CN114286370B - Method and device for determining influence of base station alarm on user perception service - Google Patents

Abstract

The embodiment of the invention provides a method and a device for determining influence of base station alarm on user perceived business, in the embodiment of the method, base station alarm data are acquired, based on a base station alarm on user perceived business influence probability reference table, the probability value of influence of base station alarm types corresponding to the base station alarm data on each business type is determined through the base station alarm on user perceived business influence probability reference table, the probability value is determined based on the number of time periods included in a preset duration and the correlation calculation result of each base station alarm type and corresponding target user perceived KPI indexes in each time period, the business types and influence probabilities of base station alarm influence can be accurately positioned, and the target user perceived KPI indexes corresponding to each base station alarm type are one or more of primary user perceived KPI indexes, so that the workload of data processing is reduced.

Description

Method and device for determining the impact of base station alarms on user-perceived services

technical field

The present invention relates to the field of wireless communication, in particular to a method and a device for determining the influence of base station alarms on user perceived services.

Background technique

The base station is the basic unit of the cellular network. The stability and reliability of its operation are directly related to the quality of the wireless network and user perception. Alarms are the most intuitive data reflecting the stability of the base station. The existing methods for calculating the relationship between base station alarms and user perception are mainly It is judged through experience, and whether it affects user perception is determined through the alarm information and the main equipment manufacturer's judgment on whether it affects the business or not. The existing evaluation methods have the following two problems:

1. Evaluation methods are not comprehensive and accurate enough

Existing evaluation methods mainly obtain base station alarm information, and correspond to alarm causes, alarm levels, and KPI (Key Performance Indicator, Key Performance Indicator) indicators when alarms occur, but cannot find the specific relationship between alarms and service types. Therefore, it is also impossible to evaluate which type of business is affected when an alarm occurs in the base station. The related results are not comprehensive and accurate enough to reflect the real situation, and it is difficult to locate accurately.

2. Huge workload

Existing evaluation methods mainly process multi-dimensional data manually, and obtain results through data association. Due to the large number of data sources, the workload of data processing and screening is large, time-consuming and labor-intensive.

Contents of the invention

Embodiments of the present invention provide a method and device for determining the impact of base station alarms on user-perceived services, which are used to solve the problems of insufficient comprehensiveness and accuracy of existing technical results, inability to reflect real conditions, difficulty in accurate positioning, and heavy workload.

In the first aspect, an embodiment of the present invention provides a method for determining the impact of a base station alarm on a service perceived by a user, including:

Obtain base station alarm data;

Based on the base station alarm impact probability reference table on user perception services, determine the probability value of the impact of the base station alarm type corresponding to the base station alarm data on each service type;

Wherein, the base station alarm impact probability reference table on user perception service includes the probability value of the influence of each base station alarm type on each of the service types, each of the service types is represented by a plurality of primary user perception KPI indicators, and the probability The value is determined based on the number of time periods included in a preset duration and the correlation calculation results between each base station alarm type and the corresponding target user perception KPI index in each said time period, and the corresponding base station alarm type The target user perception KPI indicators are one or more of the primary user perception KPI indicators.

Optionally, in the method for determining the impact of base station alarms on user perceived services according to an embodiment of the present invention, the probability value is based on the number of time periods included in a preset duration and the number of time periods that each base station alarms within each time period. The type is determined by the correlation calculation results of the corresponding target user perception KPI indicators, including:

In each of the time periods, if any one of the target user perception KPI indicators included in each of the service types is strongly correlated with the correlation calculation result of the base station alarm type, then the base station alarm type has a strong correlation with the base station alarm type. Add 1 to the numerator of the probability value of the impact of the service type; the denominator of the probability value is the number of the time period;

The correlation calculation result of each base station alarm type and the corresponding target user perception KPI index is obtained based on the correlation coefficient between each base station alarm type and the corresponding target user perception KPI index; when the absolute value of the correlation coefficient is greater than When the threshold is preset, the correlation calculation result is strong correlation.

Optionally, according to the method for determining the impact of base station alarms on user perception services according to an embodiment of the present invention, the correlation coefficient between each base station alarm type and the corresponding target user perception KPI index is based on each base station alarm type and the corresponding target The user perception KPI index is obtained by Pearson correlation analysis.

Optionally, according to the method for determining the impact of base station alarms on user-perceived services according to an embodiment of the present invention, the method further includes:

Determine the correlation calculation results of each base station alarm type and each of the multiple primary user perception KPI indicators, and filter out a plurality of target user perception KPI indicators corresponding to each base station alarm type based on the correlation calculation results; the target The correlation calculation result of the user perception KPI index and the alarm type of the base station is a strong correlation;

Classify the multiple primary user perception KPI indicators to determine multiple service types, and each service type is represented by multiple primary user perception KPI indicators.

