CN117992316A - Abnormality monitoring method, abnormality monitoring device, computer device, and computer-readable storage medium - Google Patents
Abnormality monitoring method, abnormality monitoring device, computer device, and computer-readable storage medium Download PDFInfo
- Publication number
- CN117992316A CN117992316A CN202211364325.9A CN202211364325A CN117992316A CN 117992316 A CN117992316 A CN 117992316A CN 202211364325 A CN202211364325 A CN 202211364325A CN 117992316 A CN117992316 A CN 117992316A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- data
- value
- limit value
- output result
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 287
- 230000005856 abnormality Effects 0.000 title claims abstract description 56
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000012806 monitoring device Methods 0.000 title claims abstract description 12
- 230000035945 sensitivity Effects 0.000 claims abstract description 89
- 230000002159 abnormal effect Effects 0.000 claims abstract description 61
- 238000012545 processing Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 13
- 238000012217 deletion Methods 0.000 claims description 13
- 230000037430 deletion Effects 0.000 claims description 13
- 238000007405 data analysis Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 8
- 230000001174 ascending effect Effects 0.000 claims description 5
- 230000000295 complement effect Effects 0.000 claims 1
- 230000003068 static effect Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000006854 communication Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- PUAQLLVFLMYYJJ-UHFFFAOYSA-N 2-aminopropiophenone Chemical compound CC(N)C(=O)C1=CC=CC=C1 PUAQLLVFLMYYJJ-UHFFFAOYSA-N 0.000 description 2
- 230000007175 bidirectional communication Effects 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013585 weight reducing agent Substances 0.000 description 1
Landscapes
- Debugging And Monitoring (AREA)
Abstract
The application provides an anomaly monitoring method, an anomaly monitoring device, computer equipment and a computer readable storage medium, wherein the anomaly monitoring method comprises the following steps: acquiring monitoring time sequence data in a target period from the current moment; the target time period is determined according to holiday information corresponding to the current time and preset sensitivity information; analyzing the monitoring time sequence data to obtain a first output result; inputting the first output result into a preset time sequence prediction model to obtain a second output result; analyzing the second output result to obtain an abnormal monitoring lower limit value at the current moment; the abnormal monitoring lower limit value is used for analyzing the real-time monitoring data to obtain an abnormal monitoring result of the real-time monitoring data. By adopting the method, the abnormality monitoring accuracy can be improved.
Description
Technical Field
The embodiment of the application relates to the technical field of computers, in particular to an anomaly monitoring method, an anomaly monitoring device, computer equipment and a computer readable storage medium.
Background
In the operation and maintenance work of the internet, setting the threshold value of the monitoring index is a common technical means, but the actual operation experience of operation and maintenance personnel is mainly relied on at present, and different people have different threshold value setting standards for the same index, so that the difference is great. Meanwhile, aiming at the index which only pays attention to abnormal drop, a monitoring threshold is manually set, generally only a fixed threshold is given according to experience, only the lowest lower limit of one service can be guaranteed, but in the actual service, the same monitoring index has different monitoring values in different time periods, if the abnormality is judged by the lowest lower limit threshold, the abnormality of sudden drop cannot be found in time.
Therefore, the existing anomaly monitoring method has the technical problem of low monitoring accuracy.
Disclosure of Invention
The application aims to provide an abnormality monitoring method, an abnormality monitoring device, computer equipment and a computer readable storage medium for analyzing and acquiring
In a first aspect, the present application provides an anomaly monitoring method, including:
Acquiring monitoring time sequence data in a target period from the current moment; the target time period is determined according to holiday information corresponding to the current time and preset sensitivity information;
Analyzing the monitoring time sequence data to obtain a first output result;
inputting the first output result into a preset time sequence prediction model to obtain a second output result;
analyzing the second output result to obtain an abnormal monitoring lower limit value at the current moment; the abnormal monitoring lower limit value is used for analyzing the real-time monitoring data to obtain an abnormal monitoring result of the real-time monitoring data.
In some embodiments of the present application, obtaining monitoring time sequence data within a target period up to a current time includes: acquiring historical monitoring data within a target period from the current moment; determining a first data length of the historical monitoring data, and determining a second data length required by the target period; if the first data length is smaller than the second data length, performing data alignment on the historical monitoring data based on a preset floating point zero value to obtain monitoring time sequence data; if the first data length is greater than the second data length, performing data truncation on the historical monitoring data to obtain monitoring time sequence data; wherein the data length of the monitoring time sequence data is equal to the second data length.
In some embodiments of the present application, analyzing the monitoring time sequence data to obtain a first output result includes: determining the number of floating point zero values contained in the monitoring time sequence data; if the number of the numerical values is smaller than a preset number threshold value, acquiring a minimum value of the monitoring data of the target period of time as a first output result; if the number of the numerical values is greater than or equal to the number threshold, analyzing holiday information and sensitivity information, and obtaining a first output result.
In some embodiments of the present application, if the number of values is greater than or equal to the number threshold, analyzing holiday information and sensitivity information to obtain a first output result, including: if the number of the numerical values is greater than or equal to the number threshold value, performing outlier deletion processing on the monitoring time sequence data to obtain effective monitoring data; determining a first target model according to holiday information and sensitivity information; wherein the first target model comprises at least one of an exponentially weighted moving average model, a weighted moving average model, and a moving average model; and analyzing the effective monitoring data by using the first target model to obtain a first output result.
