electronic device, and the apparatus includes:
the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a function list corresponding to an object to be monitored, the function list comprises a plurality of functions to be fitted, and one function to be fitted is used for representing a variation trend of the object to be monitored;
the fitting module is used for fitting the function to be fitted in the function list for multiple times based on the actual data value of the object to be monitored to obtain a target fitting function; the deviation between the variation trend of the object to be monitored represented by the target fitting function and the actual variation trend of the object to be monitored is minimum;
and the early warning module is used for utilizing the target fitting function to early warn the object to be monitored.
In a third aspect, an embodiment of the present application further provides an electronic device, which includes a processor and a memory, where the memory is used to store a program, and the processor is used to implement the data early warning method in the first aspect when executing the program.
In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the data early warning method in the first aspect.
Compared with the prior art, the data early warning method, the data early warning device, the electronic device and the storage medium provided by the embodiment of the application firstly acquire a function list corresponding to an object to be monitored, wherein the function list comprises a plurality of functions to be fitted, and one function to be fitted is used for representing a change trend of the object to be monitored; then, fitting the function to be fitted in the function list for multiple times based on the actual data value of the object to be monitored to obtain a target fitting function with the minimum deviation between the represented change trend of the object to be monitored and the actual change trend of the object to be monitored; finally, early warning is carried out on the object to be monitored by utilizing a target fitting function; therefore, accurate early warning can be carried out before the fault occurs.
Drawings
Fig. 1 shows a first flowchart of a data early warning method provided in an embodiment of the present application.
Fig. 2 shows a second flowchart of a data early warning method according to an embodiment of the present application.
Fig. 3 illustrates an example graph of periodic sampling provided by an embodiment of the present application.
Fig. 4 is a schematic flowchart of step S103 in the data early warning method shown in fig. 1 and 2.
Fig. 5 is a schematic flowchart of step S105 in the data early warning method shown in fig. 1 and 2.
Fig. 6 shows a block schematic diagram of a data early warning apparatus according to an embodiment of the present application.
Fig. 7 shows a block schematic diagram of an electronic device according to an embodiment of the present application.
An icon: 100-a data pre-warning device; 101-an acquisition module; 103-a fitting module; 105-an early warning module; 104-a sampling module; 10-an electronic device; 11-a processor; 12-a memory; 13-bus.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
Generally, in order to ensure smooth operation of an information system (e.g., a network monitoring system, a network management system, an IT operation and maintenance system, etc.), a system operation and maintenance person may add a series of monitoring objects to the system after the system is on-line, set a monitoring threshold value of each monitoring object, observe an operation state of the system, and intervene in time for an abnormality that may be triggered.
The monitoring mode mainly adopted at present is as follows: in the running process of the system, various monitoring objects are continuously sampled, and when the data sampling value of one monitoring object exceeds the monitoring threshold value, an alarm is given. However, since the data sampling values are all used for sampling the occurred state of the system, the method cannot predict the future by sampling data. That is, only a failure that has occurred can be warned, and it is not possible to warn in advance before the failure occurs.
Meanwhile, it is very difficult to perform early warning before a fault occurs by setting a monitoring threshold. The reason is that: the trend curve of a certain monitoring object obtained along with the operation of the system is difficult to accurately determine before the operation of the system, so that when a system operation and maintenance worker sets a monitoring threshold, the monitoring threshold is difficult to accurately set on the trend curve, and the final result is as follows: or the system abnormity happens before the monitoring threshold value is reached, or a large number of false alarm early warnings are given.
Therefore, not only is effective early warning achieved, but also unnecessary early warning misjudgment is reduced, the difficulty in setting the monitoring threshold is very high, and accurate early warning cannot be performed before a fault occurs.
In order to solve the technical problem, in the embodiment of the present application, based on an actual data value of an object to be monitored, a function to be fitted in a function list corresponding to the object to be monitored is fitted for multiple times, where the function list includes a plurality of functions to be fitted, one function to be fitted is used to represent a variation trend of the object to be monitored, a target fitting function with a minimum deviation between the represented variation trend of the object to be monitored and an actual variation trend of the object to be monitored is obtained, and then the target fitting function is used to perform early warning on the object to be monitored, so that accurate early warning can be performed before a fault occurs. As described in detail below.
The electronic device in the embodiment of the present application may be a server, for example, a single server, a server cluster, or the like; or may be a terminal, such as a desktop computer, a laptop computer, a smart phone, a tablet computer, etc. The embodiment of the present application does not set any limit to this.
In this embodiment, for an information system, for example, a network monitoring system, a network management system, an IT operation and maintenance system, and the like, before the system is online, a system operation and maintenance worker may configure a monitoring object library and a function library for the system, so as to facilitate subsequent monitoring of the system.
That is, for an information system, the electronic device may store a monitoring object library and a function library of the system in advance. For ease of understanding, before describing specific implementations of the embodiments of the present application, a description is given of a monitoring object library and a function library.
The monitoring object library may include: the system operation and maintenance personnel are various monitoring objects which are configured in advance for the system and need to be monitored in the system operation process, such as service delay, service success rate, CPU occupancy rate and the like.
Each monitoring object may include: identification, name, early warning threshold, early warning time offset, and sampling interval.
Wherein the identifier is used for uniquely identifying a monitored object for sampling. The name is used to describe the monitored object. The early warning threshold value refers to a data value of a monitored object which may cause system abnormality. The sampling interval refers to a time interval between two samplings of an actual data value of a monitored object.
The early warning time offset refers to the early warning time of the monitored object with a deviation trend. For example, for a monitored object, by using the data early warning method provided by the embodiment of the present application, it is predicted that an abnormality occurs in the day 16.
