CN111327450A

CN111327450A - Method, device, equipment and medium for determining quality difference reason

Info

Publication number: CN111327450A
Application number: CN201811545489.5A
Authority: CN
Inventors: 王博
Original assignee: China Mobile Communications Group Co Ltd; China Mobile Group Beijing Co Ltd
Current assignee: China Mobile Communications Group Co Ltd; China Mobile Group Beijing Co Ltd
Priority date: 2018-12-17
Filing date: 2018-12-17
Publication date: 2020-06-23
Anticipated expiration: 2038-12-17
Also published as: CN111327450B

Abstract

The invention discloses a method, a device, equipment and a medium for determining a cause of poor quality, which are used for accurately determining the cause of poor quality of a network. The method for determining the cause of the quality difference comprises the following steps: acquiring service performance data; extracting a plurality of target characteristics influencing network quality from the service performance data, and determining the probability of network quality difference caused by each target characteristic; and determining the reason causing the network quality difference based on the target characteristics and the probability of causing the network quality difference by each target characteristic.

Description

Method, device, equipment and medium for determining quality difference reason

Technical Field

The present invention relates to the field of communications, and in particular, to a method, an apparatus, a device, and a medium for determining a cause of quality difference.

Background

With the development of network information, the number of users entering a network is increasing, and in order to ensure that the users have good use experience, the network needs to be continuously optimized so as to ensure the high-quality operation of the network.

The current methods for determining the cause of poor cell quality mainly include the following two methods:

traffic statistical analysis method: the telephone traffic is an index reflecting the call frequency and call time of telephone users, directly reflecting the operation quality and configuration conditions of telecommunication network parts and equipment, and indirectly helping telecommunication network managers to find potential service markets and reflect the demands of the markets on telecommunication services through the index. However, the traffic statistical analysis method is an optimization method based on the conventional voice service, and does not help network optimization in the case of the 4th generation mobile communication technology (4G) data service.

DT & CQT test method: drive Test (DT) refers to the field strength Test analysis and call analysis of road signals by selecting Test areas and routes. And analyzing the collected related data by using a professional test instrument, an automatic dial test mobile phone and background analysis software, and determining the wireless network performance, the network coverage condition and the call area signal distribution condition of a test road section or area. Call Quality Test (CQT) refers to testing the performance of a wireless network by selecting a sampling point Test method and using a dial testing handset to dial a Call at a selected location. The CQT must first record a detailed geographical location, an occupied base station Identification (ID), a reception level, etc. to provide statistical analysis data for optimized items of coverage, synchronization, interference, etc. of the wireless network system, the wireless network. In practical application, because the method is a sampling method, the whole network cannot be optimized, and personnel need to be dispatched to the site to actually measure data, the cost is high, and blind spots exist.

Therefore, in the prior art, the two quality difference determining methods cannot accurately determine the cause of the network quality difference.

Disclosure of Invention

The embodiment of the invention provides a method, a device, equipment and a medium for determining a cause of poor quality, which are used for accurately determining the cause of poor quality of a network.

In a first aspect, an embodiment of the present invention provides a method for determining a cause of a quality difference, including:

acquiring service performance data;

extracting a plurality of target characteristics influencing the network quality from the service performance data, and determining the probability of network quality difference caused by each target characteristic;

and determining the reason causing the network quality difference based on the target characteristics and the probability of causing the network quality difference by each target characteristic.

In a possible implementation manner, the above method provided by the embodiment of the present invention, the target features include two or more of the following: weak coverage, overlapping coverage, modulo 3 interference, number of concurrent users, and number of network handovers.

In a possible implementation manner, an embodiment of the present invention provides the method, wherein extracting a plurality of target features that affect network quality from the traffic performance data includes:

determining a service index weight causing network quality difference based on the service performance data;

and extracting a plurality of target characteristics influencing the network quality from the service performance data according to the service index weight causing the network quality difference.