Optionally, according to the method for determining the impact of base station alarms on user-perceived services according to an embodiment of the present invention, the multiple primary user-perceived KPI indicators are based on network management KPI indicators and SOC (Service Operations Center, business operation center) perception indicators definite.

Optionally, according to the method for determining the impact of base station alarms on user-perceived services according to an embodiment of the present invention, the service types include: Internet-aware class I, Internet-aware class II, voice-aware class I, and voice-aware class II;

The user-perceived KPI index corresponding to the Internet perception class 1 includes: application store download rate, video download average rate and video playback success rate;

The user perception KPI index corresponding to the Internet perception class II includes: HTTP (HyperText Transfer Protocol, hypertext transfer protocol) response success rate, small packet uplink average time delay and small packet downlink average time delay;

The user perception KPI index corresponding to the voice perception class 1 includes: VOLTE (Voice over Long-Term Evolution, long-term evolution voice bearer) connection rate, VOLTE call drop rate and call setup average delay;

The user perception KPI index corresponding to the voice perception class II includes: an uplink average MOS (Mean OpinionScore, mean opinion value), and a downlink average MOS.

In the second aspect, the embodiment of the present invention also provides a device for determining the impact of base station alarms on user perceived services, including:

A base station alarm data acquisition module, configured to acquire base station alarm data;

A module for determining the impact of base station alarms on user-perceived services, configured to determine the probability value that the base station alarm type corresponding to the base station alarm data has an impact on each service type based on the reference table of the impact probability of base station alarms on user-perceived services;

Wherein, the base station alarm impact probability reference table on user perception service includes the probability value of the influence of each base station alarm type on each of the service types, each of the service types is represented by a plurality of primary user perception KPI indicators, and the probability The value is determined based on the number of time periods included in a preset duration and the correlation calculation results between each base station alarm type and the corresponding target user perception KPI index in each said time period, and the corresponding base station alarm type The target user perception KPI indicators are one or more of the primary user perception KPI indicators.

Optionally, according to the device for determining the impact of base station alarms on user perceived services according to an embodiment of the present invention, the probability value is based on the number of time periods included in a preset duration and the number of time periods in which each base station alarms within each time period. The type is determined by the correlation calculation results of the corresponding target user perception KPI indicators, including:

In each of the time periods, if any one of the target user perception KPI indicators included in each of the service types is strongly correlated with the correlation calculation result of the base station alarm type, then the base station alarm type has a strong correlation with the base station alarm type. Add 1 to the numerator of the probability value of the impact of the service type; the denominator of the probability value is the number of the time period;

The correlation calculation result of each base station alarm type and the corresponding target user perception KPI index is obtained based on the correlation coefficient between each base station alarm type and the corresponding target user perception KPI index; when the absolute value of the correlation coefficient is greater than When the threshold is preset, the correlation calculation result is strong correlation.

In the third aspect, the embodiment of the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the program, the above-mentioned first The steps of the method provided by the aspect.

In a fourth aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method provided in the above-mentioned first aspect are implemented.

The method and device for determining the impact of base station alarms on user-perceived services provided by the embodiments of the present invention determine the impact of the base station alarm type corresponding to the base station alarm data on each service type based on the reference table of the impact probability of base station alarms on user-perceived services Probability value, wherein, each of the service types is characterized by a plurality of primary user perception KPI indicators, and the probability value is based on the number of time periods included in a preset duration and the alarm types of each base station in each of the time periods Determined by the correlation calculation results with the corresponding target user perception KPI indicators, it is possible to accurately locate the service type and impact probability affected by base station alarms, and facilitate targeted formulation of equipment maintenance plans. The target user perception KPI indicators corresponding to each base station alarm type Perceiving one or more of the KPI indicators for the primary user can reduce the workload of data processing.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

FIG. 1 is a schematic flowchart of a method for determining the impact of a base station alarm on a user-perceived service provided by an embodiment of the present invention;

FIG. 2 is a schematic structural diagram of an apparatus for determining the impact of a base station alarm on a user-perceived service provided by an embodiment of the present invention;

Fig. 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention.

Detailed ways

In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

The existing technology cannot evaluate which type of business is affected when an alarm occurs in the base station, and the associated results are not comprehensive and accurate enough to reflect the real situation, making it difficult to locate accurately. At the same time, due to the large number of data sources, the workload of data processing and screening is heavy Time-consuming and labor-intensive, for this, embodiments of the present invention provide a method for determining the impact of base station alarms on user-perceived services. Fig. 1 is a schematic flowchart of a method for determining the impact of a base station alarm on user-perceived services provided by an embodiment of the present invention. As shown in Fig. 1 , the method includes:

Step 110, acquiring base station alarm data.

