CN111818548A

CN111818548A - Data processing method, device and equipment

Info

Publication number: CN111818548A
Application number: CN201910289568.2A
Authority: CN
Inventors: 张颖; 任元元; 刘先达; 纪迎; 林娜; 赵爽
Original assignee: China Mobile Communications Group Co Ltd; China Mobile Group Tianjin Co Ltd
Current assignee: China Mobile Communications Group Co Ltd; China Mobile Group Tianjin Co Ltd
Priority date: 2019-04-11
Filing date: 2019-04-11
Publication date: 2020-10-23
Anticipated expiration: 2039-04-11
Also published as: CN111818548B

Abstract

The embodiment of the invention discloses a data processing method, a device and equipment, wherein the method comprises the following steps: acquiring index data of a target service, and determining a correlation coefficient based on the index data; determining the type of the index according to the correlation coefficient; extracting target data matched with the index type from the index data, and determining an amplitude coefficient based on the target data; and determining a target early warning threshold of the target service according to the amplitude coefficient. By the method, the target early warning thresholds of different indexes in the target service can be timely adjusted according to the oscillation of the different indexes and the change of trend, the updating period of the target early warning thresholds is shortened, the problem of monitoring hysteresis is avoided, and the monitoring efficiency of the target service is improved.

Description

Data processing method, device and equipment

Technical Field

The present invention relates to the field of communications technologies, and in particular, to a method, an apparatus, and a device for processing data.

Background

With the continuous development of mobile communication networks, the number of users of the mobile communication networks is rapidly increased, and real-time performance monitoring needs to be performed on communication devices in the mobile communication networks in order to bring better use experience to the users of the mobile communication networks.

The current technology for real-time performance monitoring of a mobile communication network mainly adopts a technology of manually configuring a service available fixed threshold, real-time performance monitoring is carried out on index data by manually configuring the service available fixed threshold, and a large amount of index data needs to be manually configured with the available fixed threshold one by one, wherein the available fixed threshold is divided into a service available upper threshold and a service available lower threshold. If the index data is lower than the service available lower threshold value or higher than the service available lower threshold value, the monitoring system generates alarm information.

However, the above-mentioned method of manually configuring the service available fixed threshold value to configure the upper and lower threshold values of the index data has the following problems: due to the rapid increase of the mobile communication network service, the network operation and maintenance monitoring index data is also greatly increased, the cost of manually configuring the available fixed threshold of the service is high, the configuration efficiency is low, the updating period of the available fixed threshold of the manually configured service is long, the problem of monitoring delay is caused when the index data is monitored, and the monitoring effectiveness is poor.

Disclosure of Invention

Embodiments of the present invention provide a data processing method, apparatus, and device, so as to solve the problems of high labor cost, poor monitoring hysteresis, and poor monitoring effectiveness caused by a way of manually configuring a threshold in real-time performance monitoring of a mobile communication network in the prior art.

To solve the above technical problem, the embodiment of the present invention is implemented as follows:

in a first aspect, an embodiment of the present invention provides a data processing method, where the method includes:

acquiring index data of a target service, and determining a correlation coefficient based on the index data;

determining the type of the index according to the correlation coefficient;

extracting target data matched with the index type from the index data, and determining an amplitude coefficient based on the target data;

and determining a target early warning threshold of the target service according to the amplitude coefficient.

In a second aspect, an embodiment of the present invention provides an apparatus for processing data, where the apparatus includes:

the data acquisition module is used for acquiring index data of a target service and determining a correlation coefficient based on the index data;

the type determining module is used for determining the type of the index according to the correlation coefficient;

the data determination module is used for extracting target data matched with the index type from the index data and determining an amplitude coefficient based on the target data;

and the threshold determining module is used for determining a target early warning threshold of the target service according to the amplitude coefficient.

In a third aspect, an embodiment of the present invention provides an apparatus, including a processor, a memory, and a computer program stored on the memory and executable on the processor, where the computer program, when executed by the processor, implements the steps of the data processing method provided in the foregoing embodiments.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements the steps of the data processing method provided in the foregoing embodiment.

As can be seen from the above technical solutions provided by the embodiments of the present invention, in the embodiments of the present invention, index data of a target service is obtained, a correlation coefficient is determined based on the index data, then a belonging index type is determined according to the correlation coefficient, target data matched with the belonging index type is extracted from the index data, an amplitude coefficient is determined based on the target data, and finally a target early warning threshold of the target service is determined according to the amplitude coefficient. Target data is selected for the index data of different index types, so that target early warning thresholds of different indexes in the target service can be adjusted in time according to the oscillation and trend change of the different indexes, and the monitoring effectiveness is improved. Meanwhile, target data of the target service is automatically acquired to calculate the target early warning threshold of the target service, the updating period of the configuration threshold is shortened, the problem of monitoring hysteresis is avoided, the target early warning threshold of the target service does not need to be configured manually, and the labor cost is reduced.

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 introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.

FIG. 1 is a schematic flow chart of a data processing method according to the present invention;

FIG. 2 is a schematic flow chart of another data processing method according to the present invention;

FIG. 3 is a schematic diagram of monitoring abnormal conditions of switching to power based on a target early warning threshold according to the present invention;

FIG. 4 is a schematic diagram of monitoring an update success rate based on a target early warning threshold before optimization according to the present invention;

FIG. 5 is a diagram illustrating monitoring of an update success rate based on an optimized target early warning threshold according to the present invention;

FIG. 6 is a flow chart illustrating a method for processing data according to another embodiment of the present invention;

FIG. 7 is a schematic diagram of a data processing apparatus according to the present invention;

fig. 8 is a schematic structural diagram of a data processing apparatus according to the present invention.

Detailed Description

The embodiment of the invention provides a data processing method, a data processing device and data processing equipment.

In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the drawings in the embodiment of the present invention, and it is obvious that the described embodiment is only a part of the embodiment of the present invention, and not all 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.