The function library may include a plurality of system time functions, one system time function being used to characterize a trend of the monitored object.
It should be noted that each system time function in the function library is not a definite function, but a definite function template. That is, the expression of the function is determined, but each coefficient in the function is unknown, and a specific coefficient needs to be solved according to actual monitoring requirements.
Alternatively, the system time functions in the function library may include, but are not limited to, standard linear functions, standard polynomial functions, and the like. The standard polynomial function is used for representing the violent change trend of the monitored object. The functional expression of the standard linear function and the standard polynomial function is as follows:
standard linear function: f (t) = a 0 +a 1 *t
Standard polynomial function: f (t) = a 0 +a 1 *t+a 2 *t 2 +…+a n *t n+1 (n>1)
In one possible implementation, each system time function in the function library may include: function identification, function expression, default parameters and function fitting mode.
The function identifier is a character string used for identifying a unique system time function in the function library.
The function expression is used for the system operation and maintenance personnel to select a corresponding system time function, such as the function expression of the standard linear function shown above, the function expression of the standard polynomial function, and the like.
The default parameters refer to initial configuration parameters of the system time function, for example, values of the number n of terms in the above standard polynomial function, and the like.
The function fitting mode refers to a fitting mode configured for the system time function in advance, that is, a mode for solving specific coefficients in the system time function, for example, a least square method. That is, the coefficient solving calculation of the system time function may be realized by the least square method, and each coefficient value in the system time function is obtained.
In a possible situation, in practical application, a function library provided by the system may not meet a specific monitoring requirement, and in this case, system operation and maintenance personnel may also customize the extended time function according to the practical monitoring requirement, and add each customized extended time function into the function library, so as to facilitate selection from the function library in subsequent monitoring. An extended time function is used to characterize a trend of the monitored object.
Like the system time function, the various extended time functions customized by the system operation and maintenance personnel are not determined functions but determined function templates. That is, the expression of the function is determined, but each coefficient in the function is unknown, and a specific coefficient needs to be solved according to the actual monitoring requirement.
Optionally, the extended time function may include: the method comprises the following steps of function identification, a function expression, a coefficient partial derivative function group, a coefficient guess value and a function fitting mode.
The function identifier is a character string used for identifying a unique extended time function in the function library.
The function expression is self-defined by system operation and maintenance personnel, and is also a character string used for describing an evaluation calculation formula of the extended time function.
The set of coefficient partial derivative functions is an array of strings that describe the partial derivative calculation formula for each coefficient in the extended time function.
The coefficient guess value is a floating point numerical array and is used for calculating the initial value of the coefficient when the time function coefficient is expanded by the gradient descent method.
The function fitting method refers to a fitting method of the extended time function, that is, a method of solving specific coefficients in the extended time function, for example, a gradient descent method. That is, the coefficient approximation solving calculation can be realized by the gradient descent method, and each coefficient value in the extended time function is obtained.
It should be noted that the function expression of the extended time function and the partial derivative calculation formula of each coefficient in the extended time function are both an arithmetic expression, and the expressions may include coefficients, function arguments, operators, and the like.
Wherein the coefficient may be a i (i ≧ 0), for example, the extended time function may include a plurality of coefficients, which may be represented by a 0 、a 1 、a 2 8230denotes each coefficient.
Meanwhile, the system time function and the extended time function related in the embodiment of the application both correspond to time functions, so that the function argument is fixed to t.
Operators may include common operators such as, +, -, x,/, brackets, etc., where brackets allow nested use in expressions. The operators may also include function operators, such as Math.abs (x), math.pow (x, y), math.log (x), math.sin (x), math.cos (x), math.tan (x), etc., where abs is an absolute value function for x, pow is a y-th power function for x, log is a log function for x, sin is a sine function for x, cos is a cosine function for x, and tan is a tangent function for x.
Optionally, the extended time function customized by the system operation and maintenance personnel may include, but is not limited to, an exponential function, a logarithmic function, a mixture function, and the like. The exponential function, the logarithmic function and the mixing function are all used for representing the sharp variation trend of the monitored object. The function expressions for the exponential function, the logarithmic function, the mixing function, the set of coefficient partial derivative functions, and the coefficient guesses are as follows:
1. exponential function
The function expression: f (t) = a 0 *Math.pow(a 1 ,t)
Set of coefficient partial derivative functions:
Fa 0 ＝Math.pow(a 1 ,t)
Fa 1 ＝a 0 *Math.pow(a 1 ,(t-1))*t
coefficient guess value: {5.0,1.0}. Namely, a 0 And a 1 Are 5.0 and 1.0, respectively.
2. Logarithmic function
The function expression: f (t) = a 0 *Math.log(a 1 *t)+a 2
Set of coefficient partial derivative functions:
Fa 0 ＝Math.log(t)+Math.log(a 1 )
Fa 1 ＝a 0 /a 1
Fa 2 ＝1
coefficient guess value: {1.0,1.0,0.8}. Namely, a 0 、a 1 And a 2 Are 1.0,1.0 and 0.8, respectively.
3. Mixing function
The function expression: f (t) = a 0 +a 1 /(a 2 +Math.pow(t,a 3 ))
Set of coefficient partial derivative functions:
Fa 0 ＝1
Fa 1 ＝1/(Math.pow(t,a 3 )+a 2 )
Fa 2 ＝-a 1 /(Math.pow(t,(2*a 3 ))+(2*a 2 *Math.pow(t,a 3 )+Math.pow(a 2 ,2))
Fa 3 ＝-(a 1 *Math.pow(t,a 3 )*Math.log(t))/(Math.pow(t,(2*a 3 ))+2*a 2 *Math.pow(t,a 3 ))+Math.pow(a 2 ,2))
coefficient guess value: {5.0,2.0,1.0,1.0}. Namely, a 0 、a 1 、a 2 And a 3 Are 5.0,2.0,1.0 and 1.0, respectively.