Specifically, base station alarm data is the most intuitive data that reflects the stability of the base station. Analyzing the impact of base station alarms on user-perceived services can facilitate optimization and maintenance personnel to deal with base station failures in a targeted manner, quickly improve user satisfaction, and avoid waste of maintenance resources. Therefore, in order to determine the impact of base station alarms on user-perceived services, the device for determining the impact of base station alarms on user-perceived services first needs to obtain base station alarm data. As for the means of obtaining base station alarm data, it is the content of the prior art, and the present invention is implemented here not specifically limited;

Step 120, based on the base station alarm impact probability reference table on user perception services, determine the probability value of the impact of the base station alarm type corresponding to the base station alarm data on each service type;

Wherein, the base station alarm impact probability reference table on user perception service includes the probability value of the influence of each base station alarm type on each of the service types, each of the service types is represented by a plurality of primary user perception KPI indicators, and the probability The value is determined based on the number of time periods included in a preset duration and the correlation calculation results between each base station alarm type and the corresponding target user perception KPI index in each said time period, and the corresponding base station alarm type The target user perception KPI indicators are one or more of the primary user perception KPI indicators.

Specifically, the reference table for the probability of impact of base station alarms on user-perceived services includes the probability value of each base station alarm type affecting each of the service types. Therefore, the device for determining the impact of base station alarms on user-perceived services is based on the acquired base station alarm data. , the probability value of the impact of the base station alarm type corresponding to the base station alarm data on each service type can be determined by looking up the table.

Base station alarms are performance-affecting alarms defined according to existing rules. Different types of base station alarms correspond to different base station failures. Each user-perceived service type corresponds to multiple user-perceived KPI indicators. The primary user perception KPI indicators, each service type may be represented by multiple primary user perception KPI indicators. The base station alarm impact probability reference table on user perception services is obtained based on analysis of a large number of base station alarms and user perception KPI index sample data. To obtain the association relationship between base station alarms and service types, it is first necessary to obtain the association relationship between each base station alarm and the user perception KPI index corresponding to the service type. Therefore, the device for determining the impact of base station alarms on user perception services needs to be based on a predetermined The number of time periods included and the correlation calculation results of each base station alarm type and the corresponding target user perception KPI index in each described time period, and then determine the relationship between each base station alarm type and each described service type based on the correlation calculation result Probability of impact. The preset duration can be one year, each time period can correspond to one day, the preset duration can also be one month, and each time period can correspond to one hour. The specific preset duration and the division method of the time periods can be based on the actual Free setting is required, which is not specifically limited in this embodiment of the present invention.

Due to the large number of base station alarm types and primary user perception KPI indicators, the workload of correlation calculation is huge, so the target user perception KPI indicators corresponding to each base station alarm type select one or more of the primary user perception KPI indicators. Multiple, to reduce the workload of data processing, for example, the KPI index of primary user perception is 30, but for the base station alarm type I, it will only affect 5 of them, then the 5 primary user perception The KPI index is used as the target user perception KPI index of the base station alarm type I.

In the method provided by the embodiment of the present invention, the probability value of the impact of the base station alarm type corresponding to the base station alarm data on each service type is determined based on the reference table of the probability of impact of the base station alarm on the user-perceived service, wherein each service type is passed A plurality of primary user perception KPI indicators, the probability value is based on the number of time periods included in a preset duration and the correlation between each base station alarm type and the corresponding target user perception KPI indicators in each of the time periods If the calculation result is determined, it can accurately locate the service type and impact probability affected by the base station alarm, which is convenient for making a targeted equipment maintenance plan. The target user perception KPI index corresponding to each base station alarm type is the primary user perception KPI index. One or more can reduce the workload of data processing.

Based on the above embodiment, the probability value is determined based on the number of time periods included in a preset duration and the correlation calculation results between each base station alarm type and the corresponding target user perception KPI index in each time period, Specifically include:

In each of the time periods, if any one of the target user perception KPI indicators included in each of the service types is strongly correlated with the correlation calculation result of the base station alarm type, then the base station alarm type has a strong correlation with the base station alarm type. Add 1 to the numerator of the probability value of the impact of the service type; the denominator of the probability value is the number of the time period;

The correlation calculation result of each base station alarm type and the corresponding target user perception KPI index is obtained based on the correlation coefficient between each base station alarm type and the corresponding target user perception KPI index; when the absolute value of the correlation coefficient is greater than When the threshold is preset, the correlation calculation result is strong correlation.