In a possible implementation manner, in the method provided in an embodiment of the present invention, determining a service index weight causing network quality difference based on service performance data includes:

extracting network indexes from the service performance data;

and inputting the network indexes into a user experience quality hierarchical model, and determining the weight of the service indexes causing the network quality difference.

In a possible implementation manner, in the foregoing method provided by an embodiment of the present invention, the method further includes:

extracting network indexes from the service performance data;

inputting the network indexes into a user experience quality hierarchical model, determining a plurality of service indexes causing network quality difference, and determining the weight of each service index;

determining the experience quality score of a single service based on a plurality of service indexes and the weight of each service index;

determining the experience quality score of the user based on the experience quality score of the single service and pre-acquired user experience quality evaluation data;

and determining the cell optimization sequence according to the experience quality scores of the users in each cell.

In a possible implementation manner, in the method provided in an embodiment of the present invention, the service performance data includes: measurement Report (MR) data, user plane S1-U (eNodeB-SGW, S1-U) interface data, and control plane S1-MME (eNodeB-MME, S1-MME) interface data.

converting the acquired service performance data into target performance parameters;

a plurality of target features that affect network quality are extracted from the target performance parameters.

In a possible implementation manner, in the method provided in an embodiment of the present invention, the converting the obtained service performance data into the target performance parameter includes:

combining the MR data of different adjacent cells reported at the same time to obtain combined MR data;

fusing the merged MR data with the S1-MME interface data to obtain fused MR data;

fusing the fused MR data and S1-U interface data to obtain fused S1-U interface data;

and fusing the S1-MME interface data with the fused S1-U interface data to obtain target performance parameters.

and determining a cell optimization scheme based on the reason causing the network quality difference.

In a second aspect, an embodiment of the present invention provides an apparatus for determining a cause of quality difference, including:

an obtaining unit, configured to obtain service performance data;

the computing unit is used for extracting a plurality of target characteristics influencing the network quality from the service performance data and determining the probability of network quality difference caused by each target characteristic;

and the determining unit is used for determining the reason causing the network quality difference based on the target characteristics and the probability of causing the network quality difference by each target characteristic.

In a possible implementation manner, the above apparatus provided by the embodiment of the present invention, the target features include two or more of the following: weak coverage, overlapping coverage, modulo 3 interference, number of concurrent users, and number of network handovers.

In a possible implementation manner, in the apparatus provided in an embodiment of the present invention, the calculating unit is specifically configured to:

extracting network indexes from the service performance data;

In a possible implementation manner, an embodiment of the present invention provides the above apparatus, where the apparatus further includes: a processing unit to:

extracting network indexes from the service performance data;

In a possible implementation manner, in the apparatus provided in an embodiment of the present invention, the service performance data includes: measurement report MR data, user plane S1-U interface data, and control plane S1-MME interface data.

In a possible implementation manner, an embodiment of the present invention provides the apparatus, wherein the processing unit is further configured to:

In a third aspect, an embodiment of the present invention further provides a device for determining a cause of quality difference, including: the present invention also provides a computer program product for determining a cause of a quality difference, the computer program product comprising at least one processor, at least one memory and computer program instructions stored in the memory, the computer program instructions, when executed by the processor, implementing the method for determining a cause of a quality difference as provided in the first aspect of an embodiment of the present invention.

In a fourth aspect, an embodiment of the present invention further provides a computer storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method for determining the cause of the quality difference provided in the first aspect of the embodiment of the present invention is implemented.

The embodiment of the invention has the following beneficial effects:

the method, the device, the equipment and the medium for determining the cause of the quality difference, provided by the embodiment of the invention, are used for acquiring service performance data; extracting a plurality of target characteristics influencing the network quality from the service performance data, and determining the probability of network quality difference caused by each target characteristic; and determining the reason causing the network quality difference based on the target characteristics and the probability of causing the network quality difference by each target characteristic. In implementation, the reason causing the network quality difference is determined according to a plurality of target characteristics which are extracted from the service performance data and affect the network quality and the probability of causing the network quality difference of each target characteristic.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic flow chart of a method for determining a cause of a quality difference according to an embodiment of the present invention;

