Abnormal state monitoring method and alarm device of communication equipment based on 5G Internet of Things

Abstract

The present invention relates to the field of Internet of Things data processing technology, and specifically to a communication equipment abnormal state monitoring method and alarm device based on 5G Internet of Things, including: collecting various monitoring data; segmenting various monitoring data, and obtaining the possibility of normal fluctuation of each monitoring data in each time period according to the correlation between various monitoring data; obtaining the characteristic value of each data in each data according to the amplitude of each monitoring data, and obtaining the abnormal value correction coefficient of each monitoring data according to the possibility of normal fluctuation of each monitoring data in each time period; obtaining the abnormal value of the monitoring data, and obtaining the real abnormal value of the monitoring data in combination with the abnormal value correction coefficient of the monitoring data, and monitoring and alarming the state of the communication equipment. The present invention combines the connection between various data of the communication equipment to avoid the occurrence of false alarms issued by the alarm device.

Description

Technical Field

[0001] The present invention relates to the field of Internet of Things data processing, and in particular to a method and an alarm device for monitoring abnormal states of communication equipment based on 5G Internet of Things. Background Art

[0002] In the process of status monitoring of communication equipment, it involves monitoring various data of the communication equipment, but the various data of the communication equipment are easily affected by the external environment, resulting in uncontrollable fluctuations in the various data of the communication equipment; therefore, if the isolated forest is used directly to monitor the various data of the communication equipment, normal fluctuations will be judged as abnormal data, that is, if the isolated forest is used directly to monitor the various data of the communication equipment, misjudgment may occur, resulting in the alarm module may issue a false alarm; therefore, this embodiment combines the connection between the various data of the communication equipment to avoid the alarm device issuing a false alarm. Summary of the invention

[0003] The present invention provides a communication equipment abnormal state monitoring method and an alarm device based on 5G Internet of Things to solve the existing problem: the effect of using the isolation forest algorithm to monitor various data of the communication equipment is not good, resulting in the alarm device issuing a false alarm.

[0004] The abnormal state monitoring method and alarm device of communication equipment based on 5G Internet of Things of the present invention adopts the following technical solutions:

[0005] The following steps are involved:

[0006] Collect various monitoring data of communication equipment;

[0007] According to the correlation between each monitoring data, obtain the relevant data of each monitoring data; segment each monitoring data to obtain the data of each monitoring data in each time period; according to the amplitude of each monitoring data in each time period, obtain the fluctuation value of each data of each monitoring data in each time period; according to the fluctuation value of each data of each monitoring data in each time period and the fluctuation value of each data of the relevant data of each monitoring data in each time period, obtain the possibility of normal fluctuation of each monitoring data in each time period;

[0008] According to the amplitude of each monitoring data, the characteristic value of each data in each data is obtained; according to the possibility of normal fluctuation of each monitoring data in each time period and the characteristic value of each data in each monitoring data in each time period, the abnormal value correction coefficient of each monitoring data is obtained;

[0009] Acquire abnormal values ​​of the monitoring data, and acquire true abnormal values ​​of the monitoring data according to the abnormal values ​​of the monitoring data and the abnormal value correction coefficient of the monitoring data; monitor and alarm the status of the communication equipment according to the true abnormal values ​​of the monitoring data.

[0010] Preferably, the specific method of collecting various monitoring data of the communication equipment includes:

[0011] A historical period range α is preset, and current sensors, voltage sensors, temperature sensors, humidity sensors, and vibration sensors are deployed on the communication equipment to collect current data, voltage data, temperature data, humidity data, and vibration data of the communication equipment, and various data within α days from the current time are recorded as various historical data;

[0012] For the ith historical data, all data in the ith historical data are normalized by the maximum and minimum values ​​to obtain the normalized result of all data in the ith historical data, which is recorded as the ith monitoring data.

[0013] Preferably, the method of obtaining relevant data of each monitoring data according to the correlation between each monitoring data includes:

[0014] Arrange each monitoring data item in chronological order to obtain each monitoring data sequence; for the ith monitoring data sequence, first calculate the absolute value of the Pearson correlation coefficient between the ith monitoring data sequence and each monitoring data sequence except the ith monitoring data sequence, and take the monitoring data sequence with the largest absolute value of the Pearson correlation coefficient with the ith monitoring data sequence as the relevant data of the ith monitoring data.