The following describes a specific implementation of the embodiment of the present application in detail with reference to the monitoring object library and the function library described above.
Referring to fig. 1, fig. 1 is a schematic flow chart illustrating a data early warning method according to an embodiment of the present disclosure. The data early warning method is applied to electronic equipment and can comprise the following steps:
s101, a function list corresponding to an object to be monitored is obtained, wherein the function list comprises a plurality of functions to be fitted, and one function to be fitted is used for representing a variation trend of the object to be monitored.
In this embodiment, the object to be monitored may be any one of the monitoring objects in the monitoring object library, for example, the CPU occupancy. It should be noted that, in the embodiment of the present application, for convenience of understanding, any object to be monitored is taken as an example for description, and it is not intended to monitor only the object to be monitored. It can be understood that, in the system operation process, each monitored object in the monitored object library is monitored, and the object to be monitored may be any one of the monitored objects.
As can be seen from the foregoing content, the electronic device stores a function library, where the function library includes a plurality of system time functions and a plurality of extended time functions, and the extended time functions are self-defined by the system operation and maintenance personnel, and therefore, the process of obtaining the function list corresponding to the object to be monitored in step S101 may include:
responding to the selection operation, and acquiring a plurality of functions to be fitted from a function library to obtain a function list; wherein, the function to be fitted is at least one of a system time function and an extended time function.
In this embodiment, a time function in the function library is used to represent a variation trend of the monitored object, but in practice, for the object to be monitored, the system operation and maintenance personnel may not be able to estimate the variation trend of the object to be monitored in advance. Therefore, the system operation and maintenance personnel can select a plurality of time functions from the function library, and each selected time function is used as a function to be fitted.
Correspondingly, the selection operation refers to an operation of selecting a time function from the function library by the system operation and maintenance personnel, and each time function selected by the system operation and maintenance personnel is taken as a function to be fitted, so that a function list of the object to be monitored is finally obtained.
It can be understood that the plurality of functions to be fitted in the function list may all be system time functions, may all be extended time functions, and may also be a combination of the system time functions and the extended time functions. System operation and maintenance personnel can flexibly select a function to be fitted according to the possible change trend of the object to be monitored, and the embodiment of the application does not limit the function to be fitted.
S103, fitting the function to be fitted in the function list for multiple times based on the actual data value of the object to be monitored to obtain a target fitting function; and the deviation between the variation trend of the object to be monitored represented by the target fitting function and the actual variation trend of the object to be monitored is minimum.
In this embodiment, after the function list of the object to be monitored is determined, multiple fitting is performed on the function to be fitted in the function list corresponding to the object to be monitored based on the actual data value of the object to be monitored. That is, since the function to be fitted is a function template, and the coefficients therein are unknown, the coefficients in each function to be fitted in the function list are solved based on the actual data value of the object to be monitored, and this engineering is to fit the function to be fitted.
Since the function list includes a plurality of functions to be fitted, and one function to be fitted is used to represent a variation trend of the object to be monitored, the functions to be fitted in the function list need to be fitted for a plurality of times until a target fitting function with the minimum deviation between the variation trend of the represented object to be monitored and the actual variation trend of the object to be monitored is selected. It is noted that the target fitting function here, unlike the function to be fitted, is a deterministic function, i.e. the individual coefficients in the target fitting function are known.
And S105, early warning the object to be monitored by using the target fitting function.
In this embodiment, after the target fitting function is determined in step S102, the target fitting function can be used to perform early warning on the object to be monitored. Namely, the target fitting function is utilized to predict the time when the object to be monitored may be abnormal, and early warning is carried out in advance.
Meanwhile, the deviation between the variation trend of the object to be monitored represented by the target fitting function and the actual variation trend of the object to be monitored is minimum, so that the early warning accuracy can be ensured, and accurate early warning can be performed before a fault occurs.
As can be seen from the foregoing, to fit the function to be fitted in the function list according to the actual data value of the object to be monitored, the actual data value of the object to be monitored must be sampled. That is, the data early warning method provided in the embodiment of the present application includes a sampling process of an actual data value in addition to the function fitting process in step S103 and the early warning process in step S105.
Therefore, referring to fig. 2 on the basis of fig. 1, the data early warning method provided in the embodiment of the present application further includes steps S102 to S104.
And S102, periodically sampling the actual data value of the object to be monitored according to a preset sampling interval.
S104, regarding each sampling period, adding the sampling period and the corresponding actual data value thereof to a pre-constructed sampling data set as sampling data.
In this embodiment, the actual data value of the object to be monitored may be periodically sampled according to the sampling interval defined in the monitored object library. Each sampling period may be the time of each sampling, and the sampling period is t in the system time function and the extended time function described above.
As shown in fig. 3, t1, t2, and t3 respectively represent the 1 st sampling period, the 2 nd sampling period, and the 3 rd sampling period, that is, the actual data value of the object to be monitoredThe 1 st, 2 nd and 3 rd samples are taken. Each sampling period can sample the actual data value of the object to be monitored, and after each sampling, the current sampling period and the actual data value sampled at the current time are used as sampling data to be added into a pre-constructed sampling data set. Each sample in the sample set may be represented by (t) i ，y i ) Is shown by t i Denotes the sampling period, y i Representing the actual data value.
Optionally, for the object to be monitored, the current sampling period may be determined by the following formula:
wherein, t i Representing the current sampling period, T m Indicating the current system time, T 0 Representing the first sampling time of the object to be monitored and deltat representing the sampling interval.
