CN105991303B

CN105991303B - Operation and maintenance parameter monitoring sample processing method and device and communication system

Info

Publication number: CN105991303B
Application number: CN201510040914.5A
Authority: CN
Inventors: 洪楷
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd; Tencent Cloud Computing Beijing Co Ltd
Priority date: 2015-01-27
Filing date: 2015-01-27
Publication date: 2020-02-14
Anticipated expiration: 2035-01-27
Also published as: CN105991303A

Abstract

The embodiment of the invention discloses a method, a device and a system for processing operation and maintenance parameter monitoring samples. An operation and maintenance parameter monitoring sample processing method comprises the following steps: acquiring an operation and maintenance parameter monitoring sample of the current unit time period tx of the operation and maintenance server; calculating a sample statistic value sigma x of a sample space formed by the operation and maintenance parameter monitoring samples of N-1 reference unit time intervals of a reference monitoring period and the operation and maintenance parameter monitoring samples of the current unit time interval tx; if the difference between the reference sample statistical value σ N and the sample statistical value σ x exceeds a preset range, marking the operation and maintenance parameter monitoring sample of the current unit time interval tx as a dirty sample, wherein the reference sample statistical value σ N is a sample statistical value of a reference sample space formed by the operation and maintenance parameter monitoring samples of the N reference unit time intervals in the reference monitoring cycle. The technical scheme of the embodiment of the invention is beneficial to improving the identification accuracy of the dirty samples in the dimensional parameter monitoring samples.

Description

Operation and maintenance parameter monitoring sample processing method and device and communication system

Technical Field

The invention relates to the technical field of internet, in particular to an operation and maintenance parameter monitoring sample processing method and device and a communication system.

Background

The operation and maintenance process of monitoring the internet service generates a large number of operation and maintenance parameter monitoring samples. It is a common situation that a service abnormality occurs in the operation and maintenance process of an internet service. Due to the fact that the abnormal service may generate an abrupt operation and maintenance parameter monitoring sample, the operation and maintenance parameter monitoring sample may be called a dirty sample. However, these dirty samples in the operation and maintenance parameter monitoring samples are likely to reduce the accuracy of the associated alarms.

During research and practice, the inventor of the present invention finds that no effective solution for removing dirty samples from operation and maintenance parameter monitoring samples is provided in the prior art, for example, operation and maintenance parameter monitoring samples exceeding a fixed threshold value in the operation and maintenance parameter monitoring samples are generally regarded as dirty samples and marked in the prior art, but the inventor finds through repeated practice that such a solution in the prior art may be distorted due to normal growth and change of traffic. If the dirty samples in the operation and maintenance parameter monitoring samples are not effectively marked, the relevant operations (such as the relevant alarms of the operation and maintenance) based on the analysis result of the operation and maintenance parameter monitoring samples can be wrong.

Disclosure of Invention

The embodiment of the invention provides an operation and maintenance parameter monitoring sample processing method, device and system, aiming at improving the identification accuracy of dirty samples in a dimension parameter monitoring sample.

The first aspect of the embodiments of the present invention provides an operation and maintenance parameter monitoring sample processing method, including:

acquiring an operation and maintenance parameter monitoring sample of the current unit time period tx of the operation and maintenance server;

calculating a sample statistic value sigma x of a sample space formed by operation and maintenance parameter monitoring samples of N-1 reference unit time intervals of a reference monitoring cycle and operation and maintenance parameter monitoring samples of the current unit time interval tx, wherein the reference monitoring cycle comprises N reference unit time intervals, the N-1 reference unit time intervals are the rest of the N reference unit time intervals except for the reference unit time interval which has a mapping relation with the current unit time interval tx, and N is an integer greater than 1;

if the difference between the reference sample statistical value σ N and the sample statistical value σ x exceeds a preset range, marking the operation and maintenance parameter monitoring sample of the current unit time interval tx as a dirty sample, wherein the reference sample statistical value σ N is a sample statistical value of a reference sample space formed by the operation and maintenance parameter monitoring samples of the N reference unit time intervals in the reference monitoring cycle.

A second aspect of the embodiments of the present invention provides an operation and maintenance parameter monitoring sample processing apparatus, including:

the acquisition unit is used for acquiring the operation and maintenance parameter monitoring sample of the current unit time interval tx of the operation and maintenance server;

a calculating unit, configured to calculate a sample statistical value σ x of a sample space formed by operation and maintenance parameter monitoring samples of N-1 reference unit time periods of a reference monitoring cycle and operation and maintenance parameter monitoring samples of the current unit time period tx, where the reference monitoring cycle includes N reference unit time periods, the N-1 reference unit time periods are remaining reference unit time periods, except for a reference unit time period having a mapping relationship with the current unit time period tx, in the N reference unit time periods, and N is an integer greater than 1;

and the processing unit is configured to mark the operation and maintenance parameter monitoring sample of the current unit time period tx as a dirty sample if a difference between a reference sample statistical value σ N and the sample statistical value σ x exceeds a preset range, where the reference sample statistical value σ N is a sample statistical value of a reference sample space formed by the operation and maintenance parameter monitoring samples of the N reference unit time periods in the reference monitoring cycle.

A third aspect of the embodiments of the present invention provides a communication system, including:

an operation and maintenance server and monitoring equipment;

the monitoring equipment is used for acquiring operation and maintenance parameter monitoring samples of the current unit time interval tx of the operation and maintenance server; calculating a sample statistic value sigma x of a sample space formed by operation and maintenance parameter monitoring samples of N-1 reference unit time intervals of a reference monitoring cycle and operation and maintenance parameter monitoring samples of the current unit time interval tx, wherein the reference monitoring cycle comprises N reference unit time intervals, N is an integer greater than 1, and the N-1 reference unit time intervals are the rest of the N reference unit time intervals except for the reference unit time interval having a mapping relation with the current unit time interval tx; if the difference between the reference sample statistical value σ N and the sample statistical value σ x exceeds a preset range, marking the operation and maintenance parameter monitoring sample of the current unit time interval tx as a dirty sample, wherein the reference sample statistical value σ N is a sample statistical value of a reference sample space formed by the operation and maintenance parameter monitoring samples of the N reference unit time intervals in the reference monitoring cycle.