In some embodiments of the present application, if the number of values is greater than or equal to the number threshold, performing outlier deletion processing on the monitoring time sequence data to obtain effective monitoring data, including: if the number of the numerical values is greater than or equal to the number threshold value, carrying out ascending processing on the monitoring time sequence data to obtain the monitoring time sequence data; deleting floating point zero values in the monitoring time sequence data to obtain non-zero sequence data; acquiring fifteenth percentile on the non-zero sequence data as a first pixel value, and acquiring third quartile on the non-zero sequence data as a second pixel value; and determining an abnormal judgment range value according to the first image limit value and the second image limit value, and deleting the abnormal value of the monitoring time sequence data by utilizing the abnormal judgment range value to obtain effective monitoring data.
In some embodiments of the present application, determining an anomaly determination range value according to a first image limit value and a second image limit value, so as to perform anomaly value deletion processing on monitoring time series data by using the anomaly determination range value, to obtain effective monitoring data, including: obtaining the difference between the second image limit value and the first image limit value to obtain a quartile range value; obtaining the sum of the second image limit value and the quarter bit distance value of the multiple N to obtain an abnormality judgment upper limit value of an abnormality judgment range value; wherein N is more than or equal to 1; obtaining the difference between the first image limit value and the quarter bit distance value of the multiple N to obtain an abnormality judgment lower limit value of an abnormality judgment range value; and deleting the monitoring time sequence data smaller than the lower limit value of the abnormality judgment or the monitoring time sequence data larger than the upper limit value of the abnormality judgment as an abnormal value to obtain effective monitoring data.
In some embodiments of the present application, determining the first object model based on holiday information and sensitivity information includes: if the holiday information is detected to be zero and the sensitivity information is detected to be one, determining that the first target model is a weighted moving average model; if the holiday information is detected to be one and the sensitivity information is detected to be one, determining that the first target model is an exponentially weighted moving average model; if the holiday information is detected to be zero or one and the sensitivity information is detected to be zero or two, determining the first target model as a moving average model; the holiday information is zero, the holiday information is one, the holiday information is the holiday at the current time, the sensitivity information is zero, the sensitivity requirement of the holiday on the model is normal, the sensitivity information is one, the sensitivity requirement of the holiday on the model is sensitive, and the sensitivity information is two, the sensitivity requirement of the holiday on the model is slow.
In some embodiments of the present application, analyzing the second output result to obtain an anomaly monitoring lower limit value at the current time includes: if the sensitivity information is zero or two, determining a weight coefficient of the abnormal monitoring lower limit value as a first value; if the sensitivity information is one, determining a weight coefficient of the abnormal monitoring lower limit value as a second numerical value; wherein the second value is greater than the first value; and obtaining the product of the second output result and the weight coefficient to obtain the abnormal monitoring lower limit value.
In a second aspect, the present application provides an abnormality monitoring apparatus comprising:
the data acquisition module is used for acquiring monitoring time sequence data in a target period from the current moment; the target time period is determined according to holiday information corresponding to the current time and preset sensitivity information;
the data analysis module is used for analyzing the monitoring time sequence data to obtain a first output result;
the model analysis module is used for inputting the first output result into a preset moving average model to obtain a second output result;
the abnormality monitoring module is used for analyzing the second output result to obtain an abnormality monitoring lower limit value at the current moment; the abnormal monitoring lower limit value is used for analyzing the real-time monitoring data to obtain an abnormal monitoring result of the real-time monitoring data.
In a third aspect, the present application also provides a computer device comprising:
One or more processors;
A memory; and one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the anomaly monitoring method described above.
In a fourth aspect, the present application also provides a computer-readable storage medium having stored thereon a computer program that is loaded by a processor to perform steps in an anomaly monitoring method.
In a fifth aspect, embodiments of the present application provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the method provided in the first aspect.
According to the anomaly monitoring method, the anomaly monitoring device, the computer equipment and the computer readable storage medium, the server obtains the first output result by acquiring and analyzing the monitoring time sequence data related to the holiday information and the sensitivity information at the current moment, the first output result is further input into the preset time sequence prediction model, the second output result can be obtained, and finally the second output result is analyzed, so that the anomaly monitoring lower limit value which can be used for analyzing the real-time monitoring data at the current moment can be obtained. Therefore, the dynamic abnormal monitoring lower limit value is analyzed by combining the sensitivity information set by the actual service requirement and the holiday condition at the current moment, abnormal sudden drop of the index can be found in time, the low-precision influence of the static threshold on abnormal monitoring is avoided, and the accuracy of the abnormal monitoring is further effectively improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic view of a scenario of an anomaly monitoring method provided in an embodiment of the present application;
FIG. 2 is a flow chart of an anomaly monitoring method according to an embodiment of the present application;
FIG. 3 is a schematic diagram of an abnormality monitoring apparatus provided in an embodiment of the present application;
Fig. 4 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the description of the present application, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In the description of the present application, the term "for example" is used to mean "serving as an example, instance, or illustration. Any embodiment described as "for example" in this disclosure is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the application. In the following description, details are set forth for purposes of explanation. It will be apparent to one of ordinary skill in the art that the present application may be practiced without these specific details. In other instances, well-known structures and processes have not been described in detail so as not to obscure the description of the application with unnecessary detail. Thus, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.
In the embodiment of the application, the abnormality monitoring method provided by the embodiment of the application can be applied to an abnormality monitoring system shown in fig. 1. The anomaly monitoring system comprises a terminal 102 and a server 104. The terminal 102 may be a device that includes both receive and transmit hardware, i.e., a device having receive and transmit hardware capable of performing bi-directional communications over a bi-directional communication link. Such a device may include: a cellular or other communication device having a single-line display or a multi-line display or a cellular or other communication device without a multi-line display. The terminal 102 may be a desktop terminal or a mobile terminal, and the terminal 102 may be one of a mobile phone, a tablet computer, and a notebook computer. The server 104 may be a stand-alone server, or may be a server network or a server cluster of servers, including but not limited to a computer, a network host, a single network server, a set of multiple network servers, or a cloud server of multiple servers. Wherein the Cloud server is composed of a large number of computers or web servers based on Cloud Computing (Cloud Computing). In addition, the terminal 102 and the server 104 establish a communication connection through a network, and the network may specifically be any one of a wide area network, a local area network, and a metropolitan area network.
