Quality difference user determination method, apparatus, device, and medium

Abstract

The application discloses a method, device, equipment and medium for determining a poor-quality user, and the method comprises the following steps: acquiring classified data of a user, wherein the classified data comprises 5G independent networking (SA) call data, 4G general packet radio service (GPRS) call data, GPRS call data and voice over long-term evolution (VoLTE) call data; determining a call quality index of a 5G user according to the classified data, wherein the call quality index comprises at least one of the following: a back-off frequency, a proportion of a network staying time of 5G independent networking, and / or a proportion of 5G traffic; and if the call quality index meets a preset condition, determining that the user is a poor-quality user. The application improves the accuracy of the determined poor-quality user.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method, apparatus, device, and medium for identifying users with poor quality. Background Technology

[0002] 5G services are various telecommunications services based on 5G networks. At present, they are mainly high-speed Internet access services, which can provide users with more immersive and ultimate service experiences such as augmented reality, virtual reality, and ultra-high-definition (3D) video, and meet the needs of Internet of Things applications such as mobile healthcare, vehicle networking, smart home, industrial control, and environmental monitoring.

[0003] Existing solutions for assessing and locating wireless network problems are limited to quantitative analysis of key performance indicators (KPIs) at the network management cell and network element levels. They treat KPIs as user perception indicators and rely solely on them to diagnose customer experience. This flawed optimization concept—that good KPIs mean good customer experience and bad KPIs mean bad customer experience—leads to low accuracy in identifying users with poor wireless network quality. Summary of the Invention

[0004] The main objective of this invention is to provide a method, apparatus, device, and medium for identifying poor-quality users, aiming to solve the problem of how to accurately identify poor-quality users in a wireless network.

[0005] To achieve the above objectives, the present invention provides a method for identifying users with poor quality of service, the method comprising the following steps:

[0006] Acquire user data, including 5G standalone (SA) call detail records (CDRs), 4G General Packet Radio Service (GPRS) CDRs, GPRS CDRs, and VoLTE (Voice over LTE) CDRs.

[0007] The call quality indicators for 5G users are determined based on the data analysis. The call quality indicators include at least one of the following: number of rollbacks, percentage of 5G standalone network usage time, and / or percentage of 5G traffic.

[0008] If the call quality indicators meet the preset conditions, then the user is determined to be a poor quality user.

[0009] In one embodiment, the call quality indicators include the number of fallbacks, the percentage of 5G standalone network usage time, and the percentage of 5G traffic. The step of determining the user as a poor-quality user if the call quality indicators meet preset conditions includes:

[0010] If the call quality indicators meet the preset conditions, then the user is determined to be a poor quality user;

[0011] The preset conditions are that the number of rollbacks is greater than a preset number, or the percentage of the 5G standalone network's on-premises time is less than a preset first percentage, or the percentage of 5G traffic is less than a preset second percentage.

[0012] In one embodiment, the call quality metric includes the number of rollbacks, and the step of determining the call quality metric for 5G users based on the analysis data includes:

[0013] The 5G SA call detail records, 4G GPRS call detail records, the GPRS call detail records, and the VoLTE call detail records are sorted in chronological order.

[0014] Based on the sorting results, non-5G SA call details within a preset time period are determined for each 5G SA call detail.

[0015] If the non-5G SA call detail record does not include the VoLTE call detail record, then the number of rollbacks is updated according to a preset value.

[0016] In one embodiment, the call quality metric includes the percentage of time spent on the 5G standalone network, and the step of determining the call quality metric for 5G users based on the analysis data includes:

[0017] Based on the aforementioned data analysis, determine the local internet access duration, roaming internet access duration, and total 4G internet access duration in the 5G SA call detail records;

[0018] The first duration is determined based on the local internet access duration and roaming internet access duration in the 5G SA call detail record;

[0019] The second duration is determined based on the sum of the total 4G internet access duration in the GPRS call detail record and the first duration;

[0020] The proportion of the 5G standalone network's on-premises time is determined based on the ratio of the first duration to the second duration.

[0021] In one embodiment, the call quality indicator includes the proportion of 5G traffic, and the step of determining the call quality indicator of 5G users based on the data analysis includes:

[0022] Based on the data analysis, determine the 5G local internet traffic and 5G roaming internet traffic in the 5G SA call detail records, the total NSA traffic in the 5G non-standalone (NSA) call detail records, and the 4G local internet traffic and 4G roaming internet traffic in the 4G GPRS call detail records.

[0023] The first traffic volume is determined based on 5G local internet traffic, 5G roaming internet traffic, and NSA traffic;

[0024] The second data volume is determined based on 5G local internet traffic, 5G roaming internet traffic, 4G local internet traffic, and 4G roaming internet traffic.

[0025] The 5G traffic percentage is determined based on the ratio of the first traffic to the second traffic.

[0026] In one embodiment, after the step of determining that the user is a poor-quality user, the method further includes:

[0027] The local 5G cell corresponding to the poor quality user is determined based on the 5G SA call detail record.

[0028] The local 5G cells corresponding to the poor-quality users are sorted, and the local 5G cells with the highest preset ranking are designated as the permanent 5G cells of the poor-quality users.

[0029] In one embodiment, the step of sorting the local 5G cells corresponding to the poor-quality users includes:

[0030] Determine the internet access duration of the local 5G cell corresponding to the user with poor internet quality;

[0031] The local 5G cells corresponding to the users with poor internet access quality are sorted according to the duration of internet access.

[0032] To achieve the above objectives, the present invention also provides a device for determining poor-quality users, the device comprising:

[0033] The acquisition module is used to acquire the user's economic data, which includes 5G standalone (SA) call detail records (CDRs), 4G General Packet Radio Service (GPRS) CDRs, GPRS CDRs, and Long Term Evolution Voice Bearer (VoLTE) CDRs.