Example one

As shown in fig. 1, an execution main body of the method may be a server, where the server may be an independent server, or a server cluster composed of multiple servers, and the server may be a background server of a certain service (e.g., a performance index monitoring service for a communication network device). The method may specifically comprise the steps of:

in step S102, index data of the target service is acquired, and a correlation coefficient is determined based on the index data.

The target service may be a performance index monitoring service for a communication network device in the mobile communication network. The index data may be performance index data (such as a call completing rate of a switch) of the communication network device in the core network or the wireless network, or may be analysis data obtained from a database stored in the device or a database stored in the remote device, where the analysis data may be data analyzed and processed according to received original data when a fault occurs, for example, alarm data per unit time obtained according to analysis processing of the alarm data within a predetermined time period, complaint data per unit time obtained according to complaint data for the communication network device within the predetermined time period, and the like. The correlation coefficient may be data representing a degree of correlation between the index data and the time parameter.

In implementation, with the continuous development of the mobile communication network, the number of users of the mobile communication network is increased rapidly, and in order to bring better use experience to the users of the mobile communication network, real-time performance monitoring needs to be performed on communication devices in the mobile communication network. The current technology for real-time performance monitoring of a mobile communication network mainly adopts a technology of manually configuring a service available fixed threshold, real-time performance monitoring is carried out on index data by manually configuring the service available fixed threshold, and a large amount of index data needs to be manually configured with the available fixed threshold one by one, wherein the available fixed threshold is divided into a service available upper threshold and a service available lower threshold. If the index data is lower than the service available lower threshold value or higher than the service available lower threshold value, the monitoring system generates alarm information.

In addition, when the real-time performance monitoring is performed on the index data, a processing mode is provided, namely, a fixed fluctuation threshold technology is configured through manual experience, and the upper threshold and the lower threshold of the index data are determined so as to perform the real-time performance monitoring on the index data. Manually analyzing the trend of the performance indexes related to the alarm rule, then respectively configuring corresponding upper and lower threshold values for the indexes according to the characteristics of the vibration amplitude and the long-term change trend of the excavated different indexes, and if the index data is lower than the lower threshold value or higher than the upper threshold value, generating alarm information by the monitoring system. However, with the rapid increase of mobile communication network services, network operation and maintenance monitoring index data also greatly increases, and a manual experience configuration fixed fluctuation threshold technology also generates higher labor cost; secondly, the change of the network operation and maintenance monitoring index is fast, and the updating period of the fixed fluctuation threshold configured by manual experience is long, so that the real-time performance monitoring hysteresis is caused; finally, because the number of the network operation and maintenance monitoring indexes is large, the method of configuring the fixed fluctuation threshold through manual experience cannot adjust the configuration thresholds of different network operation and maintenance monitoring indexes in real time according to the characteristics of the different network operation and maintenance monitoring indexes, which may cause the problem of unreasonable threshold configuration of the network operation and maintenance monitoring indexes and also may cause poor effectiveness of real-time performance monitoring.

Therefore, another implementation scheme is provided in the embodiments of the present invention, which may specifically include the following:

index data of the target service within a predetermined time length may be obtained from a database stored in the device or from a database stored in the remote device through a Structured Query Language (SQL) statement, where the predetermined time length may be any time length, such as 60 days or 90 days. Besides the acquisition of the index data through the SQL, there may be various acquisition modes of the index data, which is not limited in the embodiment of the present invention.

After the index data is obtained, the index data may be subjected to data cleaning under a predetermined condition, for example, null values, 0 values, and data containing a predetermined character (e.g., "# dev0 |" character in the form file) in the index data may be culled so as not to affect subsequent processing of the target data. In addition, data satisfying a predetermined interference condition in the index data may be removed, for example, the predetermined interference condition may be: if the historical mean value is lower than the historical mean value, where the historical mean value may be the mean value of the index data of the target service within a predetermined time period, the data lower than the historical mean value in the index data may be removed, and the predetermined interference condition may be: and n% is lower than the historical mean value, wherein n can be any data smaller than a preset threshold value, for example, n can be any data larger than 0 and smaller than 20, and the utilization rate of the index data can be improved by performing data cleaning on the index data through the preset interference condition.

After the data of the index data are cleaned, the correlation coefficient of the index data can be calculated, and the correlation coefficients of different index data and time parameters can be calculated because different index data have different oscillation amplitudes and variation trends. For example, the target service has three different indexes (such as index 1, index 2, and index 3), and may respectively obtain index data corresponding to index 1, index 2, and index 3, and then calculate a correlation coefficient of each index according to the index data corresponding to each index, taking the calculation of the correlation coefficient of index 1 as an example, may obtain all index data of index 1 within 60 days, then perform data cleaning on the index data under a predetermined condition, and perform calculation of the correlation coefficient on the cleaned index data.

First, the average value of the index data of the index 1 for 60 days may be calculated, and then the index data may be classified according to the time period, for example, the index data of 60 days may be divided into 24 types according to the time period, and the average values of the 24 types of index data are respectively calculated, and finally, the degree of dispersion between the average value of the 24 types of index data and the average value of the total index data of 60 days is calculated as the correlation coefficient of the index 1, which is used to represent the degree of correlation of the index 1 with the time parameter. Wherein the correlation coefficient of index 1 can be calculated by the following formula:

where θ is a correlation coefficient, E (X)_j) Is the average value of the j-th index data,

is the mean of all index data for index 1 over 60 days. Wherein, E (X)_j) The calculation can be made by the following formula:

wherein n is the number of index data included in the j-th index data, X_i|T＝jIs the ith index data in the jth (i.e. the index data is the T-th) index data.

In addition, when calculating the correlation coefficient corresponding to the index data, besides the above-mentioned modes, there may be multiple calculation modes, and different calculation methods of the correlation coefficient may be selected according to different actual application scenarios, which is not limited in the embodiment of the present invention.