It should be noted that the sampling process of the actual data values in steps S102 to S104 and the function fitting process in step S103 are two processes independent from each other, and are performed in parallel.
Step S103 will be described in detail below.
Referring to fig. 4, step S103 may include S1031 to S1035, based on fig. 2.
And S1031, obtaining the last sampling data and the sampling data with the preset number from the sampling data set, and obtaining a plurality of candidate sampling data.
In this embodiment, since the sampling of the actual data values is independent of the function fitting process and the actual data values are periodically sampled at sampling intervals, i.e. the sampled data in the sampled data set is continuously increased. Therefore, in order to ensure the accuracy of subsequent early warning, when a function to be fitted in the function list is fitted each time, the last sampling data and m sampling data before the last sampling data are acquired from the sampling data set, and the specific value of m can be flexibly set by system operation and maintenance personnel according to actual requirements.
Optionally, a data queue with a set length may also be configured in advance, and a plurality of candidate sampling data used for fitting each time are added to the data queue, and then the function to be fitted in the function list may be fitted directly according to the data queue.
It can be understood that, for an object to be monitored, when fitting a function to be fitted in the function list at the 1 st time, the data queue may be empty, and therefore, the last sample data and m sample data before the last sample data need to be obtained from the sample data set and added to the data queue; and starting from the 2 nd function fitting, in order to avoid data repetition and improve fitting efficiency at the same time, only the last sampling data is acquired from the sampling data set and added into the data queue.
Optionally, the process of adding the last sample data in the sample data set to the data queue may include:
judging whether the data queue reaches a set length;
if not, adding the last sampled data in the sampled data set to the tail of the data queue;
and if so, dequeuing the head data in the data queue, and adding the last sampled data in the sampled data set to the tail of the data queue.
And S1032, fitting each function to be fitted in the function list according to the plurality of candidate sampling data to obtain each fitting function.
In this embodiment, when fitting the function to be fitted in the function list each time, the last sample data and m sample data before the last sample data may be directly obtained from the sample data set for fitting, or fitting may be performed according to the data queue.
In the fitting process, a plurality of candidate sampling data can be converted into a binomial (t, y) array, wherein t is a sampling period, y is an actual data value, and each function to be fitted in the function list is fitted according to the binomial (t, y) array.
As can be seen from the foregoing, the plurality of functions to be fitted in the function list may be a system time function, an extended time function, or a combination of the system time function and the extended time function. For the system time function, each coefficient of the system time function may be solved by a least square method. For the extended time function, each coefficient of the extended time function can be approximated and solved by a gradient descent method according to the coefficient partial derivative function group and the coefficient guess value of the extended time function.
Therefore, in S1032, the process of fitting each function to be fitted in the function list according to the multiple candidate sample data to obtain each fitted function may include:
for each function to be fitted, if the function to be fitted is a system time function, solving each coefficient in the function to be fitted by using a least square method according to a plurality of candidate sampling data to obtain a fitting function;
and if the function to be fitted is an extended time function, solving each coefficient in the function to be fitted by using a gradient descent method according to the plurality of candidate sampling data, the coefficient partial derivative function group of the extended time function and the coefficient guess value to obtain the fitting function.
That is, if the function to be fitted is a system time function, the array of binomials (t, y) is substituted into the system of coefficient equations according to the least square method, and each coefficient value [ a ] in the system of equations is solved 0 ,a 1 ,…,a k ]. If the function to be fitted is an extended time function, iterative operation is carried out according to a gradient descent method, and each coefficient value [ a ] in the extended time function is approximately solved 0 ,a 1 ,…,a k ]。
It should be noted that the fitting function here is a functional expression obtained by solving each coefficient in the function to be fitted and then substituting each coefficient into the function to be fitted.
For example, the function to be fitted is: f (t) = a 0 +a 1 * t, solving to obtain a 0 ＝1、a 1 =2, the fitting function obtained is: f (t) =1+2t.
S1033, verifying each fitting function, and determining candidate fitting functions; and the deviation between the variation trend of the object to be monitored represented by the candidate fitting function and the actual variation trend of the object to be monitored is the largest.
In this embodiment, the candidate sample data may include a candidate sample period and its corresponding actual data value.
Alternatively, the process of verifying each fitting function and determining candidate fitting functions may include S10331 to S10334.
S10331, for each fitting function, substituting the multiple candidate sampling data into the fitting function to obtain a predicted data value corresponding to each candidate sampling period.
That is, after each fitting function is obtained in S1032, taking any fitting function as an example, the predicted data value corresponding to each candidate sampling period, that is, the value of f (t), is calculated by substituting each candidate sampling period t into the fitting function.
And S10332, calculating a variance sum corresponding to the fitting function according to the predicted data value and the actual data value corresponding to each candidate sampling period, wherein the variance sum indicates the deviation between the variation trend of the object to be monitored represented by the fitting function and the actual variation trend of the object to be monitored.
Taking any one fitting function as an example, after the fitting function is utilized to calculate the predicted data value corresponding to each candidate sampling period, the formula is used for
Calculating the variance sum corresponding to the fitting function, wherein f (t) i ) Representing the predicted data value, y, corresponding to the ith candidate sampling period i Representing the actual data value corresponding to the ith candidate sampling period.
Since the fitting function represents the variation trend of the object to be monitored, the variance value represents the deviation between the variation trend of the object to be monitored represented by the fitting function and the actual variation trend of the object to be monitored. The larger the variance value is, the larger the deviation between the variation trend of the object to be monitored represented by the fitting function and the actual variation trend of the object to be monitored is; the smaller the variance value is, the smaller the deviation between the variation trend of the object to be monitored represented by the fitting function and the actual variation trend of the object to be monitored is.