[0015] Preferably, the monitoring data are segmented to obtain the data of each monitoring data in each time period; and the fluctuation value of each data of each monitoring data in each time period is obtained according to the amplitude of the data of each monitoring data in each time period, including the specific method of:

[0016] Preset a segment length T, and divide the historical period range into several time periods of T hours each;

[0017] For the yth data of the ith monitoring data in the xth time period, first take the difference between the yth data of the ith monitoring data in the xth time period and the y-1th data of the ith monitoring data in the xth time period as the fluctuation value of the yth data of the ith monitoring data in the xth time period; obtain the fluctuation value of each data of the ith monitoring data in the xth time period, as well as the fluctuation value of each data of the related data of the ith monitoring data in the xth time period.

[0018] Preferably, the possibility of normal fluctuation of each monitoring data in each time period is obtained according to the fluctuation value of each data of each monitoring data in each time period, and the fluctuation value of each data of the related data of each monitoring data in each time period, including the specific method of:

[0019] For the i-th monitoring data in the x-th time period, calculate the Pearson correlation coefficient between the data of the i-th monitoring data in the x-th time period and the data of the related data of the i-th monitoring data in the x-th time period;

[0020] According to the fluctuation value of each data of the i-th monitoring data in the x-time period, the fluctuation value of each data of the related data of the i-th monitoring data in the x-time period, the Pearson correlation coefficient between the data of the i-th monitoring data in the x-time period and the data of the related data of the i-th monitoring data in the x-time period, and the Pearson correlation coefficient between the i-th monitoring data and the related data of the i-th monitoring data, the possibility of normal fluctuation of the i-th monitoring data in the x-time period is obtained. The specific calculation formula is:

[0021]

[0022] In the formula, C i,x It indicates the possibility of normal fluctuation of the i-th monitoring data in the x-th time period; g i,x,y represents the fluctuation value of the yth data of the i-th monitoring data in the x-th time period; g i ′ ,x,y represents the fluctuation value of the yth data of the related data of the i-th monitoring data in the x-th time period; p i,x represents the Pearson correlation coefficient between the data of the i-th monitoring data in the x-th time period and the data of the related data of the i-th monitoring data in the x-th time period; p i ′ represents the Pearson correlation coefficient between the i-th monitoring data and the related data of the i-th monitoring data; Y i,x It represents the number of data of the i-th monitoring data in the x-th time period; || represents the absolute value operation; exp() represents the exponential function with a natural constant as the base.

[0023] Preferably, the method of obtaining the characteristic value of each data in each data according to the amplitude of each monitoring data includes:

[0024] For the yth data of the ith monitoring data in the xth time period, first obtain the previous data and the next data of the yth data of the ith monitoring data in the xth time period, and record them as the neighborhood data of the yth data of the ith monitoring data in the xth time period; record the absolute value of the difference between the mean of the neighborhood data of the yth data of the ith monitoring data in the xth time period and the yth data of the ith monitoring data in the xth time period as the characteristic value of the yth data of the ith monitoring data in the xth time period.

[0025] Preferably, the method of obtaining the abnormal value correction coefficient of each monitoring data according to the possibility of normal fluctuation of each monitoring data in each time period and the characteristic value of each data of each monitoring data in each time period includes the following specific methods:

[0026] For the yth data of the ith monitoring data in the xth time period, according to the characteristic values ​​of all data of the ith monitoring data in the xth time period, the characteristic values ​​of the yth data of the related data of the ith monitoring data in the xth time period, and the possibility of normal fluctuation of the ith monitoring data in the xth time period, the abnormal value correction coefficient of the yth data of the ith monitoring data in the xth time period is obtained, and the specific calculation formula is:

[0027]

[0028] In the formula, Q i,x,y represents the abnormal value correction coefficient of the yth data of the i-th monitoring data in the x-th time period; C i,x It indicates the possibility of normal fluctuation of the i-th monitoring data in the x-th time period; Y i,x Indicates the number of data of the i-th monitoring data in the x-th time period; represents the mean of the characteristic values ​​of all data of the i-th monitoring data in the x-th time period; f i,x,y represents the characteristic value of the yth data of the i-th monitoring data in the x-th time period; f i, ′ x,y It represents the characteristic value of the yth data of the related data of the ith monitoring data in the xth time period; || represents the absolute value operation; norm{} represents the normalization function.