In step S104, the index type to which the index belongs is determined according to the correlation coefficient.

The index types to which the index data belongs may include a time strong correlation type and a time weak correlation type.

In implementation, after obtaining the correlation coefficient corresponding to the index data, the index type of the index data may be determined according to a relationship between the correlation coefficient and a predetermined correlation threshold. For example, if the correlation coefficient of the index data is greater than the predetermined correlation threshold, it may be determined that the index data belongs to a time-strong correlation type, that is, the correlation between the index data and the time parameter is strong, the index data may change periodically with the passage of time, and the index data may change greatly at different times; on the contrary, if the correlation coefficient of the index data is not greater than the predetermined correlation threshold, it may be determined that the index data belongs to a time weak correlation type, that is, the correlation between the index data and the time parameter is weak, and as time goes by, the index data does not change periodically, and the index data does not change greatly at different times.

Taking the example of calculating the correlation coefficient of the index 1 in step S102, when calculating the correlation coefficient, the index data of the index 1 is divided into 24 classes according to the time period, and if the calculated correlation coefficient of the index 1 is greater than a predetermined correlation threshold, it indicates that the correlation between the index 1 and the time parameter is strong, the index 1 belongs to a time-strong correlation type, and the index 1 changes greatly in number with the change of time within 24 hours.

In addition, a corresponding preset correlation threshold value can be selected according to the attributes of the target service or the attributes corresponding to different indexes in the target service, and the correlation coefficients of the preset correlation threshold value and different index data are compared to judge the index type of the index data. For example, there may be different predetermined association thresholds for different traffic types, for example, the predetermined association threshold may be 0.1 when the target traffic is a performance detection traffic with respect to a communication network device in the core network, and the predetermined association threshold may be 0.15 when the target traffic is a performance detection traffic with respect to a communication network device in the wireless network.

In step S106, target data matching the belonging index type is extracted from the index data, and an amplitude coefficient is determined based on the target data.

Wherein the amplitude coefficient may be used to characterize the vibration amplitude of the target data.

In implementation, after the indicator type to which the indicator data belongs is determined, target data matched with the indicator type may be acquired, for example, if the indicator data belongs to a type with strong time correlation, the indicator data indicates that the association between the indicator data and the time parameter is strong, that is, the target data related to the current time may be acquired, and if the current time is 4 months, 1 day, 12:00, the indicator data of 11:00 to 13:00 of each day in three months, 1 month, 3 months, and 31 days, may be acquired as the target data extracted from the indicator data. If the index data belongs to the time weak correlation type, the correlation between the index data and the time parameter is weak, and the index data cannot change greatly along with the time, and the index data in continuous time can be selected as the target data when the target data is selected.

After the target data in the index data is determined, the corresponding amplitude coefficient can be determined based on the target data, if the target service comprises a plurality of indexes, the target data can be selected for different indexes according to different types of the indexes, and then the amplitude coefficient corresponding to each index is calculated.

In step S108, a target early warning threshold of the target service is determined according to the amplitude coefficient.

The target early warning threshold may include a target early warning upper threshold and a target early warning lower threshold.

In implementation, the oscillation amplitude of the corresponding index data in the target service can be determined according to the amplitude coefficient, and corresponding target early warning thresholds can be set for the index data of different oscillation amplitudes according to different amplitude coefficients.

After the target early warning threshold is determined, the actual index data of the current index can be obtained, data screening of preset cleaning conditions (such as whether the index data is a 0 value, whether the index data is a null value, whether the preset cleaning conditions comprise preset characters and the like) is carried out on the index data, if the index data is subjected to data screening and meets the preset cleaning conditions, whether the index data meets the target early warning threshold can be judged, if the current index data exceeds the upper target early warning threshold or is lower than the lower target early warning threshold, warning information can be sent out, and abnormal fluctuation of the index data can be recorded to prompt that the target service is abnormal.

In addition, the trend curve of the index data in the target service and the trend curve of the target early warning threshold can be displayed through the dynamic graph, so that information such as times and frequency of the index data exceeding the target early warning threshold is displayed, and reference information is provided for maintenance personnel to maintain the target service.

The index data and the corresponding target early warning threshold can be stored, maintenance personnel can select the index data and the corresponding target early warning threshold according to the communication network equipment identification of the target service corresponding to the index data, and the selected data can be exported for the maintenance personnel to analyze and use.

The embodiment of the invention provides a data processing method, which comprises the steps of obtaining index data of a target service, determining a correlation coefficient based on the index data, determining an affiliated index type according to the correlation coefficient, extracting target data matched with the affiliated index type from the index data, determining an amplitude coefficient based on the target data, and finally determining a target early warning threshold of the target service according to the amplitude coefficient. Target data is selected for the index data of different index types, so that target early warning thresholds of different indexes in the target service can be adjusted in time according to the oscillation and trend change of the different indexes, and the monitoring effectiveness is improved. Meanwhile, target data of the target service is automatically acquired to calculate the target early warning threshold of the target service, the updating period of the configuration threshold is shortened, the problem of monitoring hysteresis is avoided, the target early warning threshold of the target service does not need to be configured manually, and the labor cost is reduced.

Example two

As shown in fig. 2, an execution main body of the method may be a server, where the server may be an independent server, or a server cluster composed of a plurality of servers, and the server may be a background server of a certain service (e.g., a performance index monitoring service for a communication network device). The method may specifically comprise the steps of:

in step S202, index data of the target service is acquired, and a correlation coefficient is determined based on the index data.

In step S204, the index type is determined according to the correlation coefficient.

For the specific processing procedures of the steps S202 to S204, reference may be made to relevant contents in the steps S102 to S104 in the first embodiment, and details are not repeated here.

If the index type to which the index data belongs is a time strong correlation type, step S206 is performed, and if the index type to which the index data belongs is a time weak correlation type, step S208 is performed.