fig. 2 is a schematic flow chart of a specific process for determining a service indicator weight causing network quality difference according to an embodiment of the present invention;

fig. 3 is a schematic flow chart of a conversion process of converting service performance data into target performance parameters according to an embodiment of the present invention;

fig. 4 is a schematic flowchart of a process for determining a cell optimization order according to an embodiment of the present invention;

fig. 5 is a schematic flow chart of a specific flow of a method for determining a cause of a quality difference according to an embodiment of the present invention;

fig. 6 is a schematic structural diagram of a device for determining a cause of a quality difference according to an embodiment of the present invention;

fig. 7 is a schematic structural diagram of a device for determining a cause of quality difference according to an embodiment of the present invention.

Detailed Description

Embodiments of the present application will be described with reference to the accompanying drawings, and it should be understood that the embodiments described herein are merely illustrative and explanatory of the application and are not restrictive of the application.

The following describes specific embodiments of a method, an apparatus, a device, and a medium for determining a cause of quality difference according to embodiments of the present invention with reference to the accompanying drawings.

An embodiment of the present invention provides a method for determining a cause of a quality difference, as shown in fig. 1, the method may include the following steps:

step 101, obtaining service performance data.

It should be noted that the service performance data includes: MR data, S1-U interface data, and S1-MME interface data.

The S1-U interface data and the S1-MME interface data may be acquired through a communication interface between the base Station and the packet core network, and the MR data may be reported by a Mobile Station (MS) and an abis (abis entity) interface.

Step 102, extracting a plurality of target characteristics influencing the network quality from the service performance data, and determining the probability of each target characteristic causing the network quality difference.

In specific implementation, when extracting a plurality of target features influencing network quality from the service performance data, firstly, determining the service index weight causing network quality difference based on the service performance data, and then extracting a plurality of target features influencing the network quality from the service performance data according to the service index weight causing network quality difference. After extracting a plurality of target features affecting the network quality from the traffic performance data, the probability of each target feature causing network quality difference is determined using a preset algorithm. The preset algorithm may be a frequent item set mining algorithm or other algorithms, which is not limited in the embodiment of the present invention.

In specific implementation, when determining the service index weight causing the network quality difference based on the service performance data, extracting the network index reflecting the network performance service from the service performance data, inputting the network index into the user experience quality hierarchical model, and determining the service index weight causing the network quality difference.

The following describes in detail a specific process of determining a service index weight causing network quality difference based on service performance data in the embodiment of the present invention.

As shown in fig. 2, a schematic diagram is provided for determining a service index weight causing network quality difference based on service performance data according to an embodiment of the present invention.

Firstly, extracting a network index KPI for embodying network performance service from service performance data, taking browsing service, communication service and video service as examples, extracting the network index KPI for embodying three services of browsing service, communication service and video service, and inputting the network index KPI into a user experience quality hierarchical model to obtain the service index KQI of browsing service, communication service and video service and the weight of the service index KQI influencing network quality.

The network index KPI is input into the user experience quality hierarchical model to obtain a specific process of the service index KQI, the network index KPI can be calculated according to a mapping relation table of the network index KPI and the service index KQI shown in table 1 to obtain the service index KQI, and the user experience quality hierarchical model is utilized to obtain the service index weight causing network quality deterioration.

Table 1 mapping relation table of network indicator KPI and service indicator KQI

In order to extract network indexes and target features conveniently, the acquired service performance can be digitalized into target performance parameters, and a plurality of target features influencing network quality are extracted from the target performance parameters.

The embodiment of the present invention takes fig. 3 as an example, and details a specific process of converting the service performance data provided by the embodiment of the present invention into the target performance parameter.

Step 301, combining the MR data of different neighboring cells reported at the same time to obtain combined MR data.

In specific implementation, the MR data is reported by the MS and Abis interfaces, the MR data includes MR data of multiple cells, and when the MR data of different neighboring cells reported at the same time are merged, the MR data with the same key value may be merged by setting a key value, so as to merge the MR data of different neighboring cells reported at the same time.

