Network service evaluation method, electronic device and storage medium

By statistically analyzing key quality indicators of network services and dynamically adjusting thresholds, the problem of fixed thresholds being unable to adapt to changes in network service quality assessment is solved, achieving flexible and accurate assessment results.

CN114491406BActive Publication Date: 2024-12-03ZTE CORP
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202011155978.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-10-26
Publication Date
2024-12-03
Estimated Expiration
2040-10-26

AI Technical Summary

Technical Problem

In existing technologies, fixed thresholds for network quality indicators cannot adapt to normal fluctuations in network quality indicators, leading to errors in the evaluation results.

Method used

By statistically analyzing the key quality indicators (KQI) of network services and dynamically adjusting the thresholds, the first and second thresholds of the statistical analysis are used to evaluate the quality of network services. The dynamically adjusted thresholds serve as the evaluation criteria to adapt to the dynamic changes in network services.

Benefits of technology

It enables accurate and objective assessment of network service quality, avoiding misassessment caused by fixed thresholds, and making the assessment results more flexible and accurate.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114491406B_ABST
    Figure CN114491406B_ABST
Patent Text Reader

Abstract

The embodiment of the present invention relates to the field of communications, and discloses a network service evaluation method, electronic device, and storage medium. The network service evaluation method includes: performing statistical analysis on each key quality indicator KQI according to the call data in the first cycle to obtain the first threshold of each KQI; obtaining the second threshold of each KQI according to all the first thresholds of each KQI in the second cycle, wherein the second cycle contains at least one of the first cycles; obtaining the perception score of the network service according to the second threshold of each KQI and the call data in the third cycle. It is applied in the process of evaluating the network service.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to the field of communications, and in particular to a network service evaluation method, electronic device, and storage medium. Background Art

[0002] With the rapid development of modern communication technology, users have higher and higher requirements for the quality of network services. Therefore, network operators need to establish an effective end-to-end comprehensive evaluation system for service perception, so as to timely discover and solve the problem of poor quality of services in the entire network, and finally provide users with high-quality network services. At present, the evaluation method of service perception by network operators is mainly to use the fixed empirical threshold of quality indicators as the evaluation standard, and evaluate the quality of network services by comparing the quality indicator data of the current network services with the fixed empirical threshold of quality indicators.

[0003] However, in the case of normal fluctuations in network quality indicators, the fixed threshold of the quality indicator cannot adapt to the changes, resulting in the evaluation of the normally fluctuating network quality indicator as abnormal, thereby generating an erroneous evaluation. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to provide a network service evaluation method, electronic device and storage medium, which can correctly and objectively evaluate the quality of network services when network quality indicators fluctuate normally.

[0005] To solve the above technical problems, an embodiment of the present invention provides a method for evaluating network services, including: performing statistical analysis on each key quality indicator KQI based on the call record data within a first period to obtain a first threshold value for each KQI; obtaining a second threshold value for each KQI based on all the first threshold values ​​of each KQI within a second period, wherein the second period contains at least one of the first periods; obtaining a perception score of the network service based on the second threshold value of each KQI and the call record data within a third period.

[0006] An embodiment of the present invention further provides an electronic device, including:

[0007] at least one processor; and,

[0008] a memory communicatively connected to the at least one processor; wherein,

[0009] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned network service evaluation method.

[0010] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program, wherein the computer program implements the above-mentioned network service evaluation method when executed by a processor.