Specifically, for each time period, calculate the correlation coefficient between each base station alarm type and the corresponding target user perception KPI index, and when the absolute value of the correlation coefficient is greater than the preset threshold, the correlation calculation result is a strong correlation , assuming that the correlation calculation result of the current base station alarm type and the corresponding target user perception KPI index is a strong correlation, it is considered that the current base station alarm type will have an impact on the target user perception KPI index, so it is judged that the current base station alarm type will affect the target user The service type corresponding to the perceived KPI index has an impact, and the number of times the current base station alarm type has an impact on the service type corresponding to the target user's perceived KPI index is increased by 1, that is, the numerator of the probability value of the impact of the base station alarm type on the service type is increased by 1 , if the above correlation calculation result is a weak correlation, the numerator remains unchanged. Therefore, for each time period, the number of times a base station alarm type affects a business type will only be 1 or 0, so the corresponding probability of impact Add 1 or 0 to the numerator of the value, use the number of time periods as the denominator, and use the cumulative value of the number of times the same base station alarm type affects the same service type in each time period as the numerator, you can get the impact of each base station alarm type on each The probability value of the impact of the business type. For example, if the preset time period is 1 year, and each time period is 1 day, then the number of time periods is 365. For the base station alarm types and target user perception KPI index data corresponding to each day, calculate the alarm types of each base station respectively. The correlation coefficient with the corresponding target user perception KPI index, assuming that the correlation calculation result of the base station alarm type I and the corresponding target user perception KPI index is strongly correlated, then the service type corresponding to the target user perception KPI index of the base station alarm type I Add 1 to the numerator of the probability value of the impact. If the correlation calculation results between the base station alarm type I and the corresponding target user perception KPI indicators are all strongly correlated in 300 of the 365 time periods, then the base station alarm type I is The target user perceives that the probability value of the service type corresponding to the KPI indicator is 300/365≈82%.

It is worth noting that since the target user perception KPI index is one or more of the primary user perception KPI indicators, how many of all primary user perception KPI indicators included in each service type may be target user perception KPI indicators, as long as any one of the target user perception KPI indicators included in each service type is strongly correlated with the correlation calculation result of the base station alarm type, then the base station alarm type has a strong impact on the service Add 1 to the numerator of the probability value affected by the type. Even if multiple target user perception KPI indicators included in the same service type are strongly related to the base station alarm type, the numerator of the probability value is still only added 1, because this is a judgment The result of whether the service type will be affected by the base station alarm type will only be 1 or 0, so even if multiple user perception KPI indicators are affected, the service type is only considered to be affected once.

In the method provided by the embodiment of the present invention, within each of the time periods, if any of the target user perception KPI indicators included in each of the service types is strongly correlated with the base station alarm type, then Add 1 to the numerator of the probability value of the impact of the base station alarm type on the service type, and the denominator of the probability value is the number of time periods. By analyzing a large number of sample data, the impact of each base station alarm type on each The probability value of the impact of the service type ensures the accuracy of the analysis of the impact of the base station alarm on the service perceived by the user.

Based on the above-mentioned embodiment, the correlation coefficients between each base station alarm type and the corresponding target user perception KPI index are obtained by performing Pearson correlation analysis based on each base station alarm type and the corresponding target user perception KPI index.

Specifically, the calculation formula of the Pearson correlation coefficient in the Pearson correlation analysis is:

ρX _,Y is the Pearson correlation coefficient of two continuous variables X and Y, and the Pearson correlation coefficient is used to measure the degree of linear correlation. cov(X,Y) is the covariance of X and Y, σ _X is the standard deviation of X, and σ _Y is the standard deviation of Y. μ _X and μ _Y are the expectations of X and Y, respectively, and E(X), E(Y) and E(XY) are the variances of X, Y, and XY, respectively.

The value of Pearson's correlation coefficient is always between -1.0 and 1.0. Variables close to 0 are called no correlation, and variables close to 1 or -1 are called strong correlation. For the embodiment of the present invention, X is the value of each base station alarm type corresponding to each time period. When the base station alarm occurs, the corresponding value is 1, and when it does not occur, the corresponding value is 0; Y is the corresponding value of each time period. Target user perception KPI index value. It is worth noting that the target user perception KPI index values are obtained by counting the corresponding indicators of tens of millions of users. As for the specific statistical method, it is the content of the prior art, and the embodiment of the present invention does not specifically limit it. .

In the method provided by the embodiment of the present invention, the correlation coefficient between each base station alarm type and the corresponding target user perception KPI index is obtained by performing Pearson correlation analysis based on each base station alarm type and the corresponding target user perception KPI index, which ensures The accuracy of the correlation analysis results ensures the accuracy of analysis of the impact of base station alarms on user-perceived services.