It can be seen that in the technical solution of the embodiment of the present invention, after obtaining the operation and maintenance parameter monitoring samples of the current unit time interval tx of the operation and maintenance server, a sample statistical value σ x of a sample space formed by the operation and maintenance parameter monitoring samples of N-1 reference unit time intervals of a reference monitoring cycle and the operation and maintenance parameter monitoring samples of the current unit time interval tx is calculated, and since the difference between the reference sample statistical value σ N and the sample statistical value σ x exceeds a preset range, the operation and maintenance parameter monitoring samples of the current unit time interval tx are marked as dirty samples, that is, the above technical solution of the embodiment of the present invention combines the operation and maintenance parameter monitoring samples of the current unit time interval tx and the operation and maintenance parameter monitoring samples of N reference unit time intervals of the reference monitoring cycle, and comprehensively determines whether the operation and maintenance parameter monitoring samples of the current unit time interval tx are dirty samples according to the statistical value calculation result, compared with the mechanism that whether the operation and maintenance parameter monitoring samples are dirty samples is judged through the comparison result of the fixed threshold and the operation and maintenance parameter monitoring samples in the prior art, the scheme of the embodiment of the invention is beneficial to improving the identification accuracy of the dirty samples in the operation and maintenance parameter monitoring samples.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic flow chart of a method for processing an operation and maintenance parameter monitoring sample according to an embodiment of the present invention;

FIG. 2-a is a schematic flow chart of another operation and maintenance parameter monitoring sample processing method according to an embodiment of the present invention;

fig. 2-b is a schematic structural diagram of a communication system according to an embodiment of the present invention;

FIG. 2-c is a schematic diagram of a sample space formation scheme provided by an embodiment of the present invention;

FIG. 2-d is a schematic diagram of a reference sample space updating method according to an embodiment of the present invention;

fig. 3-a is a schematic flow chart of another operation and maintenance parameter monitoring sample processing method according to an embodiment of the present invention;

FIG. 3-b is a schematic diagram of a sample space formation scheme provided by an embodiment of the present invention;

FIG. 3-c is a schematic diagram of a reference sample space updating method according to an embodiment of the present invention;

fig. 4 is a schematic diagram of an operation and maintenance parameter monitoring sample processing apparatus according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of a monitoring device provided by an embodiment of the invention;

fig. 6 is a schematic diagram of a communication system according to an embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The following are detailed below.

The terms "first," "second," "third," and "fourth," etc. in the description and claims of the invention and the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

The invention discloses an embodiment of an operation and maintenance parameter monitoring sample processing method. The operation and maintenance parameter monitoring sample processing method comprises the following steps: acquiring an operation and maintenance parameter monitoring sample of the current unit time period tx of the operation and maintenance server; calculating a sample statistic value sigma x of a sample space formed by operation and maintenance parameter monitoring samples of N-1 reference unit time intervals of a reference monitoring cycle and operation and maintenance parameter monitoring samples of the current unit time interval tx, wherein the reference monitoring cycle comprises N reference unit time intervals, the N-1 reference unit time intervals are the rest of the N reference unit time intervals except for the reference unit time interval which has a mapping relation with the current unit time interval tx, and N is an integer greater than 1; if the difference between the reference sample statistical value σ N and the sample statistical value σ x exceeds a preset range, marking the operation and maintenance parameter monitoring sample of the current unit time interval tx as a dirty sample, wherein the reference sample statistical value σ N is a sample statistical value of a reference sample space formed by the operation and maintenance parameter monitoring samples of the N reference unit time intervals in the reference monitoring cycle.

Referring to fig. 1, fig. 1 is a schematic flow chart of an operation and maintenance parameter monitoring sample processing method according to an embodiment of the present invention. As shown in fig. 1, an operation and maintenance parameter monitoring sample processing method according to an embodiment of the present invention may include:

101. and acquiring an operation and maintenance parameter monitoring sample of the current unit time interval tx of the operation and maintenance server.

The operation and maintenance parameter monitoring sample in the embodiment of the present invention is, for example, a traffic monitoring sample, a packet quantity monitoring sample, an access quantity monitoring sample, a transaction quantity monitoring sample, or a monitoring sample of another type of operation and maintenance parameter.

The operation and maintenance server may be, for example, an operation and maintenance server of an internet service or a mobile communication service or other services.

For example, the operation and maintenance server may be an operation and maintenance server of an internet communication service (e.g., an instant messaging service such as a QQ service, a wechat service, etc.), an operation and maintenance server of an internet audio/video service, an operation and maintenance server of an internet game service, or an operation and maintenance server of an internet financial service.

102. And calculating a sample statistic value sigma x of a sample space formed by the operation and maintenance parameter monitoring samples of N-1 reference unit time intervals of the reference monitoring period and the operation and maintenance parameter monitoring samples of the current unit time interval tx. The reference monitoring cycle includes N reference unit periods, the N-1 reference unit periods are remaining ones of the N reference unit periods except for a reference unit period having a mapping relation with the current unit period tx, and N is an integer greater than 1.

The duration of the reference monitoring period and the number of included reference unit periods can be determined according to the needs of a specific scene. The duration of the reference monitoring period may be 1 hour, 1 day, 1 week, 1 month, or 1 year, or other duration.

For example, if the duration of each reference unit period included in the reference monitoring cycle is 1 day, and the duration of each reference unit period included in the reference monitoring cycle is 1 hour, n is equal to 24 in this case, assuming that the current unit period tx is 15 to 16 points, the reference unit period having a mapping relation with the current unit period tx among the N reference unit periods in the reference monitoring period is 15 to 16 points, and it is assumed that the current unit period tx is 20 to 21 points, the reference unit period having a mapping relation with the current unit period tx among the N reference unit periods in the reference monitoring period is 20 to 21 points, and it is assumed that the current unit period tx is 23 to 24 points, the reference unit period having a mapping relation with the current unit period tx among the N reference unit periods in the reference monitoring period is 23 to 24 points, and so on. Also for example, assuming that the duration of the reference monitoring period is 1 day, if the duration of each reference unit period included in the reference monitoring period is half an hour, then N in this case equals 48. For another example, if the duration of the reference monitoring period is 1 day, and if the duration of each reference unit time period included in the reference monitoring period is 1 minute, then N is equal to 1440 in this case, and so on if the duration of the reference unit time period is other values.