[0011] Compared with the prior art, the embodiments of the present invention can statistically analyze KQI according to the call data in the first cycle, obtain the first threshold of each KQI, so that the first threshold of each KQI is not a fixed value, but a threshold that is affected by the call data in the first cycle and changes adaptively, and then process all the first thresholds contained in the second cycle to obtain the second threshold of each KQI, so that the obtained threshold is more effective and reliable, and then obtain the perception score of the network service according to the second threshold of each KQI, so that the evaluation of the network service can be quantified, so that the evaluation result is more objective. The problem that the fixed threshold of the quality indicator in the prior art cannot adapt to the change and causes the normal fluctuation of the network quality indicator to be evaluated as abnormal, thereby causing an error. Since the first threshold of each KQI is obtained by statistically analyzing KQI according to the call data, the threshold of KQI will change with the change of the call data, so as to adapt to the dynamic change of the network service displayed by the call data, that is, when the technical solution provided by the embodiment of the present invention is used to evaluate the network service, the dynamically changing threshold can be used as the evaluation standard to evaluate the network service, which is more flexible and accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 is a flow chart of a network service evaluation method provided by a first embodiment of the present invention;

[0013] Figure 2 is a flow chart of a network service evaluation method provided by a second embodiment of the present invention;

[0014] Figure 3 is a partial networking diagram of packet core evolution in long term evolution in the second embodiment of the present invention;

[0015] Figure 4 is a flow chart of a network service evaluation method provided by a third embodiment of the present invention;

[0016] Figure 5 yes Figure 4 The flowchart of step 403 in the network service evaluation method provided by the third embodiment of the present invention is shown;

[0017] Figure 6 is a distribution curve diagram of a video download rate indicator in a third embodiment of the present invention;

[0018] Figure 7is a distribution curve diagram of the average time index of the web page display in the third embodiment of the present invention;

[0019] Figure 8 is a flow chart of a network service evaluation method provided by a fourth embodiment of the present invention;

[0020] Fig. 9 is a flow chart of a network service evaluation method provided by a fifth embodiment of the present invention;

[0021] Fig.10 It is a schematic structural diagram of an electronic device provided by a sixth embodiment of the present invention. DETAILED DESCRIPTION

[0022] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the embodiments of the present application will be described in detail below in conjunction with the accompanying drawings. However, it will be appreciated by those skilled in the art that in the present application, many technical details are proposed in order to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical scheme claimed in the present application can also be implemented. The division of the following embodiments is for the convenience of description, and the specific implementation of the present application should not be construed as any limitation, and the various embodiments can be combined and referenced with each other under the premise of no contradiction.

[0023] The first embodiment of the present invention relates to a network service evaluation method, which can be applied to the evaluation of network services in 3G, 4G and other communication systems. The process is as follows Figure 1 As shown, including:

[0024] Step 101: Perform statistical analysis on each key quality indicator KQI according to the call record data in a first period to obtain a first threshold value of each KQI.

[0025] In this embodiment, the first cycle is pre-set. Key Quality Indicators (KQI) are service quality parameters close to user experience mainly proposed for different services, and this embodiment does not provide specific examples of KQIs for network services. In actual use, step 101 can statistically analyze any KQI of any network service.

[0026] It should be noted that, in this implementation, the bill data in the first cycle includes bill data of at least one type of network service, and any type of network service corresponds to at least one KQI.

[0027] Step 102: Obtain a second threshold value of each KQI according to all first threshold values ​​of each KQI in a second period, wherein the second period includes at least one first period.

[0028] In this embodiment, the second cycle includes at least one first cycle, and each first cycle in the second cycle can obtain the first threshold of the KQI according to step 101. A comprehensive analysis is performed on all the first thresholds of each KQI obtained to obtain a more effective second threshold. The comprehensive analysis method can be to obtain an average value. It should be noted that the specific average method is not limited in this embodiment and other embodiments below.

[0029] Step 103: Acquire a perception score of the network service according to the second threshold of each KQI and the call record data in the third period.

[0030] In this embodiment, the obtained effective threshold is compared with the KQI in the call record data, and further analysis is performed based on the comparison results to obtain a quantitative value of the perceived evaluation of the network service. The quantitative value can be used directly as the perception score or further analyzed and processed to obtain the numerical value as the perception score.

[0031] It should be noted that in this embodiment, each type of network service has a perception score, and step 103 obtains the perception score of at least one type of network service.