[0029] Preferably, the method of obtaining the abnormal value of the monitoring data, and obtaining the real abnormal value of the monitoring data according to the abnormal value of the monitoring data and the abnormal value correction coefficient of the monitoring data, includes the following specific methods:

[0030] For the i-th monitoring data, all the data in the i-th monitoring data are input into the isolation forest algorithm to obtain the outliers of all the data in the i-th monitoring data;

[0031] For the vth data in the ith monitoring data, the product of the outlier value of the vth data in the ith monitoring data and the outlier value correction coefficient of the vth data in the ith monitoring data is taken as the true outlier value of the vth data in the ith monitoring data.

[0032] Preferably, the monitoring and alarming of the status of the communication equipment according to the real abnormal value of the monitoring data includes the following specific methods:

[0033] An abnormal threshold τ is preset. If the real abnormal value of the latest collected monitoring data is greater than τ, the latest collected monitoring data is abnormal data, the communication device is in an abnormal state, and the alarm device is immediately triggered to sound an alarm.

[0034] Another embodiment of the present invention provides an abnormal state alarm device for communication equipment based on 5G Internet of Things, including an alarm unit, a communication unit, a storage unit, a processing unit, and a computer program stored on the storage unit and executable on the processing unit. When the computer program is executed by the processing unit, the computer program implements any step of the above-mentioned abnormal state monitoring method for communication equipment based on 5G Internet of Things, and sends the execution result to the alarm unit through the communication unit, and the alarm unit issues an alarm according to the execution result.

[0035] The beneficial effects of the technical solution of the present invention are as follows: the present application first obtains various monitoring data by standardizing various data so as to better analyze multiple data; then the various monitoring data are segmented, and based on the correlation between the various monitoring data, the possibility of normal fluctuation of each monitoring data in each time period is obtained, so as to prepare data for the subsequent calculation of the abnormal value correction coefficient of each monitoring data; according to the amplitude of each monitoring data, the characteristic value of each data in the various data is obtained, and the abnormal value correction coefficient of each monitoring data is obtained according to the possibility of normal fluctuation of each monitoring data in each time period, so that the abnormal value correction coefficient of the data with normal fluctuation is much smaller than the abnormal value correction coefficient of the abnormal data; the abnormal value of the monitoring data is obtained, combined with the abnormal value correction coefficient of the monitoring data, the real abnormal value of the monitoring data is obtained, and the status of the communication equipment is monitored to avoid the alarm device from issuing a false alarm. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 This is a flowchart of the steps of the abnormal state monitoring method of communication equipment based on 5G Internet of Things of the present invention;

[0038] Figure 2 This is a flow chart of triggering the alarm device of the present invention. DETAILED DESCRIPTION

[0039] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the abnormal state monitoring method and alarm device of the communication equipment based on the 5G Internet of Things proposed by the present invention, its specific implementation method, structure, characteristics and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0040] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0041] The specific scheme of the abnormal state monitoring method and alarm device of communication equipment based on 5G Internet of Things provided by the present invention is described in detail below with reference to the accompanying drawings.

[0042] See also Figure 1 , which shows a flowchart of a method for monitoring abnormal status of a communication device based on 5G Internet of Things provided by an embodiment of the present invention, the method comprising the following steps:

[0043] Step S001: Collect various monitoring data of communication equipment.

[0044] It should be noted that this embodiment, as a method for monitoring abnormal status of communication equipment based on 5G Internet of Things, includes but is not limited to the following modules:

[0045] Image acquisition module: collects image data of communication equipment in real time through the camera;

[0046] Data acquisition module: collects various data of communication equipment by deploying various sensors such as current sensor, voltage sensor, vibration sensor, temperature sensor, humidity sensor, etc. on the communication equipment;

[0047] Data transmission module: transmits image data and various data of communication equipment through 5G Internet of Things;

[0048] Data comprehensive processing module: by analyzing the image data and various data of the communication device transmitted, judging whether there is abnormal data in the image data and various data of the communication device;

[0049] Alarm module: Determine whether to issue an alarm based on the analysis results in the data comprehensive processing module.