And S10333, calculating a fitting result weight of each fitting function according to the variance sum corresponding to each fitting function, wherein the fitting result weight represents the fitting effect of the fitting function.
In this embodiment, after the variance sum corresponding to each fitting function is calculated, the fitting result weight of each fitting function may be calculated according to the variance sum corresponding to each fitting function. The fitting result weight represents the fitting effect of the fitting function, and the greater the fitting result weight is, the worse the fitting effect of the fitting function is; the smaller the weight of the fitting result is, the better the fitting effect of the fitting function is.
Optionally, the process of calculating the fitting result weight of each fitting function according to the variance sum corresponding to each fitting function includes:
according to the variance sum corresponding to each fitting function, a preset formula is utilized
Calculating the fitting result weight of each fitting function;
wherein, W ij Representing the fitting result weight of the ith fitting function in the jth fitting; w i(j-1) Represents the weight of the fitting result of the ith fitting function in the (j-1) th fitting, and W i(j-1) Is 0; sum ij Representing the corresponding variance sum of the ith fitting function in the jth fitting; sum total Representing the sum of the variances for each of the fitting functions participating in the jth fit,
n represents the number of fitting functions participating in the jth fitting, and k represents the number of fitting functions participating in the jth fitting.
And S10334, taking the fitting function with the maximum fitting result weight as a candidate fitting function.
It should be noted that the process of fitting each function to be fitted in S1032 and the process of verifying each fitting function in S1033 may be performed concurrently, so as to shorten the time of multidimensional fitting calculation and ensure the timeliness of early warning.
S1034, removing the function to be fitted corresponding to the candidate fitting function from the function list.
In this embodiment, the larger the weight of the fitting result is, the worse the fitting effect of the fitting function is; the smaller the weight of the fitting result is, the better the fitting effect of the fitting function is. Therefore, in the current fitting, the candidate fitting function with the largest fitting result weight needs to be found, and the function to be fitted corresponding to the candidate fitting function is deleted from the function list, so that the function to be fitted does not participate in the next fitting.
Optionally, each monitored object in the monitored object library may further include a fitting interval. The fitting interval refers to a time interval for fitting the function to be fitted in the function list corresponding to the monitored object twice. That is, after completing the fitting of one time, the next fitting is performed after waiting for the fitting interval.
It should be noted that S1031 to S1034 are processes of performing one-time fitting on functions to be fitted in the function list, after the one-time fitting is performed (i.e., S1034 is performed), whether the number of the functions to be fitted in the function list is 1 may be detected, and if not, the subsequent fitting needs to be performed again, that is, S1031 to S1034 are repeatedly performed until only one function to be fitted remains in the function list; and if the fitting time is 1, stopping subsequent fitting, and taking a fitting function obtained by the last fitting of only one function to be fitted in the function list as a target fitting function.
Alternatively, a participation fitting flag may be set for each function to be fitted in the function list, and the participation fitting flag defaults to "true". After the first fitting is completed, modifying the fitting mark of the function to be fitted corresponding to the candidate fitting function into 'false', which indicates that the function does not participate in the subsequent fitting again; then, counting the number of the functions to be fitted with the fitting marks of 'true' in the function list, and if the number is more than 1, performing subsequent fitting again by using the functions to be fitted with each fitting mark of 'true'; and if the number is equal to 1, taking a fitting function obtained by the function to be fitted with the fitting mark 'true' in the last fitting as a target fitting function.
And S1035, only one function to be fitted is left in the function list, and the fitting function obtained by the function to be fitted in the last fitting is used as a target fitting function.
Step S105 will be described in detail below.
Referring to fig. 5 in addition to fig. 2, step S105 may include S1051 to S1054.
S1051, obtaining the sampling period of the last sampling data from the sampling data set.
As can be seen from fig. 2, for an object to be monitored, an actual data value of the object to be monitored is periodically sampled according to a set sampling interval. The sampling of the actual data values is continuous and independent of the function fitting process and the pre-warning process. Therefore, in order to ensure the accuracy of the early warning, in the early warning process, early warning trial calculation is performed based on the sampling period of the last sampling data in the sampling data set.
And S1052, determining a future sampling period to be predicted according to the sampling period and the sampling interval of the last sampling data and a preset early warning time offset.
In this embodiment, the following formula may be preset:
determining a future sampling period to be predicted; wherein, t Δ Representing the sampling period to be predicted, T p Representing the early warning time offset, Δ t representing the sampling interval, t max Indicating the sampling period of the last sampled data.
And S1053, substituting the sampling period to be predicted into the target fitting function to obtain the predicted value of the object to be monitored in the sampling period to be predicted.
In this embodiment, assuming that the target fitting function is f (t) =1+2t, then t = t Δ Substituting the target fitting function into the target fitting function to obtain the predicted value y of the object to be monitored in the sampling period to be predicted Estimation of 。
S1054, if the predicted value exceeds the early warning threshold, early warning is carried out on the object to be monitored at the early warning moment; the early warning time is before the sampling period to be predicted, and the early warning time and the sampling period to be predicted have the difference of early warning time offset.
In this embodiment, a predicted value y of the object to be monitored in the sampling period to be predicted is obtained Estimation of Then, predict value y Estimation of And comparing the current value with the early warning threshold value of the object to be monitored.
If the predicted value does not exceed the early warning threshold value, it indicates that the object to be monitored does not have abnormality in the sampling period to be predicted, and continues to perform the next early warning detection, that is, returns to execute S1051.
If the predicted value exceeds the early warning threshold value, the object to be monitored is abnormal in the sampling period to be predicted, and the object to be monitored is alarmed at the early warning moment. The early warning time is at the early warning time offset before the sampling period to be predicted, for example, the sampling period to be predicted is 16. Obviously, the object to be monitored is alarmed at the early warning moment, and controllable abnormal intervention time can be reserved for system operation and maintenance personnel.