[0032] Compared with the prior art, the embodiments of the present invention can statistically analyze KQI according to the call data in the first cycle, obtain the first threshold of each KQI, so that the first threshold of each KQI is not a fixed value, but a threshold that is affected by the call data in the first cycle and changes adaptively, and then process all the first thresholds contained in the second cycle to obtain the second threshold of each KQI, so that the obtained threshold is more effective and reliable, and then obtain the perception score of the network service according to the second threshold of each KQI, so that the evaluation of the network service can be quantified, so that the evaluation result is more objective. The problem that the fixed threshold of the quality indicator in the prior art cannot adapt to the change and causes the normal fluctuation of the network quality indicator to be evaluated as abnormal, thereby causing an error. Since the first threshold of each KQI is obtained by statistically analyzing KQI according to the call data, the threshold of KQI will change with the change of the call data, so as to adapt to the dynamic change of the network service displayed by the call data, that is, when the technical solution provided by the embodiment of the present invention is used to evaluate the network service, the dynamically changing threshold can be used as the evaluation standard to evaluate the network service, which is more flexible and accurate.

[0033] The second embodiment of the present invention relates to a network service evaluation method, which is basically the same as the network service evaluation method provided by the first embodiment of the present invention, except that it is necessary to obtain call list data of the same network service, such as Figure 2 As shown, it also includes:

[0034] Step 201, obtaining call record data of the user plane S1-U interface collected by a probe, wherein the probe is set between a wireless base station and a service gateway.

[0035] In this embodiment, if Figure 3 The partial networking diagram of the Evolved Packet Core (EPC) shown in the figure, the Service Gateway (SGW) is mainly responsible for user plane processing, responsible for data packet routing and forwarding, and supports the switching of different access technologies of the Third Generation Partnership Project (3GPP). It serves as the anchor point of the user plane when switching occurs. For each user equipment related to the evolved packet system, there is an SGW serving it at a point in time; the user plane S1-U is a main interface of the EPC network, located between the wireless base station and the SGW. eNodeB is the name of the base station in LTE, EPC is the abbreviation of Evolved Packet Core, PGW is the abbreviation of PDN Gateway, MME is the abbreviation of Mobility Management Entity, S1-U, S1-MME, S5 / 8, S11, S10 are the corresponding interfaces between different connection objects in the Evolved Packet Core networking. Therefore, the probe set between the wireless base station and the SGW can be used to collect data from the user plane S1-U interface, and the S1-U interface obtains XDR (External Data Representation) call record data.

[0036] Step 202: setting the first period, the second period and the third period.

[0037] In this implementation, the first cycle and the third cycle are not limited and can be set according to actual needs during implementation. The second cycle can be set according to needs under the condition of containing one or more first cycles.

[0038] Step 203: divide the call bill data of the S1-U interface according to the type of network service and the first period, and obtain the call bill data in the first period.

[0039] In this embodiment, the types of network services can be divided into web pages, videos, games, various services provided to users through the Internet (Over The Top, OTT), voice, OTT video, and traffic types according to the service characteristics and network performance requirements. Of course, the above are only specific examples. In actual use, the types of network services may also include other types or other types obtained according to different classification criteria, which will not be described one by one here.

[0040] Specifically, first, according to the type of network service, different types of call bill data such as web page, video, game, OTT voice, OTT video and traffic are screened and divided from the XDR call bill of the S1-U interface for one day, and then the time of obtaining data is divided with the first cycle as the basic unit to obtain the call bill data within the first cycle. It should be noted that the data of the time "day" is only for example, and other time lengths can also be used. The order of division according to network service and division according to the first cycle is not limited.

[0041] Step 204: divide the call list data of the S1-U interface according to the type of network service and the third period, and obtain the call list data in the third period.

[0042] In this embodiment, the types of network services can be divided into web pages, videos, games, various services provided to users through the Internet (Over The Top, OTT), voice, OTT video, and traffic types according to the service characteristics and network performance requirements. Of course, the above are only specific examples. In actual use, the types of network services may also include other types or other types obtained according to different classification criteria, which will not be described one by one here.