In step S206, the matched target data is obtained based on the first selection rule corresponding to the strong time correlation type.

The first selection rule may be that target data of a predetermined time corresponding to the current time within a first predetermined time period is obtained from the index data, the predetermined time may be any granularity time related to the current time, for example, if the predetermined time may be the same determined time point as the current time, for example, the current time is 12:00, the predetermined time may also be 12:00, that is, the index data of 12:00 per day within 30 days may be obtained, and if the predetermined time is any time including the current time, the predetermined time may be 11:00-13: 00.

In implementation, if the target service is a service for performing real-time performance index monitoring on the communication network device 1 and the communication network device 2 in the core network, the obtained index data in the communication network device 1 includes index data of the index 1 and the index 2, and the obtained index data in the communication network device 2 includes index data of the index 1 and the index 3, a correlation coefficient of the index 1 and a correlation coefficient of the index 2 in the communication network device 1 may be respectively calculated, and the index types to which the index 1 and the index 2 belong in the communication network device 1 may be determined according to the corresponding correlation coefficients, and meanwhile, the correlation coefficients of the index 1 and the index 3 in the communication network device 2 and the corresponding index types may also be determined according to the index data in the communication network device 2.

If index 2 in the communication network device 1 and index 3 in the communication network device 2 are of the time strongly correlated type, the target data of index 2 and index 3 at a predetermined time corresponding to the current time within the first predetermined time period and the two communication network devices may be acquired, wherein, the relevance between the index data of the time strong correlation type and the time parameter is strong, the corresponding first predetermined time length may be shorter, such as 30 days or 15 days, taking the first predetermined time length as 30 days as an example, if the current time is 1 month, 31 days and 12:00, 1 month, 1 day to 1 month, 30 days corresponding to the index 2 in the communication network device 1 can be acquired, the index data of 11:00 to 13:00 (i.e. predetermined time) each day, the obtained index data is the target data of the index 2 in the communication network device 1, and the obtained target data of the index 2 in the communication network device 1 may be as follows:

where spe is target data of index 2 of the communication network device 1, x_m.nIndex data at the nth time of day m, d_mDay m, t_nAt the nth time, m in the target data spe corresponding to the indicator 2 of the communication network device 1 is 30, n is 11:00-13: the total amount of index data included in 00 at all times.

By analogy, the following data can be obtained from 1 month 1 day to 1 month 30 days, 11:00 to 13:00, index data corresponding to index 3 in the communication network device 2, as target data of index 3.

In step S208, the matched target data is obtained based on the second selection rule corresponding to the weak time correlation type.

The second selection rule may be to obtain target data within a second predetermined time period from the index data.

In implementation, if the index data belongs to a weak time correlation type, it indicates that the index has a weak relationship with the time parameter, and does not change by a large order of magnitude with the passage of time, so that the second predetermined time period may be short, for example, 10 days or 5 days, thereby ensuring that the extracted target data has a high reference value. All target data on the target service in the same communication network device within the second predetermined time period may be acquired, for example, in the above step S206, index 1 in communication network device 1 and index 1 in communication network device 2 are both of the type of weak time correlation, all index data on index 1 in communication network device 1 within the second predetermined time period may be acquired as target data on index 1 in communication network device 1, and all index data on index 1 in communication network device 2 within the second predetermined time period may be acquired as target data on index 1 in communication network device 2.

In step S210, the target data is substituted into the following formula to be calculated,

and obtaining the amplitude coefficient corresponding to the target data.

Where η is the amplitude coefficient, n is the total number of the target data, X_iIs the ith target data.

In step S212, it is determined whether the amplitude coefficient is greater than a predetermined amplitude threshold.

In an implementation, after obtaining the amplitude coefficient of the target data, the amplitude coefficient may be compared to a predetermined amplitude threshold. The predetermined amplitude threshold may be 3%, that is, whether the amplitude coefficient of the target data is greater than 3 times the amplitude range is determined.

The result of empirical analysis on the index data shows that 64.21% of normal data in the index data fluctuate within a 1-time amplitude range, 89.37% of normal data fluctuate within a 2-time amplitude range, 99.12% of normal data fluctuate within a 3-time amplitude range, if a preset amplitude threshold value is smaller than 1, the service requirement of a target service cannot be met, and if the preset amplitude threshold value is larger than 3, the fluctuation of the index data cannot be accurately judged, so that 3 η can be used as a monitoring multiple, when the index fluctuation is extremely small, namely 3 η is smaller than 10%, and η is smaller than 3.5%, the fluctuation threshold range calculated by 3-time amplitude is too narrow, and the monitoring requirement of the operation and maintenance of the communication industry is not met, and therefore, the preset amplitude threshold value can be set to be 3.5%.

The method for determining the predetermined amplitude threshold is an optional and realizable determination method, and in an actual application scenario, there may be a plurality of different determination methods, which is not limited in the embodiment of the present invention.

After step S210 is performed, the amplitude coefficient of the target data may be obtained, and then the amplitude coefficient of the target data may be compared with a predetermined amplitude threshold, step S212 is performed, and step S214 is performed.

In step S214, if the amplitude coefficient of the target data is greater than the predetermined amplitude threshold, a target warning threshold of the target service is calculated based on a predetermined first calculation coefficient.

Wherein the first calculation coefficient may be any value greater than 1.

In implementation, since the amplitude coefficient of the target data is already greater than the predetermined amplitude threshold, indicating that the amplitude range of the target data meets the service requirement of the target service, the first calculation coefficient may be any data greater than 1, and when calculating the target early warning threshold of the target service, the target data and the first calculation coefficient may be substituted into the following formula for calculation,

obtaining a target early warning upper threshold of the target service, wherein uplimit is the target early warning upper threshold of the target service, n is the total amount of target data, and X is_iFor the ith item of target data, the data is,

the coefficient is calculated for the first.