Based on the foregoing embodiments, the method further includes:

Determine the correlation calculation results of each base station alarm type and each of the multiple primary user perception KPI indicators, and filter out a plurality of target user perception KPI indicators corresponding to each base station alarm type based on the correlation calculation results; the target The correlation calculation result of the user perception KPI index and the alarm type of the base station is a strong correlation;

Classify the multiple primary user perception KPI indicators to determine multiple service types, and each service type is represented by multiple primary user perception KPI indicators.

Specifically, due to the large number of primary user perception KPI indicators, if for each time period, the correlation coefficient between each base station alarm type and each primary user perception KPI indicator is calculated, the calculation workload will be very huge. Therefore, the In order to reduce the calculation workload and improve the calculation efficiency, first, based on a sample data, determine the correlation calculation results of each base station alarm type and a plurality of primary user perception KPI indicators, and based on the correlation calculation results, Use the primary user perception KPI indicators that are strongly correlated with the base station alarm types as the target user perception KPI indicators corresponding to each base station alarm type, that is, retain the correspondence between the strong correlation base station alarms and user perception KPI indicators , the user-perceived KPI indicators that are not strongly correlated are eliminated, which will greatly reduce the workload of subsequent calculation of the correlation between the alarm types of each base station and the corresponding target user-perceived KPI indicators in each of the mentioned time periods. Primary selection of user perception KPI indicators that will be affected by base station alarms avoids unnecessary calculation work.

At the same time, the device for determining the impact of base station alarms on user-perceived services classifies the multiple primary user-perceived KPI indicators to determine multiple service types, and each service type is represented by multiple primary user-perceived KPI indicators , in order to carry out the subsequent calculation of the probability value.

In the method provided by the embodiment of the present invention, by determining the correlation calculation results between each base station alarm type and each of multiple primary user perception KPI indicators, based on the correlation calculation results, multiple KPIs corresponding to each base station alarm type are screened out. The target user perception KPI index, the target user perception KPI index and the correlation calculation result of the base station alarm type are strongly correlated, which greatly reduces the workload of probability value calculation, and at the same time, the plurality of primary user perception KPI indicators Classification is performed to determine multiple service types, and each service type is represented by multiple primary user perception KPI indicators, so that the probability value of the impact of each base station alarm type on each of the service types can be accurately obtained.

Based on the foregoing embodiment, the plurality of primary user perception KPI indicators are determined based on network management KPI indicators and SOC perception indicators.

Specifically, the network management KPI indicator and the SOC perception indicator include multiple user perception KPI indicators. In practical applications, several primary user perception KPI indicators are selected according to the importance of the indicators.

The method provided by the embodiment of the present invention can accurately reflect the impact of the corresponding service type according to the multiple primary user perception KPI indicators by determining multiple primary user perception KPI indicators based on the network management KPI indicators and SOC perception indicators, ensuring that the base station The accuracy of the analysis of the impact of alarms on user perception and business.

Based on the above embodiments, the service types include: Internet-aware class I, Internet-aware class II, voice-aware class I, and voice-aware class II;

The user-perceived KPI index corresponding to the Internet perception class 1 includes: application store download rate, video download average rate and video playback success rate;

The user perception KPI indicators corresponding to the Internet perception class II include: HTTP response success rate, small packet uplink average delay and small packet downlink average delay;

The user perception KPI index corresponding to the voice perception class 1 includes: VOLTE connection rate, VOLTE call drop rate and call setup average delay;

The user perception KPI indicators corresponding to the voice perception class II include: uplink average MOS and downlink average MOS.

Specifically, the user-perceived KPI indicators are classified based on the correspondence between the user-perceived KPI indicators and service types. Of course, the business types are not limited to the above four types. According to the actual selection of primary user perception KPI indicators, the corresponding business types and the number of user perception KPI indicators included in each business type will change. The embodiment of the present invention This is not specifically limited.

The method provided by the embodiment of the present invention can accurately obtain the impact of base station alarms on user-perceived services by classifying user-perceived KPI indicators based on the correspondence between user-perceived KPI indicators and service types.

The following uses a specific example to further illustrate the generation process and usage method of the reference table for the probability of impact of base station alarms on user-perceived services in any of the above-mentioned embodiments:

(1) Data extraction: Obtain base station alarm data and user perception KPI index data corresponding to a preset duration.