For another example, assuming that the duration of the reference monitoring cycle is 1 week, if the duration of each reference unit time period included in the reference monitoring cycle is 1 day, then N in this case is equal to 7, in this case, assuming that the current unit time period tx is monday, then a reference unit time period having a mapping relationship with the current unit time period tx in the N reference unit time periods in the reference monitoring cycle is monday, further assuming that the current unit time period tx is friday, then a reference unit time period having a mapping relationship with the current unit time period tx in the N reference unit time periods in the reference monitoring cycle is friday, further assuming that the current unit time period tx is sunday, a reference unit time period having a mapping relationship with the current unit time period tx in the reference monitoring cycle is sunday, and so on. For another example, if the duration of the reference monitoring period is 1 week, and if the duration of each reference unit time period included in the reference monitoring period is 1 hour, then N is equal to 168 in this case; if the duration of each reference unit time period included in the reference monitoring cycle is 1 minute, N in this case is 10080, and so on for the case where the duration of the reference unit time period is other values.

For another example, assuming that the duration of the reference monitoring cycle is 30 days, if the duration of each reference unit time period included in the reference monitoring cycle is 1 day, then N is equal to 30 in this case, it is assumed that the current unit time period tx is No. 1, then a reference unit time period having a mapping relationship with the current unit time period tx among the N reference unit time periods in the reference monitoring cycle is No. 1, and it is further assumed that the current unit time period tx is No. 17, then a reference unit time period having a mapping relationship with the current unit time period tx among the N reference unit time periods in the reference monitoring cycle is No. 17, it is further assumed that the current unit time period tx is No. 25, a reference unit time period having a mapping relationship with the current unit time period tx among the N reference unit time periods in the reference monitoring cycle is No. 25, and so on. For another example, assuming that the duration of the reference monitoring period may be 30 days, if the duration of each reference unit time period included in the reference monitoring period is 1 hour, then N is equal to 900 in this case, and so on for the case where the duration of the reference unit time period is other values.

For another example, assuming that the duration of the reference monitoring cycle is 1 year, if the duration of each reference unit period included in the reference monitoring cycle is 1 month, then N is equal to 12 in this case, assuming that the current unit period tx is 1 month, then a reference unit period having a mapping relationship with the current unit period tx in the N reference unit periods in the reference monitoring cycle is 1 month, further assuming that the current unit period tx is 7 months, then a reference unit period having a mapping relationship with the current unit period tx in the N reference unit periods in the reference monitoring cycle is 7 months, further assuming that the current unit period tx is 12 months, a reference unit period having a mapping relationship with the current unit period tx in the reference monitoring cycle is 12 months, and so on. For another example, if the duration of the reference monitoring period is 1 week, and if the duration of each reference unit time period included in the reference monitoring period is 1 day, then N in this case may be equal to 365; refer to the case where the duration of the unit period is other values, and so on.

103. And in the case that the difference between the reference sample statistic value sigma n and the sample statistic value sigma x exceeds a preset range, marking the operation and maintenance parameter monitoring sample of the current unit time interval tx as a dirty sample. The reference sample statistical value σ N is a sample statistical value of a reference sample space formed by the operation and maintenance parameter monitoring samples of the N reference unit periods in the reference monitoring cycle.

Alternatively, in some possible embodiments of the present invention, the sample statistic may be a sample standard deviation or a sample variance or other parameters that can be used to characterize the fluctuation between samples in the sample space. For example, the sample statistic σ x is a sample standard deviation and the reference sample statistic σ n is a sample standard deviation, or the sample statistic σ x is a sample variance and the reference sample statistic σ n is a sample variance.

Optionally, in some possible embodiments of the present invention, the reference sample statistic σ n is smaller than or equal to a first threshold. That is to say, in the sample space formed by the operation and maintenance parameter monitoring samples of the N reference unit time periods of the reference monitoring cycle, the fluctuation between the samples is small, for example, the operation and maintenance parameter monitoring samples of the adjacent N reference unit time periods, which have smooth changes in the recent parameter baseline, may be selected as the operation and maintenance parameter monitoring samples of the N reference unit time periods of the reference monitoring cycle.

Of course, the operation and maintenance parameter monitoring samples of the N reference unit periods of the reference monitoring cycle may also be updated. For example, in a case that the difference between the reference sample statistic σ N and the sample statistic σ x does not exceed a preset range, the operation and maintenance parameter monitoring sample of the reference unit period having a mapping relation with the current unit period tx in the N reference unit periods of the reference monitoring cycle may be replaced with the operation and maintenance parameter monitoring sample of the current unit period tx. Practice shows that, the operation and maintenance parameter monitoring samples of the reference unit period in the reference monitoring cycle having a mapping relation with the current unit period can be replaced by the operation and maintenance parameter monitoring samples of the current unit period, which is beneficial to keeping the operation and maintenance parameter monitoring samples of the N reference unit periods in the reference monitoring cycle at a certain timeliness all the time and having a strong correlation with the recent operation and maintenance parameter, so that the operation and maintenance parameter monitoring samples of the N reference unit periods based on the updated reference monitoring cycle are beneficial to better and more accurately judging whether the operation and maintenance parameter monitoring samples of the subsequent unit periods of the current unit period tx (such as the next unit period of the current unit period tx or the next unit period of the current unit period tx) are dirty samples.

Optionally, in some possible embodiments of the present invention, an alarm may be further issued to monitor that the operation and maintenance parameter of the operation and maintenance server in the current unit time period tx is abnormal when the difference between the reference sample statistical value σ n and the sample statistical value σ x exceeds a preset range.

Optionally, in some possible embodiments of the present invention, the difference between the reference sample statistic σ n and the sample statistic σ x exceeds a preset range, which includes: an absolute value of a difference between the reference sample statistic σ n and the sample statistic σ x is greater than or equal to a second threshold, or a quotient of an absolute value of a difference between the reference sample statistic σ n and the sample statistic σ x divided by the reference sample statistic σ n is greater than or equal to a third threshold (e.g., equal to 5%, 6%, 8%, 10%, 15%, or other values), or a quotient of an absolute value of a difference between the reference sample statistic σ n and the sample statistic σ x divided by the sample statistic σ x is greater than or equal to a fourth threshold (e.g., equal to 5%, 6%, 8%, 10%, 15%, 18%, or other values), or a ratio of the reference sample statistic σ n to the sample statistic σ x is greater than or equal to a fifth threshold (where, a fifth threshold value may be, for example, equal to 110%, 105%, 115%, 116%, 120%, or other value), or the ratio of the reference sample statistic σ n to the sample statistic σ x is less than or equal to a sixth threshold value (where the sixth threshold value may be, for example, equal to 90%, 95%, 92%, 87%, 85%, or other value). It can be understood that the specific value of each threshold can be set according to the needs of a specific scenario. Of course, the difference between the reference sample statistic σ n and the sample statistic σ x can be determined to exceed a predetermined range by other methods.