And step 302, fusing the merged MR data with the S1-MME interface data to obtain fused MR data.

In specific implementation, the mobile user identification mark is used as a key, the MR data and the S1-MME interface data are sorted according to time, the mobile user identification mark is added to the MR data, and the fused MR data is obtained.

And step 303, fusing the fused MR data and the S1-U interface data to obtain fused S1-U interface data.

In specific implementation, the MR data in the specified detection time in the fused MR data is added to the S1-U interface data to obtain the fused S1-U interface data.

And step 304, fusing the S1-MME interface data with the fused S1-U interface data to obtain target performance parameters.

In specific implementation, the process type codes and the process state data in the S1-MME interface data are added into the matched and fused S1-U interface data to obtain target performance parameters.

It should be noted that, the flow type code and the flow state data in the S1-MME interface data are added to the matched fused S1-U interface data, and the field format of the fused S1-U interface data is:

In one possible implementation, after obtaining the target performance parameters, determining a service index weight causing network deterioration based on the target performance parameters, extracting a plurality of target features affecting network quality from the target performance parameters according to the service index weight causing network deterioration, and determining a probability that each target feature causes network deterioration.

It should be noted that the preset algorithm may be a frequent item set mining algorithm or other algorithms, which is not limited in the embodiment of the present invention.

The following describes in detail a specific process of extracting a plurality of target features affecting network quality from target performance parameters according to a service index weight causing network quality difference in the embodiment of the present invention.

Firstly, inputting the network index into a user experience quality hierarchical model, and determining the business index weight causing poor network quality. And then determining data which influences the network quality and is related to the service index in the target performance parameters according to the service index weight causing the network quality difference, calculating whether the data meets a preset threshold value, and determining the data to be the target characteristic influencing the network quality when the data meets the preset threshold value.

The table of correspondence between the target characteristics and the target performance parameters is shown in table 2, and in specific implementation, data affecting network quality and related to the service index in the target performance parameters may be calculated according to contents in the table of correspondence between the target characteristics and the target performance parameters, and when the data satisfies a preset threshold, the data is determined as the target characteristics affecting network quality.

TABLE 2 table of correspondence between target characteristics and target performance parameters

It should be noted that the preset threshold may be set according to implementation conditions, taking table 2 as an example, when the number of concurrent users in the S1-U interface data within a preset time exceeds 80% of the maximum number of concurrent users of all websites, it may be considered that a condition is satisfied, that is, the number of concurrent users is a target characteristic that affects network quality.

The preset time may be within one minute or other time duration, which is not limited in the embodiment of the present invention.

After a plurality of target features influencing the network quality are extracted from the target performance parameters, the probability of network quality difference caused by each target feature is calculated by using a preset algorithm.

The preset algorithm may be a frequent item set mining algorithm or other algorithms, which is not limited in the embodiment of the present invention.

And 103, determining the reason causing the poor network quality based on the target characteristics and the probability of causing the network by each target characteristic.

It should be noted that the target features may include, but are not limited to, two or more of the following: weak coverage, overlapping coverage, modulo 3 interference, number of concurrent users, and number of network handovers.

In one example, if the probability of network quality difference caused by weak coverage of the target feature is 0.8, and the probability of network quality difference caused by the number of concurrent users of the target feature is 0.5, it can be determined that the primary cause of network quality difference is weak coverage, and the secondary cause of network quality difference is the number of concurrent users.

After determining the cause of the network degradation, a cell optimization scheme may be determined based on the primary cause and the secondary cause of the network degradation.

Still continuing with the above example, the probability of poor network quality caused by weak coverage of the target feature is 0.8, and the probability of poor network quality caused by the number of concurrent users of the target feature is 0.5, and when optimizing the cell, the problem of weak coverage of the cell can be optimized first, and then the problem of the number of concurrent users of the cell can be optimized.