It will be appreciated by those skilled in the art that the application environment shown in fig. 1 is only one application scenario suitable for the present solution, and is not limited to the application scenario of the present solution, and other application environments may include more or fewer devices than those shown in fig. 1. For example, only 1 server is shown in fig. 1. It will be appreciated that the anomaly monitoring system may also include one or more other devices, and is not limited in particular herein. Additionally, the anomaly monitoring system may also include a memory for storing data, such as historical monitoring data.
It should be noted that, the schematic view of the scenario of the anomaly monitoring system shown in fig. 1 is only an example, and the anomaly monitoring system and the scenario described in the embodiment of the present invention are for more clearly describing the technical solution of the embodiment of the present invention, and do not constitute a limitation to the technical solution provided by the embodiment of the present invention, and those skilled in the art can know that, with the evolution of the anomaly monitoring system and the appearance of a new service scenario, the technical solution provided by the embodiment of the present invention is equally applicable to similar technical problems.
Referring to fig. 2, an embodiment of the present application provides an anomaly monitoring method, which is mainly applied to the server 104 in fig. 1 for illustration, and the method includes steps S201 to S204, specifically as follows:
S201, acquiring monitoring time sequence data in a target period from the current moment; the target time period is determined according to holiday information corresponding to the current time and preset sensitivity information.
The target period may refer to a window (window), which is specifically a period defined by a specified start time and end time (the current time of the server 104), or may be a period defined by a specified end time and a fixed duration. For example, a specified period of time between zero minutes at 1 month 1 of 2022 and zero minutes (current time) at 2 days 1 month 2 of 2022; for another example, the historical period of time zero minutes up to 24 hours expires at 1 month 1 day 2022.
The monitoring time sequence value may be monitoring data recorded sequentially along with the time, and the monitoring time sequence value has a time sequence attribute and can be referred to, but the embodiment of the application of the main device of the monitoring data is not limited, that is, the monitoring time sequence data mentioned in the embodiment of the application may be hardware or software monitoring data.
The holiday information may be information indicating whether the current time is a holiday, for example, a holiday information of "0" indicates that the current time is not a holiday, and a holiday information of "1" indicates that the current time is a holiday.
The sensitivity information may be information indicating a requirement of the holiday for the model sensitivity (sensitivity), for example, a sensitivity information of "0" indicates that the sensitivity requirement of the holiday for the model is "normal", a sensitivity information of "1" indicates that the sensitivity requirement of the holiday for the model is "sensitive", and a sensitivity information of "2" indicates that the sensitivity requirement of the holiday for the model is "slow".
In a specific implementation, the monitoring time sequence data may be obtained and sent by the terminal 102, or may be obtained by other devices after obtaining and transmitting the monitoring time sequence data through the terminal 102, where the obtaining manner includes but is not limited to one of the following manners: 1. in a common network architecture, the server 104 receives monitoring timing data from the terminal 102 or other cloud devices with network connections established; 2. in a preset blockchain network, the server 104 can synchronously acquire monitoring time sequence data from other terminal nodes or server nodes, and the blockchain network can be a public chain, a private chain and the like; 3. in the preset tree structure, the server 104 may request the monitoring timing data from the upper server or may poll the monitoring timing data from the lower server.
Note that, if the holiday information "0", windows=30; if holiday information "1" and sensitivity information is "0", windows=30; if holiday information "1" and sensitivity information is "1", windows=20; if holiday information "1" and sensitivity information is "2", windows=40.
In one embodiment, the step includes: acquiring historical monitoring data within a target period from the current moment; determining a first data length of the historical monitoring data, and determining a second data length required by the target period; if the first data length is smaller than the second data length, performing data alignment on the historical monitoring data based on a preset floating point zero value to obtain monitoring time sequence data; if the first data length is greater than the second data length, performing data truncation on the historical monitoring data to obtain monitoring time sequence data; wherein the data length of the monitoring time sequence data is equal to the second data length.
Wherein, since the obtained monitoring data is cut off to the current time, it can be called as history monitoring data, and the data format of the history monitoring data is List [ float ], so the history monitoring data can be expressed as "ponit _list". The monitoring timing data may be denoted as "input_ ponit _list".
The second data length required for the target period may be denoted as "windows", and the value thereof may be any positive integer. For example, windows=30, windows=40, and the like. It should be noted that, if windows has no special setting, the default value may be "30".
Wherein a floating point type zero value may be represented as "0.0".
In a specific implementation, in order to obtain the monitoring time sequence data in a target period from the current time, the server 104 may first obtain the history monitoring data in a target period from the current time, then determine the data length of the history monitoring data as the first data length "data_length", and determine the second data length "window", and further compare the sizes of the first data length "data_length" and the second data length "window", so as to obtain the monitoring time sequence data according to the comparison result.
Specifically, if the first data length is smaller than the second data length, the historical monitoring data is data-complemented based on a preset floating point zero value of 0.0, so that the monitoring time sequence data can be obtained. For example, if the history monitoring data "ponit _list= [2.1,3.4] and window=4", the monitoring time sequence data after the data is filled is "input_ ponit _list= [0.0,0.0,2.1,3.4 ].
Further, if the first data length is greater than the second data length, the historical monitoring data is subjected to data truncation, and then the monitoring time sequence data can be obtained. For example, if the history monitor data "ponit _list= [2.1,3.4,5.6] and window=2", the monitor time sequence data after the data interception is "input_ ponit _list= [3.4,5.6 ].