[0043] Specifically, first, according to the type of network service, different types of call bill data such as web page, video, game, OTT voice, OTT video and traffic are screened and divided from the XDR call bill of the S1-U interface for one day, and then the time of obtaining data is continued to be divided with the third period as the basic unit to obtain the call bill data within the first period. It should be noted that the data of the time "day" is only for example, and other time lengths can also be used. The order of division according to network service and division according to the third period is not limited.

[0044] Compared with the prior art, the embodiments of the present invention, on the basis of achieving the beneficial effects brought by the first embodiment, can dynamically obtain the KQI threshold and at the same time obtain the classified call record data in real time, so that the changes in network service quality indicators can be perceived in real time, and the obtained threshold is further made more sensitive to data changes and the perception score is more accurate.

[0045] The third embodiment of the present invention relates to a network service evaluation method, which is basically the same as the network service evaluation method provided by the first embodiment of the present invention, except that: Figure 4 As shown, step 101 includes:

[0046] Step 401, obtaining each KQI value of each user according to the call list data in the first cycle.

[0047] In this embodiment, the bill data in the first cycle is the bill data obtained within a certain period of time. Therefore, for each user, a KQI corresponds to a group of data. Specifically, all values ​​of a certain KQI of each user in the first cycle are averaged, or the median is calculated, and the average or median processed value is used as the KQI value of each user. Of course, other statistical methods can also be used to process a group of KQI data of each user to obtain a KQI value that can reflect the characteristics of a group of KQI values ​​of the user in the first cycle.

[0048] Step 402: Count the number of users at different values ​​of each KQI to obtain a probability density curve of each KQI.

[0049] In this embodiment, specifically, if a certain network service corresponds to N KQIs, then a specific value KQI of the i-th KQI in The number of users under is m, and the total number of users counted is M, then KQI in Probability of occurrence The density curve function of the i-th KQI is: Among them, KQI in is the specific value of the i-th KQI indicator, m in Is the specific value KQI in The corresponding number of users, M i is the number of all users corresponding to the i-th KQI indicator.

[0050] Step 403: Analyze the probability density curve of each KQI to obtain the first threshold of each KQI.

[0051] Specifically, Figure 5 As shown, step 403 may include:

[0052] Step 501: Set a first threshold quantile and a second threshold quantile for each KQI, wherein the first threshold quantile is smaller than the second threshold quantile.

[0053] In this embodiment, the value ranges of the first threshold quantile and the second threshold quantile are (0, 1), which can be set according to actual situations or default values can be used. The first threshold quantiles and the second threshold quantiles of different KQIs can be the same or different. It should be noted that setting the first threshold quantile less than the second threshold quantile is only for convenience of representation.

[0054] It should be noted that in this embodiment, two threshold quantiles are set, but in the actual application process, the number of threshold quantiles is not limited, and one or more threshold quantiles can be set according to actual needs.

[0055] Step 502: Obtain the first threshold of each KQI according to the change characteristics of each KQI, the probability density curve of each KQI, the first threshold quantile, and the second threshold quantile, where the first threshold of each KQI includes a high-quality threshold and a poor-quality threshold.

[0056] In this embodiment, set the first threshold quantile as p1, the second threshold quantile as p2, and 0 < p1 < p2 < 1. Then when the larger the KQI, the better (in this case, the KQI is a positive indicator), the poor-quality threshold quantile is p1, the high-quality threshold quantile is p2, and the value of the KQI corresponding to the quantile p1 is the poor-quality threshold worst dynamic , and the value of the KQI corresponding to the quantile p2 is the high-quality threshold best dynamic ; when the smaller the KQI, the better (in this case, the KQI is a negative indicator), the high-quality threshold quantile is p1, the poor-quality threshold quantile is p2, and the value of the KQI corresponding to the quantile p1 is the high-quality threshold best dynamic , and the value of the KQI corresponding to the quantile p2 is the poor-quality threshold worst dynamic .