While the target data and the first calculation coefficient may be substituted into the following formula for calculation,

and obtaining a target early warning lower threshold of the target service, wherein the downlink limit is the target early warning lower threshold of the target service.

Based on the above scheme, when the first calculation coefficient is 3, calculating a target early warning upper threshold and a target early warning lower threshold of a target service, performing empirical analysis on a switching success rate (i.e. index data) in a communication network device of the target service, and obtaining an available threshold of a manual configuration service and a fixed fluctuation threshold of manual experience configuration for the switching success rate of the communication network device, and the target early warning threshold of the switching success rate calculated based on the scheme of the present invention, the result is shown in fig. 3, and abnormal conditions that the switching success rate (i.e. index data) cannot be monitored based on the available threshold of the manual configuration service and the fixed fluctuation threshold of the manual experience configuration (i.e. the fixed fluctuation threshold of the manual experience) can be detected in time according to the scheme of the present invention, and can be changed along with oscillation or trend of the index data, and automatically adjusting the target early warning threshold.

In step S216, if the amplitude coefficient of the target data is not greater than the predetermined amplitude threshold, a target warning threshold of the target service is calculated based on a predetermined second calculation coefficient.

In practice, the target data and the second calculation coefficient may be substituted into the following formula for calculation,

obtaining a target early warning upper threshold of the target service, wherein beta is a second calculation coefficient;

the target data and the second calculation coefficient are substituted into the following formula to be calculated,

and obtaining a target early warning lower threshold of the target service.

When the amplitude coefficient of the target data is not greater than the predetermined amplitude threshold, the range of the fluctuation threshold is too small due to too small amplitude coefficient, and a false alarm condition is generated, so when the amplitude coefficient is not greater than the predetermined amplitude threshold, the target early warning threshold can be adjusted through a second calculation coefficient, wherein the second calculation coefficient can be any data which is greater than 0 and less than 1, and different values can be selected according to different practical application scenarios.

As shown in fig. 4, taking the index data of the update success rate of the tracking area in the LTE system in the target service as an example, if the target early warning threshold is not properly adjusted according to the magnitude of the amplitude coefficient, when the amplitude coefficient is smaller than the predetermined amplitude threshold, the target early warning threshold cannot be correspondingly changed according to the change of the amplitude coefficient, and a false alarm situation occurs. As shown in fig. 5, according to the scheme, when the target early warning threshold corresponding to the index data is calculated, the early warning threshold can be adjusted in time according to the amplitude coefficient, so that the occurrence of false alarm caused by the inadaptation of the target early warning threshold is effectively avoided.

In step S218, according to the target early warning threshold, the index data of the target service at the current time is monitored to determine whether the target service is abnormal.

In step S220, if the target service is abnormal, alarm information is output according to a predetermined alarm manner.

The preset alarm mode comprises one or more of a mode of sending preset alarm information to a preset communication account, a mode of sending the preset alarm information to appointed display equipment and a mode of dispatching an electronic work order.

In implementation, if there is index data exceeding the corresponding upper target early warning threshold or being lower than the lower target early warning threshold in the target service at the current moment, the device may acquire a stored predetermined communication account, and send predetermined warning information (such as a predetermined warning short message) to the predetermined communication account to notify a maintenance person to process the target service. Or the equipment can display the preset alarm information on the appointed display equipment (such as an alarm display board and the like), and can also send an electronic work order to preset workers and the like.

In step S222, the number of times that the index data of the target service exceeds the target early warning threshold within the predetermined time is obtained.

In step S224, if the number of times of exceeding the target early warning threshold is greater than the predetermined detection threshold, a maintenance notification related to the target service is issued.

EXAMPLE III

As shown in fig. 6, an execution main body of the method may be a server, where the server may be an independent server, or a server cluster composed of multiple servers, and the server may be a background server of a certain service (e.g., a performance index monitoring service for a communication network device). The method may specifically comprise the steps of:

in step S602, index data of the target service is acquired, and a correlation coefficient is determined based on the index data.

In step S604, the index type is determined according to the correlation coefficient.

In step S606, target data matching the belonging index type is extracted from the index data, and an amplitude coefficient is determined based on the target data.

For the specific processing procedures of the steps S602 to S606, reference may be made to relevant contents in the steps S102 to S106 in the first embodiment, and details are not repeated here.

In step S608, a first warning threshold of the target service is determined according to the amplitude coefficient.

In implementation, the method for determining the first early warning threshold of the target service may refer to the method for determining the target early warning threshold in steps S212 to S216 in embodiment two, and details are not repeated here.

In step S610, a target early warning threshold of the target service is determined according to a predetermined early warning threshold and the first early warning threshold of the target service.

In implementation, the first early warning upper threshold and the predetermined early warning upper threshold may be compared, and the smallest value is taken as the target early warning upper threshold in the target early warning thresholds, and the first early warning lower threshold and the predetermined early warning lower threshold may be compared, and the largest value is taken as the target early warning lower threshold in the target early warning thresholds.

Before comparison, updating detection can be performed on the preset early warning threshold, that is, whether an updated preset early warning threshold exists is detected, if the updated preset early warning threshold exists, validity detection needs to be performed on the updated preset early warning threshold, if the updated preset early warning threshold exists, the updated preset early warning threshold is written into the database, the preset early warning threshold is updated, and after the updating is completed, the preset early warning threshold is compared with the first early warning threshold, and the target early warning threshold of the target service is finally determined, wherein the updated preset early warning threshold can only contain the updated preset early warning upper threshold or only contain the updated preset early warning lower threshold, and can also contain the updated preset early warning upper threshold and the updated preset early warning lower threshold.

In step S612, according to the target early warning threshold, the index data of the target service at the current time is monitored to determine whether the target service is abnormal.

In step S614, if the target service is abnormal, alarm information is output according to a predetermined alarm manner.

In step S616, the number of times that the index data of the target service exceeds the target early warning threshold within the predetermined time is obtained.