Compared with the prior art, the embodiment of the application has the following beneficial effects:
firstly, the future operation condition of an object to be monitored is estimated by using a time function, and system operation and maintenance personnel can customize and expand the time function to obtain the time function which is more in line with the monitoring requirement, so that the problem of high difficulty in a mode of setting a monitoring threshold in the prior art is solved;
secondly, selecting a plurality of time functions from the function library as functions to be fitted, wherein one function to be fitted is used for representing a change trend of the object to be monitored, and the plurality of functions to be fitted can be system time functions, extended time functions or both the system time functions and the extended time functions, so that the problem that the object to be monitored is lack of the corresponding fitting function determined in advance in practice can be avoided, and the practical operability is high;
thirdly, a least square method is adopted to fit the system time function and a gradient descent method is adopted to fit the extended time function, so that the support types of the fitting function are increased, and the time efficiency of fitting calculation is improved;
fourthly, in the function fitting calculation, a processing mode of multi-fitting calculation and parallel execution is adopted, so that the time required by the multi-dimensional function fitting calculation is greatly shortened, and the timeliness of early warning is ensured;
fifthly, fitting result feedback is introduced, when multiple functions are fitted, fitting variances and larger functions to be fitted are eliminated through multiple fitting calculation, and finally a target fitting function with the minimum deviation between the represented change trend of the object to be monitored and the actual change trend of the object to be monitored is selected, so that the error ranges of actual data values and predicted data values can be reduced when the target fitting function is used for subsequent early warning, and the accuracy of early warning is improved;
sixthly, in the early warning stage, if the fact that the object to be monitored is possibly abnormal in a certain future sampling period is predicted, an alarm is given in advance, and therefore controllable abnormal intervention time can be reserved for system operation and maintenance personnel.
In order to perform the corresponding steps in the above method embodiments and various possible embodiments, an implementation manner of the data early warning apparatus is provided below.
Referring to fig. 6, fig. 6 is a block diagram illustrating a data early warning apparatus 100 according to an embodiment of the present disclosure. The data early warning device 100 is applied to electronic equipment and comprises: the system comprises an acquisition module 101, a fitting module 103 and an early warning module 105.
The obtaining module 101 is configured to obtain a function list corresponding to an object to be monitored, where the function list includes a plurality of functions to be fitted, and one function to be fitted is used to represent a variation trend of the object to be monitored.
The fitting module 103 is configured to perform multiple fitting on a function to be fitted in the function list based on an actual data value of an object to be monitored to obtain a target fitting function; and the deviation between the variation trend of the object to be monitored represented by the target fitting function and the actual variation trend of the object to be monitored is minimum.
And the early warning module 105 is configured to perform early warning on the object to be monitored by using the target fitting function.
Optionally, the electronic device stores a function library, where the function library includes a plurality of system time functions and a plurality of extended time functions, and the extended time functions are self-defined by system operation and maintenance personnel;
the obtaining module 101 is specifically configured to: responding to the selection operation, and acquiring a plurality of functions to be fitted from a function library to obtain a function list; wherein, the function to be fitted is at least one of a system time function and an extended time function.
Optionally, the data early warning apparatus 100 further includes a sampling module 104, and the sampling module 104 is configured to:
periodically sampling actual data values of an object to be monitored according to a preset sampling interval;
and aiming at each sampling period, taking the sampling period and the corresponding actual data value as one sampling data and adding the sampling data into a pre-constructed sampling data set.
Optionally, the fitting module 103 is specifically configured to:
acquiring the last sampling data and the sampling data with the preset number from the sampling data set to obtain a plurality of candidate sampling data;
fitting each function to be fitted in the function list according to the candidate sampling data to obtain each fitting function;
verifying each fitting function and determining candidate fitting functions; the variation trend of the object to be monitored represented by the candidate fitting function is the largest in deviation with the actual variation trend of the object to be monitored;
removing the function to be fitted corresponding to the candidate fitting function from the function list;
and repeating the steps until only one function to be fitted remains in the function list, and taking the fitting function obtained by the function to be fitted in the last fitting as a target fitting function.
Optionally, the fitting module 103 performs a manner of fitting each function to be fitted in the function list according to a plurality of candidate sample data to obtain each fitted function, which may include:
aiming at each function to be fitted, if the function to be fitted is a system time function, solving each coefficient in the function to be fitted by utilizing a least square method according to a plurality of candidate sampling data to obtain a fitting function;
and if the function to be fitted is an extended time function, solving each coefficient in the function to be fitted by using a gradient descent method according to the plurality of candidate sampling data, the coefficient partial derivative function group of the extended time function and the coefficient guess value to obtain the fitting function.
Optionally, the candidate sampling data includes a candidate sampling period and an actual data value corresponding to the candidate sampling period, and the fitting module 103 performs verification on each fitting function and determines a manner of the candidate fitting function, which may include:
substituting a plurality of candidate sampling data into the fitting function aiming at each fitting function to obtain a predicted data value corresponding to each candidate sampling period;
calculating a variance sum corresponding to the fitting function according to the predicted data value and the actual data value corresponding to each candidate sampling period, wherein the variance sum indicates the deviation between the variation trend of the object to be monitored represented by the fitting function and the actual variation trend of the object to be monitored;
calculating a fitting result weight of each fitting function according to the variance sum corresponding to each fitting function, wherein the fitting result weight represents the fitting effect of the fitting function;
and taking the fitting function with the maximum fitting result weight as a candidate fitting function.