[0057] More specifically, taking the on-demand video service in the live network of Operator O in a certain country as an example, the distribution curve of the video download rate index calculated by user dimension with a daily time granularity is as Figure 6 shown, and the video download rate index is a positive indicator. Set the poor-quality threshold quantile p1 = 0.4, the high-quality threshold quantile p2 = 0.925. In the ascending order of the video download rate index value, take the index value at the p1 quantile as the poor-quality threshold worst dynamic , and take the index value at the p2 quantile as the high-quality threshold best dynamic . After calculation, the adaptive threshold of the video download rate is worst dynamic = 20 Kbps, best dynamic= 900Kbps. Taking the web browsing service in the existing network of operator O in a certain country as an example, the distribution curve of the average web page display duration indicator calculated according to the user dimension with a time granularity of day is as follows: Figure 7 As shown in the figure, the average webpage display time indicator is a negative indicator. Set the high-quality threshold quantile p1 = 0.075, the poor-quality threshold quantile p2 = 0.6, and take the p1 quantile value as the best high-quality threshold value according to the direction of the average webpage display time indicator value from small to large. dynamic , take the index value of p2 quantile as the worst quality threshold dynamic After calculation, the adaptive threshold of the average web page display time is the worst dynamic =3800ms, best dynamic =400ms.

[0058] Compared with the prior art, the embodiments of the present invention, on the basis of achieving the beneficial effects brought by the first embodiment, can use probability distribution to determine the value at a special position when the KQI values ​​are orderly distributed, and use the special value as the threshold, so that the obtained threshold is more objective and accurate.

[0059] The fourth embodiment of the present invention relates to a network service evaluation method, which is basically the same as the network service evaluation method provided by the first embodiment of the present invention, except that: Figure 8 As shown, step 103 includes:

[0060] Step 801, classify the call record data in the third cycle, and obtain the KQI of each type of call record data.

[0061] In this embodiment, classification is performed according to one or more combinations of dimensions such as user, province, city, district, county, region, community, APP or site. Of course, the above is only a specific example, and the classification method can also include other divisions in actual use, which will not be described one by one here.

[0062] It should be noted that, in the present embodiment, the smallest unit of KQI for each category of call record data obtained is a single user. The KQI obtained for the user should be the operation corresponding to step 401. For example, step 401 averages the KQI of users within a period of time, and step 801 obtains the KQI of the smallest unit, which should also be averaged, and then each category is calculated based on the average of each user.

[0063] Step 802: Average the KQI of each type of call record data to obtain the average of each KQI in the third period.

[0064] Step 803: Determine a scoring function for each KQI according to the second threshold of each KQI.

[0065] In this embodiment, the specific mapping relationship of the scoring function of each KQI is related to the second threshold value and can be mapped to the entire set scoring value space. This can avoid the problem that the score can take too few values ​​and the score cannot intuitively reflect the difference between the qualities represented by the KQI values. It should be noted that the specific mapping relationship of the scoring function is not limited, and any function that meets the above idea can be used as a scoring function.

[0066] Specifically, taking the score result as QoE (according to the calculation formula of QoE, the value range of QoE is 0 to 5 points) as an example, the score of the i-th KQI of a certain network service is Score i The following formula can be used:

[0067] Among them: Score i is the score of the ith KQI of the network service, worst i is the poor quality threshold of the i-th KQI of the network service, best i is the quality threshold of the i-th KQI of a certain network service, worst i and best i The value of is obtained from the third implementation mode. direction is the direction of the indicator. For example, the larger the KQI, the better, it is a positive indicator and direction = 1, otherwise direction = -1. It should be noted that in the actual implementation process, the scoring value space is not limited, but the scoring value space of all KQIs of the same network remains consistent.

[0068] Step 804: Determine the evaluation score of each KQI according to the average of each KQI and the scoring function of each KQI.

[0069] In this embodiment, a specific method is to sequentially substitute the average of each KQI into the scoring function of the corresponding KQI obtained in step 803, and the obtained function value is the evaluation score of each KQI.