In step S618, if the number of times of exceeding the target warning threshold is greater than the predetermined detection threshold, a maintenance notification related to the target service is issued.

For the specific processing procedure of the steps S612 to S618, reference may be made to the relevant contents in the steps S218 to S224 in the second embodiment, and details are not repeated here.

Example four

Based on the same idea, the foregoing data processing method provided in the embodiment of the present invention further provides a data processing apparatus, as shown in fig. 7.

The data processing device comprises: a data obtaining module 701, a type determining module 702, a data determining module 703 and a threshold determining module 704, wherein:

a data obtaining module 701, configured to obtain index data of a target service, and determine a correlation coefficient based on the index data;

a type determining module 702, configured to determine the type of the indicator according to the correlation coefficient;

a data determining module 703, configured to extract target data matching the indicator type from the indicator data, and determine an amplitude coefficient based on the target data;

a threshold determining module 704, configured to determine a target early warning threshold of the target service according to the amplitude coefficient.

In the embodiment of the invention, the target early warning threshold comprises a target early warning upper threshold and a target early warning lower threshold;

the threshold determining module 704 includes:

a first threshold determining unit, configured to determine a first upper warning threshold and a first lower warning threshold of the target service according to the amplitude coefficient;

the upper threshold determining unit is used for comparing the first early warning upper threshold with a preset early warning upper threshold and taking the minimum value as a target early warning upper threshold;

and the lower threshold determining unit is used for comparing the first early warning lower threshold with a preset early warning lower threshold and taking the value with the maximum value as a target early warning lower threshold.

In the embodiment of the invention, the index types comprise a time strong correlation type and a time weak correlation type;

the data determining module 703 includes:

the first obtaining unit is used for obtaining matched target data based on a first selection rule if the type of the target data belongs to is a time strong correlation type, wherein the first selection rule is used for obtaining the target data of a preset time corresponding to the current time within a first preset time length from the index data;

and the second acquisition unit is used for acquiring matched target data based on a second selection rule if the type of the target data belongs to the weak time correlation type, wherein the second selection rule is used for acquiring the target data within a second preset time length from the index data.

In this embodiment of the present invention, the data determining module 703 is configured to:

the target data is substituted into the following formula to be calculated,

obtaining an amplitude coefficient corresponding to the target data, wherein eta is the amplitude coefficient, n is the total number of the target data, and X_iIs the ith target data.

the threshold determining module 704 includes:

a judging unit for determining whether the amplitude coefficient is greater than a predetermined amplitude threshold value;

a first calculation unit for substituting the target data and a first calculation coefficient into the following formula to perform calculation if the amplitude coefficient is larger than a predetermined amplitude threshold value,

obtaining a target early warning upper threshold of the target service, wherein the up lim it is the target early warning upper threshold of the target service, n is the total amount of the target data, and X is_iFor the ith item of target data, the data is,

calculating a coefficient for the first;

a second calculation unit for substituting the target data and the first calculation coefficient into the following formula to perform calculation,

and obtaining a target early warning lower threshold of the target service, wherein the downtit is the target early warning lower threshold of the target service.

In an embodiment of the present invention, the apparatus further includes:

a first calculation module for substituting the target data and a second calculation coefficient into the following formula to calculate if the amplitude coefficient is not greater than a predetermined amplitude threshold,

obtaining a target early warning upper threshold of the target service, wherein beta is the second calculation coefficient;

a second calculation module for substituting the target data and the second calculation coefficient into the following formula for calculation,

and obtaining a target early warning lower threshold of the target service.

In an embodiment of the present invention, the apparatus further includes:

the frequency acquisition module is used for acquiring the frequency that the index data of the target service exceeds the target early warning threshold within a preset time length;

the warning module is used for sending out a maintenance notice related to the target service if the times of exceeding the target early warning threshold are larger than a preset detection threshold, or outputting warning information according to a preset warning mode;

The embodiment of the invention provides a data processing device, which is used for determining a correlation coefficient based on index data by acquiring the index data of a target service, then determining the affiliated index type according to the correlation coefficient, extracting the target data matched with the affiliated index type from the index data, determining an amplitude coefficient based on the target data, and finally determining a target early warning threshold of the target service according to the amplitude coefficient. Target data is selected for the index data of different index types, so that target early warning thresholds of different indexes in the target service can be adjusted in time according to the oscillation and trend change of the different indexes, and the monitoring effectiveness is improved. Meanwhile, target data of the target service is automatically acquired to calculate the target early warning threshold of the target service, the updating period of the configuration threshold is shortened, the problem of monitoring hysteresis is avoided, the target early warning threshold of the target service does not need to be configured manually, and the labor cost is reduced.

EXAMPLE five

Figure 8 is a hardware block diagram of an apparatus implementing various embodiments of the invention,

the apparatus 800 includes, but is not limited to: a radio frequency unit 801, a network module 802, an audio output unit 803, an input unit 804, a sensor 805, a display unit 806, a user input unit 807, an interface unit 808, a memory 809, a processor 810, and a power supply 811. Those skilled in the art will appreciate that the configuration of the device shown in fig. 8 does not constitute a limitation of the device, and that the device may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components. In the embodiment of the present invention, the device includes, but is not limited to, a mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle-mounted terminal, a wearable device, a pedometer, and the like.

The processor 810 is configured to obtain index data of a target service, and determine a correlation coefficient based on the index data;

the processor 810 is further configured to determine the type of the indicator according to the correlation coefficient;

the processor 810 is further used for extracting target data matched with the type of the index from the index data and determining an amplitude coefficient based on the target data;

in addition, the processor 810 is further configured to determine a target early warning threshold of the target service according to the amplitude coefficient.