S202, analyzing the monitoring time sequence data to obtain a first output result.
In a specific implementation, the server 104 may analyze the monitoring time sequence data by using a time sequence prediction model to obtain the first output result, or may analyze the monitoring time sequence data without using the time sequence prediction model, that is, analyze the monitoring time sequence data in other manners to obtain the first output result, which will be described in detail below.
The timing prediction Model may be at least one of an exponentially weighted moving average Model (Exponentially Weighted Moving Averages Model, EWMA Model), a weighted moving average Model (Weighted Moving Average Model, WMAModel), a moving average Model (Moving Average Model, AVGModel), a differentially integrated moving average autoregressive Model (Autoregressive Integrated Moving Average Model, ARIMA), an autoregressive integrated moving average Model (Auto-REGRESSIVE INTEGRATED Moving Averages, autoARIMA), and a Informer Model.
In one embodiment, the step includes: determining the number of floating point zero values contained in the monitoring time sequence data; if the number of the numerical values is smaller than a preset number threshold value, acquiring a minimum value of the monitoring data of the target period of time as a first output result; if the number of the numerical values is greater than or equal to the number threshold, analyzing holiday information and sensitivity information, and obtaining a first output result.
Wherein, the floating point zero value can be expressed as 0.0, and the number threshold can be set according to the actual service requirement, for example, the number threshold is set as 11 in the embodiment of the application.
In a specific implementation, after the server 104 analyzes the monitoring time sequence data, the number of floating point zero values contained in the monitoring time sequence data can be analyzed, and the size relation between the number of floating point zero values and the number threshold is judged, if the number of the floating point zero values is smaller than the number threshold (the number of 0.0 is smaller than 11), the minimum value of the normal condition of the same period from the yesterday zero point to the current moment can be directly returned, and the floating point zero values can be directly taken out through a reading database without calculation. If the number of the numerical values is greater than or equal to a number threshold (the number of 0.0 is greater than or equal to 11), holiday information and sensitivity information are required to be analyzed to obtain a first output result. The holiday information and sensitivity information analysis steps involved in the present embodiment will be described in detail below.
In one embodiment, if the number of values is greater than or equal to the number threshold, analyzing holiday information and sensitivity information to obtain a first output result, including: if the number of the numerical values is greater than or equal to the number threshold value, performing outlier deletion processing on the monitoring time sequence data to obtain effective monitoring data; determining a first target model according to holiday information and sensitivity information; wherein the first target model comprises at least one of an exponentially weighted moving average model, a weighted moving average model, and a moving average model; and analyzing the effective monitoring data by using the first target model to obtain a first output result.
Wherein the first target model comprises at least one of an exponentially weighted moving average model, a weighted moving average model and a moving average model, and even comprises at least one of a differentially integrated moving average autoregressive model, an autoregressive integrated moving average model and a Informer model.
In a specific implementation, the foregoing embodiment has described that, when the server 104 detects that the number of values is smaller than the preset number threshold, the minimum value of the monitoring data in the target period may be directly obtained as the first output result. However, when the server 104 detects that the number of values is greater than or equal to the preset number threshold, the first output result may be obtained according to the sensitivity information and holiday information.
Specifically, the server 104 may perform abnormal value deletion processing on the monitoring time sequence data, that is, delete the floating point zero value "0.0" in the monitoring time sequence data, and then continue processing the data deleted the floating point zero value, so as to obtain effective monitoring data. Finally, the available first target model is determined by analysis, so that the first output result can be obtained by analyzing the effective monitoring data by using the first target model, which will be described in detail below.
It should be noted that, the exponentially weighted moving average model "F t1", the weighted moving average model "F t2", and the moving average model "F t3" may be respectively expressed by the following formulas:
Ft1＝βFt-1+(1-β)At
Wherein, F t1 represents the predicted value at the time t, A t represents the actual value at the time t, beta represents the rate of weight reduction, and the default value is 0.9, which can be adjusted by self according to the requirement.
Ft2＝w1At-1+w2At-2+…+wnAt-n
Wherein F t2 represents a predicted value at time t; a t-n represents the actual value corresponding to the first n-phase, w n represents the weight of the t-n-th phase, w 1+w2+…+wn =1,
Ft＝(At-1+At-2+…+At-n)/n
Wherein F t represents a predicted value at time t, a t-n represents an actual value corresponding to the previous n phases, and n represents the total number of digits involved in calculation.
In one embodiment, if the number of values is greater than or equal to the number threshold, performing outlier deletion processing on the monitoring time sequence data to obtain effective monitoring data, including: if the number of the numerical values is greater than or equal to the number threshold value, carrying out ascending processing on the monitoring time sequence data to obtain the monitoring time sequence data; deleting floating point zero values in the monitoring time sequence data to obtain non-zero sequence data; acquiring fifteenth percentile on the non-zero sequence data as a first pixel value, and acquiring third quartile on the non-zero sequence data as a second pixel value; and determining an abnormal judgment range value according to the first image limit value and the second image limit value, and deleting the abnormal value of the monitoring time sequence data by utilizing the abnormal judgment range value to obtain effective monitoring data.
In a specific implementation, if the number of the floating-point zero values detected by the server 104 is greater than or equal to the number threshold (e.g. 11), all the floating-point zero values can be removed first, and then the monitoring time sequence data with zero removal is obtained and sorted. Or firstly, carrying out ascending arrangement on the monitoring time sequence data to obtain the monitoring time sequence data, and then removing all floating point zero values in the monitoring time sequence data to obtain the non-zero sequence data.
Further, the server 104 may acquire the 15 th percentile of the non-zero sequence data as the first pixel value "first_qua" and the 75 th percentile of the non-zero sequence data as the second pixel value "third_qua", and may then continue to analyze the first and second pixel values to determine an anomaly determination range value for performing anomaly value deletion processing on the monitored time series data, as will be described in detail below.
In one embodiment, determining an anomaly determination range value according to the first and second image values to perform anomaly value deletion processing on the monitoring time series data using the anomaly determination range value to obtain effective monitoring data includes: obtaining the difference between the second image limit value and the first image limit value to obtain a quartile range value; obtaining the sum of the second image limit value and the quarter bit distance value of the multiple N to obtain an abnormality judgment upper limit value of an abnormality judgment range value; wherein N is more than or equal to 1; obtaining the difference between the first image limit value and the quarter bit distance value of the multiple N to obtain an abnormality judgment lower limit value of an abnormality judgment range value; and deleting the monitoring time sequence data smaller than the lower limit value of the abnormality judgment or the monitoring time sequence data larger than the upper limit value of the abnormality judgment as an abnormal value to obtain effective monitoring data.
Wherein the first image limit value may be denoted as "first_qua", the second image limit value may be denoted as "third_qua", the quarter-bit distance value may be denoted as "iqr", the abnormality determination upper limit value may be denoted as "up_limit", and the abnormality determination lower limit value may be denoted as "down_limit".
In particular implementations, to determine the anomaly determination range value, the server 104 may first obtain the difference between the second and first image values as a quarter-bit distance value. Then, the sum of the second image limit value and the quarter bit distance value of the multiple N is obtained as the abnormality determination upper limit value. And, the difference between the second image limit value and the quarter bit distance value of the multiple N is obtained as the abnormality determination lower limit value. Thus, the abnormality determination range values "down_limit" to "up_limit" can be determined.
For example, n=3, "iqr=threaded_quat-first_quat", "up_limit=threaded_quat+3 iqr", "down_limit=first_quat-3 iqr". Thus, the monitoring time sequence data smaller than 'down_limit' or larger than 'up_limit' can be removed as abnormal values and do not participate in subsequent calculation.
Further, after the server 104 analyzes the effective monitoring data, the effective monitoring data may be input to the first target model, so that the first target model analyzes the effective monitoring data, and a first output result "first_layer_output" may be obtained. It should be noted that, the data format of the first output result is "List [ float ]", and the data length is "window".
In one embodiment, determining the first object model based on holiday information and sensitivity information includes: if the holiday information is detected to be zero and the sensitivity information is detected to be one, determining that the first target model is a weighted moving average model; if the holiday information is detected to be one and the sensitivity information is detected to be one, determining that the first target model is an exponentially weighted moving average model; if the holiday information is detected to be zero or one and the sensitivity information is detected to be zero or two, determining the first target model as a moving average model; the holiday information is zero, the holiday information is one, the holiday information is the holiday at the current time, the sensitivity information is zero, the sensitivity requirement of the holiday on the model is normal, the sensitivity information is one, the sensitivity requirement of the holiday on the model is sensitive, and the sensitivity information is two, the sensitivity requirement of the holiday on the model is slow.
In a specific implementation, if the holiday information is "0" and the sensitivity information is "1", the first target model may be a weighted moving average model "WMAModel"; if holiday information is "1" and sensitivity information is "1", the first target model may be an exponentially weighted moving average model "EWMA". In addition to the two cases, the first object model in other cases may be a moving average model "AVGModel".
S203, inputting the first output result into a preset time sequence prediction model to obtain a second output result.
The time sequence prediction model in the embodiment can be a moving average model 'AVGModel'. It should be noted that, the time sequence prediction model for analyzing the first output result may be referred to as a second target model, and the first target model and the second target model selected in the embodiment of the present application may be used alternatively.
In a specific implementation, after the server 104 analyzes the first output result, the first output result may be input into the second target model for analysis and prediction, so as to obtain a second output result "second_layer_output". In addition, it should be noted that, the data input into the second object model may be the first output result "first_layer_output" after the floating point zero value is removed.
S204, analyzing the second output result to obtain an abnormal monitoring lower limit value at the current moment; the abnormal monitoring lower limit value is used for analyzing the real-time monitoring data to obtain an abnormal monitoring result of the real-time monitoring data.
The anomaly monitoring lower limit value at the present time may be expressed as "down_threshold".
In a specific implementation, after the server 104 analyzes the second output result "second_layer_output", the anomaly monitoring lower limit value may be analyzed by using the second output result, for example, by using a weight coefficient superposition calculation, which will be described in detail below.
In one embodiment, the step includes: if the sensitivity information is zero or two, determining a weight coefficient of the abnormal monitoring lower limit value as a first value; if the sensitivity information is one, determining a weight coefficient of the abnormal monitoring lower limit value as a second numerical value; wherein the second value is greater than the first value; and obtaining the product of the second output result and the weight coefficient to obtain the abnormal monitoring lower limit value.
The weight coefficient of the anomaly monitoring lower limit value may be expressed as "decrease _rate".
In a specific implementation, if the sensitivity information is "0" or "2", the weight coefficient "decrease _rate" of the anomaly monitoring lower limit value may be determined to be a first value "0.7"; if the sensitivity information is "1", the weight coefficient "decrease _rate" of the abnormality monitoring lower limit value may be determined to be the first value "0.8". Thus, the product of the second output result 'second layer output' and the weight coefficient is calculated, and the anomaly monitoring lower limit value at the current moment can be obtained. It can be understood that the anomaly monitoring lower limit value dynamically changes in real time, and is related to the current time, and the server 104 obtains a reasonable anomaly monitoring lower limit value to analyze real-time monitoring data based on the specificity of the current time, so that the anomaly monitoring accuracy is higher.
Specifically, if the real-time monitoring data at the present time, which is less than the abnormality monitoring lower limit value (down_threshold), the server 104 may give a monitoring result determined to be an abnormal state; otherwise, the server 104 may give a monitoring result determined to be in a normal state.
According to the anomaly monitoring method in the embodiment, the server obtains the first output result by obtaining and analyzing the monitoring time sequence data related to the holiday information and the sensitivity information at the current moment, then inputs the first output result into the preset time sequence prediction model to obtain the second output result, and finally analyzes the second output result to obtain the anomaly monitoring lower limit value which can be used for analyzing the real-time monitoring data at the current moment. Therefore, the dynamic abnormal monitoring lower limit value is analyzed by combining the sensitivity information set by the actual service requirement and the holiday condition at the current moment, abnormal sudden drop of the index can be found in time, the influence of the static threshold on the low precision of the abnormal monitoring is avoided without depending on manpower, and the accuracy and the efficiency of the abnormal monitoring are further effectively improved.
It should be understood that, although the steps in the flowchart of fig. 2 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
In order to better implement the anomaly monitoring method provided in the embodiment of the present application, on the basis of the anomaly monitoring method provided in the embodiment of the present application, an anomaly monitoring device is further provided in the embodiment of the present application, as shown in fig. 3, the anomaly monitoring device 300 includes:
a data acquisition module 310, configured to acquire monitoring time sequence data within a target period from the current time; the target time period is determined according to holiday information corresponding to the current time and preset sensitivity information;
The data analysis module 320 is configured to analyze the monitoring time sequence data to obtain a first output result;
the model analysis module 330 is configured to input the first output result into a preset moving average model to obtain a second output result;
the anomaly monitoring module 340 is configured to parse the second output result to obtain an anomaly monitoring lower limit value at the current moment; the abnormal monitoring lower limit value is used for analyzing the real-time monitoring data to obtain an abnormal monitoring result of the real-time monitoring data.
In one embodiment, the data obtaining module 310 is further configured to obtain historical monitoring data within a target period up to the current time; determining a first data length of the historical monitoring data, and determining a second data length required by the target period; if the first data length is smaller than the second data length, performing data alignment on the historical monitoring data based on a preset floating point zero value to obtain monitoring time sequence data; if the first data length is greater than the second data length, performing data truncation on the historical monitoring data to obtain monitoring time sequence data; wherein the data length of the monitoring time sequence data is equal to the second data length.
In one embodiment, the data analysis module 320 is further configured to determine a number of values of floating-point zero values included in the monitoring time series data; if the number of the numerical values is smaller than a preset number threshold value, acquiring a minimum value of the monitoring data of the target period of time as a first output result; if the number of the numerical values is greater than or equal to the number threshold, analyzing holiday information and sensitivity information, and obtaining a first output result.
In one embodiment, the data analysis module 320 is further configured to perform outlier deletion processing on the monitoring time sequence data if the number of values is greater than or equal to the number threshold value, so as to obtain effective monitoring data; determining a first target model according to holiday information and sensitivity information; wherein the first target model comprises at least one of an exponentially weighted moving average model, a weighted moving average model, and a moving average model; and analyzing the effective monitoring data by using the first target model to obtain a first output result.
In one embodiment, the data analysis module 320 is further configured to perform ascending processing on the monitoring time sequence data to obtain the monitoring time sequence data if the number of the values is greater than or equal to the number threshold; deleting floating point zero values in the monitoring time sequence data to obtain non-zero sequence data; acquiring fifteenth percentile on the non-zero sequence data as a first pixel value, and acquiring third quartile on the non-zero sequence data as a second pixel value; and determining an abnormal judgment range value according to the first image limit value and the second image limit value, and deleting the abnormal value of the monitoring time sequence data by utilizing the abnormal judgment range value to obtain effective monitoring data.
In one embodiment, the data analysis module 320 is further configured to obtain a difference between the second image value and the first image value to obtain a quarter bit distance value; obtaining the sum of the second image limit value and the quarter bit distance value of the multiple N to obtain an abnormality judgment upper limit value of an abnormality judgment range value; wherein N is more than or equal to 1; obtaining the difference between the first image limit value and the quarter bit distance value of the multiple N to obtain an abnormality judgment lower limit value of an abnormality judgment range value; and deleting the monitoring time sequence data smaller than the lower limit value of the abnormality judgment or the monitoring time sequence data larger than the upper limit value of the abnormality judgment as an abnormal value to obtain effective monitoring data.
In one embodiment, the data analysis module 320 is further configured to determine that the first target model is a weighted moving average model if the holiday information is detected to be zero and the sensitivity information is one; if the holiday information is detected to be one and the sensitivity information is detected to be one, determining that the first target model is an exponentially weighted moving average model; if the holiday information is detected to be zero or one and the sensitivity information is detected to be zero or two, determining the first target model as a moving average model; the holiday information is zero, the holiday information is one, the holiday information is the holiday at the current time, the sensitivity information is zero, the sensitivity requirement of the holiday on the model is normal, the sensitivity information is one, the sensitivity requirement of the holiday on the model is sensitive, and the sensitivity information is two, the sensitivity requirement of the holiday on the model is slow.
In one embodiment, the anomaly monitoring module 340 is further configured to determine that the weight coefficient of the anomaly monitoring lower limit value is a first value if the sensitivity information is zero or two; if the sensitivity information is one, determining a weight coefficient of the abnormal monitoring lower limit value as a second numerical value; wherein the second value is greater than the first value; and obtaining the product of the second output result and the weight coefficient to obtain the abnormal monitoring lower limit value.
In the above embodiment, by combining the sensitivity information set by the actual service requirement and the holiday condition at the current moment, the dynamic abnormal monitoring lower limit value is analyzed, so that abnormal sudden drop of the index can be found in time, the dependence on manpower is not needed, namely, the low-precision influence of the static threshold on the abnormal monitoring is avoided, and the accuracy and the efficiency of the abnormal monitoring are further effectively improved.
It should be noted that, the specific limitation of the abnormality monitoring device may be referred to the limitation of the abnormality monitoring method hereinabove, and will not be described herein. The respective modules in the abnormality monitoring apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or independent of a processor in the electronic device, or may be stored in software in a memory in the electronic device, so that the processor may call and execute operations corresponding to the above modules.
In some embodiments of the present application, the anomaly monitoring device 300 may be implemented in the form of a computer program that is executable on a computer device such as that shown in FIG. 4. The memory of the computer device may store various program modules constituting the abnormality monitoring apparatus 300, such as the data acquisition module 310, the data analysis module 320, the model analysis module 330, and the abnormality monitoring module 340 shown in fig. 3; the computer program constituted by the respective program modules causes the processor to execute the steps in the abnormality monitoring method of the respective embodiments of the present application described in the present specification. For example, the computer apparatus shown in fig. 4 may perform step S201 through the data acquisition module 310 in the abnormality monitoring device 300 shown in fig. 3. The computer device may perform step S202 through the data analysis module 320. The computer device may perform step S203 through the model analysis module 330. The computer device may perform step S204 through the anomaly monitoring module 340. The computer device includes a processor, a memory, and a network interface coupled 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 includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external computer device through a network connection. The computer program, when executed by a processor, implements a method of anomaly monitoring.
It will be appreciated by persons skilled in the art that the architecture shown in fig. 4 is merely a block diagram of some of the architecture relevant to the present inventive arrangements and is not limiting as to the computer device to which the present inventive arrangements are applicable, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In some embodiments of the application, a computer device is provided that includes one or more processors; a memory; and one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to perform the steps of the anomaly monitoring method described above. The steps of the anomaly monitoring method herein may be the steps in the anomaly monitoring method of each of the embodiments described above.
In some embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, the computer program being loaded by a processor, so that the processor performs the steps of the anomaly monitoring method described above. The steps of the anomaly monitoring method herein may be the steps in the anomaly monitoring method of each of the embodiments described above.
Those of ordinary skill in the art will appreciate that implementing all or part of the above-described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein can include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing describes in detail a method, apparatus, computer device and computer readable storage medium for monitoring anomalies provided by embodiments of the present application, and specific examples are applied to illustrate the principles and embodiments of the present application, and the above description of the embodiments is only for helping to understand the method and core ideas of the present application; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in light of the ideas of the present application, the present description should not be construed as limiting the present application.
Claims (11)
1. An anomaly monitoring method, comprising:
Acquiring monitoring time sequence data in a target period from the current moment; the target time period is determined according to holiday information corresponding to the current moment and preset sensitivity information;
analyzing the monitoring time sequence data to obtain a first output result;
inputting the first output result into a preset time sequence prediction model to obtain a second output result;
Analyzing the second output result to obtain an abnormal monitoring lower limit value at the current moment; the abnormal monitoring lower limit value is used for analyzing the real-time monitoring data to obtain an abnormal monitoring result of the real-time monitoring data.
2. The method of claim 1, wherein the acquiring monitoring time series data within a target period from the current moment in time comprises:
Acquiring historical monitoring data within a target period from the current moment;
determining a first data length of the historical monitoring data, and determining a second data length required by the target period;
If the first data length is smaller than the second data length, performing data complement on the historical monitoring data based on a preset floating point zero value to obtain the monitoring time sequence data;
if the first data length is larger than the second data length, performing data truncation on the historical monitoring data to obtain the monitoring time sequence data; wherein the data length of the monitoring time sequence data is equal to the second data length.
3. The method according to claim 1 or 2, wherein analyzing the monitoring time series data to obtain a first output result comprises:
Determining the number of floating point zero values contained in the monitoring time sequence data;
If the number of the numerical values is smaller than a preset number threshold, acquiring a monitoring data minimum value of the target period as the first output result;
And if the number of the numerical values is greater than or equal to the number threshold, analyzing the holiday information and the sensitivity information to acquire the first output result.
4. The method of claim 3, wherein analyzing the holiday information and the sensitivity information if the number of values is greater than or equal to the number threshold, obtaining the first output result comprises:
if the number of the numerical values is greater than or equal to the number threshold, performing outlier deletion processing on the monitoring time sequence data to obtain effective monitoring data;
Determining a first target model according to the holiday information and the sensitivity information; wherein the first target model comprises at least one of an exponentially weighted moving average model, a weighted moving average model, and a moving average model;
And analyzing the effective monitoring data by using the first target model to obtain the first output result.
5. The method of claim 4, wherein if the number of values is greater than or equal to the number threshold, performing outlier deletion processing on the monitoring time series data to obtain effective monitoring data, including:
If the number of the numerical values is greater than or equal to the number threshold, carrying out ascending processing on the monitoring time sequence data to obtain monitoring time sequence data;
Deleting floating point zero values in the monitoring time sequence data to obtain non-zero sequence data;
Acquiring a fifteenth quantile on the non-zero sequence data as a first pixel value and acquiring a third quantile on the non-zero sequence data as a second pixel value;
And determining an abnormal judgment range value according to the first image limit value and the second image limit value, and performing abnormal value deletion processing on the monitoring time sequence data by using the abnormal judgment range value to obtain the effective monitoring data.
6. The method of claim 5, wherein determining an anomaly determination range value based on the first and second image values to perform anomaly value deletion processing on the monitoring time series data using the anomaly determination range value to obtain the effective monitoring data, comprises:
obtaining the difference between the second image limit value and the first image limit value to obtain a quartile range value;
obtaining the sum of the second image limit value and the quarter bit distance value of N times to obtain an abnormality judgment upper limit value of the abnormality judgment range value; wherein N is more than or equal to 1;
obtaining the difference between the first image limit value and the quarter bit distance value of N times to obtain an abnormality judgment lower limit value of the abnormality judgment range value;
and deleting the monitoring time sequence data smaller than the lower limit value of the abnormality judgment or the monitoring time sequence data larger than the upper limit value of the abnormality judgment as an abnormal value to obtain the effective monitoring data.
7. The method of claim 4, wherein said determining a first target model based on said holiday information and said sensitivity information comprises:
if the holiday information is detected to be zero and the sensitivity information is detected to be one, determining the first target model as the weighted moving average model;
if the holiday information is detected to be one and the sensitivity information is detected to be one, determining the first target model to be the exponentially weighted moving average model;
If the holiday information is detected to be zero or one and the sensitivity information is detected to be zero or two, determining the first target model as the moving average model; wherein,
The holiday information is zero, the holiday information is one, the current time is the holiday, the sensitivity information is zero, the sensitivity requirement of the holiday on the model is normal, the sensitivity information is one, the sensitivity requirement of the holiday on the model is sensitive, and the sensitivity information is two, the sensitivity requirement of the holiday on the model is slow.
8. The method of claim 1, wherein the parsing the second output result to obtain the anomaly monitoring lower limit value for the current time comprises:
if the sensitivity information is zero or two, determining that the weight coefficient of the abnormal monitoring lower limit value is a first numerical value;
If the sensitivity information is one, determining that the weight coefficient of the abnormal monitoring lower limit value is a second numerical value; wherein the second value is greater than the first value;
and obtaining the product of the second output result and the weight coefficient to obtain the abnormal monitoring lower limit value.
9. An abnormality monitoring device, characterized by comprising:
The data acquisition module is used for acquiring monitoring time sequence data in a target period from the current moment; the target time period is determined according to holiday information corresponding to the current moment and preset sensitivity information;
The data analysis module is used for analyzing the monitoring time sequence data to obtain a first output result;
The model analysis module is used for inputting the first output result into a preset moving average model to obtain a second output result;
the abnormality monitoring module is used for analyzing the second output result to obtain an abnormality monitoring lower limit value at the current moment; the abnormal monitoring lower limit value is used for analyzing the real-time monitoring data to obtain an abnormal monitoring result of the real-time monitoring data.
10. A computer device, the computer device comprising:
One or more processors;
A memory; and one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the anomaly monitoring method of any one of claims 1 to 8.
11. A computer-readable storage medium, having stored thereon a computer program, the computer program being loaded by a processor to perform the steps of the anomaly monitoring method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211364325.9A CN117992316A (en) | 2022-11-02 | 2022-11-02 | Abnormality monitoring method, abnormality monitoring device, computer device, and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211364325.9A CN117992316A (en) | 2022-11-02 | 2022-11-02 | Abnormality monitoring method, abnormality monitoring device, computer device, and computer-readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117992316A true CN117992316A (en) | 2024-05-07 |
Family
ID=90900290
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211364325.9A Pending CN117992316A (en) | 2022-11-02 | 2022-11-02 | Abnormality monitoring method, abnormality monitoring device, computer device, and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117992316A (en) |
-
2022
- 2022-11-02 CN CN202211364325.9A patent/CN117992316A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107809331B (en) | Method and device for identifying abnormal flow | |
| US11979433B2 (en) | Highly scalable four-dimensional web-rendering geospatial data system for simulated worlds | |
| CN109345130B (en) | Method and device for commercial site selection, computer equipment and storage medium | |
| CN109471783B (en) | Method and device for predicting task operation parameters | |
| CN112835769A (en) | Service data abnormity diagnosis method, device, equipment and storage medium | |
| CN114500339B (en) | Node bandwidth monitoring method and device, electronic equipment and storage medium | |
| CN108809943B (en) | Website monitoring method and device | |
| CN114449343A (en) | Video processing method, device, equipment and storage medium | |
| CN111311014B (en) | Service data processing method, device, computer equipment and storage medium | |
| CN117992316A (en) | Abnormality monitoring method, abnormality monitoring device, computer device, and computer-readable storage medium | |
| CN116938953A (en) | Block chain-based data processing method and device, electronic equipment and storage medium | |
| CN116187387A (en) | Neural network model quantization method, device, computer equipment and storage medium | |
| CN113590447B (en) | Buried point processing method and device | |
| CN114861909A (en) | Model quality monitoring method and device, electronic equipment and storage medium | |
| CN114710397B (en) | Service link fault root cause positioning method and device, electronic equipment and medium | |
| CN113449128B (en) | Picture generation method and related device for displaying key equity structure | |
| CN114372212B (en) | Numerical weather forecasting method and device based on supercomputer | |
| CN114202292B (en) | Stock information sending method and device, electronic equipment and computer readable medium | |
| CN113762510B (en) | Data processing method and device for target model, electronic equipment and medium | |
| CN113362097B (en) | User determination method and device | |
| CN115964549B (en) | Community mining method, device, equipment and storage medium | |
| CN116483658A (en) | Method, device, system, equipment and storage medium for monitoring server performance | |
| US20240070477A1 (en) | Server device | |
| CN117453248A (en) | Gray scale issuing method, device, computer equipment and storage medium | |
| CN116401133A (en) | Method, device, equipment and storage medium for predicting end time |
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 |