Optionally, in some possible embodiments of the present invention, the difference between the reference sample statistic σ n and the sample statistic σ x does not exceed a preset range, and the method may include: an absolute value of a difference between the reference sample statistic σ n and the sample statistic σ x is smaller than a second threshold, or a quotient obtained by dividing an absolute value of a difference between the reference sample statistic σ n and the sample statistic σ x by the reference sample statistic σ n is smaller than a third threshold, or a quotient obtained by dividing an absolute value of a difference between the reference sample statistic σ n and the sample statistic σ x by the sample statistic σ x is smaller than a fourth threshold, or a ratio of the reference sample statistic σ n to the sample statistic σ x is smaller than a fifth threshold, or a ratio of the reference sample statistic σ n to the sample statistic σ x is larger than a sixth threshold. Of course, the difference between the reference sample statistic σ n and the sample statistic σ x may be determined not to exceed a predetermined range in other ways.

In order to better understand and implement the above-mentioned schemes of the embodiments of the present invention, some specific application scenarios are exemplified below.

Referring to fig. 2-a and fig. 2-b, fig. 2-a is a schematic flow chart of an operation and maintenance parameter monitoring sample processing method according to another embodiment of the present invention. The method illustrated in fig. 2-a may be embodied in the network architecture shown in fig. 2-b. In this embodiment, the duration of the reference monitoring period is 1 week, the number N of the reference unit time periods included in the reference monitoring period is equal to 7, and so on. As shown in fig. 2-a, another embodiment of the present invention provides an operation and maintenance parameter monitoring sample processing method, which includes:

201. and the monitoring equipment acquires the operation and maintenance parameter monitoring sample of the current day tx of the operation and maintenance server.

202. The monitoring device calculates a sample statistic σ x of a sample space (which may be referred to as a sample space to be evaluated) formed by the operation and maintenance parameter monitoring samples of 6 reference unit periods of the reference monitoring cycle and the operation and maintenance parameter monitoring samples of the current day tx.

The reference monitoring cycle comprises 7 reference unit time periods, wherein the duration of each reference unit time period comprised by the reference monitoring cycle is 1 day. Wherein the 6 reference unit periods are remaining reference unit periods of the 7 reference unit periods except for a reference unit period having a mapping relation with the current day tx.

For example, assuming that the current day tx is monday, a reference unit time interval having a mapping relationship with the current day tx among N reference unit time intervals in the reference monitoring period is monday, and assuming that the current day tx is friday, a reference unit time interval having a mapping relationship with the current day tx among N reference unit time intervals in the reference monitoring period is friday, and assuming that the current day tx is sunday, a reference unit time interval having a mapping relationship with the current day tx among N reference unit time intervals in the reference monitoring period is sunday, and so on.

203. The monitoring equipment judges whether the difference between the reference sample statistic value sigma n and the sample statistic value sigma x exceeds a preset range.

If yes, go to step 204.

If not, go to step 205.

Wherein, the reference sample statistical value σ N is a sample statistical value of a reference sample space formed by the operation and maintenance parameter monitoring samples of the N reference unit periods in the reference monitoring cycle.

Referring to fig. 2-c, fig. 2-c illustrate one manner of forming the sample space to be evaluated and the reference sample space to be evaluated.

Optionally, in some possible embodiments of the present invention, the difference between the reference sample statistic σ n and the sample statistic σ x exceeds a preset range, which includes: the absolute value of the difference between the reference sample statistic σ n and the sample statistic σ x is greater than or equal to a second threshold, or the quotient of the absolute value of the difference between the reference sample statistic σ n and the sample statistic σ x divided by the reference sample statistic σ n is greater than or equal to a third threshold (e.g., equal to 5%, 6%, 8%, 10%, or 15%, or other values), or the quotient of the absolute value of the difference between the reference sample statistic σ n and the sample statistic σ x divided by the sample statistic σ x is greater than or equal to a fourth threshold (e.g., equal to 5%, 6%, 8%, 10%, 15%, 18%, or other values), or the ratio of the reference sample statistic σ n to the sample statistic σ x is greater than or equal to a fifth threshold (e.g., 110%, a fifth threshold, 105%, 115%, 116%, 120%, or other value), or the ratio of the reference sample statistic σ n to the sample statistic σ x is less than or equal to a sixth threshold (which may be, for example, equal to 90%, 95%, 92%, 87%, 85%, or other value). It can be understood that the specific value of each threshold can be set according to the needs of a specific scenario.

Optionally, in some possible embodiments of the present invention, the difference between the reference sample statistic σ n and the sample statistic σ x does not exceed a preset range, and the method may include: an absolute value of a difference between the reference sample statistic σ n and the sample statistic σ x is smaller than a second threshold, or a quotient obtained by dividing an absolute value of a difference between the reference sample statistic σ n and the sample statistic σ x by the reference sample statistic σ n is smaller than a third threshold, or a quotient obtained by dividing an absolute value of a difference between the reference sample statistic σ n and the sample statistic σ x by the sample statistic σ x is smaller than a fourth threshold, or a ratio of the reference sample statistic σ n to the sample statistic σ x is smaller than a fifth threshold, or a ratio of the reference sample statistic σ n to the sample statistic σ x is larger than a sixth threshold. It is also possible to determine that the difference between the reference sample statistic σ n and the sample statistic σ x does not exceed a predetermined range by other means.

204. When the difference between the reference sample statistic σ n and the sample statistic σ x exceeds a preset range, the monitoring device may mark the operation and maintenance parameter monitoring sample of the current unit time period tx as a dirty sample.

The monitoring device may write the operation parameter monitoring sample of the current unit time period tx into a dirty sample database, for example.

205. And replacing the operation and maintenance parameter monitoring sample of the reference unit time interval with the operation and maintenance parameter monitoring sample of the current day tx by the monitoring equipment, wherein the reference unit time interval has a mapping relation with the current day tx in the N reference unit time intervals of the reference monitoring period, under the condition that the difference between the reference sample statistic σ N and the sample statistic σ x does not exceed a preset range.