In addition, the target early warning threshold comprises a target early warning upper threshold and a target early warning lower threshold; the processor 810 is further configured to determine a first upper warning threshold and a first lower warning threshold of the target service according to the amplitude coefficient;

in addition, the processor 810 is further configured to compare the first early warning upper threshold with a predetermined early warning upper threshold, and use the minimum value as a target early warning upper threshold;

in addition, the processor 810 is further configured to compare the first early warning lower threshold with a predetermined early warning lower threshold, and use the maximum value as a target early warning lower threshold.

Further, the index types include a time strong correlation type and a time weak correlation type.

In addition, the processor 810 is further configured to, if the type to which the target data belongs is a time-strong correlation type, obtain the matched target data based on a first selection rule, where the first selection rule is to obtain the target data at a predetermined time corresponding to the current time within a first predetermined time period from the index data;

in addition, the processor 810 is further configured to obtain the matched target data based on a second selection rule if the type is a weak time-related type, where the second selection rule is to obtain the target data within a second predetermined time period from the index data

The processor 810 is further configured to substitute the target data into the following formula for calculation,

Additionally, the processor 810 is further configured to determine whether the amplitude coefficient is greater than a predetermined amplitude threshold;

in addition, the target early warning threshold comprises a target early warning upper threshold and a target early warning lower threshold; the processor 810 is further configured to calculate by substituting the target data and a first calculation coefficient into the following equation if the amplitude coefficient is greater than a predetermined amplitude threshold,

obtaining a target early warning upper threshold of the target service, wherein uplimit is the target early warning upper threshold of the target service, n is the total amount of the target data, and X is_iFor the ith item of target data, the data is,

calculating a coefficient for the first;

substituting the target data and the first calculation coefficient into the following formula to calculate,

and obtaining a target early warning lower threshold of the target service, wherein the target early warning lower threshold is the target early warning lower threshold of the target service.

In addition, the processor 810 is further configured to calculate the target data and a second calculation coefficient by substituting the target data and the second calculation coefficient into the following formula if the amplitude coefficient is not greater than the predetermined amplitude threshold,

substituting the target data and the second calculation coefficient into the following formula to calculate,

and obtaining a target early warning lower threshold of the target service.

In addition, the processor 810 is further configured to obtain the number of times that the index data of the target service exceeds the target early warning threshold within a predetermined time period;

in addition, the processor 810 is further configured to send a maintenance notification related to the target service if the number of times of exceeding the target early warning threshold is greater than a predetermined detection threshold, or output warning information according to a predetermined warning manner;

The embodiment of the invention provides equipment, which is characterized in that index data of a target service are obtained, a correlation coefficient is determined based on the index data, an affiliated index type is determined according to the correlation coefficient, the target data matched with the affiliated index type is extracted from the index data, an amplitude coefficient is determined based on the target data, and a target early warning threshold of the target service is determined according to the amplitude coefficient. Target data is selected for the index data of different index types, so that target early warning thresholds of different indexes in the target service can be adjusted in time according to the oscillation and trend change of the different indexes, and the monitoring effectiveness is improved. Meanwhile, target data of the target service is automatically acquired to calculate the target early warning threshold of the target service, the updating period of the configuration threshold is shortened, the problem of monitoring hysteresis is avoided, the target early warning threshold of the target service does not need to be configured manually, and the labor cost is reduced.

It should be understood that, in the embodiment of the present invention, the radio frequency unit 801 may be used for receiving and sending signals during a message sending and receiving process or a call process, and specifically, receives downlink data from a base station and then processes the received downlink data to the processor 810; in addition, the uplink data is transmitted to the base station. In general, radio frequency unit 801 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like. Further, the radio frequency unit 801 can also communicate with a network and other devices through a wireless communication system.

The device provides wireless broadband internet access to the user through the network module 802, such as to assist the user in sending and receiving e-mails, browsing web pages, and accessing streaming media.

The audio output unit 803 may convert audio data received by the radio frequency unit 801 or the network module 802 or stored in the memory 809 into an audio signal and output as sound. Also, the audio output unit 803 may also provide audio output related to a specific function performed by the apparatus 800 (e.g., a call signal reception sound, a message reception sound, etc.). The audio output unit 803 includes a speaker, a buzzer, a receiver, and the like.

The input unit 804 is used for receiving an audio or video signal. The input Unit 804 may include a Graphics Processing Unit (GPU) 8041 and a microphone 8042, and the Graphics processor 8041 processes image data of a still picture or video obtained by an image capturing device (such as a camera) in a video capturing mode or an image capturing mode. The processed image frames may be displayed on the display unit 806. The image frames processed by the graphics processor 8041 may be stored in the memory 809 (or other storage medium) or transmitted via the radio frequency unit 801 or the network module 802. The microphone 8042 can receive sound, and can process such sound into audio data. The processed audio data may be converted into a format output transmittable to a mobile communication base station via the radio frequency unit 801 in case of a phone call mode.

The device 800 also includes at least one sensor 805, such as light sensors, motion sensors, and other sensors. Specifically, the light sensor includes an ambient light sensor that can adjust the brightness of the display panel 8061 according to the brightness of ambient light, and a proximity sensor that can turn off the display panel 8061 and/or the backlight when the device 800 is moved to the ear. As one type of motion sensor, an accelerometer sensor can detect the magnitude of acceleration in each direction (generally three axes), detect the magnitude and direction of gravity when stationary, and can be used to identify the device attitude (such as horizontal and vertical screen switching, related games, magnetometer attitude calibration), vibration identification related functions (such as pedometer, tapping), and the like; the sensors 805 may also include fingerprint sensors, pressure sensors, iris sensors, molecular sensors, gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., which are not described in detail herein.

The display unit 806 is used to display information input by the user or information provided to the user. The Display unit 806 may include a Display panel 8061, and the Display panel 8061 may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like.