[0050] It needs to be further explained that the data of the communication equipment are easily affected by the external environment, resulting in uncontrollable fluctuations in the data of the communication equipment. For example, the temperature difference between day and night and the change in air humidity will cause uncontrollable fluctuations in the monitored data, and this fluctuation is a normal fluctuation; therefore, if the data of the isolated forest monitoring communication equipment is directly used, the normal fluctuation will be judged as abnormal data, that is, if the data of the isolated forest monitoring communication equipment is directly used, misjudgment will occur, resulting in the alarm module issuing a false alarm; therefore, this embodiment combines the connection between the data of the communication equipment to avoid the alarm device issuing a false alarm. To this end, it is first necessary to collect the data of the communication equipment.

[0051] Specifically, a historical period range α is preset, and the specific value of α can be set according to the actual situation. In this embodiment, α=7 is used for description. Various sensors such as current sensors, voltage sensors, temperature sensors, humidity sensors, and vibration sensors are deployed on the communication equipment to collect current data, voltage data, temperature data, humidity data, vibration data and other data of the communication equipment, and the data within α days from the current time are recorded as various historical data.

[0052] It should be noted that, since the communication equipment status monitoring is performed based on the analysis of multiple historical data, in order to better analyze the multiple historical data, it is also necessary to standardize the various historical data.

[0053] Specifically, for the i-th item of historical data, all data in the i-th item of historical data are normalized by maximum and minimum values ​​to obtain a normalized result of all data in the i-th item of historical data, which is recorded as the i-th item of monitoring data.

[0054] At this point, various monitoring data are obtained.

[0055] Step S002: According to the correlation between each monitoring data, obtain the relevant data of each monitoring data; segment each monitoring data to obtain the data of each monitoring data in each time period; according to the amplitude of each monitoring data in each time period, obtain the fluctuation value of each data of each monitoring data in each time period; according to the fluctuation value of each data of each monitoring data in each time period and the fluctuation value of each data of the relevant data of each monitoring data in each time period, obtain the possibility of normal fluctuation of each monitoring data in each time period.

[0056] It should be noted that, since the present embodiment monitors the status of the communication device by analyzing various data of the communication device, and since the various data of the communication device are not independent but have a certain continuity between the various data, when a certain data fluctuates normally, the data related to the data will also fluctuate normally. Therefore, by obtaining the relevant data of each data, a preliminary judgment can be made as to whether it is a normal fluctuation based on the relevant data of each data and each data.

[0057] Specifically, each monitoring data is arranged in chronological order to obtain each monitoring data sequence; for the i-th monitoring data sequence, the absolute value of the Pearson correlation coefficient between the i-th monitoring data sequence and each monitoring data sequence except the i-th monitoring data sequence is first calculated, and the monitoring data sequence with the largest absolute value of the Pearson correlation coefficient with the i-th monitoring data sequence is taken as the relevant data of the i-th monitoring data, and the relevant data of each monitoring data is obtained; since the specific process of obtaining the Pearson correlation coefficient is a well-known prior art, it will not be repeated in this embodiment.

[0058] It should be further explained that in order to avoid judging normal fluctuations as abnormal data, which would lead to inaccurate isolated forest monitoring results, this embodiment first segments the data according to time, and calculates the possibility of normal fluctuations in the data in each time period. When using the isolated forest to monitor the data of the communication equipment, the participation of time periods with a high possibility of normal fluctuations is reduced, thereby avoiding normal fluctuations from being judged as abnormal data, thereby improving the accuracy of communication equipment status monitoring.

[0059] Specifically, firstly, a segment length T is preset. The specific value of T can be set by oneself in combination with the actual situation. This embodiment does not make a rigid requirement. In this embodiment, T=1 is used for description, and the historical period range is evenly divided into several time periods with a time length of T hours.