Optionally, the manner of calculating the fitting result weight of each fitting function according to the sum of variances corresponding to each fitting function by the fitting module 103 may include:
according to the variance sum corresponding to each fitting function, a preset formula is utilized
Calculating the fitting result weight of each fitting function;
wherein, W ij Representing the fitting result weight of the ith fitting function in the jth fitting; w is a group of i(j-1) Represents the weight of the fitting result of the ith fitting function in the (j-1) th fitting, and W i(j-1) Is 0; sum ij Representing the corresponding variance sum of the ith fitting function in the jth fitting; sum of total Representing the sum of the variances for each of the fitting functions involved in the jth fit,
n represents the number of fitting functions participating in the jth fitting, and k represents the number of fitting functions participating in the jth fitting.
Optionally, the early warning module 105 is specifically configured to:
acquiring the sampling period of the last sampling data from the sampling data set;
determining a future sampling period to be predicted according to the sampling period and the sampling interval of the last sampling data and a preset early warning time offset;
substituting the sampling period to be predicted into a target fitting function to obtain a predicted value of the object to be monitored in the sampling period to be predicted;
if the predicted value exceeds the early warning threshold value, early warning is carried out on the object to be monitored at the early warning moment; the early warning moment is before the sampling period to be predicted, and the early warning moment and the sampling period to be predicted have a difference of an early warning time offset.
It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working process of the data early warning apparatus 100 described above may refer to the corresponding process in the foregoing method embodiment, and is not described herein again.
Referring to fig. 7, fig. 7 is a block diagram illustrating an electronic device 10 according to an embodiment of the present disclosure. The electronic device 10 includes a processor 11, a memory 12, and a bus 13, and the processor 11 is connected to the memory 12 through the bus 13.
The memory 12 is used for storing a program, such as the data early warning apparatus 100 shown in fig. 6, the data early warning apparatus 100 includes at least one software functional module which can be stored in the memory 12 in a form of software or firmware (firmware), and the processor 11 executes the program after receiving an execution instruction to implement the data early warning method disclosed in the foregoing embodiment.
The Memory 12 may include a Random Access Memory (RAM) and may also include a non-volatile Memory (NVM).
The processor 11 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 11. The processor 11 may be a general-purpose processor, and includes chips such as a Central Processing Unit (CPU), a Micro Control Unit (MCU), a Complex Programmable Logic Device (CPLD), a Field Programmable Gate Array (FPGA), and an embedded ARM.
To sum up, according to the data early warning method, the data early warning device, the electronic device, and the storage medium provided by the embodiments of the present application, a function list corresponding to an object to be monitored is obtained first for the object to be monitored, where the function list includes a plurality of functions to be fitted, and one function to be fitted is used to represent a variation trend of the object to be monitored; then, fitting the function to be fitted in the function list for multiple times based on the actual data value of the object to be monitored to obtain a target fitting function with the minimum deviation between the represented change trend of the object to be monitored and the actual change trend of the object to be monitored; finally, early warning is carried out on the object to be monitored by utilizing a target fitting function; therefore, accurate early warning can be carried out before the fault occurs.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (11)
1. A data early warning method is applied to electronic equipment, and the method comprises the following steps:
acquiring a function list corresponding to an object to be monitored, wherein the function list comprises a plurality of functions to be fitted, and one function to be fitted is used for representing a variation trend of the object to be monitored;
fitting the function to be fitted in the function list for multiple times based on the actual data value of the object to be monitored to obtain a target fitting function; the deviation between the variation trend of the object to be monitored represented by the target fitting function and the actual variation trend of the object to be monitored is minimum;
and early warning the object to be monitored by utilizing the target fitting function.
2. The method of claim 1, wherein the method further comprises:
periodically sampling the actual data value of the object to be monitored according to a preset sampling interval;
and aiming at each sampling period, taking the sampling period and the corresponding actual data value thereof as sampling data, and adding the sampling data as a pre-constructed sampling data set.
3. The method of claim 2, wherein the step of fitting the function to be fitted in the function list a plurality of times based on the actual data value of the object to be monitored to obtain the target fitting function comprises:
acquiring the last sampling data and the sampling data with the preset number from the sampling data set to obtain a plurality of candidate sampling data;
fitting each function to be fitted in the function list according to the candidate sampling data to obtain each fitting function;
verifying each fitting function and determining candidate fitting functions; the variation trend of the object to be monitored represented by the candidate fitting function is the largest in deviation with the actual variation trend of the object to be monitored;
removing the function to be fitted corresponding to the candidate fitting function from the function list;
and repeatedly executing the steps until only one function to be fitted remains in the function list, and taking a fitting function obtained by the function to be fitted in the last fitting as the target fitting function.
4. The method of claim 3, wherein said step of fitting each of said functions to be fitted in said function list based on said plurality of candidate sample data to obtain each fitted function comprises:
for each function to be fitted, if the function to be fitted is a system time function, solving each coefficient in the function to be fitted by using a least square method according to the plurality of candidate sampling data to obtain the fitting function;
and if the function to be fitted is an extended time function, solving each coefficient in the function to be fitted by using a gradient descent method according to the plurality of candidate sampling data, the coefficient partial derivative function group of the extended time function and the coefficient guess value to obtain the fitting function.
5. The method of claim 3, wherein the candidate sample data comprises candidate sample periods and their corresponding actual data values;
the step of verifying each fitting function and determining candidate fitting functions comprises:
for each fitting function, substituting the candidate sampling data into the fitting function to obtain a prediction data value corresponding to each candidate sampling period;
calculating a variance sum corresponding to the fitting function according to the predicted data value and the actual data value corresponding to each candidate sampling period, wherein the variance sum indicates the deviation between the variation trend of the object to be monitored represented by the fitting function and the actual variation trend of the object to be monitored;
calculating a fitting result weight of each fitting function according to the variance sum corresponding to each fitting function, wherein the fitting result weight represents the fitting effect of the fitting function;
and taking the fitting function with the maximum fitting result weight as the candidate fitting function.