Turning to fig. 2-d, fig. 2-d illustrates one manner of updating the operation and maintenance parameter monitoring samples for N reference unit periods of the reference monitoring cycle.

Practice shows that the monitoring device can replace the operation and maintenance parameter monitoring sample of the reference unit period having a mapping relation with the current day tx in the reference monitoring cycle with the operation and maintenance parameter monitoring sample of the reference unit period of the current unit period, which is beneficial to keeping certain timeliness of the operation and maintenance parameter monitoring samples of the N reference unit periods in the reference monitoring cycle and having strong relevance with the recent operation and maintenance parameter, so that the operation and maintenance parameter monitoring samples of the N reference unit periods based on the updated reference monitoring cycle are beneficial to better and more accurately judging whether the operation and maintenance parameter monitoring samples of the subsequent unit periods of the current day tx (such as the next unit period of the current day tx or the next unit period of the current day tx, etc.) are dirty samples.

It can be seen that in the technical solution of the embodiment of the present invention, after obtaining the operation and maintenance parameter monitoring samples of the current day tx of the operation and maintenance server, a sample statistical value σ x of a sample space formed by the operation and maintenance parameter monitoring samples of N-1 reference unit time periods of a reference monitoring period and the operation and maintenance parameter monitoring samples of the current day tx is calculated, and since the difference between the reference sample statistical value σ N and the sample statistical value σ x exceeds a preset range, the operation and maintenance parameter monitoring samples of the current day tx are marked as dirty samples, that is, the above technical solution of the embodiment of the present invention combines the operation and maintenance parameter monitoring samples of the current day tx and the operation and maintenance parameter monitoring samples of N reference unit time periods of the reference monitoring period, and comprehensively determines whether the operation and maintenance parameter monitoring samples of the current day tx are dirty samples according to the statistical value calculation result, compared with the mechanism that whether the operation and maintenance parameter monitoring samples are dirty samples is judged through the comparison result of the fixed threshold and the operation and maintenance parameter monitoring samples in the prior art, the scheme of the embodiment of the invention is beneficial to improving the identification accuracy of the dirty samples in the operation and maintenance parameter monitoring samples.

Referring to fig. 3-a, fig. 3-a is a schematic flow chart of an operation and maintenance parameter monitoring sample processing method according to another embodiment of the present invention. The method illustrated in fig. 3-a may be implemented in the network architecture shown in fig. 2-b. In this embodiment, the duration of the reference monitoring period is 1 month (here, 1 month is 30 days is taken as an example), the number N of the reference unit time periods included in the reference monitoring period is equal to 30 as an example, and so on may be performed when N is equal to other values. As shown in fig. 3-a, a method for processing an operation and maintenance parameter monitoring sample according to another embodiment of the present invention may specifically include:

301. and the monitoring equipment acquires the operation and maintenance parameter monitoring sample of the current day tx of the operation and maintenance server.

302. The monitoring device calculates a sample statistic σ x of a sample space (which may be referred to as a sample space to be evaluated) formed by the operation and maintenance parameter monitoring samples of 29 reference unit time intervals of the reference monitoring cycle and the operation and maintenance parameter monitoring samples of the current day tx.

The reference monitoring cycle comprises 30 reference unit time periods, wherein the duration of each reference unit time period comprised by the reference monitoring cycle is 1 day. Wherein the 29 reference unit periods are remaining ones of the 30 reference unit periods except for a reference unit period having a mapping relation with the current day tx.

For example, assuming that the current day tx is 10, a reference unit time period having a mapping relationship with the current day tx among 30 reference unit time periods in the reference monitoring cycle is 10, assuming that the current day tx is 25, a reference unit time period having a mapping relationship with the current day tx among 30 reference unit time periods in the reference monitoring cycle is 25, assuming that the current day tx is 30, a reference unit time period having a mapping relationship with the current day tx among 30 reference unit time periods in the reference monitoring cycle is 30, and so on.

303. The monitoring equipment judges whether the difference between the reference sample statistic value sigma n and the sample statistic value sigma x exceeds a preset range.

If so, go to step 304.

If not, go to step 305.

Wherein, the reference sample statistical value σ n is a sample statistical value of a reference sample space formed by the operation and maintenance parameter monitoring samples of the 30 reference unit time intervals in the reference monitoring cycle.

Referring to fig. 3-b, fig. 3-b illustrates one manner of forming a sample space to be evaluated and a reference sample space to be evaluated.

Optionally, in some possible embodiments of the present invention, the difference between the reference sample statistic σ n and the sample statistic σ x exceeds a preset range, which includes: the absolute value of the difference between the reference sample statistic σ n and the sample statistic σ x is greater than or equal to a second threshold, or the quotient of the absolute value of the difference between the reference sample statistic σ n and the sample statistic σ x divided by the reference sample statistic σ n is greater than or equal to a third threshold (e.g., equal to 5%, 6%, 8%, 10%, or 15%, or other values), or the quotient of the absolute value of the difference between the reference sample statistic σ n and the sample statistic σ x divided by the sample statistic σ x is greater than or equal to a fourth threshold (e.g., equal to 5%, 6%, 8%, 10%, 15%, 18%, or other values), or the ratio of the reference sample statistic σ n to the sample statistic σ x is greater than or equal to a fifth threshold (e.g., 110%, a fifth threshold, 105%, 115%, 118%, 120%, or other value), or the ratio of the reference sample statistic σ n to the sample statistic σ x is less than or equal to a sixth threshold (which may be, for example, equal to 90%, 95%, 93%, 87%, 85%, or other value). It can be understood that the specific value of each threshold can be set according to the needs of a specific scenario.

304. When the difference between the reference sample statistic σ n and the sample statistic σ x exceeds a preset range, the monitoring device may mark the operation and maintenance parameter monitoring sample of the current unit time period tx as a dirty sample.

305. And replacing the operation and maintenance parameter monitoring sample of the reference unit time interval with the operation and maintenance parameter monitoring sample of the current day tx by the monitoring equipment, wherein the reference unit time interval has a mapping relation with the current day tx in the N reference unit time intervals of the reference monitoring period, under the condition that the difference between the reference sample statistic σ N and the sample statistic σ x does not exceed a preset range.