The embodiment of the invention optimizes the cells after determining the network optimization scheme, and can determine the optimization sequence of the cells according to the influence of the reason causing poor network quality on user experience when a plurality of cells need to be optimized. Specifically, the cell optimization order may be determined by:

step 401, extracting network indexes from the service performance data.

In specific implementation, when the network index is extracted from the service performance data, the network index representing the network service is extracted from the service performance data.

In order to extract network indexes conveniently, when a plurality of target features influencing network quality are extracted from the service performance data, the obtained service performance data can be converted into target performance parameters, and the network indexes reflecting network services are extracted from the target performance parameters.

Step 402, inputting the network index into the user experience quality hierarchical model, determining a plurality of service indexes causing network quality difference, and determining the weight of each service index.

In specific implementation, the network indexes are input into the user experience quality hierarchical model, when a plurality of service indexes causing network deterioration are determined, the network indexes are input into the user experience quality hierarchical model, the plurality of service indexes causing network deterioration and the plurality of service index proportions causing network deterioration are obtained, and meanwhile, the service indexes can be converted into percentage forms.

Firstly, extracting a network index KPI for embodying network performance service from service performance data, taking browsing service, communication service and video service as examples, extracting the network index KPI for embodying three services of browsing service, communication service and video service, and inputting the network index KPI into a user experience quality hierarchical model to obtain service indexes KQI of browsing service, communication service and video service and weights of the service indexes KQI influencing network quality.

And 403, determining the experience quality score of the single service based on the multiple service indexes and the weight of each service index.

It should be noted that the quality of experience score of a single service is obtained based on the acquired service performance data, and each piece of acquired network performance data records a service process perceived by a user.

In specific implementation, the weight of each service index and the percentage of the service index are multiplied to obtain the experience quality score of each service, and the experience quality scores of each service are summarized to obtain the experience quality score of a single service.

And step 404, determining the experience quality score of the user based on the experience quality score of the single service and the pre-acquired user experience quality evaluation data.

In specific implementation, according to the service experience quality score of the user in the pre-acquired user experience quality evaluation data, the service experience quality score is converted into a binary number value, and the value obtained by summing the binary number value is compared with the total evaluation times to obtain the user experience quality score.

It should be noted that the user experience quality assessment data records a service experience quality assessment result of user participation within a preset time period.

The preset time period may be set according to an actual situation, and may be 1 hour or 1.5 hours, which is not limited in the embodiment of the present invention.

In specific implementation, when the experience quality score of the service is converted into a binary value, the conversion condition can be set according to whether the user quality evaluation exceeds a preset threshold value.

In one example, the quality of experience score of a service with a service quality of experience score higher than a preset threshold is set to 1, and the other is set to 0. The preset threshold may be set according to an actual situation, for example: the preset threshold may be 0.8 or 0.7, which is not limited in the embodiment of the present invention.

Step 405, determining a cell optimization sequence according to the quality of experience scores of the users in each cell.

In specific implementation, experience quality scores of users in a cell are converted into binary according to a preset threshold, the numerical value obtained by summing the binary numerical values is compared with the number of users in the cell to obtain the cell quality difference level, the cells are sorted according to the cell quality difference level, and the cell optimization sequence is determined.

In one possible embodiment, after determining the cell optimization order, the cells are optimized in turn according to the cell optimization order.

The method for determining the cause of the quality difference according to the embodiment of the present invention is described in detail below with reference to fig. 5 and a scheme for determining an optimization order of cells.

As shown in fig. 5, the method for determining the cause of the quality difference according to the embodiment of the present invention may include:

step 501, obtaining service performance data.

The S1-U interface data and the S1-MME interface data can be obtained through a communication interface between the base station and the packet core network, and the MR data can be obtained through reporting of MS and Abis interfaces.

Step 502, converting the obtained service performance index into a target performance parameter.

Step 503, extracting the network index from the target performance parameter, inputting the network index into the user experience quality hierarchical model, and determining the service index weight causing the network quality difference.