[0060] For the yth data of the ith monitoring data in the xth time period, firstly, the difference between the yth data of the ith monitoring data in the xth time period and the y-1th data of the ith monitoring data in the xth time period is taken as the fluctuation value of the yth data of the ith monitoring data in the xth time period, and the fluctuation value of the first data of the ith monitoring data in the xth time period is made equal to the fluctuation value of the second data of the ith monitoring data in the xth time period; obtain the fluctuation value of each data of the ith monitoring data in the xth time period, and the fluctuation value of each data of the related data of the ith monitoring data in the xth time period;

[0061] Then, the Pearson correlation coefficient between the data of the i-th monitoring data in the x-th time period and the data of the related data of the i-th monitoring data in the x-th time period is calculated;

[0062] According to the fluctuation value of each data of the i-th monitoring data in the x-time period, the fluctuation value of each data of the related data of the i-th monitoring data in the x-time period, the Pearson correlation coefficient between the data of the i-th monitoring data in the x-time period and the data of the related data of the i-th monitoring data in the x-time period, and the Pearson correlation coefficient between the i-th monitoring data and the related data of the i-th monitoring data, the possibility of normal fluctuation of the i-th monitoring data in the x-time period is obtained. The specific calculation formula is:

[0063]

[0064] In the formula, C i,x It indicates the possibility of normal fluctuation of the i-th monitoring data in the x-th time period; g i,x,y represents the fluctuation value of the yth data of the i-th monitoring data in the x-th time period; g i ′ ,x,y represents the fluctuation value of the yth data of the related data of the i-th monitoring data in the x-th time period; p i,x represents the Pearson correlation coefficient between the data of the i-th monitoring data in the x-th time period and the data of the related data of the i-th monitoring data in the x-th time period; p i ′ represents the Pearson correlation coefficient between the i-th monitoring data and the related data of the i-th monitoring data; Y i,x It represents the number of data of the i-th monitoring data in the x-th time period; || represents the absolute value operation; exp() represents an exponential function with a natural constant as the base. This embodiment adopts the exp(-β) model to present the inverse proportional and normalized relationship. β is the input of the model. The implementer can set the inverse proportional and normalized function according to the actual situation.

[0065] It should be noted that since normal fluctuations are caused by the influence of the natural environment, when a certain data fluctuates normally, the related data of the data will also fluctuate accordingly. In this embodiment, this phenomenon is called synergy. When a certain data is abnormal, there will be no synergy. The smaller the value of is, the stronger the correlation of the i-th monitoring data in the x-th time period is; |p i,x -p i ′ The smaller the value of |, the closer the Pearson correlation coefficient between the data of the i-th monitoring data in the x-th time period and the data related to the i-th monitoring data in the x-th time period is, and the Pearson correlation coefficient between the i-th monitoring data and the related data of the i-th monitoring data is, and the Pearson correlation coefficient between the i-th monitoring data and the related data of the i-th monitoring data is always high, so |p i,x -p i ′ The smaller the value of |, the stronger the correlation of the i-th monitoring data in the x-th time period, so C i,x The larger the value of , the more likely the fluctuation in the i-th monitoring data in the x-th time period is a normal fluctuation.

[0066] At this point, the possibility of normal fluctuation of each monitoring data in each time period is obtained.

[0067] Step S003: According to the amplitude of each monitoring data, obtain the characteristic value of each data in each data; according to the possibility of normal fluctuation of each monitoring data in each time period and the characteristic value of each monitoring data in each time period, obtain the abnormal value correction coefficient of each monitoring data.

[0068] It should be noted that the present embodiment analyzes various data of the communication equipment to prevent normal fluctuations caused by the natural environment from being identified as abnormal data. After obtaining the possibility of normal fluctuations of each monitoring data in each time period through step S002, the abnormality of each data of each monitoring data in each time period can be obtained based on the possibility of normal fluctuations of each monitoring data in each time period.