6. The method according to claim 5, wherein the step of calculating the fitting result weight of each fitting function according to the variance sum corresponding to each fitting function comprises:
according to the variance sum corresponding to each fitting function, a preset formula is utilized
Calculating the fitting result weight of each fitting function;
wherein, W ij Representing the fitting result weight of the ith fitting function in the jth fitting; w i(j-1) Represents the weight of the fitting result of the ith fitting function in the (j-1) th fitting, and W i(j-1) Is 0; sum ij Representing the corresponding variance sum of the ith fitting function in the jth fitting; sum of total Representing the sum of the variances and sums corresponding to each of said fitting functions participating in the jth fitting,
n represents the number of said fitting functions participating in the jth fitting, and k represents the number of said fitting functions participating in the jth fitting.
7. The method of claim 2, wherein the step of pre-warning the object to be monitored using the target fitting function comprises:
obtaining a sampling period of the last sampling data from the sampling data set;
determining a future sampling period to be predicted according to the sampling period of the last sampling data, the sampling interval and a preset early warning time offset;
substituting the sampling period to be predicted into the target fitting function to obtain a predicted value of the object to be monitored in the sampling period to be predicted;
if the predicted value exceeds an early warning threshold value, early warning is carried out on the object to be monitored at the early warning moment;
the early warning moment is before the sampling period to be predicted, and the early warning moment and the sampling period to be predicted have the difference of the early warning time offset.
8. The method of claim 1, wherein the electronic device stores a function library, the function library comprising a plurality of system time functions and a plurality of extended time functions, the plurality of extended time functions being customized by a system operation and maintenance person;
the step of obtaining the function list corresponding to the object to be monitored comprises the following steps:
responding to selection operation, and acquiring a plurality of functions to be fitted from the function library to obtain the function list; wherein the function to be fitted is at least one of the system time function and the extended time function.
9. A data early warning device is characterized in that the device is applied to electronic equipment, and the device comprises:
the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a function list corresponding to an object to be monitored, the function list comprises a plurality of functions to be fitted, and one function to be fitted is used for representing a variation trend of the object to be monitored;
the fitting module is used for fitting the function to be fitted in the function list for multiple times based on the actual data value of the object to be monitored to obtain a target fitting function; the deviation between the variation trend of the object to be monitored represented by the target fitting function and the actual variation trend of the object to be monitored is minimum;
and the early warning module is used for utilizing the target fitting function to carry out early warning on the object to be monitored.
10. An electronic device comprising a processor and a memory, the memory storing a program, the processor when executing the program implementing the data alert method of any of claims 1-8.
11. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the data prewarning method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211327899.9A CN115617613A (en) | 2022-10-27 | 2022-10-27 | Data early warning method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211327899.9A CN115617613A (en) | 2022-10-27 | 2022-10-27 | Data early warning method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115617613A true CN115617613A (en) | 2023-01-17 |
Family
ID=84876798
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211327899.9A Pending CN115617613A (en) | 2022-10-27 | 2022-10-27 | Data early warning method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115617613A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117933827A (en) * | 2024-03-13 | 2024-04-26 | 深圳市吉方工控有限公司 | Computer terminal industrial control information data processing method, electronic equipment and storage medium |
-
2022
- 2022-10-27 CN CN202211327899.9A patent/CN115617613A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117933827A (en) * | 2024-03-13 | 2024-04-26 | 深圳市吉方工控有限公司 | Computer terminal industrial control information data processing method, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112436968B (en) | Network traffic monitoring method, device, equipment and storage medium | |
| CN105320727B (en) | Method for detecting anomalies in real-time sequences | |
| CN110888788A (en) | Anomaly detection method and device, computer equipment and storage medium | |
| JP6678824B2 (en) | Unsteady detection device, unsteady detection system, and unsteady detection method | |
| CN111064614A (en) | Fault root cause positioning method, device, equipment and storage medium | |
| KR20190025474A (en) | Apparatus and Method for Predicting Plant Data | |
| US20150046757A1 (en) | Performance Metrics of a Computer System | |
| CN110570544A (en) | method, device, equipment and storage medium for identifying faults of aircraft fuel system | |
| CN112231181A (en) | Data abnormal update detection method and device, computer equipment and storage medium | |
| EP2963552B1 (en) | System analysis device and system analysis method | |
| CN115617613A (en) | Data early warning method and device, electronic equipment and storage medium | |
| JPH08234832A (en) | Device and method for monitoring and diagnostic plant | |
| CN114298221A (en) | Fault determination method and device, electronic equipment and computer readable storage medium | |
| CN110795324B (en) | Data processing method and device | |
| CN114037673A (en) | Hardware connection interface monitoring method and system based on machine vision | |
| CN111814557A (en) | Action flow detection method, device, equipment and storage medium | |
| WO2008127535A1 (en) | Machine condition monitoring using pattern rules | |
| CN112380073B (en) | Fault position detection method and device and readable storage medium | |
| Lando | Testing departures from the increasing hazard rate property | |
| CN113916673A (en) | Safety early warning method and system based on container state monitoring | |
| CN113295399A (en) | Converter valve element state evaluation method and device, electronic equipment and storage medium | |
| CN110458713B (en) | Model monitoring method, device, computer equipment and storage medium | |
| CN112100037B (en) | Alarm level identification method, device, electronic equipment and storage medium | |
| CN116700955A (en) | Job processing method, apparatus, computer device, and readable storage medium | |
| CN111555899A (en) | Alarm rule configuration method, equipment state monitoring method, device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |