CN105991303A - Method and apparatus for processing operation parameter monitoring samples, and communication system - Google Patents

Method and apparatus for processing operation parameter monitoring samples, and communication system Download PDF

Info

Publication number
CN105991303A
CN105991303A CN201510040914.5A CN201510040914A CN105991303A CN 105991303 A CN105991303 A CN 105991303A CN 201510040914 A CN201510040914 A CN 201510040914A CN 105991303 A CN105991303 A CN 105991303A
Authority
CN
China
Prior art keywords
sample
period
value
parameter
statistical value
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201510040914.5A
Other languages
Chinese (zh)
Other versions
CN105991303B (en
Inventor
洪楷
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Tencent Cloud Computing Beijing Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tencent Technology Shenzhen Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Priority to CN201510040914.5A priority Critical patent/CN105991303B/en
Publication of CN105991303A publication Critical patent/CN105991303A/en
Application granted granted Critical
Publication of CN105991303B publication Critical patent/CN105991303B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The embodiment of the invention discloses a method and an apparatus for processing operation parameter monitoring samples, and a communication system. The method for processing operation parameter monitoring samples comprises the steps of acquiring operation parameter monitoring samples within the current unit time period (tx) of an operation server; calculating a sample statistical value (signal x) of a sample space formed by operation parameter monitoring samples within the (N-1) reference unit time periods of a reference monitoring cycle and operation parameter monitoring samples within the current unit time period (tx); on the condition that the difference between a reference sample statistical value (signal n) and the sample statistical value (signal x) exceeds a preset range, marking operation parameter monitoring samples within the current unit time period (tx) as dirty samples. The reference sample statistical value (signal n) is a sample statistical value of a reference sample space formed by operation parameter monitoring samples within the N reference unit time periods of the reference monitoring cycle. According to the technical scheme of the embodiments in the invention, the recognition accuracy of dirty samples in operation parameter monitoring samples is improved.

Description

O&M parameter monitors sample processing method and device and communication system
Technical field
The present invention relates to Internet technical field, be specifically related to O&M parameter monitoring sample processing method and device And communication system.
Background technology
The O&M process of monitoring Internet service will produce substantial amounts of O&M parameter monitoring sample.In internet industry Occur during the O&M of business that service exception is more typically situation.Owing to service exception may produce the fortune of sudden change Dimension parameter monitoring sample, this kind of O&M parameter monitoring sample can be referred to as dirty sample.But, O&M parameter is supervised These dirty samples in control sample are likely to reduce the accuracy of relevant alarm.
The present inventor finds in research and practice process, and it is effective not provide in prior art For rejecting the scheme of dirty sample in O&M parameter monitoring sample, such as generally by O&M in prior art The O&M parameter monitoring sample exceeding fixed threshold in parameter monitoring sample is considered as dirty sample and is marked, but Inventor is by repeatedly practising discovery, and existing this scheme is likely to be due to portfolio and normally increases change and go out Existing distortion.If O&M parameter monitoring sample in dirty sample more effectively do not marked, this it is possible to Make associative operation (being correlated with of such as O&M done based on the analysis result to O&M parameter monitoring sample Alarm) mistake.
Summary of the invention
The embodiment of the present invention provides O&M parameter monitoring sample processing method and Apparatus and system, to improving dimension The recognition accuracy of the dirty sample in parameter monitoring sample.
Embodiment of the present invention first aspect provides a kind of O&M parameter monitoring sample processing method, including:
Obtain the O&M parameter monitoring sample of the current one period tx of O&M server;
Calculate the reference monitor cycle N-1 reference units period O&M parameter monitoring sample and described currently The sample statistics value σ x of the sample space that the O&M parameter monitoring sample of unit time period tx is formed, described with reference to prison The control cycle includes N number of reference units period, when described N-1 the reference units period is described N number of reference units Residue reference in addition to the reference units period that there are mapping relations with described current one period tx in Duan Unit time period, described N is the integer more than 1;
If the difference of sample for reference statistical value σ n and described sample statistics value σ x exceedes preset range, work as described The O&M parameter monitoring sample labeling of front unit time period tx is dirty sample, wherein, and described sample for reference statistical value σ n is that the O&M parameter of the described N number of reference units period in the described reference monitor cycle monitors sample institute shape The sample statistics value in the sample for reference space become.
Embodiment of the present invention second aspect provides a kind of O&M parameter monitoring sample processing apparatus, including:
Acquiring unit, for obtaining the O&M parameter monitoring sample of the current one period tx of O&M server;
Computing unit, for calculating the O&M parameter monitoring of N-1 the reference units period in reference monitor cycle The sample statistics of the sample space that the O&M parameter monitoring sample of sample and described current one period tx is formed Being worth σ x, the described reference monitor cycle includes that N number of reference units period, described N-1 reference units period are When described N number of reference units period removes the reference units with described current one period tx with mapping relations The residue reference units period outside period, described N is the integer more than 1;
Processing unit, if the difference for sample for reference statistical value σ n and described sample statistics value σ x exceedes default Scope, the O&M parameter of described current one period tx is monitored sample labeling is dirty sample, described with reference to sample This statistical value σ n is the O&M parameter monitoring of the described N number of reference units period in the described reference monitor cycle The sample statistics value in the sample for reference space that sample is formed.
The embodiment of the present invention third aspect provides a kind of communication system, including:
O&M server and monitoring device;
Described monitoring device, for obtaining the O&M parameter prison of the current one period tx of described O&M server Control sample;Calculate the O&M parameter monitoring sample of N-1 reference units period in reference monitor cycle with described The sample statistics value σ x of the sample space that the O&M parameter monitoring sample of current one period tx is formed, described ginseng Examining the monitoring cycle includes N number of reference units period, and wherein, described N is the integer more than 1, described N-1 The reference units period is except having mapping pass with described current one period tx in described N number of reference units period The residue reference units period outside the reference units period of system;If sample for reference statistical value σ n and described sample The difference of statistical value σ x exceedes preset range, and the O&M parameter of described current one period tx is monitored sample mark Being designated as dirty sample, described sample for reference statistical value σ n is that the described N number of reference in the described reference monitor cycle is single The sample statistics value in the sample for reference space that the O&M parameter monitoring sample of position period is formed.
It can be seen that in the technical scheme of the embodiment of the present invention, when obtaining the current one of O&M server After the O&M parameter monitoring sample of section tx, calculate the fortune of N-1 the reference units period in reference monitor cycle Dimension parameter monitoring sample monitors, with the O&M parameter of described current one period tx, the sample space that sample is formed Sample statistics value σ x, owing to being to surpass in the difference of sample for reference statistical value σ n and described sample statistics value σ x In the case of crossing preset range, the O&M parameter of described current one period tx is monitored sample labeling is dirty Sample, say, that the technique scheme of the embodiment of the present invention is by the fortune by current one period tx Dimension parameter monitoring sample and the O&M parameter of N number of reference units period in reference monitor cycle monitoring sample enter Row combines, and carrys out the O&M parameter monitoring sample of synthetic determination current one period tx according to statistical value result of calculation Whether it is dirty sample, is tied by the comparison of fixed threshold and O&M parameter monitoring sample relative in prior art Fruit judges that whether O&M parameter monitoring sample is the mechanism of dirty sample, and the such scheme of the embodiment of the present invention has It is beneficial to improve the recognition accuracy of the dirty sample in dimension parameter monitoring sample.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to enforcement In example or description of the prior art, the required accompanying drawing used is briefly described, it should be apparent that, describe below In accompanying drawing be only some embodiments of the present invention, for those of ordinary skill in the art, do not paying On the premise of going out creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the flow process signal of a kind of O&M parameter monitoring sample processing method that the embodiment of the present invention provides Figure;
Fig. 2-a is that the flow process of the another kind of O&M parameter monitoring sample processing method that the embodiment of the present invention provides is shown It is intended to;
Fig. 2-b is the configuration diagram of a kind of communication system that the embodiment of the present invention provides;
Fig. 2-c is the schematic diagram of the sample space generation type that the embodiment of the present invention provides;
Fig. 2-d is the schematic diagram of a kind of sample for reference spatial update mode that the embodiment of the present invention provides;
Fig. 3-a is that the flow process of the another kind of O&M parameter monitoring sample processing method that the embodiment of the present invention provides is shown It is intended to;
Fig. 3-b is the schematic diagram of the sample space generation type that the embodiment of the present invention provides;
Fig. 3-c is the schematic diagram of a kind of sample for reference spatial update mode that the embodiment of the present invention provides;
Fig. 4 is the schematic diagram of a kind of O&M parameter monitoring sample processing apparatus that the embodiment of the present invention provides;
Fig. 5 is the schematic diagram of a kind of monitoring device that the embodiment of the present invention provides;
Fig. 6 is the schematic diagram of a kind of communication system that the embodiment of the present invention provides.
Detailed description of the invention
The embodiment of the present invention provides O&M parameter monitoring sample processing method and Apparatus and system, to improving dimension The recognition accuracy of the dirty sample in parameter monitoring sample.
In order to make those skilled in the art be more fully understood that the present invention program, implement below in conjunction with the present invention Accompanying drawing in example, is clearly and completely described the technical scheme in the embodiment of the present invention, it is clear that institute The embodiment described is only the embodiment of a present invention part rather than whole embodiments.Based on this Embodiment in bright, the institute that those of ordinary skill in the art are obtained under not making creative work premise There are other embodiments, all should belong to the scope of protection of the invention.
It is described in detail individually below.
Term " first " in description and claims of this specification and above-mentioned accompanying drawing, " second ", " Three " and " the 4th " etc. is for distinguishing different object rather than for describing particular order.Additionally, art Language " includes " and " having " and their any deformation, it is intended that cover non-exclusive comprising.Such as Contain series of steps or the process of unit, method, system, product or equipment are not limited to list Step or unit, but the most also include step or the unit do not listed, or the most also include right In intrinsic other step of these processes, method, product or equipment or unit.
One embodiment of O&M parameter of the present invention monitoring sample processing method.Wherein, a kind of O&M parameter prison Control sample processing method, may include that the O&M parameter prison of the current one period tx obtaining O&M server Control sample;Calculate the O&M parameter monitoring sample of N-1 reference units period in reference monitor cycle with described The sample statistics value σ x of the sample space that the O&M parameter monitoring sample of current one period tx is formed, described ginseng Examining the monitoring cycle includes N number of reference units period, and wherein, described N-1 the reference units period is described N In the individual reference units period except with described current one period tx have mapping relations the reference units period it The outer residue reference units period, wherein, described N is the integer more than 1;If sample for reference statistical value σ n Preset range is exceeded, by the O&M parameter of described current one period tx with the difference of described sample statistics value σ x Monitoring sample labeling is dirty sample, and wherein, described sample for reference statistical value σ n is in the described reference monitor cycle The sample in sample for reference space that formed of the O&M parameter monitoring sample of described N number of reference units period Statistical value.
See a kind of O&M parameter monitoring sample process that Fig. 1, Fig. 1 provide for one embodiment of the present of invention The schematic flow sheet of method.As it is shown in figure 1, a kind of O&M parameter prison that one embodiment of the present of invention provides Control sample processing method may include that
101, the O&M parameter monitoring sample of the current one period tx of O&M server is obtained.
Wherein, the monitoring of the O&M parameter in the embodiment of the present invention sample for example, traffic monitoring sample, packet Amount monitoring sample, visit capacity monitoring sample, trading volume monitoring sample or the monitoring of other types O&M parameter Sample.
Wherein, above-mentioned O&M server can be such as Internet service or mobile communication business or other business O&M server.
The most above-mentioned O&M server can be Internet communication services (such as the instant messaging business such as QQ, wechat) O&M server, the O&M server of the Internet audio frequency and video business, the O&M service of internet gaming business The O&M server of device or the Internet financial business.
102, the O&M parameter monitoring sample of N-1 reference units period in reference monitor cycle is calculated with described The sample statistics value σ x of the sample space that the O&M parameter monitoring sample of current one period tx is formed.Described ginseng Examining the monitoring cycle includes that N number of reference units period, described N-1 reference units period are described N number of with reference to single Residue in addition to the reference units period that there are mapping relations with described current one period tx in the period of position The reference units period, described N is the integer more than 1.
Wherein, duration and the quantity of included reference units period in reference monitor cycle can be according to concrete field Scape needs to determine.The duration in reference monitor cycle can be 1 hour, 1 day, 1 week, 1 month or 1 year or its His duration.
For example, it is assumed that the reference monitor cycle time a length of 1 day, if the reference monitor cycle include each with reference to single Position the period time a length of 1 hour, then in this case N be equal to 24, in the case of this assume current one time Section tx be 15 o'clock to 16 o'clock, then in the N number of reference units period in the reference monitor cycle with described current one It is 15 o'clock to 16 o'clock that period tx has a reference units period of mapping relations, assumes that again current one period tx is 20 o'clock to 21 o'clock, then in the N number of reference units period in the reference monitor cycle with described current one period tx The reference units period with mapping relations is 20 o'clock to 21 o'clock, assumes that again current one period tx is at 23 and arrives 24 points, then have with described current one period tx in the N number of reference units period in the reference monitor cycle and reflect The reference units period penetrating relation is 23 o'clock to 24 o'clock, by that analogy.The most such as assume the reference monitor cycle Shi Changwei 1 day, if each reference units period of including in reference monitor cycle time a length of half an hour, then this In the case of Zhong, N is equal to 48.The most such as assume the reference monitor cycle time a length of 1 day, if the reference monitor cycle Including each reference units period time a length of 1 minute, then N is equal to 1440 in this case, with reference to single Position the period time other values a length of situation by that analogy.
Again for example, it is assumed that the reference monitor cycle time a length of 1 week, if each reference that the reference monitor cycle includes Unit time period time a length of 1 day, then in this case N be equal to 7, in the case of this assume the current one period Tx is Monday, then have with described current one period tx in the N number of reference units period in the reference monitor cycle The reference units period having mapping relations is Monday, assumes that again current one period tx is Friday, then with reference to prison The reference with described current one period tx in the N number of reference units period in the control cycle with mapping relations is single The position period is Friday, again it is assumed that current one period tx is Sunday, and the N number of reference in the reference monitor cycle The reference units period having mapping relations with described current one period tx in unit time period is Sunday, with this Analogize.Again for example, it is assumed that the reference monitor cycle time a length of 1 week, if each ginseng that the reference monitor cycle includes Examine unit time period time a length of 1 hour, then in this case N be equal to 168;If the reference monitor cycle includes Each reference units period time a length of 1 minute, then in this case N be equal to 10080, during reference units Section time other values a length of situation by that analogy.
Again for example, it is assumed that the reference monitor cycle time a length of 30 days, if each reference that the reference monitor cycle includes Unit time period time a length of 1 day, then in this case N be equal to 30, in the case of this assume current one time Section tx is No. 1, then have with described current one period tx in the N number of reference units period in the reference monitor cycle The reference units period having mapping relations is No. 1, assumes that again current one period tx is No. 17, then with reference to prison The reference with described current one period tx in the N number of reference units period in the control cycle with mapping relations is single The position period is No. 17, again it is assumed that current one period tx is No. 25, and the N number of reference in the reference monitor cycle The reference units period having mapping relations with described current one period tx in unit time period is No. 25, with this Analogize.Again for example, it is assumed that the duration in reference monitor cycle can be 30 days, if the reference monitor cycle include each The reference units period time a length of 1 hour, then in this case N be equal to 900, the reference units period time The situation of other values a length of is by that analogy.
Again for example, it is assumed that the reference monitor cycle time a length of 1 year, if each reference that the reference monitor cycle includes Unit time period time a length of January, then in this case N be equal to 12, in the case of this assume current one time Section tx be January, then in the N number of reference units period in the reference monitor cycle with described current one period tx The reference units period with mapping relations is January, assumes that again current one period tx is July, then joins Examine in the N number of reference units period in the monitoring cycle, with described current one period tx, there is the ginseng of mapping relations Examining unit time period is July, again it is assumed that current one period tx is December, and the N in the reference monitor cycle The reference units period having mapping relations with described current one period tx in the individual reference units period is 12 Month, by that analogy.Again for example, it is assumed that the reference monitor cycle time a length of 1 week, if the reference monitor cycle Including each reference units period time a length of 1 day, then N can be equal to 365 in this case;Reference units Period time other values a length of situation by that analogy.
103, the difference at sample for reference statistical value σ n Yu described sample statistics value σ x exceedes preset range In the case of, the O&M parameter of described current one period tx is monitored sample labeling is dirty sample.Described ginseng Examine the O&M parameter that sample statistics value σ n is the described N number of reference units period in the described reference monitor cycle The sample statistics value in the sample for reference space that monitoring sample is formed.
Optionally, among some possible embodiments of the present invention, sample statistics value can be sample standard deviation Sample variance or other can be used for characterizing in sample space the parameter of fluctuation between each sample.The most described sample This statistical value σ x is sample standard deviation and described sample for reference statistical value σ n is sample standard deviation, or described Sample statistics value σ x is sample variance and described sample for reference statistical value σ n is sample variance.
It can be seen that in the technical scheme of the embodiment of the present invention, when obtaining the current one of O&M server After the O&M parameter monitoring sample of section tx, calculate N-1 the reference units period in reference monitor cycle The sample that O&M parameter monitoring sample is formed with the O&M parameter monitoring sample of described current one period tx is empty Between sample statistics value σ x, owing to being the difference at sample for reference statistical value σ n Yu described sample statistics value σ x Different exceed preset range in the case of, the O&M parameter of described current one period tx is monitored sample mark It is designated as dirty sample, say, that the technique scheme of the embodiment of the present invention is by by the current one period The O&M parameter monitoring sample of tx and the monitoring of the O&M parameter of N number of reference units period in reference monitor cycle Sample is combined, and carrys out the O&M parameter of synthetic determination current one period tx according to statistical value result of calculation Whether monitoring sample is dirty sample, monitors sample relative in prior art by fixed threshold and O&M parameter Comparative result judge that whether O&M parameter monitoring sample is the mechanism of dirty sample, the embodiment of the present invention upper Scheme of stating is conducive to improving the recognition accuracy of the dirty sample in dimension parameter monitoring sample.
Optionally, among some possible embodiments of the present invention, described sample for reference statistical value σ n is less than Or equal to first threshold.It is to say, the O&M parameter prison of N number of reference units period in reference monitor cycle In the sample space that control sample is formed, fluctuate between each sample less, such as, can choose recent parameter base Line changes the O&M parameter monitoring sample of more smooth adjacent N number of reference units period as with reference to prison The O&M parameter monitoring sample of N number of reference units period in control cycle.
Certainly, the O&M parameter monitoring sample of N number of reference units period in reference monitor cycle can also be carried out Update.For example, the difference at described sample for reference statistical value σ n and described sample statistics value σ x does not surpass In the case of crossing preset range, can by described N number of reference units period in described reference monitor cycle with Described current one period tx has the O&M parameter monitoring sample of the reference units period of mapping relations, replaces O&M parameter for described current one period tx monitors sample.Practice finds, owing to can utilize current list The O&M parameter monitoring sample of position period is replaced having with the current one period in the reference monitor cycle and is reflected Penetrating the O&M parameter monitoring sample of the reference units period of relation, this is advantageous for so that in the reference monitor cycle The O&M parameter monitoring sample of N number of reference units period remain certain ageing, and with in the recent period O&M parameter there is stronger relatedness, therefore, based on the reference monitor cycle after above-mentioned renewal N number of The O&M parameter monitoring sample of reference units period, is conducive to preferably judging the current one period more accurately Following unitary period of tx is (under next unit time period of current one period tx or current one period tx Next unit time period etc.) O&M parameter monitoring the dirtiest sample of sample.
Optionally, among some possible embodiments of the present invention, also can unite at described sample for reference further In the case of difference between evaluation σ n and described sample statistics value σ x exceedes preset range, send and monitor institute There is abnormal alarm in the O&M parameter of the current one period tx stating O&M server.
Optionally, among some possible embodiments of the present invention, described sample for reference statistical value σ n is with described The difference of sample statistics value σ x exceedes preset range, including: described sample for reference statistical value σ n and described sample The absolute value of the difference between statistical value σ x is more than or equal to Second Threshold, or described sample for reference statistical value The absolute value of the difference between σ n and described sample statistics value σ x obtains divided by described sample for reference statistical value σ n The business arrived more than or equal to the 3rd threshold value (the 3rd threshold value such as equal to 5%, 6%, 8%, 10%, 15% or Other values of person), or the difference between described sample for reference statistical value σ n and described sample statistics value σ x is exhausted The business obtained value divided by described sample statistics value σ x more than or equal to the 4th threshold value, (such as may be used by the 4th threshold value Equal to 5%, 6%, 8%, 10%, 15%, 18% or other values), or described sample for reference statistical value More than or equal to the 5th threshold value, (wherein, the 5th threshold value such as can wait the ratio of σ n and described sample statistics value σ x In 110%, 105%, 115%, 116%, 120% or other values), or described sample for reference statistical value Less than or equal to the 6th threshold value, (wherein, the 6th threshold value such as can wait the ratio of σ n and described sample statistics value σ x In 90%, 95%, 92%, 87%, 85% or other values).It is appreciated that the concrete value of each threshold value Can need to set according to concrete scene.Certainly also can determine that described sample for reference is added up by other means The difference of value σ n and described sample statistics value σ x exceedes preset range.
Optionally, among some possible embodiments of the present invention, described sample for reference statistical value σ n is with described The difference of sample statistics value σ x is not less than preset range, it may include: described sample for reference statistical value σ n is with described The absolute value of the difference between sample statistics value σ x is less than Second Threshold, or described sample for reference statistical value σ n And the absolute value of the difference between described sample statistics value σ x obtains divided by described sample for reference statistical value σ n Business less than difference between the 3rd threshold value, or described sample for reference statistical value σ n and described sample statistics value σ x The business that obtains divided by described sample statistics value σ x of absolute value less than the 4th threshold value, or described sample for reference system The ratio of evaluation σ n and described sample statistics value σ x is less than the 5th threshold value, or described sample for reference statistical value σ n It is more than the 6th threshold value with the ratio of described sample statistics value σ x.Certainly also can determine described by other means The difference of sample for reference statistical value σ n and described sample statistics value σ x is not less than preset range.
For ease of being better understood from and implement the such scheme of the embodiment of the present invention, concrete below by some Application scenarios is illustrated.
See Fig. 2-a and Fig. 2-b, a kind of O&M parameter prison that Fig. 2-a provides for an alternative embodiment of the invention The schematic flow sheet of control sample processing method.The method that Fig. 2-a is illustrated can be in the network architecture shown in Fig. 2-b In be embodied as.Wherein, in the present embodiment with the reference monitor cycle time a length of 1 week, the reference monitor cycle As a example by quantity N of included reference units period is equal to 7, wherein, N can be with this equal to the situation of other values Analogize.As shown in Fig. 2-a, at a kind of O&M parameter monitoring sample that an alternative embodiment of the invention provides Reason method may include that
201, monitoring device obtains the O&M parameter monitoring sample working as the tx day before yesterday of O&M server.
Wherein, the monitoring of the O&M parameter in the embodiment of the present invention sample for example, traffic monitoring sample, packet Amount monitoring sample, visit capacity monitoring sample, trading volume monitoring sample or the monitoring of other types O&M parameter Sample.
202, the O&M parameter of 6 reference units periods that above-mentioned monitoring device calculates the reference monitor cycle monitors (this sample space can claim the sample space that sample is formed with the described O&M parameter monitoring sample working as the tx day before yesterday For sample space to be assessed) sample statistics value σ x.
Wherein, the described reference monitor cycle includes 7 reference units periods, wherein, described reference monitor week Each reference units period that phase includes time a length of 1 day.Wherein, described 6 reference units periods are described In 7 reference units periods except with described surplus in addition to reference units period that tx has mapping relations day before yesterday The remaining reference units period.
As an example it is assumed that working as the tx day before yesterday is Monday, then the N number of reference units period in the reference monitor cycle Among with described when the day before yesterday tx to have a reference units period of mapping relations be Monday, assume again when the day before yesterday tx be Friday, then the N number of reference units period in the reference monitor cycle have mapping relations with the described tx day before yesterday that works as The reference units period be Friday, again it is assumed that when the day before yesterday tx be Sunday, N number of among the reference monitor cycle In the reference units period with described when the day before yesterday tx to have a reference units period of mapping relations be Sunday, can be with this Analogize.
203, above-mentioned monitoring device judges the difference of sample for reference statistical value σ n and described sample statistics value σ x Whether exceed preset range.
The most then perform step 204.
If it is not, then perform step 205.
Wherein, described sample for reference statistical value σ n is that the described N number of reference in the described reference monitor cycle is single The sample statistics value in the sample for reference space that the O&M parameter monitoring sample of position period is formed.
See the exemplified sample space to be assessed of Fig. 2-c, Fig. 2-c and with reference to sample space to be assessed A kind of generation type.
Optionally, among some possible embodiments of the present invention, described sample for reference statistical value σ n and institute The difference stating sample statistics value σ x exceedes preset range, including: described sample for reference statistical value σ n is with described The absolute value of the difference between sample statistics value σ x is more than or equal to Second Threshold, or described sample for reference The absolute value of the difference between statistical value σ n and described sample statistics value σ x is divided by described sample for reference statistical value σ n and the business that obtains is more than or equal to the 3rd threshold value that (the 3rd threshold value is such as equal to 5%, 6%, 8%, 10% Or 15% or other values), or between described sample for reference statistical value σ n and described sample statistics value σ x The business that obtains divided by described sample statistics value σ x of the absolute value of difference more than or equal to the 4th threshold value (the Four threshold values such as can equal to 5%, 6%, 8%, 10%, 15%, 18% or other values), or described The ratio of sample for reference statistical value σ n and described sample statistics value σ x is more than or equal to the 5th threshold value (the 5th threshold Value such as can equal to 110%, 105%, 115%, 116%, 120% or other values), or described ginseng Examine the ratio of sample statistics value σ n and described sample statistics value σ x less than or equal to the 6th threshold value (the 6th threshold value Such as can equal to 90%, 95%, 92%, 87%, 85% or other values).It is appreciated that each threshold value Concrete value can need to set according to concrete scene.
Optionally, among some possible embodiments of the present invention, described sample for reference statistical value σ n and institute State the difference of sample statistics value σ x not less than preset range, it may include: described sample for reference statistical value σ n And the absolute value of the difference between described sample statistics value σ x is less than Second Threshold, or described sample for reference The absolute value of the difference between statistical value σ n and described sample statistics value σ x is divided by described sample for reference statistical value σ n and the business that obtains are less than the 3rd threshold value, or described sample for reference statistical value σ n and described sample statistics value σ x Between the business that obtains divided by described sample statistics value σ x of the absolute value of difference less than the 4th threshold value, or institute The ratio stating sample for reference statistical value σ n and described sample statistics value σ x is less than the 5th threshold value, or described reference The ratio of sample statistics value σ n and described sample statistics value σ x is more than the 6th threshold value.Certainly can also be passed through it His mode determines that the difference of described sample for reference statistical value σ n and described sample statistics value σ x is not less than presetting Scope.
204, the difference at sample for reference statistical value σ n Yu described sample statistics value σ x has exceeded preset range In the case of, the O&M parameter of described current one period tx can be monitored sample labeling by above-mentioned monitoring device For dirty sample.
Wherein, the O&M parameter of described current one period tx such as can be monitored sample by above-mentioned monitoring device Write in dirty sample database.
Optionally, among some possible embodiments of the present invention, also can unite at described sample for reference further In the case of difference between evaluation σ n and described sample statistics value σ x exceedes preset range, send and monitor institute There is abnormal alarm in the O&M parameter of the current one period tx stating O&M server.
205, in the difference of described sample for reference statistical value σ n and described sample statistics value σ x not less than presetting In the case of scope, monitoring device is by described N number of reference units period in described reference monitor cycle With the described tx day before yesterday that works as, there is the O&M parameter monitoring sample of the reference units period of mapping relations, replace with Described when the O&M parameter monitoring sample of the tx day before yesterday.
Participate in Fig. 2-d, Fig. 2-d exemplified N number of reference units period updating the reference monitor cycle A kind of mode of O&M parameter monitoring sample.
Practice finds, replaces owing to monitoring device may utilize the O&M parameter monitoring sample of current one period In the reference monitor cycle with when the day before yesterday tx have the reference units period of mapping relations O&M parameter monitoring Sample, this is advantageous for monitoring so that the O&M parameter of the N number of reference units period in the reference monitor cycle Sample remains certain ageing, and has stronger relatedness, therefore base with recent O&M parameter The O&M parameter monitoring sample of N number of reference units period in the reference monitor cycle after updating, is conducive to Judge that the following unitary period as the tx day before yesterday is (as when next unit time period of the tx day before yesterday the most more accurately Or when the day before yesterday tx next unit time period etc.) O&M parameter monitoring the dirtiest sample of sample.
It can be seen that in the technical scheme of the embodiment of the present invention, obtain O&M server as the tx day before yesterday O&M parameter monitoring sample after, calculate the reference monitor cycle N-1 reference units period O&M join The sample statistics of the sample space that amount monitoring sample is formed with the described O&M parameter monitoring sample working as the tx day before yesterday Value σ x, owing to being to exceed default model in the difference of sample for reference statistical value σ n Yu described sample statistics value σ x In the case of enclosing, it is dirty sample by the described O&M parameter monitoring sample labeling working as the tx day before yesterday, namely Say the technique scheme of the embodiment of the present invention be by will when the day before yesterday tx O&M parameter monitoring sample and ginseng The O&M parameter monitoring sample of the N number of reference units period examining the monitoring cycle is combined, according to statistical value Result of calculation come synthetic determination when the day before yesterday tx O&M parameter monitoring sample whether be dirty sample, relative to existing Have in technology and judge that O&M parameter monitors by the comparative result of fixed threshold and O&M parameter monitoring sample Whether sample is the mechanism of dirty sample, and the such scheme of the embodiment of the present invention is conducive to improving dimension parameter monitoring sample The recognition accuracy of the dirty sample in Ben.
See a kind of O&M parameter monitoring sample that Fig. 3-a, Fig. 3-a provides for an alternative embodiment of the invention The schematic flow sheet of processing method.The method that Fig. 3-a is illustrated can have in the network architecture shown in Fig. 2-b Body is implemented.Wherein, in the present embodiment with the reference monitor cycle time within a length of 1 month, (this sentences 1 month for 30 As a example by it), as a example by quantity N of the reference units period included by the reference monitor cycle is equal to 30, N is equal to it His situation of value can be by that analogy.As shown in Fig. 3-a, a kind of fortune that an alternative embodiment of the invention provides Dimension parameter monitoring sample processing method specifically may include that
301, monitoring device obtains the O&M parameter monitoring sample working as the tx day before yesterday of O&M server.
Wherein, the monitoring of the O&M parameter in the embodiment of the present invention sample for example, traffic monitoring sample, packet Amount monitoring sample, visit capacity monitoring sample, trading volume monitoring sample or the monitoring of other types O&M parameter Sample.
302, the O&M parameter of 29 reference units periods that above-mentioned monitoring device calculates the reference monitor cycle is supervised (this sample space can for the sample space that control sample is formed with the described O&M parameter monitoring sample working as the tx day before yesterday Referred to as sample space to be assessed) sample statistics value σ x.
Wherein, the described reference monitor cycle includes 30 reference units periods, wherein, described reference monitor week Each reference units period that phase includes time a length of 1 day.Wherein, described 29 reference units periods are institute State in 30 reference units periods except with described in addition to reference units period that tx has mapping relations day before yesterday The residue reference units period.
As an example it is assumed that working as the tx day before yesterday is No. 10, then 30 reference units periods in the reference monitor cycle Among with described when the day before yesterday tx to have a reference units period of mapping relations be No. 10, assume again when the day before yesterday tx be No. 25, then 30 reference units periods in the reference monitor cycle have mapping relations with the described tx day before yesterday that works as The reference units period be No. 25, again it is assumed that when the day before yesterday tx be No. 30,30 among the reference monitor cycle In the reference units period with described when the day before yesterday tx to have a reference units period of mapping relations be No. 30, can be with this Analogize.
303, above-mentioned monitoring device judges the difference of sample for reference statistical value σ n and described sample statistics value σ x Whether exceed preset range.
The most then perform step 304.
If it is not, then perform step 305.
Wherein, described sample for reference statistical value σ n is that described 30 references in the described reference monitor cycle are single The sample statistics value in the sample for reference space that the O&M parameter monitoring sample of position period is formed.
See the exemplified sample space to be assessed of Fig. 3-b, Fig. 3-b and with reference to sample space to be assessed A kind of generation type.
Optionally, among some possible embodiments of the present invention, described sample for reference statistical value σ n and institute The difference stating sample statistics value σ x exceedes preset range, including: described sample for reference statistical value σ n is with described The absolute value of the difference between sample statistics value σ x is more than or equal to Second Threshold, or described sample for reference The absolute value of the difference between statistical value σ n and described sample statistics value σ x is divided by described sample for reference statistical value σ n and the business that obtains is more than or equal to the 3rd threshold value that (the 3rd threshold value is such as equal to 5%, 6%, 8%, 10% Or 15% or other values), or between described sample for reference statistical value σ n and described sample statistics value σ x The business that obtains divided by described sample statistics value σ x of the absolute value of difference more than or equal to the 4th threshold value (the Four threshold values such as can equal to 5%, 6%, 8%, 10%, 15%, 18% or other values), or described The ratio of sample for reference statistical value σ n and described sample statistics value σ x is more than or equal to the 5th threshold value (the 5th threshold Value such as can equal to 110%, 105%, 115%, 118%, 120% or other values), or described ginseng Examine the ratio of sample statistics value σ n and described sample statistics value σ x less than or equal to the 6th threshold value (the 6th threshold value Such as can equal to 90%, 95%, 93%, 87%, 85% or other values).It is appreciated that each threshold value Concrete value can need to set according to concrete scene.
Optionally, among some possible embodiments of the present invention, described sample for reference statistical value σ n and institute State the difference of sample statistics value σ x not less than preset range, it may include: described sample for reference statistical value σ n And the absolute value of the difference between described sample statistics value σ x is less than Second Threshold, or described sample for reference The absolute value of the difference between statistical value σ n and described sample statistics value σ x is divided by described sample for reference statistical value σ n and the business that obtains are less than the 3rd threshold value, or described sample for reference statistical value σ n and described sample statistics value σ x Between the business that obtains divided by described sample statistics value σ x of the absolute value of difference less than the 4th threshold value, or institute The ratio stating sample for reference statistical value σ n and described sample statistics value σ x is less than the 5th threshold value, or described reference The ratio of sample statistics value σ n and described sample statistics value σ x is more than the 6th threshold value.Certainly can also be passed through it His mode determines that the difference of described sample for reference statistical value σ n and described sample statistics value σ x is not less than presetting Scope.
304, the difference at sample for reference statistical value σ n Yu described sample statistics value σ x has exceeded preset range In the case of, the O&M parameter of described current one period tx can be monitored sample labeling by above-mentioned monitoring device For dirty sample.
Wherein, the O&M parameter of described current one period tx such as can be monitored sample by above-mentioned monitoring device Write in dirty sample database.
Optionally, among some possible embodiments of the present invention, also can unite at described sample for reference further In the case of difference between evaluation σ n and described sample statistics value σ x exceedes preset range, send and monitor institute There is abnormal alarm in the O&M parameter of the current one period tx stating O&M server.
305, in the difference of described sample for reference statistical value σ n and described sample statistics value σ x not less than presetting In the case of scope, monitoring device is by described N number of reference units period in described reference monitor cycle With the described tx day before yesterday that works as, there is the O&M parameter monitoring sample of the reference units period of mapping relations, replace with Described when the O&M parameter monitoring sample of the tx day before yesterday.
Participate in Fig. 3-c, Fig. 3-c exemplified N number of reference units period updating the reference monitor cycle A kind of mode of O&M parameter monitoring sample, can form new sample for reference space, based on new by updating Sample for reference space is conducive to the following unitary period judging to work as the tx day before yesterday the most more accurately (as currently Next day of day tx or next day etc. of current one period tx) O&M parameter monitoring sample the dirtiest Sample.
Practice finds, owing to monitoring device can utilize the O&M parameter monitoring sample of current one period to replace Change in the reference monitor cycle with when the day before yesterday tx have the reference units period of mapping relations O&M parameter prison Control sample, this is advantageous for supervising so that the O&M parameter of the N number of reference units period in the reference monitor cycle Control sample remains certain ageing, and has stronger relatedness with recent O&M parameter, therefore The O&M parameter monitoring sample of N number of reference units period based on the reference monitor cycle after updating, favorably In preferably judge the most more accurately the following unitary period as the tx day before yesterday (as when the day before yesterday tx next unit time Section or when the day before yesterday tx next unit time period etc.) O&M parameter monitoring the dirtiest sample of sample.
It can be seen that in the technical scheme of the embodiment of the present invention, obtain O&M server as the tx day before yesterday After O&M parameter monitoring sample, calculate the O&M parameter of N-1 the reference units period in reference monitor cycle The sample statistics value of the sample space that monitoring sample is formed with the described O&M parameter monitoring sample working as the tx day before yesterday σ x, owing to being to exceed preset range in the difference of sample for reference statistical value σ n Yu described sample statistics value σ x In the case of, it is dirty sample by the described O&M parameter monitoring sample labeling working as the tx day before yesterday, say, that this The technique scheme of bright embodiment is by working as O&M parameter monitoring sample and the reference monitor of the tx day before yesterday The O&M parameter monitoring sample of N number of reference units period in cycle is combined, according to statistical value result of calculation Come synthetic determination when the day before yesterday tx O&M parameter monitoring sample whether be dirty sample, logical relative in prior art Cross the comparative result of fixed threshold and O&M parameter monitoring sample to judge that whether O&M parameter monitoring sample is The mechanism of dirty sample, the such scheme of the embodiment of the present invention is conducive to improving the dirty sample in dimension parameter monitoring sample This recognition accuracy.
It is appreciated that Fig. 2-b is as a example by two autonomous devices by monitoring device and O&M server, at some Under application scenarios, monitoring device and O&M server can integrate.
Seeing Fig. 4, the embodiment of the present invention also provides for a kind of O&M parameter monitoring sample processing apparatus 400, permissible Including: acquiring unit 410, computing unit 420 and processing unit 430.
Wherein, acquiring unit 410, for obtaining the O&M parameter of the current one period tx of O&M server Monitoring sample.
Wherein, above-mentioned O&M server can be such as Internet service or mobile communication business or other business O&M server.
Wherein, the monitoring of the O&M parameter in the embodiment of the present invention sample for example, traffic monitoring sample, packet Amount monitoring sample, visit capacity monitoring sample, trading volume monitoring sample or the monitoring of other types O&M parameter Sample.
Computing unit 420, for calculating the O&M parameter prison of N-1 the reference units period in reference monitor cycle The sample system of the sample space that the O&M parameter monitoring sample of control sample and described current one period tx is formed Evaluation σ x, the described reference monitor cycle includes N number of reference units period, described N-1 reference units period For in described N number of reference units period except with described current one period tx, there is the reference units of mapping relations The residue reference units period outside period, described N is the integer more than 1.
Processing unit 430, if the difference for sample for reference statistical value σ n and described sample statistics value σ x exceedes Preset range, the O&M parameter of described current one period tx is monitored sample labeling is dirty sample, described ginseng Examine the O&M parameter that sample statistics value σ n is the described N number of reference units period in the described reference monitor cycle The sample statistics value in the sample for reference space that monitoring sample is formed.
Optionally, among some possible embodiments of the present invention, sample statistics value can be sample standard deviation Sample variance or other can be used for characterizing in sample space the parameter of fluctuation between each sample.The most described sample This statistical value σ x is sample standard deviation and described sample for reference statistical value σ n is sample standard deviation, or described sample This statistical value σ x is sample variance and described sample for reference statistical value σ n is sample variance.
Optionally, among some possible embodiments of the present invention, described sample for reference statistical value σ n is less than Or equal to first threshold.It is to say, the O&M parameter prison of N number of reference units period in reference monitor cycle In the sample space that control sample is formed, fluctuate between each sample less, such as, can choose recent parameter base Line changes the O&M parameter monitoring sample of more smooth adjacent N number of reference units period as with reference to prison The O&M parameter monitoring sample of N number of reference units period in control cycle.
Optionally, among some possible embodiments of the present invention, described device 400 may also include that
Sample Refreshment unit 440, for described sample for reference statistical value σ n and described sample statistics value σ x's In the case of difference is not above preset range, during by described N number of reference units in described reference monitor cycle The O&M parameter monitoring of the reference units period with described current one period tx with mapping relations in period Sample, replaces with the O&M parameter monitoring sample of described current one period tx.
Optionally, among some possible embodiments of the present invention, described device 400 may also include that
Alarm Unit 450, the difference between described sample for reference statistical value σ n and described sample statistics value σ x In the case of exceeding preset range, send the O&M of the current one period tx monitoring described O&M server There is abnormal alarm in parameter.
Wherein, duration and the quantity of included reference units period in reference monitor cycle can be according to concrete field Scape needs to determine.The duration in reference monitor cycle can be 1 hour, 1 day, 1 week, 1 month or 1 year or its His duration.
Optionally, among some possible embodiments of the present invention, described sample for reference statistical value σ n is with described The difference of sample statistics value σ x exceedes preset range, including: described sample for reference statistical value σ n and described sample The absolute value of the difference between statistical value σ x is more than or equal to Second Threshold, or described sample for reference statistical value The absolute value of the difference between σ n and described sample statistics value σ x obtains divided by described sample for reference statistical value σ n The business arrived more than or equal to the 3rd threshold value (the 3rd threshold value such as equal to 5%, 6%, 8%, 10%, 15% or Other values of person), or the difference between described sample for reference statistical value σ n and described sample statistics value σ x is exhausted The business obtained value divided by described sample statistics value σ x more than or equal to the 4th threshold value, (such as may be used by the 4th threshold value Equal to 5%, 6%, 8%, 10%, 15%, 18% or other values), or described sample for reference statistical value More than or equal to the 5th threshold value, (wherein, the 5th threshold value such as can wait the ratio of σ n and described sample statistics value σ x In 110%, 105%, 115%, 116%, 120% or other values), or described sample for reference statistical value Less than or equal to the 6th threshold value, (wherein, the 6th threshold value such as can wait the ratio of σ n and described sample statistics value σ x In 90%, 95%, 92%, 87%, 85% or other values).It is appreciated that the concrete value of each threshold value Can need to set according to concrete scene.Certainly also can determine that described sample for reference is added up by other means The difference of value σ n and described sample statistics value σ x exceedes preset range.
Optionally, among some possible embodiments of the present invention, described sample for reference statistical value σ n is with described The difference of sample statistics value σ x is not less than preset range, it may include: described sample for reference statistical value σ n is with described The absolute value of the difference between sample statistics value σ x is less than Second Threshold, or described sample for reference statistical value σ n And the absolute value of the difference between described sample statistics value σ x obtains divided by described sample for reference statistical value σ n Business less than difference between the 3rd threshold value, or described sample for reference statistical value σ n and described sample statistics value σ x The business that obtains divided by described sample statistics value σ x of absolute value less than the 4th threshold value, or described sample for reference system The ratio of evaluation σ n and described sample statistics value σ x is less than the 5th threshold value, or described sample for reference statistical value σ n It is more than the 6th threshold value with the ratio of described sample statistics value σ x.Certainly also can determine described by other means The difference of sample for reference statistical value σ n and described sample statistics value σ x is not less than preset range.
It is appreciated that O&M parameter monitoring sample processing apparatus 400 and O&M server can be two independences As a example by equipment, under some application scenarios, O&M parameter monitoring sample processing apparatus 400 and O&M server can Integrate.
It is understood that each functional module of the O&M parameter monitoring sample processing apparatus 400 of the present embodiment Function can implement according to the method in said method embodiment, it implements process and is referred to Stating the associated description of embodiment of the method, here is omitted.
It can be seen that in the technical scheme of the embodiment of the present invention, O&M parameter monitoring sample processing apparatus 400 After obtaining the O&M parameter of current one period tx of O&M server monitoring sample, calculate reference monitor The O&M parameter monitoring sample of N-1 the reference units period in cycle and the O&M of described current one period tx The sample statistics value σ x of sample space that parameter monitoring sample is formed, owing to being at sample for reference statistical value σ n In the case of exceeding preset range with the difference of described sample statistics value σ x, by described current one period tx O&M parameter monitoring sample labeling be dirty sample, say, that the technique scheme of the embodiment of the present invention It is by the O&M parameter of current one period tx is monitored sample and N number of reference units in reference monitor cycle The O&M parameter monitoring sample of period is combined, and carrys out synthetic determination current one according to statistical value result of calculation Period tx O&M parameter monitoring sample whether be dirty sample, so relative in prior art by fixing threshold The comparative result of value and O&M parameter monitoring sample judges whether O&M parameter monitoring sample is dirty sample Mechanism, the such scheme of the embodiment of the present invention is conducive to improving the identification of the dirty sample in dimension parameter monitoring sample Accuracy.
See the structured flowchart that Fig. 5, Fig. 5 are the monitoring devices 500 that another embodiment of the present invention provides.
Wherein, monitoring device 500 may include that at least 1 processor 501, memorizer 505 and at least 1 Communication bus 502.Communication bus 502 is for realizing the connection communication between these assemblies.Wherein, this monitoring Equipment 500 optionally comprises user interface 503, including display (such as touch screen, liquid crystal display, holography Imaging (English: Holographic) or projection (English: Projector) etc.), pointing device (such as Mouse, trace ball (English: trackball) touch-sensitive plate or touch screen etc.), photographic head and/or sound pick up equipment Etc..
Wherein, this monitoring device 500 may also include at least 1 network interface 504.
Wherein, memorizer 505 can include read only memory and random access memory, and to processor 501 Instruction and data is provided.Wherein, the part in memorizer 505 can also include that non-volatile random accesses Memorizer.
In some embodiments, memorizer 505 stores following element, executable module or data Structure, or their subset, or their superset:
Operating system 5051, comprises various system program, be used for realizing various basic business and process based on The task of hardware.
Application program module 5052, comprises various application program, is used for realizing various applied business.
In embodiments of the present invention, by calling program or instruction, the processor 501 of memorizer 505 storage Obtain the O&M parameter monitoring sample of the current one period tx of O&M server;Calculate the reference monitor cycle The O&M parameter monitoring sample of N-1 reference units period and the O&M parameter prison of described current one period tx Controlling the sample statistics value σ x of the sample space that sample is formed, the described reference monitor cycle includes N number of reference units Period, described N-1 the reference units period is to remove and described current one in described N number of reference units period The residue reference units period outside the reference units period that period tx has mapping relations, described N is more than 1 Integer;If the difference of sample for reference statistical value σ n and described sample statistics value σ x exceedes preset range, by institute The O&M parameter monitoring sample labeling stating current one period tx is dirty sample, described sample for reference statistical value σ n O&M parameter monitoring sample by the described N number of reference units period in the described reference monitor cycle is formed The sample statistics value in sample for reference space.
Wherein, the monitoring of the O&M parameter in the embodiment of the present invention sample for example, traffic monitoring sample, packet Amount monitoring sample, visit capacity monitoring sample, trading volume monitoring sample or the monitoring of other types O&M parameter Sample.
Optionally, among some possible embodiments of the present invention, sample statistics value can be sample standard deviation Sample variance or other can be used for characterizing in sample space the parameter of fluctuation between each sample.The most described sample This statistical value σ x is sample standard deviation and described sample for reference statistical value σ n is sample standard deviation, or described sample This statistical value σ x is sample variance and described sample for reference statistical value σ n is sample variance.
Optionally, among some possible embodiments of the present invention, described sample for reference statistical value σ n is less than Or equal to first threshold.It is to say, the O&M parameter prison of N number of reference units period in reference monitor cycle In the sample space that control sample is formed, fluctuate between each sample less, such as, can choose recent parameter base Line changes the O&M parameter monitoring sample of more smooth adjacent N number of reference units period as with reference to prison The O&M parameter monitoring sample of N number of reference units period in control cycle.
Optionally, among some possible embodiments of the present invention, processor 501 is additionally operable in described reference In the case of the difference of sample statistics value σ n and described sample statistics value σ x is not above preset range, by described Having with described current one period tx in described N number of reference units period in reference monitor cycle maps pass The O&M parameter monitoring sample of the reference units period of system, replaces with the O&M ginseng of described current one period tx Amount monitoring sample.
Optionally, among some possible embodiments of the present invention, processor 501 is additionally operable in described reference In the case of difference between sample statistics value σ n and described sample statistics value σ x exceedes preset range, send prison There is abnormal alarm to the O&M parameter of the current one period tx of described O&M server in control.
Wherein, duration and the quantity of included reference units period in reference monitor cycle can be according to concrete field Scape needs to determine.The duration in reference monitor cycle can be 1 hour, 1 day, 1 week, 1 month or 1 year or its His duration.
Optionally, among some possible embodiments of the present invention, described sample for reference statistical value σ n is with described The difference of sample statistics value σ x exceedes preset range, including: described sample for reference statistical value σ n and described sample The absolute value of the difference between statistical value σ x is more than or equal to Second Threshold, or described sample for reference statistical value The absolute value of the difference between σ n and described sample statistics value σ x obtains divided by described sample for reference statistical value σ n The business arrived more than or equal to the 3rd threshold value (the 3rd threshold value such as equal to 5%, 6%, 8%, 10%, 15% or Other values of person), or the difference between described sample for reference statistical value σ n and described sample statistics value σ x is exhausted The business obtained value divided by described sample statistics value σ x more than or equal to the 4th threshold value, (such as may be used by the 4th threshold value Equal to 5%, 6%, 8%, 10%, 15%, 18% or other values), or described sample for reference statistical value More than or equal to the 5th threshold value, (wherein, the 5th threshold value such as can wait the ratio of σ n and described sample statistics value σ x In 110%, 105%, 115%, 116%, 120% or other values), or described sample for reference statistical value Less than or equal to the 6th threshold value, (wherein, the 6th threshold value such as can wait the ratio of σ n and described sample statistics value σ x In 90%, 95%, 92%, 87%, 85% or other values).It is appreciated that the concrete value of each threshold value Can need to set according to concrete scene.Certainly also can determine that described sample for reference is added up by other means The difference of value σ n and described sample statistics value σ x exceedes preset range.
Optionally, among some possible embodiments of the present invention, described sample for reference statistical value σ n is with described The difference of sample statistics value σ x is not less than preset range, it may include: described sample for reference statistical value σ n is with described The absolute value of the difference between sample statistics value σ x is less than Second Threshold, or described sample for reference statistical value σ n And the absolute value of the difference between described sample statistics value σ x obtains divided by described sample for reference statistical value σ n Business less than difference between the 3rd threshold value, or described sample for reference statistical value σ n and described sample statistics value σ x The business that obtains divided by described sample statistics value σ x of absolute value less than the 4th threshold value, or described sample for reference system The ratio of evaluation σ n and described sample statistics value σ x is less than the 5th threshold value, or described sample for reference statistical value σ n It is more than the 6th threshold value with the ratio of described sample statistics value σ x.Certainly also can determine described by other means The difference of sample for reference statistical value σ n and described sample statistics value σ x is not less than preset range.
It is understood that the function of each functional module of the monitoring device 500 of the present embodiment can be according to above-mentioned Method in embodiment of the method implements, and it implements process and is referred to the phase of said method embodiment Closing and describe, here is omitted.
It can be seen that in the technical scheme of the embodiment of the present invention, monitoring device 500 is obtaining O&M server Current one period tx O&M parameter monitoring sample after, calculate the reference monitor cycle N-1 reference The O&M parameter monitoring sample of unit time period and the O&M parameter monitoring sample shape of described current one period tx The sample statistics value σ x of sample space become, owing to being in sample for reference statistical value σ n and described sample statistics value In the case of the difference of σ x exceedes preset range, the O&M parameter of described current one period tx is monitored sample Originally dirty sample it is labeled as, say, that the technique scheme of the embodiment of the present invention is by by current one The O&M parameter monitoring sample of period tx and the O&M parameter of N number of reference units period in reference monitor cycle prison Control sample is combined, and carrys out the O&M parameter of synthetic determination current one period tx according to statistical value result of calculation Whether monitoring sample is dirty sample, is so monitored by fixed threshold and O&M parameter relative in prior art The comparative result of sample judges that whether O&M parameter monitoring sample is the mechanism of dirty sample, the embodiment of the present invention Such scheme be conducive to improving the recognition accuracy of dirty sample in dimension parameter monitoring sample.
See Fig. 6, the embodiment of the present invention also provides for a kind of communication system, it may include:
O&M server 610 and monitoring device 620.
Described monitoring device 610, for obtaining the O&M ginseng of the current one period tx of described O&M server Amount monitoring sample;Calculate the reference monitor cycle N-1 reference units period O&M parameter monitoring sample and The sample statistics value σ x of the sample space that the O&M parameter monitoring sample of described current one period tx is formed, institute Stating the reference monitor cycle includes N number of reference units period, and described N is the integer more than 1, described N-1 ginseng Examining unit time period is except having mapping relations with described current one period tx in described N number of reference units period The reference units period outside the residue reference units period;If sample for reference statistical value σ n unites with described sample The difference of evaluation σ x exceedes preset range, and the O&M parameter of described current one period tx is monitored sample labeling For dirty sample, described sample for reference statistical value σ n is the described N number of reference units in the described reference monitor cycle The sample statistics value in the sample for reference space that the O&M parameter monitoring sample of period is formed.
Wherein, the monitoring of the O&M parameter in the embodiment of the present invention sample for example, traffic monitoring sample, packet Amount monitoring sample, visit capacity monitoring sample, trading volume monitoring sample or the monitoring of other types O&M parameter Sample.
Wherein, duration and the quantity of included reference units period in reference monitor cycle can be according to concrete field Scape needs to determine.The duration in reference monitor cycle can be 1 hour, 1 day, 1 week, 1 month or 1 year or its His duration.
For example, it is assumed that the reference monitor cycle time a length of 1 day, if the reference monitor cycle include each with reference to single Position the period time a length of 1 hour, then in this case N be equal to 24, in the case of this assume current one time Section tx be 15 o'clock to 16 o'clock, then in the N number of reference units period in the reference monitor cycle with described current one It is 15 o'clock to 16 o'clock that period tx has a reference units period of mapping relations, assumes that again current one period tx is 20 o'clock to 21 o'clock, then in the N number of reference units period in the reference monitor cycle with described current one period tx The reference units period with mapping relations is 20 o'clock to 21 o'clock, assumes that again current one period tx is at 23 and arrives 24 points, then have with described current one period tx in the N number of reference units period in the reference monitor cycle and reflect The reference units period penetrating relation is 23 o'clock to 24 o'clock, by that analogy.The most such as assume the reference monitor cycle Shi Changwei 1 day, if each reference units period of including in reference monitor cycle time a length of half an hour, then this In the case of Zhong, N is equal to 48.The most such as assume the reference monitor cycle time a length of 1 day, if the reference monitor cycle Including each reference units period time a length of 1 minute, then N is equal to 1440 in this case, with reference to single Position the period time other values a length of situation by that analogy.
Optionally, among some possible embodiments of the present invention, sample statistics value can be sample standard deviation Sample variance or other can be used for characterizing in sample space the parameter of fluctuation between each sample.The most described sample This statistical value σ x is sample standard deviation and described sample for reference statistical value σ n is sample standard deviation, or described sample This statistical value σ x is sample variance and described sample for reference statistical value σ n is sample variance.
Optionally, among some possible embodiments of the present invention, described sample for reference statistical value σ n is less than Or equal to first threshold.It is to say, the O&M parameter prison of N number of reference units period in reference monitor cycle In the sample space that control sample is formed, fluctuating less between each sample, such as monitoring device 620 can be chosen Recent parameter baseline changes the O&M parameter monitoring sample of more smooth adjacent N number of reference units period This monitors sample as the O&M parameter of N number of reference units period in reference monitor cycle.
Certainly, the O&M parameter monitoring sample of N number of reference units period in reference monitor cycle can also be carried out Update.For example, the difference at described sample for reference statistical value σ n and described sample statistics value σ x does not surpass In the case of crossing preset range, monitoring device 620 can be by single for described N number of reference in described reference monitor cycle The O&M parameter of the reference units period with described current one period tx with mapping relations in the period of position Monitoring sample, replaces with the O&M parameter monitoring sample of described current one period tx.Practice finds, due to Can utilize the current one period O&M parameter monitoring sample to replace in the reference monitor cycle with currently Unit time period have the reference units period of mapping relations O&M parameter monitoring sample, this be advantageous for so that When the O&M parameter monitoring sample of the N number of reference units period in the reference monitor cycle remains certain Effect property, and with recent O&M parameter, there is stronger relatedness, therefore, based on the ginseng after above-mentioned renewal Examine the O&M parameter monitoring sample of N number of reference units period in monitoring cycle, be conducive to the most more accurately Judge current one period tx the following unitary period (as current one period tx next unit time period or work as Next unit time period etc. of front unit time period tx) O&M parameter monitoring the dirtiest sample of sample.
Optionally, among some possible embodiments of the present invention, monitoring device 620 also can be in described reference In the case of difference between sample statistics value σ n and described sample statistics value σ x exceedes preset range, send prison There is abnormal alarm to the O&M parameter of the current one period tx of described O&M server in control.
Optionally, among some possible embodiments of the present invention, described sample for reference statistical value σ n is with described The difference of sample statistics value σ x exceedes preset range, including: described sample for reference statistical value σ n and described sample The absolute value of the difference between statistical value σ x is more than or equal to Second Threshold, or described sample for reference statistical value The absolute value of the difference between σ n and described sample statistics value σ x obtains divided by described sample for reference statistical value σ n The business arrived more than or equal to the 3rd threshold value (the 3rd threshold value such as equal to 5%, 6%, 8%, 10%, 15% or Other values of person), or the difference between described sample for reference statistical value σ n and described sample statistics value σ x is exhausted The business obtained value divided by described sample statistics value σ x more than or equal to the 4th threshold value, (such as may be used by the 4th threshold value Equal to 5%, 6%, 8%, 10%, 15%, 18% or other values), or described sample for reference statistical value More than or equal to the 5th threshold value, (wherein, the 5th threshold value such as can wait the ratio of σ n and described sample statistics value σ x In 110%, 105%, 115%, 116%, 120% or other values), or described sample for reference statistical value Less than or equal to the 6th threshold value, (wherein, the 6th threshold value such as can wait the ratio of σ n and described sample statistics value σ x In 90%, 95%, 92%, 87%, 85% or other values).It is appreciated that the concrete value of each threshold value Can need to set according to concrete scene.Certainly also can determine that described sample for reference is added up by other means The difference of value σ n and described sample statistics value σ x exceedes preset range.
Optionally, among some possible embodiments of the present invention, described sample for reference statistical value σ n is with described The difference of sample statistics value σ x is not less than preset range, it may include: described sample for reference statistical value σ n is with described The absolute value of the difference between sample statistics value σ x is less than Second Threshold, or described sample for reference statistical value σ n And the absolute value of the difference between described sample statistics value σ x obtains divided by described sample for reference statistical value σ n Business less than difference between the 3rd threshold value, or described sample for reference statistical value σ n and described sample statistics value σ x The business that obtains divided by described sample statistics value σ x of absolute value less than the 4th threshold value, or described sample for reference system The ratio of evaluation σ n and described sample statistics value σ x is less than the 5th threshold value, or described sample for reference statistical value σ n It is more than the 6th threshold value with the ratio of described sample statistics value σ x.Certainly also can determine described by other means The difference of sample for reference statistical value σ n and described sample statistics value σ x is not less than preset range.
It can be seen that in the technical scheme of the embodiment of the present invention, monitoring device 620 is obtaining O&M server After the O&M parameter monitoring sample of the current one period tx of 610, calculate N-1 the ginseng in reference monitor cycle Examine the O&M parameter monitoring sample of unit time period and the O&M parameter monitoring sample of described current one period tx The sample statistics value σ x of sample space formed, owing to being at sample for reference statistical value σ n and described sample statistics In the case of the difference of value σ x exceedes preset range, the O&M parameter of described current one period tx is monitored Sample labeling is dirty sample, say, that the technique scheme of the embodiment of the present invention is by by currently single The O&M parameter monitoring sample of position period tx and the O&M parameter of N number of reference units period in reference monitor cycle Monitoring sample is combined, and carrys out the O&M ginseng of synthetic determination current one period tx according to statistical value result of calculation Whether amount monitoring sample is dirty sample, monitors sample relative in prior art by fixed threshold and O&M parameter This comparative result judges that whether O&M parameter monitoring sample is the mechanism of dirty sample, the embodiment of the present invention Such scheme is conducive to improving the recognition accuracy of the dirty sample in dimension parameter monitoring sample.
The embodiment of the present invention also provides for a kind of computer-readable storage medium, and wherein, this computer-readable storage medium can be deposited Containing program, this program includes any O&M parameter monitoring described in said method embodiment when performing The part or all of step of sample processing method.
It should be noted that for aforesaid each method embodiment, in order to be briefly described, therefore it is all stated For a series of combination of actions, but those skilled in the art should know, the present invention is not by described The restriction of sequence of movement because according to the present invention, some step can use other orders or with Shi Jinhang.Secondly, those skilled in the art also should know, embodiment described in this description is equal Belong to preferred embodiment, necessary to involved action and the module not necessarily present invention.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and does not has in certain embodiment The part being described in detail, may refer to the associated description of other embodiments.
In several embodiments provided herein, it should be understood that disclosed device, can be passed through it Its mode realizes.Such as, device embodiment described above is only schematically, the most described list The division of unit, is only a kind of logic function and divides, and actual can have other dividing mode, example when realizing As multiple unit or assembly can in conjunction with or be desirably integrated into another system, or some features can be neglected Slightly, or do not perform.Another point, shown or discussed coupling each other or direct-coupling or communication link Connecing can be the INDIRECT COUPLING by some interfaces, device or unit or communication connection, can be electrical or it Its form.
The described unit illustrated as separating component can be or may not be physically separate, as The parts that unit shows can be or may not be physical location, i.e. may be located at a place, or Can also be distributed on multiple NE.Can select therein some or all of according to the actual needs Unit realizes the purpose of the present embodiment scheme.
It addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, Can also be that unit is individually physically present, it is also possible to two or more unit are integrated in a unit In.Above-mentioned integrated unit both can realize to use the form of hardware, it would however also be possible to employ SFU software functional unit Form realizes.
If described integrated unit realizes and as independent production marketing using the form of SFU software functional unit Or when using, can be stored in a computer read/write memory medium.Based on such understanding, this Part that prior art is contributed by bright technical scheme the most in other words or this technical scheme complete Portion or part can embody with the form of software product, and this computer software product is stored in a storage In medium, including some instructions with so that computer equipment (can be personal computer, server or Person's network equipment etc.) perform all or part of step of method described in each embodiment of the present invention.And it is aforesaid Storage medium includes: USB flash disk, read only memory (ROM, Read-Only Memory), random access memory are deposited Reservoir (RAM, Random Access Memory), portable hard drive, magnetic disc or CD etc. are various permissible The medium of storage program code.
The above, above example only in order to technical solution of the present invention to be described, is not intended to limit;Although Being described in detail the present invention with reference to previous embodiment, wherein, those of ordinary skill in the art should Work as understanding: the technical scheme described in foregoing embodiments still can be modified by it, or to wherein Portion of techniques feature carries out equivalent;And these amendments or replacement, do not make the basis of appropriate technical solution Matter departs from the scope of various embodiments of the present invention technical scheme.

Claims (14)

1. an O&M parameter monitoring sample processing method, it is characterised in that including:
Obtain the O&M parameter monitoring sample of the current one period tx of O&M server;
Calculate the reference monitor cycle N-1 reference units period O&M parameter monitoring sample and described currently The sample statistics value σ x of the sample space that the O&M parameter monitoring sample of unit time period tx is formed, described with reference to prison The control cycle includes N number of reference units period, when described N-1 the reference units period is described N number of reference units Residue reference in addition to the reference units period that there are mapping relations with described current one period tx in Duan Unit time period, described N is the integer more than 1;
If the difference of sample for reference statistical value σ n and described sample statistics value σ x exceedes preset range, work as described The O&M parameter monitoring sample labeling of front unit time period tx is dirty sample, wherein, and described sample for reference statistical value σ n is that the O&M parameter of the described N number of reference units period in the described reference monitor cycle monitors sample institute shape The sample statistics value in the sample for reference space become.
Method the most according to claim 1, it is characterised in that described sample statistics value σ x is sample mark Quasi-difference and described sample for reference statistical value σ n are sample standard deviation, or described sample statistics value σ x is sample side Poor and described sample for reference statistical value σ n is sample variance.
Method the most according to claim 1 and 2, it is characterised in that described sample for reference statistical value σ n Less than or equal to first threshold.
4. according to the method described in any one of claims 1 to 3, it is characterised in that
Described method also includes:
Difference at described sample for reference statistical value σ n Yu described sample statistics value σ x is not above preset range In the case of, by described N number of reference units period in described reference monitor cycle with described current one Period tx has the O&M parameter monitoring sample of the reference units period of mapping relations, replaces with described current list The O&M parameter monitoring sample of position period tx.
5. according to the method described in any one of Claims 1-4, it is characterised in that
Described method also includes: the difference between described sample for reference statistical value σ n and described sample statistics value σ x Different exceed preset range in the case of, send the fortune of the current one period tx monitoring described O&M server There is abnormal alarm in dimension parameter.
6. according to the method described in any one of claim 1 to 5, it is characterised in that described sample for reference is united The difference of evaluation σ n and described sample statistics value σ x exceedes preset range, including: described sample for reference statistical value The absolute value of the difference between σ n and described sample statistics value σ x is more than or equal to Second Threshold, or described ginseng Examine the absolute value of difference between sample statistics value σ n and described sample statistics value σ x divided by described sample for reference Statistical value σ n and the business that obtains are more than or equal to the 3rd threshold value, or described sample for reference statistical value σ n is with described The business that the absolute value of the difference between sample statistics value σ x obtains divided by described sample statistics value σ x more than or Equal to the 4th threshold value, or the ratio of described sample for reference statistical value σ n and described sample statistics value σ x more than or Equal to the 5th threshold value, or the ratio of described sample for reference statistical value σ n and described sample statistics value σ x less than or Equal to the 6th threshold value.
7. according to the method described in any one of claim 1 to 6, it is characterised in that described O&M parameter is supervised Control sample is traffic monitoring sample, packet amount monitoring sample, visit capacity monitoring sample or trading volume monitoring Sample.
8. an O&M parameter monitoring sample processing apparatus, it is characterised in that including:
Acquiring unit, for obtaining the O&M parameter monitoring sample of the current one period tx of O&M server;
Computing unit, for calculating the O&M parameter monitoring of N-1 the reference units period in reference monitor cycle The sample statistics of the sample space that the O&M parameter monitoring sample of sample and described current one period tx is formed Being worth σ x, the described reference monitor cycle includes that N number of reference units period, described N-1 reference units period are When described N number of reference units period removes the reference units with described current one period tx with mapping relations The residue reference units period outside period, described N is the integer more than 1;
Processing unit, if the difference for sample for reference statistical value σ n and described sample statistics value σ x exceedes default Scope, the O&M parameter of described current one period tx is monitored sample labeling is dirty sample, described with reference to sample This statistical value σ n is the O&M parameter monitoring of the described N number of reference units period in the described reference monitor cycle The sample statistics value in the sample for reference space that sample is formed.
Device the most according to claim 8, it is characterised in that described sample statistics value σ x is sample mark Quasi-difference and described sample for reference statistical value σ n are sample standard deviation, or described sample statistics value σ x is sample side Poor and described sample for reference statistical value σ n is sample variance.
Device the most according to claim 8 or claim 9, it is characterised in that described sample for reference statistical value σ n Less than or equal to first threshold.
11. according to Claim 8 to the device described in 10 any one, it is characterised in that
Described device also includes: Sample Refreshment unit, at described sample for reference statistical value σ n and described sample In the case of the difference of this statistical value σ x is not above preset range, by the described N in described reference monitor cycle The individual reference units period has reference units period of mapping relations with described current one period tx O&M parameter monitoring sample, replaces with the O&M parameter monitoring sample of described current one period tx.
12. according to Claim 8 to the device described in 11 any one, it is characterised in that
Described device also includes: Alarm Unit, for uniting with described sample at described sample for reference statistical value σ n In the case of difference between evaluation σ x exceedes preset range, send and monitor the current of described O&M server There is abnormal alarm in the O&M parameter of unit time period tx.
13. according to Claim 8 to the device described in 12 any one, it is characterised in that described sample for reference The difference of statistical value σ n and described sample statistics value σ x exceedes preset range, including: described sample for reference is added up The absolute value of the difference between value σ n and described sample statistics value σ x is more than or equal to Second Threshold or described The absolute value of the difference between sample for reference statistical value σ n and described sample statistics value σ x is divided by described reference sample This statistical value σ n and the business that obtains are more than or equal to the 3rd threshold value, or described sample for reference statistical value σ n and institute State the business that the absolute value of the difference between sample statistics value σ x obtains divided by described sample statistics value σ x to be more than Or equal to the 4th threshold value, or the ratio of described sample for reference statistical value σ n and described sample statistics value σ x is more than Or equal to the 5th threshold value, or the ratio of described sample for reference statistical value σ n and described sample statistics value σ x is less than Or equal to the 6th threshold value.
14. 1 kinds of communication systems, it is characterised in that including:
O&M server and monitoring device;
Described monitoring device, for obtaining the O&M parameter prison of the current one period tx of described O&M server Control sample;Calculate the O&M parameter monitoring sample of N-1 reference units period in reference monitor cycle with described The sample statistics value σ x of the sample space that the O&M parameter monitoring sample of current one period tx is formed, described ginseng Examining the monitoring cycle includes N number of reference units period, and wherein, described N is the integer more than 1, described N-1 The reference units period is except having mapping pass with described current one period tx in described N number of reference units period The residue reference units period outside the reference units period of system;If sample for reference statistical value σ n and described sample The difference of statistical value σ x exceedes preset range, and the O&M parameter of described current one period tx is monitored sample mark Being designated as dirty sample, described sample for reference statistical value σ n is that the described N number of reference in the described reference monitor cycle is single The sample statistics value in the sample for reference space that the O&M parameter monitoring sample of position period is formed.
CN201510040914.5A 2015-01-27 2015-01-27 Operation and maintenance parameter monitoring sample processing method and device and communication system Active CN105991303B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510040914.5A CN105991303B (en) 2015-01-27 2015-01-27 Operation and maintenance parameter monitoring sample processing method and device and communication system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510040914.5A CN105991303B (en) 2015-01-27 2015-01-27 Operation and maintenance parameter monitoring sample processing method and device and communication system

Publications (2)

Publication Number Publication Date
CN105991303A true CN105991303A (en) 2016-10-05
CN105991303B CN105991303B (en) 2020-02-14

Family

ID=57034709

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510040914.5A Active CN105991303B (en) 2015-01-27 2015-01-27 Operation and maintenance parameter monitoring sample processing method and device and communication system

Country Status (1)

Country Link
CN (1) CN105991303B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1547145A (en) * 2003-12-08 2004-11-17 西安交通大学 Dynamic detecting and ensuring method for equipment operating status data quality
WO2004079991A8 (en) * 2003-03-05 2004-11-18 Cisco Tech Ind System and method for monitoring noise within a communication link
CN101964997A (en) * 2009-07-21 2011-02-02 中国移动通信集团黑龙江有限公司 Method and device for carrying out early warning on network performance
CN102111307A (en) * 2009-12-29 2011-06-29 亿阳信通股份有限公司 Method and device for monitoring and controlling network risks
CN102930344A (en) * 2012-10-09 2013-02-13 中国电力科学研究院 Method for forecasting ultra-short term bus load based on load trend changes
CN103167442A (en) * 2011-12-15 2013-06-19 上海粱江通信系统股份有限公司 Method for generating spam message filtering policy based on text message flow information
CN103824129A (en) * 2014-02-26 2014-05-28 国家电网公司 High-speed rail power quality abnormal condition prewarning method based on dynamic threshold

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2004079991A8 (en) * 2003-03-05 2004-11-18 Cisco Tech Ind System and method for monitoring noise within a communication link
CN1547145A (en) * 2003-12-08 2004-11-17 西安交通大学 Dynamic detecting and ensuring method for equipment operating status data quality
CN101964997A (en) * 2009-07-21 2011-02-02 中国移动通信集团黑龙江有限公司 Method and device for carrying out early warning on network performance
CN102111307A (en) * 2009-12-29 2011-06-29 亿阳信通股份有限公司 Method and device for monitoring and controlling network risks
CN103167442A (en) * 2011-12-15 2013-06-19 上海粱江通信系统股份有限公司 Method for generating spam message filtering policy based on text message flow information
CN102930344A (en) * 2012-10-09 2013-02-13 中国电力科学研究院 Method for forecasting ultra-short term bus load based on load trend changes
CN103824129A (en) * 2014-02-26 2014-05-28 国家电网公司 High-speed rail power quality abnormal condition prewarning method based on dynamic threshold

Also Published As

Publication number Publication date
CN105991303B (en) 2020-02-14

Similar Documents

Publication Publication Date Title
US11301597B2 (en) Simulation apparatus and method
US8412620B1 (en) Methods and systems related to trading engines
EP3678072A1 (en) Model integration method and device
CN108038040A (en) Computer cluster performance indicator detection method, electronic equipment and storage medium
US20180039895A1 (en) Data predicting method and apparatus
CN110390584A (en) A kind of recognition methods of abnormal user, identification device and readable storage medium storing program for executing
US9600795B2 (en) Measuring process model performance and enforcing process performance policy
CN109445884B (en) Function label display method and terminal equipment
CN109190930A (en) A kind of index generation method and device
CN109165691A (en) Training method, device and the electronic equipment of the model of cheating user for identification
CN109426912B (en) Wind control system optimization method, system and device and electronic equipment
CN110471821A (en) Abnormal alteration detection method, server and computer readable storage medium
CN109298786A (en) Mark accuracy rate appraisal procedure and device
CN109461067A (en) A kind of detection method of foreign exchange quotation abnormal data, apparatus and system
CN108322350A (en) Business monitoring method and device and electronic equipment
CN109614414A (en) A kind of determination method and device of user information
CN111538852B (en) Multimedia resource processing method, device, storage medium and equipment
AU2014201264A1 (en) Scenario based customer lifetime value determination
CN110766184A (en) Order quantity prediction method and device
CN110675249A (en) Matching method, device, server and storage medium for network lending
CN109976875A (en) A kind of data monitoring method and device of super fusion cloud computing system
CN110287082A (en) Database table spatial content monitoring method and device
CN110852602A (en) Data monitoring method and device based on machine learning
CN108268351A (en) A kind of accurate monitoring method of running state of process and system
CN109800085A (en) Detection method, device, storage medium and the electronic equipment of resource distribution

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right

Effective date of registration: 20231222

Address after: 518057 Tencent Building, No. 1 High-tech Zone, Nanshan District, Shenzhen City, Guangdong Province, 35 floors

Patentee after: TENCENT TECHNOLOGY (SHENZHEN) Co.,Ltd.

Patentee after: TENCENT CLOUD COMPUTING (BEIJING) Co.,Ltd.

Address before: 2, 518000, East 403 room, SEG science and Technology Park, Zhenxing Road, Shenzhen, Guangdong, Futian District

Patentee before: TENCENT TECHNOLOGY (SHENZHEN) Co.,Ltd.

TR01 Transfer of patent right