And step 504, extracting a plurality of target characteristics influencing the network quality from the target performance parameters according to the service index weight causing the network quality difference.

And step 505, determining the probability of each target feature causing network quality difference.

In specific implementation, a preset algorithm is utilized to obtain the probability of network quality difference caused by each target feature.

It should be noted that the preset algorithm may be a frequent item set mining algorithm, or may be other algorithms, which is not limited in the embodiment of the present invention.

Step 506, determining the reason causing the network quality difference based on the target characteristics and the probability of causing the network quality difference by each target characteristic.

And 507, determining a cell optimization scheme based on the reason of poor network quality.

Step 508, extracting network indexes from the target performance parameters, inputting the network indexes into the user experience quality hierarchical model, determining a plurality of service indexes causing network quality difference, and determining the weight of each service index.

Step 509, determining the quality of experience score of the single service based on the plurality of service indicators and the weight of each service indicator.

And step 510, determining the experience quality score of the user based on the experience quality score of the single service and the pre-acquired user experience quality evaluation data.

The preset time period may be set according to an actual situation, and may be one hour or one and a half hours, which is not limited in the embodiment of the present invention.

In specific implementation, when the experience quality score of the service is converted into a binary value, the experience quality score of the service of the user is converted into the binary value according to a preset threshold value.

In an example, the quality of experience of the service with the quality of service experience score higher than the preset threshold is set to 1, and the others are set to 0.

The preset threshold may be set according to an actual situation, for example: the preset threshold may be 0.8 or 0.7, which is not limited in the embodiment of the present invention.

And 511, determining a cell optimization sequence according to the quality of experience scores of the users in each cell.

In an example, the user experience quality score with a score higher than a preset threshold value in the user experience quality is set to be 1, and the rest are 0.

And step 512, optimizing the cells in sequence based on the cell optimization sequence.

Based on the same inventive concept, the embodiment of the invention also provides a device for determining the cause of the quality difference.

As shown in fig. 6, an apparatus for determining a cause of a quality difference according to an embodiment of the present invention includes:

an obtaining unit 601, configured to obtain service performance data;

a calculating unit 602, configured to extract a plurality of target features that affect network quality from the service performance data, and determine a probability that each target feature causes network quality difference;

a determining unit 603 configured to determine a cause of causing the network quality difference based on the target features and the probability of causing the network quality difference for each target feature.

In one possible embodiment, the target features include two or more of the following: weak coverage, overlapping coverage, modulo 3 interference, number of concurrent users, and number of network handovers.

In a possible implementation, the computing unit 602 is specifically configured to:

In a possible implementation, the computing unit 602 is specifically configured to: extracting network indexes from the service performance data; and inputting the network indexes into a user experience quality hierarchical model, and determining the weight of the service indexes causing the network quality difference.

In one possible embodiment, the apparatus further comprises: a processing 604 unit to:

extracting network indexes from the service performance data; inputting the network indexes into a user experience quality hierarchical model, determining a plurality of service indexes causing network quality difference, and determining the weight of each service index; determining the experience quality score of the user based on the experience quality score of the single service and pre-acquired user experience quality evaluation data; and determining the cell optimization sequence according to the experience quality scores of the users in each cell.

In one possible embodiment, the service performance data includes: measurement report MR data, user plane S1-U interface data, and control plane S1-MME interface data.

In a possible implementation, the processing unit 604 is further configured to:

and determining an optimization scheme based on the reason causing the network quality difference.

In addition, the method and apparatus for determining the cause of the quality difference according to the embodiments of the present invention described in conjunction with fig. 1 to 6 may be implemented by a device for determining the cause of the quality difference. Fig. 7 is a schematic diagram illustrating a hardware structure of the device for determining the cause of the quality difference according to the embodiment of the present invention.

The determination device of the cause of the quality difference may comprise a processor 701 and a memory 702 in which computer program instructions are stored.

Specifically, the processor 701 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured as one or more Integrated circuits implementing an embodiment of the present invention.