[0070] Step 805 , weighted average the evaluation scores of the KQIs of the same network service according to preset weights to obtain a perception score of the network service.

[0071] In this embodiment, the calculation formula of the perception score is: Among them: Score i Calculated in step 804, w i is the preset weight of the i-th KQI and satisfies w i ≥0.

[0072] It should be noted that the preset weight is set according to actual needs and can be preset according to the importance of the impact of the i-th KQI on network service perception.

[0073] More specifically, taking the gaming service in the existing network of operator O in a certain country as an example, the indicator weights and the adaptive thresholds for calculating 3G and 4G services are shown in the following table.

[0074]

[0075] More specifically, taking the on-demand video service in the existing network of operator O in a certain country as an example, assuming that there are five KQIs, namely, video playback success rate, video playback waiting delay, video freeze frequency, video freeze duration ratio and video download rate, and the relevant data of each KQI is calculated and determined as follows: The weights are: w1 = 0.20, w2 = 0.25, w3 = 0.15, w4 = 0.15, w5 = 0.25, then the perception score is calculated as follows:

[0076] QoE=0.20×Score 播放成功率 +0.25×Score 播放等待时延 +0.15×Score 卡顿次数 +0.15×Score 卡顿时长占比 +0.25×Score 下载速率

[0077] Substituting the data into the input, we get a perception score of 2.28.

[0078] Compared with the prior art, the embodiments of the present invention, on the basis of achieving the beneficial effects brought by the first embodiment, adopt a predefined function that can be mapped to the entire score value range when obtaining the score, so that the obtained perception score is not affected by subjective factors, and the obtained score has many value conditions, which can reflect the perception difference and make the evaluation more discriminatory; at the same time, weighted average is adopted to distinguish different KQIs, so that the obtained perception score can better represent the quality of network services.

[0079] The fifth embodiment of the present invention relates to a network service evaluation method, which is basically the same as the network service evaluation method provided by the first embodiment of the present invention, except that the assessment period is adjustable, such as Fig. 9 As shown, specifically including:

[0080] Step 901, adjusting the second cycle from small to large.

[0081] Specifically, a smaller value can be selected in the early second cycle, and a larger value can be gradually selected over time until the second cycle is adjusted to a stable impact on the perception score, and the second cycle is no longer adjusted. It should be noted that the specific number of adjustments and the magnitude of each adjustment are not limited.

[0082] Step 902: Update the second threshold of each KQI according to the adjusted second period.

[0083] In this embodiment, step 902 is performed once each time the second period is adjusted.

[0084] Compared with the prior art, the implementation mode of the present invention, on the basis of achieving the beneficial effects brought by the first implementation mode, can ensure the stability of the effective threshold of the service quality indicator after the algorithm has run for a long time because the assessment period can be adjusted. Otherwise, the calculated perception score will vary greatly, which is not conducive to the analysis of poor service quality problems.

[0085] A sixth embodiment of the present invention relates to an electronic device, such as Fig.10 As shown, including:

[0086] at least one processor 1001; and,

[0087] A memory 1002 is communicatively connected to the at least one processor 1001; wherein,

[0088] The memory 1002 stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor 1001 to enable the at least one processor 1001 to execute the network service evaluation method described in the first to fifth embodiments of the present invention.

[0089] Among them, the memory and the processor are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors and memories together. The bus can also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor is transmitted on a wireless medium via an antenna, and further, the antenna also receives data and transmits the data to the processor.

[0090] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0091] The seventh embodiment of the present invention relates to a computer-readable storage medium storing a computer program, which implements the above method embodiment when executed by a processor.

[0092] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0093] Those skilled in the art will appreciate that the above-mentioned embodiments are specific examples for implementing the present invention, and in actual applications, various changes may be made thereto in form and detail without departing from the spirit and scope of the present invention.

Claims

1. A method for evaluating network services, characterized in that: include: Perform statistical analysis on each key quality indicator KQI according to the call record data in the first cycle to obtain a first threshold value of each KQI; Acquire a second threshold value of each KQI according to all the first threshold values ​​of each KQI in a second period, wherein the second period includes at least one of the first periods; The perceived score of the network service is obtained according to the second threshold of each KQI and the call record data in the third period.

2. The method according to claim 1, characterized in that: Before performing statistical analysis on each key quality indicator KQI according to the call record data in the first cycle and obtaining the first threshold of each KQI, the method further includes: Acquire call list data of a user plane S1-U interface collected by a probe, wherein the probe is arranged between a wireless base station and a service gateway; Setting the first period, the second period and the third period; Dividing the call bill data of the S1-U interface according to the type of network service and the first period, and acquiring the call bill data in the first period; The call list data of the S1-U interface is divided according to the type of the network service and the third period, and the call list data in the third period is obtained.

3. The method according to claim 1, characterized in that The performing statistical analysis on each key quality indicator KQI according to the call record data in the first cycle to obtain the first threshold value of each KQI includes: Obtain each KQI value of each user according to the call record data in the first cycle; Counting the number of users at different values ​​of each KQI to obtain a probability density curve of each KQI; The probability density curve of each KQI is analyzed to obtain a first threshold of each KQI.

4. The method according to claim 3, characterized in that The analyzing the probability density curve of each KQI to obtain the first threshold of each KQI includes: Set a first threshold quantile and a second threshold quantile for each KQI, respectively, wherein the first threshold quantile is smaller than the second threshold quantile; According to the variation characteristics of each KQI, the probability density curve of each KQI, the first threshold quantile and the second threshold quantile, a first threshold of each KQI is obtained, wherein the first threshold of each KQI includes a high-quality threshold and a poor-quality threshold.

5. The method according to claim 4, characterized in that The step of obtaining the first threshold of each KQI according to the variation characteristics of each KQI, the probability density curve of each KQI, the first threshold quantile, and the second threshold quantile, wherein the first threshold of each KQI includes a high-quality threshold and a poor-quality threshold, and includes: If the variation characteristic of the KQI is that the larger the value, the better the network service quality, the KQI value corresponding to the first threshold quantile on the probability density curve is the poor quality threshold, and the KQI value corresponding to the second threshold quantile on the probability density curve is the high quality threshold; If the changing characteristic of the KQI is that the smaller the value, the better the network service quality, the KQI value corresponding to the first threshold quantile on the probability density curve is the high-quality threshold, and the KQI value corresponding to the second threshold quantile on the probability density curve is the poor-quality threshold.

6. The method according to claim 1, characterized in that The acquiring, according to all the first thresholds of each KQI in the second period, the second threshold of each KQI, wherein the second period includes at least one of the first periods, comprises: All the first thresholds of each KQI in the second period are averaged to obtain a second threshold of each KQI.

7. The method according to claim 1, characterized in that The acquiring the perception score of the network service according to the second threshold of each KQI and the call record data in the third period includes: Classifying the call record data in the third period and obtaining the KQI of each type of call record data; Averaging the KQIs of each type of call record data respectively to obtain the average of each KQI within the third period; determining a scoring function for each KQI according to the second threshold of each KQI; The evaluation score of each KQI is determined according to the average of each KQI and the scoring function of each KQI; the evaluation scores of the KQIs of the same network service are weighted averaged according to preset weights to obtain the perception score of the network service.

8. The method according to claim 1, characterized in that Before obtaining the perception score of the network service according to the second threshold of each KQI and the call record data in the third period, the method further includes: Adjusting the second period from small to large; The second threshold of each KQI is updated according to the adjusted second period.

9. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the network service evaluation method according to any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the network service evaluation method according to any one of claims 1 to 8 is implemented.

Citation Information

Patent Citations

  • Client perception evaluating method and system

    CN101562830A

  • Method and equipment for acquiring KQI threshold

    CN103840978A