The alarm data of the base station is based on the impact performance alarm defined by the group. Taking a main equipment manufacturer as an example, there are a total of 309 items, as shown in Table 1:

Table 1

The user perception KPI index data is 36 indicators related to user perception selected according to the network management KPI index and SOC perception index, that is, the primary user perception KPI index, as shown in Table 2:

Table 2

(2) Determine the Pearson correlation coefficient of each of the above-mentioned 309 base station alarm types and the above-mentioned 36 primary user perception KPI indicators, as shown in Table 3:

table 3

Indicator 1 Indicator 2 Indicator 3 Indicator 4 Indicator 5 ... Alarm type 1 0.96 0.32 -0.97 0.56 -0.32 0.75 Alarm type 2 0.61 0.75 -0.13 0.08 -0.21 0.86 Alarm type 3 -0.71 0.81 0.23 0.15 -0.53 -0.70 Alarm type 4 0.11 -0.27 0.31 -0.29 0.06 0.95 Alarm type 5 0.81 -0.13 0.19 0.78 -0.55 -0.78 Alarm type 6 0.74 0.07 0.57 -0.70 -0.25 0.16 Alarm type 7 -0.52 0.57 -0.18 0.64 -0.25 0.25 ... 0.95 0.52 -0.41 0.43 0.61 -0.91

In addition, the preset threshold value is 0.8. When the absolute value of the correlation coefficient is greater than 0.8, the correlation calculation result is a strong correlation, and the 36 primary user perception KPI indicators are strongly correlated with each base station alarm type The index of is used as the target user perception KPI index corresponding to the base station alarm type.

(3) Classify the 36 primary user perception KPI indicators, determine multiple service types, and each service type is characterized by multiple primary user perception KPI indicators. As shown in Table 4:

Table 4

(4) Assuming that an alarm type X occurs, the service type that may be affected is Y, and each possible Y corresponds to a conditional probability when an alarm type X occurs: P(Y|X).

Dividing the base station alarm data and user perception KPI index data corresponding to the preset duration into multiple time periods, within each time period, if any of the primary user perception KPI indicators included in each of the service types A correlation calculation result with the base station alarm type is a strong correlation, then the numerator of the probability value (i.e. the above-mentioned conditional probability) that the base station alarm type has an impact on the service type is increased by 1; the denominator of the probability value is The number of time periods in question.

Taking the cumulative value of the number of impacts of the same base station alarm type on the same service type in each time period as the numerator, the probability value of the impact of each base station alarm type on each service type can be obtained, and the base station alarm pair is generated based on the probability value. The user perception service impact probability reference table is shown in Table 5:

table 5

After obtaining the base station alarm impact probability reference table on user perception services, based on the acquired base station alarm data, the probability value of the impact of the base station alarm type corresponding to the base station alarm data on each service type can be determined by looking up the table. For example, after obtaining a piece of base station alarm information, based on the manufacturer's alarm ID of the alarm information, the matching manufacturer's alarm ID is searched in the reference table to obtain the impact probability of the alarm type corresponding to the alarm information on each service type.

Based on any of the above embodiments, FIG. 2 is a schematic diagram of a device for determining the impact of a base station alarm on user-perceived services provided by an embodiment of the present invention. As shown in FIG. 2 , the device includes:

The base station alarm data acquisition module 210 is configured to acquire base station alarm data.

Specifically, in order to determine the impact of base station alarms on user-perceived services, the base station alarm data acquisition module 210 first needs to acquire base station alarm data. As for the means of obtaining base station alarm data, it is the content of the prior art, and the implementation of the present invention is not specifically limited here. .

The impact determination module 220 of the base station alarm on the user-perceived service is configured to determine the probability value that the base station alarm type corresponding to the base station alarm data has an impact on each service type based on the reference table of the impact probability of the base station alarm on the user-perceived service;

Wherein, the base station alarm impact probability reference table on user perception service includes the probability value of the influence of each base station alarm type on each of the service types, each of the service types is represented by a plurality of primary user perception KPI indicators, and the probability The value is determined based on the number of time periods included in a preset duration and the correlation calculation results between each base station alarm type and the corresponding target user perception KPI index in each said time period, and the corresponding base station alarm type The target user perception KPI indicators are one or more of the primary user perception KPI indicators.

Specifically, the base station alarm impact probability reference table on user-perceived services includes the probability value of each base station alarm type affecting each of the service types, therefore, the base station alarm impact on user-perceived service determination module 220 based on the obtained , the probability value of the impact of the base station alarm type corresponding to the base station alarm data on each service type can be determined by looking up the table.

To obtain the association relationship between base station alarms and service types, it is first necessary to obtain the association relationship between each base station alarm and the user perception KPI index corresponding to the service type. The number of time periods included and the correlation calculation results of each base station alarm type and the corresponding target user perception KPI index in each described time period, and then determine the relationship between each base station alarm type and each described service type based on the correlation calculation result Probability of impact.