Memory 702 may include a mass storage for data or instructions. By way of example, and not limitation, memory 702 may include a Hard Disk Drive (HDD), a floppy Disk Drive, flash memory, an optical Disk, a magneto-optical Disk, tape, or a Universal Serial Bus (USB) Drive or a combination of two or more of these. Memory 702 may include removable or non-removable (or fixed) media, where appropriate. The memory 702 may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory 702 is non-volatile solid-state memory. In a particular embodiment, the memory 702 includes Read Only Memory (ROM). Where appropriate, the ROM may be mask-programmed ROM, Programmable ROM (PROM), Erasable PROM (EPROM), Electrically Erasable PROM (EEPROM), electrically rewritable ROM (EAROM), or flash memory or a combination of two or more of these.

The processor 701 may read and execute the computer program instructions stored in the memory 702 to implement the method for determining the cause of any of the quality differences in the above embodiments.

In one example, the device for determining the cause of the quality difference may further include a communication interface 703 and a bus 710. As shown in fig. 7, the processor 701, the memory 702, and the communication interface 703 are connected by a bus 710 to complete mutual communication.

The communication interface 703 is mainly used for implementing communication between modules, apparatuses, units and/or devices in the embodiment of the present invention.

The bus 710 comprises hardware, software, or both to couple the components of the device that determine the cause of the quality difference to each other. By way of example, and not limitation, a bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hypertransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus or a combination of two or more of these. Bus 710 may include one or more buses, where appropriate. Although specific buses have been described and shown in the embodiments of the invention, any suitable buses or interconnects are contemplated by the invention.

The determining device of the cause of the quality difference may execute the determining method of the cause of the quality difference in the embodiment of the present invention based on the obtained service performance data, thereby implementing the determining method and apparatus of the cause of the quality difference described in conjunction with fig. 1 to 6.

In addition, in combination with the method for determining the cause of the quality difference in the above embodiments, the embodiments of the present invention may be implemented by providing a computer-readable storage medium. The computer readable storage medium having stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement the method of determining a cause of quality difference in any of the above embodiments.

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, 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.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims

1. A method for determining a cause of a quality difference, comprising:

acquiring service performance data;

extracting a plurality of target characteristics influencing network quality from the service performance data, and determining the probability of network quality difference caused by each target characteristic;

2. The method of claim 1, wherein the target features include two or more of: weak coverage, overlapping coverage, modulo 3 interference, number of concurrent users, and number of network handovers.

3. The method of claim 1, wherein extracting a plurality of target features from the traffic performance data that affect network quality comprises:

4. The method of claim 3, wherein determining a traffic indicator weight that causes network degradation based on the traffic performance data comprises:

extracting network indexes from the service performance data;

and inputting the network index into a user experience quality hierarchical model, and determining the weight of the service index causing poor network quality.

5. The method of claim 1, further comprising:

extracting network indexes from the service performance data;

determining the experience quality score of the single service based on the plurality of service indexes and the weight of each service index;

6. The method of claim 1, wherein the service performance data comprises: measurement report MR data, user plane S1-U interface data, and control plane S1-MME interface data.

7. The method of claim 6, wherein extracting a plurality of target features from the traffic performance data that affect network quality comprises:

8. The method of claim 7, wherein the converting the obtained service performance data into the target performance parameter comprises:

fusing the fused MR data and the S1-U interface data to obtain fused S1-U interface data;

and fusing the S1-MME interface data with the fused S1-U interface data to obtain the target performance parameters.

9. The method according to any one of claims 1-8, further comprising: and determining an optimization scheme based on the reason causing the network quality difference.

10. An apparatus for determining a cause of quality difference, comprising:

an obtaining unit, configured to obtain service performance data;

11. An apparatus for determining a cause of quality difference, comprising: at least one processor, at least one memory, and computer program instructions stored in the memory that, when executed by the processor, implement the method of any of claims 1-9.

12. A computer-readable storage medium having computer program instructions stored thereon, which when executed by a processor implement the method of any one of claims 1-9.