[0069] Specifically, for the yth data of the ith monitoring data in the xth time period, first obtain the previous data and the next data of the yth data of the ith monitoring data in the xth time period, record them as the neighborhood data of the yth data of the ith monitoring data in the xth time period, and take the absolute value of the difference between the mean of the neighborhood data of the yth data of the ith monitoring data in the xth time period and the yth data of the ith monitoring data in the xth time period as the characteristic value of the yth data of the ith monitoring data in the xth time period, record it as f i,x,y , if the yth data of the i-th monitoring data in the x-th time period is the first or last data in the i-th monitoring data, then the second or second-to-last data in the i-th monitoring data is used as the neighborhood data of the yth data of the i-th monitoring data in the x-th time period; obtain the characteristic values ​​of all data of the i-th monitoring data in the x-th time period, and the characteristic values ​​of the yth data of the related data of the i-th monitoring data in the x-th time period;

[0070] According to the characteristic values ​​of all data of the i-th monitoring data in the x-th time period, the characteristic values ​​of the y-th data of the related data of the i-th monitoring data in the x-th time period, and the possibility of normal fluctuation of the i-th monitoring data in the x-th time period, the abnormal value correction coefficient of the y-th data of the i-th monitoring data in the x-th time period is obtained. The specific calculation formula is:

[0071]

[0072] In the formula, Q i,x,y represents the abnormal value correction coefficient of the yth data of the i-th monitoring data in the x-th time period; C i,x It indicates the possibility of normal fluctuation of the i-th monitoring data in the x-th time period; Y i,x Indicates the number of data of the i-th monitoring data in the x-th time period; represents the mean of the characteristic values ​​of all data of the i-th monitoring data in the x-th time period; f i,x,y represents the characteristic value of the yth data of the i-th monitoring data in the x-th time period; f i, ′ x,y represents the characteristic value of the yth data in the xth time period of the related data of the i-th monitoring data; || represents the absolute value operation; norm{} represents the normalization function, and the normalization object is all the data in the i-th monitoring data.

[0073] It should be noted that C i,xThe larger the value of is, the more likely the abnormal value of the data in the i-th monitoring data in the x-th time period is to be caused by normal fluctuations, so it is more necessary to reduce the abnormal value of the data in the i-th monitoring data in the x-th time period; the characteristic value of the data represents the difference between the data and the surrounding data; therefore, the higher the characteristic value of the data, the more likely the data is abnormal data, that is, The larger the value of is, the higher the possibility that the data of the i-th monitoring data in the x-th time period is abnormal data; because in the scenario where the communication equipment monitoring status is normal, when a certain data changes, the related data of the data will always change at the same time, so The closer the value of is to 1, the more it is necessary to reduce the abnormal value of the yth data in the i-th monitoring data in the x-th time period; therefore, Q i,x,y The smaller the value of needs to be, the lower the abnormal value of the y-th data of the i-th monitoring data in the x-th time period needs to be.

[0074] At this point, the outlier correction coefficient of each monitoring data is obtained.

[0075] Step S004: Obtain abnormal values ​​of the monitoring data, and obtain the true abnormal values ​​of the monitoring data according to the abnormal values ​​of the monitoring data and the abnormal value correction coefficient of the monitoring data; monitor and alarm the status of the communication equipment according to the true abnormal values ​​of the monitoring data.

[0076] It should be noted that after obtaining the outlier correction coefficient of each monitoring data through step S003, the outlier value of each monitoring data can be obtained through the isolation forest algorithm, and the true outlier value of each monitoring data can be obtained by combining the outlier correction coefficient of each monitoring data.

[0077] Specifically, for the i-th monitoring data, all data in the i-th monitoring data are input into the isolation forest algorithm to obtain the abnormal values ​​of all data in the i-th monitoring data. Since the isolation forest algorithm is a well-known prior art, it will not be described in detail in this embodiment;

[0078] For the v-th data in the ith monitoring data, the product of the outlier value of the v-th data in the ith monitoring data and the outlier correction coefficient of the v-th data in the ith monitoring data is taken as the true outlier value of the v-th data in the ith monitoring data; the true outlier value of each monitoring data is obtained.

[0079] It should be noted that the true abnormal value of each monitoring data obtained avoids the situation where the abnormal value of the monitoring data is too high due to normal fluctuations, causing the alarm device to issue a false alarm; at this time, the true abnormal value of the monitoring data can be used to determine whether to issue an alarm, thereby avoiding the situation where the alarm device issues a false alarm.