In the device provided by the embodiment of the present invention, the module for determining the impact of base station alarms on user-perceived services determines the probability value that the base station alarm type corresponding to the base station alarm data has an impact on each service type based on the base station alarm-based user-perceived service impact probability reference table , wherein, each of the service types is characterized by a plurality of primary user perception KPI indicators, and the probability value is based on the number of time periods included in a preset duration and each base station alarm type in each of the time periods and the corresponding If the correlation calculation results of the target user perception KPI indicators are determined, the service types and impact probability affected by base station alarms can be accurately located, and it is convenient to formulate equipment maintenance plans in a targeted manner. The target user perception KPI indicators corresponding to each base station alarm type are One or more of the primary user perception KPI indicators mentioned above can reduce the workload of data processing.

Based on the above embodiment, the probability value is determined based on the number of time periods included in a preset duration and the correlation calculation results between each base station alarm type and the corresponding target user perception KPI index in each time period, Specifically include:

In each of the time periods, if any one of the target user perception KPI indicators included in each of the service types is strongly correlated with the correlation calculation result of the base station alarm type, then the base station alarm type has a strong correlation with the base station alarm type. Add 1 to the numerator of the probability value of the impact of the service type; the denominator of the probability value is the number of the time period;

The correlation calculation result of each base station alarm type and the corresponding target user perception KPI index is obtained based on the correlation coefficient between each base station alarm type and the corresponding target user perception KPI index; when the correlation coefficient is greater than the preset threshold When , the correlation calculation result is a strong correlation.

Based on the above-mentioned embodiment, the correlation coefficients between each base station alarm type and the corresponding target user perception KPI index are obtained by performing Pearson correlation analysis based on each base station alarm type and the corresponding target user perception KPI index.

Based on the above-mentioned embodiments, the device for determining the impact of the base station alarm on the service perceived by the user is also used for:

Determine the correlation calculation results of each base station alarm type and each of the multiple primary user perception KPI indicators, and filter out a plurality of target user perception KPI indicators corresponding to each base station alarm type based on the correlation calculation results; the target The correlation calculation result of the user perception KPI index and the alarm type of the base station is a strong correlation;

Classify the multiple primary user perception KPI indicators to determine multiple service types, and each service type is represented by multiple primary user perception KPI indicators.

Based on the foregoing embodiment, the plurality of primary user perception KPI indicators are determined based on network management KPI indicators and SOC perception indicators.

Based on the above embodiments, the service types include: Internet-aware class I, Internet-aware class II, voice-aware class I, and voice-aware class II;

The user-perceived KPI index corresponding to the Internet perception class 1 includes: application store download rate, video download average rate and video playback success rate;

The user perception KPI indicators corresponding to the Internet perception class II include: HTTP response success rate, small packet uplink average delay and small packet downlink average delay;

The user perception KPI index corresponding to the voice perception class 1 includes: VOLTE connection rate, VOLTE call drop rate and call setup average delay;

The user perception KPI indicators corresponding to the voice perception class II include: uplink average MOS and downlink average MOS.

The device for determining the impact of base station alarms on user-perceived services provided by the embodiments of the present invention can implement the above-mentioned method for determining the impact of base station alarms on user-perceived services. repeat.

FIG. 3 illustrates a schematic diagram of the physical structure of an electronic device. As shown in FIG. 3 , the electronic device may include: a processor (processor) 310, a communication interface (Communications Interface) 320, a memory (memory) 330 and a communication bus 340, Wherein, the processor 310 , the communication interface 320 , and the memory 330 communicate with each other through the communication bus 340 . The processor 310 may invoke logic instructions in the memory 330 to execute the steps and procedures provided in the foregoing method embodiments.

In addition, the above-mentioned logic instructions in the memory 330 may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes. .

On the other hand, the embodiments of the present invention also provide a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps and procedures provided by the above method embodiments are implemented.

The device embodiments described above are only illustrative, and the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network elements. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. It can be understood and implemented by those skilled in the art without any creative efforts.

Through the above description of the implementations, those skilled in the art can clearly understand that each implementation can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the prior art can be embodied in the form of software products, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, magnetic discs, optical discs, etc., including several instructions to make a computer device (which may be a personal computer, server, or network device, etc.) execute the methods described in various embodiments or some parts of the embodiments.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still be Modifications are made to the technical solutions described in the foregoing embodiments, or equivalent replacements are made to some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims (8)