Referring to fig. 3-c, fig. 3-c illustrates an example of a manner of updating the operation and maintenance parameter monitoring samples of N reference unit time intervals of the reference monitoring cycle, a new reference sample space may be formed by the updating, and it is beneficial to better and more accurately judge whether the operation and maintenance parameter monitoring samples of the unit time intervals subsequent to the current day tx (e.g., the next day of the current day tx or the next day of the current unit time interval tx) are dirty samples based on the new reference sample space.

Practice shows that the monitoring device can replace the operation and maintenance parameter monitoring samples of the reference unit period having a mapping relation with the current day tx in the reference monitoring cycle with the operation and maintenance parameter monitoring samples of the reference unit period of the current unit period, which is beneficial to keeping certain timeliness of the operation and maintenance parameter monitoring samples of the N reference unit periods in the reference monitoring cycle and having strong relevance with the recent operation and maintenance parameter, so that the operation and maintenance parameter monitoring samples of the N reference unit periods based on the updated reference monitoring cycle are beneficial to better and more accurately judging whether the operation and maintenance parameter monitoring samples of the subsequent unit periods of the current day tx (such as the next unit period of the current day tx or the next unit period of the current day tx, etc.) are dirty samples.

It is understood that fig. 2-b exemplifies that the monitoring device and the operation and maintenance server are two independent devices, and the monitoring device and the operation and maintenance server may be integrated together in some application scenarios.

Referring to fig. 4, an embodiment of the present invention further provides an operation and maintenance parameter monitoring sample processing apparatus 400, which may include: an acquisition unit 410, a calculation unit 420 and a processing unit 430.

The obtaining unit 410 is configured to obtain an operation and maintenance parameter monitoring sample of the current unit time interval tx of the operation and maintenance server.

A calculating unit 420, configured to calculate a sample statistical value σ x of a sample space formed by the operation and maintenance parameter monitoring samples of N-1 reference unit time periods of a reference monitoring cycle and the operation and maintenance parameter monitoring samples of the current unit time period tx, where the reference monitoring cycle includes N reference unit time periods, the N-1 reference unit time periods are remaining reference unit time periods, except for a reference unit time period having a mapping relationship with the current unit time period tx, in the N reference unit time periods, and N is an integer greater than 1.

The processing unit 430 is configured to mark the operation and maintenance parameter monitoring sample of the current unit time interval tx as a dirty sample if a difference between the reference sample statistical value σ N and the sample statistical value σ x exceeds a preset range, where the reference sample statistical value σ N is a sample statistical value of a reference sample space formed by the operation and maintenance parameter monitoring samples of the N reference unit time intervals in the reference monitoring cycle.

Optionally, in some possible embodiments of the present invention, the apparatus 400 may further include:

a sample updating unit 440, configured to replace, in a case that a difference between the reference sample statistical value σ N and the sample statistical value σ x does not exceed a preset range, the operation and maintenance parameter monitoring sample of a reference unit time interval having a mapping relationship with the current unit time interval tx in the N reference unit time intervals of the reference monitoring cycle with the operation and maintenance parameter monitoring sample of the current unit time interval tx.

the alarm unit 450 sends an alarm for monitoring that the operation and maintenance parameter of the current unit time interval tx of the operation and maintenance server is abnormal when the difference between the reference sample statistic σ n and the sample statistic σ x exceeds a preset range.

It is understood that the operation parameter monitoring sample processing apparatus 400 and the operation server may be two independent devices, for example, and in some application scenarios, the operation parameter monitoring sample processing apparatus 400 and the operation server may be integrated together.

It is to be understood that the functions of the functional modules of the operation and maintenance parameter monitoring sample processing apparatus 400 of this embodiment may be specifically implemented according to the method in the foregoing method embodiment, and the specific implementation process may refer to the related description of the foregoing method embodiment, which is not described herein again.

It can be seen that in the technical solution of the embodiment of the present invention, after obtaining the operation and maintenance parameter monitoring sample of the current unit time interval tx of the operation and maintenance server, the operation and maintenance parameter monitoring sample processing device 400 calculates the sample statistical value σ x of the sample space formed by the operation and maintenance parameter monitoring samples of N-1 reference unit time intervals of the reference monitoring cycle and the operation and maintenance parameter monitoring sample of the current unit time interval tx, and since the difference between the reference sample statistical value σ N and the sample statistical value σ x exceeds the preset range, the operation and maintenance parameter monitoring sample of the current unit time interval tx is marked as a dirty sample, that is, the above technical solution of the embodiment of the present invention comprehensively determines whether the operation and maintenance parameter monitoring sample of the current unit time interval tx is a dirty sample according to the statistical value calculation result Compared with the mechanism that whether the operation and maintenance parameter monitoring sample is the dirty sample is judged through the comparison result of the fixed threshold and the operation and maintenance parameter monitoring sample in the prior art, the dirty sample identification method and the operation and maintenance parameter monitoring device are beneficial to improving the identification accuracy of the dirty sample in the operation and maintenance parameter monitoring sample.

Referring to fig. 5, fig. 5 is a block diagram of a monitoring device 500 according to another embodiment of the present invention.

Among them, the monitoring apparatus 500 may include: at least 1 processor 501, memory 505, and at least 1 communication bus 502. A communication bus 502 is used to enable connective communication between these components. The monitoring device 500 optionally includes a user interface 503 including a display (e.g., a touch screen, a liquid crystal display, a Holographic (Holographic) or projection (Projector), etc.), a pointing device (e.g., a mouse, a trackball (trackball) touch pad or touch screen, etc.), a camera and/or a sound pickup device, etc.

Wherein, the monitoring device 500 may further comprise at least 1 network interface 504.

Memory 505 may include both read-only memory and random access memory, among other things, and provides instructions and data to processor 501. Some of the memory 505 may also include non-volatile random access memory, among others.

In some embodiments, memory 505 stores the following elements, executable modules or data structures, or a subset thereof, or an expanded set thereof:

operating system 5051 includes various system programs for implementing various underlying services and for handling hardware-based tasks.

The application module 5052 contains various applications for implementing various application services.

In the embodiment of the present invention, by calling a program or an instruction stored in the memory 505, the processor 501 obtains an operation and maintenance parameter monitoring sample of the current unit time period tx of the operation and maintenance server; calculating a sample statistic value sigma x of a sample space formed by operation and maintenance parameter monitoring samples of N-1 reference unit time intervals of a reference monitoring cycle and operation and maintenance parameter monitoring samples of the current unit time interval tx, wherein the reference monitoring cycle comprises N reference unit time intervals, the N-1 reference unit time intervals are the rest of the N reference unit time intervals except for the reference unit time interval which has a mapping relation with the current unit time interval tx, and N is an integer greater than 1; if the difference between the reference sample statistical value σ N and the sample statistical value σ x exceeds a preset range, marking the operation and maintenance parameter monitoring sample of the current unit time interval tx as a dirty sample, wherein the reference sample statistical value σ N is a sample statistical value of a reference sample space formed by the operation and maintenance parameter monitoring samples of the N reference unit time intervals in the reference monitoring cycle.

Optionally, in some possible embodiments of the present invention, the processor 501 is further configured to replace the operation and maintenance parameter monitoring sample of a reference unit time interval having a mapping relationship with the current unit time interval tx in the N reference unit time intervals of the reference monitoring cycle with the operation and maintenance parameter monitoring sample of the current unit time interval tx when the difference between the reference sample statistical value σ N and the sample statistical value σ x does not exceed a preset range.

Optionally, in some possible embodiments of the present invention, the processor 501 is further configured to issue an alarm that the operation and maintenance parameter monitored to the operation and maintenance server is abnormal in the current unit time period tx when a difference between the reference sample statistic σ n and the sample statistic σ x exceeds a preset range.

It can be understood that the functions of the functional modules of the monitoring device 500 in this embodiment may be specifically implemented according to the method in the foregoing method embodiment, and the specific implementation process may refer to the relevant description of the foregoing method embodiment, which is not described herein again.

It can be seen that in the technical solution of the embodiment of the present invention, after obtaining the operation and maintenance parameter monitoring samples of the current unit time interval tx of the operation and maintenance server, the monitoring device 500 calculates the sample statistical value σ x of the sample space formed by the operation and maintenance parameter monitoring samples of N-1 reference unit time intervals of the reference monitoring cycle and the operation and maintenance parameter monitoring samples of the current unit time interval tx, and since the difference between the reference sample statistical value σ N and the sample statistical value σ x exceeds the preset range, the operation and maintenance parameter monitoring samples of the current unit time interval tx are marked as dirty samples, that is, the above technical solution of the embodiment of the present invention combines the operation and maintenance parameter monitoring samples of the current unit time interval tx and the operation and maintenance parameter monitoring samples of N reference unit time intervals of the reference monitoring cycle, and comprehensively determines whether the operation and maintenance parameter monitoring samples of the current unit time interval tx are dirty samples according to the statistical value calculation result, compared with the mechanism that whether the operation and maintenance parameter monitoring samples are dirty samples is judged through the comparison result of the fixed threshold and the operation and maintenance parameter monitoring samples in the prior art, the scheme of the embodiment of the invention is beneficial to improving the identification accuracy of the dirty samples in the operation and maintenance parameter monitoring samples.

Referring to fig. 6, an embodiment of the present invention further provides a communication system, which may include:

an operation and maintenance server 610 and a monitoring device 620.

The monitoring device 610 is configured to obtain an operation and maintenance parameter monitoring sample of the operation and maintenance server in the current unit time period tx; calculating a sample statistic value sigma x of a sample space formed by operation and maintenance parameter monitoring samples of N-1 reference unit time intervals of a reference monitoring cycle and operation and maintenance parameter monitoring samples of the current unit time interval tx, wherein the reference monitoring cycle comprises N reference unit time intervals, N is an integer greater than 1, and the N-1 reference unit time intervals are the rest of the N reference unit time intervals except for the reference unit time interval having a mapping relation with the current unit time interval tx; if the difference between the reference sample statistical value σ N and the sample statistical value σ x exceeds a preset range, marking the operation and maintenance parameter monitoring sample of the current unit time interval tx as a dirty sample, wherein the reference sample statistical value σ N is a sample statistical value of a reference sample space formed by the operation and maintenance parameter monitoring samples of the N reference unit time intervals in the reference monitoring cycle.

Optionally, in some possible embodiments of the present invention, the reference sample statistic σ n is smaller than or equal to a first threshold. That is to say, in the sample space formed by the operation and maintenance parameter monitoring samples of the N reference unit time periods of the reference monitoring cycle, the fluctuation between the samples is small, for example, the monitoring device 620 may select the operation and maintenance parameter monitoring samples of the adjacent N reference unit time periods, which have smooth changes in the recent parameter baseline, as the operation and maintenance parameter monitoring samples of the N reference unit time periods of the reference monitoring cycle.

Of course, the operation and maintenance parameter monitoring samples of the N reference unit periods of the reference monitoring cycle may also be updated. For example, in a case that the difference between the reference sample statistic σ N and the sample statistic σ x does not exceed a preset range, the monitoring apparatus 620 may replace the operation and maintenance parameter monitoring sample of the reference unit time interval having a mapping relation with the current unit time interval tx in the N reference unit time intervals of the reference monitoring cycle with the operation and maintenance parameter monitoring sample of the current unit time interval tx. Practice shows that, the operation and maintenance parameter monitoring samples of the reference unit period in the reference monitoring cycle having a mapping relation with the current unit period can be replaced by the operation and maintenance parameter monitoring samples of the current unit period, which is beneficial to keeping the operation and maintenance parameter monitoring samples of the N reference unit periods in the reference monitoring cycle at a certain timeliness all the time and having a strong correlation with the recent operation and maintenance parameter, so that the operation and maintenance parameter monitoring samples of the N reference unit periods based on the updated reference monitoring cycle are beneficial to better and more accurately judging whether the operation and maintenance parameter monitoring samples of the subsequent unit periods of the current unit period tx (such as the next unit period of the current unit period tx or the next unit period of the current unit period tx) are dirty samples.

Optionally, in some possible embodiments of the present invention, the monitoring device 620 may further issue an alarm that the operation and maintenance parameter monitored to the operation and maintenance server is abnormal in the current unit time period tx when the difference between the reference sample statistic σ n and the sample statistic σ x exceeds a preset range.