The user input unit 807 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the apparatus. Specifically, the user input unit 807 includes a touch panel 8071 and other input devices 8072. The touch panel 8071, also referred to as a touch screen, may collect touch operations by a user on or near the touch panel 8071 (e.g., operations by a user on or near the touch panel 8071 using a finger, a stylus, or any other suitable object or accessory). The touch panel 8071 may include two portions of a touch detection device and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts the touch information into touch point coordinates, sends the touch point coordinates to the processor 810, receives a command from the processor 810, and executes the command. In addition, the touch panel 8071 can be implemented by various types such as a resistive type, a capacitive type, an infrared ray, and a surface acoustic wave. In addition to the touch panel 8071, the user input unit 807 can include other input devices 8072. In particular, other input devices 8072 may include, but are not limited to, a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which are not described in detail herein.

Further, the touch panel 8071 can be overlaid on the display panel 8061, and when the touch panel 8071 detects a touch operation on or near the touch panel 8071, the touch operation is transmitted to the processor 810 to determine the type of the touch event, and then the processor 810 provides a corresponding visual output on the display panel 8061 according to the type of the touch event. Although in fig. 8, the touch panel 8071 and the display panel 8061 are two independent components to implement the input and output functions of the device, in some embodiments, the touch panel 8071 and the display panel 8061 may be integrated to implement the input and output functions of the device, which is not limited herein.

The interface unit 808 is an interface for connecting an external device to the apparatus 800. For example, the external device may include a wired or wireless headset port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device having an identification module, an audio input/output (I/O) port, a video I/O port, an earphone port, and the like. The interface unit 808 may be used to receive input (e.g., data information, power, etc.) from external devices and transmit the received input to one or more elements within the apparatus 800 or may be used to transmit data between the apparatus 800 and external devices.

The memory 809 may be used to store software programs as well as various data. The memory 809 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. Further, the memory 409 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.

The processor 810 is the control center of the device, connects various parts of the entire device using various interfaces and lines, performs various functions of the device and processes data by running or executing software programs and/or modules stored in the memory 809 and calling data stored in the memory 809, thereby monitoring the device as a whole. Processor 810 may include one or more processing units; preferably, the processor 810 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into processor 810.

The device 800 may also include a power supply 811 (e.g., a battery) for powering the various components, and preferably the power supply 811 may be logically coupled to the processor 810 via a power management system to manage charging, discharging, and power consumption management functions via the power management system.

Preferably, an embodiment of the present invention further provides an apparatus, including a processor 810, a memory 809, and a computer program stored in the memory 809 and capable of running on the processor 810, where the computer program, when executed by the processor 810, implements each process of the foregoing data processing method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not described here again.

EXAMPLE six

The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the data processing method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here. The computer-readable storage medium may be a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.

The embodiment of the invention provides a computer-readable storage medium, which is characterized in that index data of a target service are obtained, a correlation coefficient is determined based on the index data, an affiliated index type is determined according to the correlation coefficient, the target data matched with the affiliated index type are extracted from the index data, an amplitude coefficient is determined based on the target data, and a target early warning threshold of the target service is determined according to the amplitude coefficient. Target data is selected for the index data of different index types, so that target early warning thresholds of different indexes in the target service can be adjusted in time according to the oscillation and trend change of the different indexes, and the monitoring effectiveness is improved. Meanwhile, target data of the target service is automatically acquired to calculate the target early warning threshold of the target service, the updating period of the configuration threshold is shortened, the problem of monitoring hysteresis is avoided, the target early warning threshold of the target service does not need to be configured manually, and the labor cost is reduced.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The above description is only an example of the present invention, and is not intended to limit the present invention. Various modifications and alterations to this invention will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A method of processing data, the method comprising:

determining the type of the index according to the correlation coefficient;

2. The method of claim 1, wherein the target early warning threshold comprises a target early warning upper threshold and a target early warning lower threshold;

the determining a target early warning threshold of the target service according to the amplitude coefficient includes:

determining a first early warning upper threshold and a first early warning lower threshold of the target service according to the amplitude coefficient;

comparing the first early warning upper threshold with a preset early warning upper threshold, and taking the minimum value as a target early warning upper threshold;

and comparing the first early warning lower threshold with a preset early warning lower threshold, and taking the value with the maximum value as a target early warning lower threshold.

3. The method of claim 1, wherein the index types include a temporal strong correlation type and a temporal weak correlation type;

the extracting of the target data matched with the index type from the index data comprises:

if the type is a time strong correlation type, acquiring matched target data based on a first selection rule, wherein the first selection rule is to acquire the target data of a preset time corresponding to the current time within a first preset time length from the index data;

and if the type is a time weak correlation type, acquiring matched target data based on a second selection rule, wherein the second selection rule is used for acquiring the target data within a second preset time length from the index data.

4. The method of claim 1, wherein determining an amplitude coefficient based on the target data comprises:

the target data is substituted into the following formula to be calculated,

5. The method of claim 1, wherein the target early warning threshold comprises a target early warning upper threshold and a target early warning lower threshold;

determining whether the amplitude coefficient is greater than a predetermined amplitude threshold;

if the amplitude coefficient is larger than a predetermined amplitude threshold value, the target data and a first calculation coefficient are substituted into the following formula for calculation,

calculating a coefficient for the first;

and obtaining a target early warning lower threshold of the target service, wherein the down lim it is the target early warning lower threshold of the target service.

6. The method of claim 5, wherein after determining whether the amplitude coefficient is greater than a predetermined amplitude threshold, further comprising:

if the amplitude coefficient is not greater than a predetermined amplitude threshold value, the target data and a second calculation coefficient are substituted into the following formula for calculation,

and obtaining a target early warning lower threshold of the target service.

7. The method according to any of claims 1-6, further comprising:

acquiring the times that index data of the target service exceeds the target early warning threshold within a preset time;

if the times of exceeding the target early warning threshold are larger than a preset detection threshold, sending a maintenance notice related to the target service, or outputting alarm information according to a preset alarm mode;

8. An apparatus for processing data, the apparatus comprising:

9. An apparatus comprising a processor, a memory and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of a method of processing data according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the method of processing data according to any one of claims 1 to 7.