1. A method for determining the impact of base station alarms on user-perceived services, comprising: Obtain base station alarm data; Based on the base station alarm impact probability reference table on user perception services, determine the probability value of the impact of the base station alarm type corresponding to the base station alarm data on each service type; Wherein, the base station alarm impact probability reference table on user perception service includes the probability value of the influence of each base station alarm type on each of the service types, each of the service types is represented by a plurality of primary user perception KPI indicators, and the probability The value is determined based on the number of time periods included in a preset duration and the correlation calculation results between each base station alarm type and the corresponding target user perception KPI index in each said time period, and the corresponding base station alarm type The target user-perceived KPI indicators are one or more of the primary user-perceived KPI indicators; The probability value is determined based on the number of time periods included in a preset time period and the calculation results of the correlation between each base station alarm type and the corresponding target user perception KPI index in each time period, specifically including: In each of the time periods, if any one of the target user perception KPI indicators included in each of the service types is strongly correlated with the correlation calculation result of the base station alarm type, then the base station alarm type has a strong correlation with the base station alarm type. Add 1 to the numerator of the probability value of the impact of the service type; the denominator of the probability value is the number of the time period; The correlation calculation result of each base station alarm type and the corresponding target user perception KPI index is obtained based on the correlation coefficient between each base station alarm type and the corresponding target user perception KPI index; when the absolute value of the correlation coefficient is greater than When the threshold is preset, the correlation calculation result is strong correlation. 2. The method for determining the impact of base station alarms on user perception services according to claim 1, wherein the correlation coefficient between each base station alarm type and the corresponding target user perception KPI index is based on each base station alarm type and the corresponding The target user perception KPI index is obtained by Pearson correlation analysis. 3. The method for determining the impact of base station alarms on user perception services according to claim 1, wherein the method further comprises: Determine the correlation calculation results of each base station alarm type and each of the multiple primary user perception KPI indicators, and filter out a plurality of target user perception KPI indicators corresponding to each base station alarm type based on the correlation calculation results; the target The correlation calculation result of the user perception KPI index and the alarm type of the base station is a strong correlation; Classify the multiple primary user perception KPI indicators to determine multiple service types, and each service type is represented by multiple primary user perception KPI indicators. 4. The method for determining the impact of base station alarms on user perception services according to claim 3, wherein the plurality of primary user perception KPI indicators are determined based on network management KPI indicators and SOC perception indicators. 5. The method for determining the impact of base station alarms on user-perceived services according to claim 4, wherein the service types include: Internet-aware class I, Internet-aware class II, voice-aware class I and voice-aware class II; The user-perceived KPI index corresponding to the Internet perception class 1 includes: application store download rate, video download average rate and video playback success rate; The user perception KPI indicators corresponding to the Internet perception class II include: HTTP response success rate, small packet uplink average delay and small packet downlink average delay; The user perception KPI index corresponding to the voice perception class 1 includes: VOLTE connection rate, VOLTE call drop rate and call setup average delay; The user perception KPI indicators corresponding to the voice perception class II include: uplink average MOS and downlink average MOS. 6. A device for determining the impact of base station alarms on user-perceived services, comprising: A base station alarm data acquisition module, configured to acquire base station alarm data; A module for determining the impact of base station alarms on user-perceived services, configured to determine the probability value that the base station alarm type corresponding to the base station alarm data has an impact on each service type based on the reference table of the impact probability of base station alarms on user-perceived services; Wherein, the base station alarm impact probability reference table on user perception service includes the probability value of the influence of each base station alarm type on each of the service types, each of the service types is represented by a plurality of primary user perception KPI indicators, and the probability The value is determined based on the number of time periods included in a preset duration and the correlation calculation results between each base station alarm type and the corresponding target user perception KPI index in each said time period, and the corresponding base station alarm type The target user-perceived KPI indicators are one or more of the primary user-perceived KPI indicators; The probability value is determined based on the number of time periods included in a preset time period and the calculation results of the correlation between each base station alarm type and the corresponding target user perception KPI index in each time period, specifically including: In each of the time periods, if any one of the target user perception KPI indicators included in each of the service types is strongly correlated with the correlation calculation result of the base station alarm type, then the base station alarm type has a strong correlation with the base station alarm type. Add 1 to the numerator of the probability value of the impact of the service type; the denominator of the probability value is the number of the time period; The correlation calculation result of each base station alarm type and the corresponding target user perception KPI index is obtained based on the correlation coefficient between each base station alarm type and the corresponding target user perception KPI index; when the absolute value of the correlation coefficient is greater than When the threshold is preset, the correlation calculation result is strong correlation. 7. An electronic device comprising a memory, a processor, and a computer program stored on the memory and operable on the processor, wherein the processor implements any of claims 1 to 5 when executing the program. The steps of the method for determining the impact of the base station alarm on the user's perception of service described in the item. 8. A non-transitory computer-readable storage medium, on which a computer program is stored, characterized in that, when the computer program is executed by a processor, it realizes the base station alarm to user perception service as described in any one of claims 1 to 5. Steps in the determination method of impact.