It can be seen that in the technical solution of the embodiment of the present invention, after obtaining the operation and maintenance parameter monitoring samples of the current unit time interval tx of the operation and maintenance server 610, the monitoring device 620 calculates the sample statistical value σ x of the sample space formed by the operation and maintenance parameter monitoring samples of N-1 reference unit time intervals of the reference monitoring cycle and the operation and maintenance parameter monitoring samples of the current unit time interval tx, and marks the operation and maintenance parameter monitoring samples of the current unit time interval tx as dirty samples because the difference between the reference sample statistical value σ N and the sample statistical value σ x exceeds the preset range, that is, the above technical solution of the embodiment of the present invention combines the operation and maintenance parameter monitoring samples of the current unit time interval tx and the operation and maintenance parameter monitoring samples of N reference unit time intervals of the reference monitoring cycle, and comprehensively determines whether the operation and maintenance parameter monitoring samples of the current unit time interval tx are dirty samples according to the statistical value calculation result, compared with the mechanism that whether the operation and maintenance parameter monitoring samples are dirty samples is judged through the comparison result of the fixed threshold and the operation and maintenance parameter monitoring samples in the prior art, the scheme of the embodiment of the invention is beneficial to improving the identification accuracy of the dirty samples in the operation and maintenance parameter monitoring samples.

The embodiment of the present invention further provides a computer storage medium, where the computer storage medium may store a program, and when the program is executed, the program includes some or all of the steps of any one of the operation and maintenance parameter monitoring sample processing methods described in the above method embodiments.

It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implementing, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some interfaces, devices or units, and may be an electric or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

The above-mentioned embodiments are only used for illustrating the technical solution of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An operation and maintenance parameter monitoring sample processing method is characterized by comprising the following steps:

2. The method of claim 1, wherein the sample statistic σ x is a sample standard deviation and the reference sample statistic σ n is a sample standard deviation, or wherein the sample statistic σ x is a sample variance and the reference sample statistic σ n is a sample variance.

3. The method of claim 1, wherein the reference sample statistic σ n is less than or equal to a first threshold.

4. The method of claim 2, wherein the reference sample statistic σ n is less than or equal to a first threshold.

5. The method according to any one of claims 1 to 4,

the method further comprises the following steps:

and replacing the operation and maintenance parameter monitoring sample of the reference unit time interval with the operation and maintenance parameter monitoring sample of the current unit time interval tx, which has a mapping relation with the current unit time interval tx, in the N reference unit time intervals of the reference monitoring period, under the condition that the difference between the reference sample statistic σ N and the sample statistic σ x does not exceed a preset range.

6. The method according to any one of claims 1 to 4,

the method further comprises the following steps: and sending an alarm for monitoring that the operation and maintenance parameters of the operation and maintenance server in the current unit time interval tx are abnormal under the condition that the difference between the reference sample statistic value sigma n and the sample statistic value sigma x exceeds a preset range.

7. The method of claim 5,

8. An operation and maintenance parameter monitoring sample processing method, characterized in that the method has all the features of any one of the method claims 1 to 7, and the difference between the reference sample statistic σ n and the sample statistic σ x exceeds a preset range, comprising: an absolute value of a difference between the reference sample statistic σ n and the sample statistic σ x is greater than or equal to a second threshold, or a quotient obtained by dividing an absolute value of a difference between the reference sample statistic σ n and the sample statistic σ x by the reference sample statistic σ n is greater than or equal to a third threshold, or a quotient obtained by dividing an absolute value of a difference between the reference sample statistic σ n and the sample statistic σ x by the sample statistic σ x is greater than or equal to a fourth threshold, or a ratio of the reference sample statistic σ n to the sample statistic σ x is greater than or equal to a fifth threshold, or a ratio of the reference sample statistic σ n to the sample statistic σ x is less than or equal to a sixth threshold.

9. An operation and maintenance parameter monitoring sample processing method, characterized in that the method has all the features of the method of any one of claims 1 to 8, and the operation and maintenance parameter monitoring sample is a traffic monitoring sample, a packet quantity monitoring sample, an access quantity monitoring sample or a transaction quantity monitoring sample.

10. An operation and maintenance parameter monitoring sample processing device, comprising:

11. The apparatus of claim 10, wherein the sample statistic σ x is a sample standard deviation and the reference sample statistic σ n is a sample standard deviation, or wherein the sample statistic σ x is a sample variance and the reference sample statistic σ n is a sample variance.

12. The apparatus of claim 10, wherein the reference sample statistic σ n is less than or equal to a first threshold.

13. The apparatus of claim 11, wherein the reference sample statistic σ n is less than or equal to a first threshold.

14. The apparatus according to any one of claims 10 to 13,

the device further comprises: a sample updating unit, configured to replace, in a case that a difference between the reference sample statistical value σ N and the sample statistical value σ x does not exceed a preset range, an operation and maintenance parameter monitoring sample of a reference unit time interval having a mapping relationship with the current unit time interval tx in the N reference unit time intervals of the reference monitoring cycle with the operation and maintenance parameter monitoring sample of the current unit time interval tx.

15. The apparatus according to any one of claims 10 to 13,

the device further comprises: and the alarm unit is used for sending an alarm for monitoring that the operation and maintenance parameters of the current unit time interval tx of the operation and maintenance server are abnormal under the condition that the difference between the reference sample statistic value sigma n and the sample statistic value sigma x exceeds a preset range.

16. The apparatus of claim 14,

17. An operation and maintenance parameter monitoring sample processing apparatus, characterized in that the apparatus has all the features of the apparatus of any one of claims 10 to 16, and the difference between the reference sample statistic σ n and the sample statistic σ x exceeds a preset range, comprising: an absolute value of a difference between the reference sample statistic σ n and the sample statistic σ x is greater than or equal to a second threshold, or a quotient obtained by dividing an absolute value of a difference between the reference sample statistic σ n and the sample statistic σ x by the reference sample statistic σ n is greater than or equal to a third threshold, or a quotient obtained by dividing an absolute value of a difference between the reference sample statistic σ n and the sample statistic σ x by the sample statistic σ x is greater than or equal to a fourth threshold, or a ratio of the reference sample statistic σ n to the sample statistic σ x is greater than or equal to a fifth threshold, or a ratio of the reference sample statistic σ n to the sample statistic σ x is less than or equal to a sixth threshold.

18. A communication system, comprising:

an operation and maintenance server and monitoring equipment;

19. A monitoring device, comprising a processor and a memory; the processor is configured to execute a computer program stored in the memory to implement the method of any one of claims 1 to 9.

20. A computer-readable storage medium, characterized in that it stores a computer program which, when executed by hardware, is capable of implementing the method of any one of claims 1 to 9.