[0080] Specifically, an abnormal threshold τ is preset. The specific value of τ can be set according to the actual situation. This embodiment does not make a rigid requirement. In this embodiment, τ=0.6 is used for description. If the actual abnormal value of the latest collected monitoring data is greater than τ, then the latest collected monitoring data is abnormal data, the communication equipment is in an abnormal state, and the alarm device is immediately triggered to sound an alarm.

[0081] Another embodiment of the present invention provides an abnormal state alarm device for communication equipment based on 5G Internet of Things, including an alarm unit, a communication unit, a storage unit, a processing unit, and a computer program stored on the storage unit and executable on the processing unit. When the computer program is executed by the processing unit, the steps of the abnormal state monitoring method for communication equipment based on 5G Internet of Things in steps S001 to S004 are implemented, and the execution result is sent to the alarm unit through the communication unit, and the alarm unit issues an alarm according to the execution result.

[0082] The flowchart of the triggering alarm device in this embodiment is as follows: Figure 2 shown.

[0083] At this point, this embodiment is completed.

[0084] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for monitoring abnormal status of communication equipment based on 5G Internet of Things, characterized in that: The method comprises the following steps: Collect various monitoring data of communication equipment; According to the correlation between each monitoring data, the relevant data of each monitoring data is obtained, including: arranging each monitoring data in a time series order to obtain each monitoring data sequence; for the i-th monitoring data sequence, firstly calculating the absolute value of the Pearson correlation coefficient between the i-th monitoring data sequence and each monitoring data sequence except the i-th monitoring data sequence, and taking the monitoring data sequence with the largest absolute value of the Pearson correlation coefficient with the i-th monitoring data sequence as the relevant data of the i-th monitoring data; Each monitoring data is segmented to obtain the data of each monitoring data in each time period; according to the amplitude of each monitoring data in each time period, the fluctuation value of each data of each monitoring data in each time period is obtained; according to the fluctuation value of each data of each monitoring data in each time period and the fluctuation value of each data of the related data of each monitoring data in each time period, the possibility of normal fluctuation of each monitoring data in each time period is obtained; According to the amplitude of each monitoring data, the characteristic value of each data in each data is obtained; according to the possibility of normal fluctuation of each monitoring data in each time period and the characteristic value of each data in each monitoring data in each time period, the abnormal value correction coefficient of each monitoring data is obtained, and the calculation formula is: In the formula, Q i,x,y represents the abnormal value correction coefficient of the yth data of the i-th monitoring data in the x-th time period; C i,x It indicates the possibility of normal fluctuation of the i-th monitoring data in the x-th time period; Y i,x Indicates the number of data of the i-th monitoring data in the x-th time period; represents the mean of the characteristic values ​​of all data of the i-th monitoring data in the x-th time period; f i,x,y represents the characteristic value of the yth data of the i-th monitoring data in the x-th time period; f i, ′ x,y represents the characteristic value of the yth data of the related data of the i-th monitoring data in the x-th time period; || represents the absolute value operation; norm{} represents the normalization function; The outliers of the monitoring data are obtained according to the isolation forest algorithm, and the real outliers of the monitoring data are obtained according to the outliers of the monitoring data and the outlier correction coefficient of the monitoring data; the status of the communication equipment is monitored and an alarm is performed according to the real outliers of the monitoring data.

2. According to the method for monitoring abnormal status of communication equipment based on 5G Internet of Things according to claim 1, it is characterized in that: The specific method of collecting various monitoring data of the communication equipment includes: A historical period range α is preset, and current sensors are deployed on the communication equipment to collect current data, voltage sensors are deployed to collect voltage data, temperature sensors are deployed to collect temperature data, humidity sensors are deployed to collect humidity data, and vibration sensors are deployed to collect vibration data, and various data within α days from the current time are recorded as various historical data; For the ith historical data, all data in the ith historical data are normalized by the maximum and minimum values ​​to obtain the normalized result of all data in the ith historical data, which is recorded as the ith monitoring data.

3. According to claim 2, the abnormal state monitoring method of communication equipment based on 5G Internet of Things is characterized in that: The monitoring data are segmented to obtain the data of each monitoring data in each time period; and the fluctuation value of each data of each monitoring data in each time period is obtained according to the amplitude of the data of each monitoring data in each time period, including the specific method of: Preset a segment length T, and divide the historical period range into several time periods of T hours each; For the yth data of the ith monitoring data in the xth time period, first take the difference between the yth data of the ith monitoring data in the xth time period and the y-1th data of the ith monitoring data in the xth time period as the fluctuation value of the yth data of the ith monitoring data in the xth time period; obtain the fluctuation value of each data of the ith monitoring data in the xth time period, as well as the fluctuation value of each data of the related data of the ith monitoring data in the xth time period.

4. According to the method for monitoring abnormal status of communication equipment based on 5G Internet of Things according to claim 1, it is characterized in that: The possibility of normal fluctuation of each monitoring data in each time period is obtained according to the fluctuation value of each data of each monitoring data in each time period, and the fluctuation value of each data of the related data of each monitoring data in each time period, including the specific method of: For the i-th monitoring data in the x-th time period, calculate the Pearson correlation coefficient between the data of the i-th monitoring data in the x-th time period and the data of the related data of the i-th monitoring data in the x-th time period; The probability of normal fluctuation of the i-th monitoring data in the x-th time period is obtained. The specific calculation formula is: In the formula, C i,x It indicates the possibility of normal fluctuation of the i-th monitoring data in the x-th time period; g i,x,y represents the fluctuation value of the yth data of the i-th monitoring data in the x-th time period; g i ′ ,x,y represents the fluctuation value of the yth data of the related data of the i-th monitoring data in the x-th time period; p i,x represents the Pearson correlation coefficient between the data of the i-th monitoring data in the x-th time period and the data of the related data of the i-th monitoring data in the x-th time period; p i ′ represents the Pearson correlation coefficient between the i-th monitoring data and the related data of the i-th monitoring data; Y i,x It represents the number of data of the i-th monitoring data in the x-th time period; || represents the absolute value operation; exp() represents the exponential function with a natural constant as the base.

5. According to the method for monitoring abnormal status of communication equipment based on 5G Internet of Things according to claim 1, it is characterized in that: The specific method of obtaining the characteristic value of each data in each data according to the amplitude of each monitoring data is as follows: For the yth data of the ith monitoring data in the xth time period, first obtain the previous data and the next data of the yth data of the ith monitoring data in the xth time period, and record them as the neighborhood data of the yth data of the ith monitoring data in the xth time period; record the absolute value of the difference between the mean of the neighborhood data of the yth data of the ith monitoring data in the xth time period and the yth data of the ith monitoring data in the xth time period as the characteristic value of the yth data of the ith monitoring data in the xth time period.

6. The method for monitoring abnormal status of communication equipment based on 5G Internet of Things according to claim 1 is characterized in that: The method of obtaining the abnormal value of the monitoring data and obtaining the real abnormal value of the monitoring data according to the abnormal value of the monitoring data and the abnormal value correction coefficient of the monitoring data includes the following specific methods: For the vth data in the ith monitoring data, the product of the outlier value of the vth data in the ith monitoring data and the outlier value correction coefficient of the vth data in the ith monitoring data is taken as the true outlier value of the vth data in the ith monitoring data.

7. The method for monitoring abnormal status of communication equipment based on 5G Internet of Things according to claim 1 is characterized in that: The specific method of monitoring and alarming the status of the communication equipment according to the real abnormal value of the monitoring data includes: An abnormal threshold τ is preset. If the actual abnormal value of the latest collected monitoring data is greater than τ, the latest collected monitoring data is abnormal data, and the communication device is in an abnormal state, which immediately triggers the alarm device to sound an alarm.

8. A communication device abnormal state alarm device based on 5G Internet of Things, comprising an alarm unit, a communication unit, a storage unit, a processing unit, and a computer program stored in the storage unit and executable on the processing unit, characterized in that: When the computer program is executed by the processing unit, the steps of the abnormal state monitoring method of communication equipment based on 5G Internet of Things are implemented as described in any one of claims 1 to 7, and the execution result is sent to the alarm unit through the communication unit, and the alarm unit issues an alarm according to the execution result.

Images