[0034] The calculation module is used to determine the call quality indicators of 5G users based on the data analysis. The call quality indicators include at least one of the following: number of fallbacks, percentage of 5G standalone network usage time, and / or percentage of 5G traffic.

[0035] The determination module is used to determine the user as a poor-quality user if the call quality indicators meet preset conditions.

[0036] To achieve the above objectives, the present invention also provides a poor quality user determination device, the poor quality user determination device including a memory, a processor, and a poor quality user determination program stored in the memory and executable on the processor, wherein the poor quality user determination program, when executed by the processor, implements the various steps of the poor quality user determination method as described above.

[0037] To achieve the above objectives, the present invention also provides a computer-readable storage medium storing a poor-quality user determination program, which, when executed by a processor, implements the various steps of the poor-quality user determination method as described above.

[0038] This invention provides a method, apparatus, device, and medium for identifying users with poor call quality. The method acquires user call quality data, including 5G Standalone (SA) call detail records (CDRs), 4G General Packet Radio Service (GPRS) CDRs, and VoLTE (Voice over LTE) CDRs. Based on the CDRs, the method determines the call quality indicators for 5G users, including at least one of the following: number of fallbacks, percentage of 5G SA network usage time, and / or percentage of 5G traffic. If the call quality indicators meet preset conditions, the user is identified as a user with poor call quality. By determining the number of fallbacks, percentage of 5G SA network usage time, and / or percentage of 5G traffic based on the CDRs, and accurately identifying users with poor call quality, the method improves the accuracy of identifying such users. Attached Figure Description

[0039] Figure 1 This is a schematic diagram of the hardware structure of the device for determining poor quality users according to an embodiment of the present invention;

[0040] Figure 2 This is a flowchart illustrating the first embodiment of the method for determining poor-quality users according to the present invention.

[0041] Figure 3 A detailed flowchart of step S20 of the second embodiment of the method for determining poor-quality users of the present invention;

[0042] Figure 4 A detailed flowchart of step S20 of the third embodiment of the method for determining poor-quality users of the present invention;

[0043] Figure 5 This is a schematic diagram of the logic structure of the poor quality user determination device of the present invention.

[0044] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0045] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0046] The main solution of this invention is as follows: Acquire user call detail records (CDRs), including 5G Standalone (SA) call detail records, 4G General Packet Radio Service (GPRS) call detail records, GPRS call detail records, and VoLTE call detail records; determine the call quality indicators of the 5G user based on the CDRs, including at least one of the following: number of fallbacks, 5G SA network dwell time percentage, and / or 5G traffic percentage; if the call quality indicators meet preset conditions, the user is identified as a poor-quality user. By determining the number of fallbacks, 5G SA network dwell time percentage, and / or 5G traffic percentage based on the CDRs, and accurately identifying poor-quality users, the accuracy of identifying poor-quality users is improved.

[0047] As one implementation scheme, users with poor quality determine that the equipment can be like... Figure 1 As shown.

[0048] The embodiments of the present invention relate to a device for determining poor user quality, which includes: a processor 101, such as a CPU, a memory 102, and a communication bus 103. The communication bus 103 is used to enable communication between these components.

[0049] Memory 102 can be high-speed RAM or stable memory (non-volatile memory), such as disk storage. Figure 1 As shown, the memory 102, which is a computer-readable storage medium, may include a user program for determining poor quality; and the processor 101 may be used to call the user program for determining poor quality stored in the memory 102 and perform the following operations:

[0050] Acquire user data, including 5G standalone (SA) call detail records (CDRs), 4G General Packet Radio Service (GPRS) CDRs, GPRS CDRs, and VoLTE (Voice over LTE) CDRs.

[0051] The call quality indicators for 5G users are determined based on the data analysis. The call quality indicators include at least one of the following: number of rollbacks, percentage of 5G standalone network usage time, and / or percentage of 5G traffic.

[0052] If the call quality indicators meet the preset conditions, then the user is determined to be a poor quality user.

[0053] In one embodiment, processor 101 can be used to invoke a poor quality user determination program stored in memory 102 and perform the following operations:

[0054] If the call quality indicators meet the preset conditions, then the user is determined to be a poor quality user;

[0055] The preset conditions are that the number of rollbacks is greater than a preset number, or the percentage of the 5G standalone network's on-premises time is less than a preset first percentage, or the percentage of 5G traffic is less than a preset second percentage.

[0056] In one embodiment, processor 101 can be used to invoke a poor quality user determination program stored in memory 102 and perform the following operations:

[0057] The 5G SA call detail records, 4G GPRS call detail records, the GPRS call detail records, and the VoLTE call detail records are sorted in chronological order.

[0058] Based on the sorting results, non-5G SA call details within a preset time period are determined for each 5G SA call detail.

[0059] If the non-5G SA call detail record does not include the VoLTE call detail record, then the number of rollbacks is updated according to a preset value.

[0060] In one embodiment, processor 101 can be used to invoke a poor quality user determination program stored in memory 102 and perform the following operations:

[0061] Based on the aforementioned data analysis, determine the local internet access duration, roaming internet access duration, and total 4G internet access duration in the 5G SA call detail records;

[0062] The first duration is determined based on the local internet access duration and roaming internet access duration in the 5G SA call detail record;

[0063] The second duration is determined based on the sum of the total 4G internet access duration in the GPRS call detail record and the first duration;

[0064] The proportion of the 5G standalone network's on-premises time is determined based on the ratio of the first duration to the second duration.

[0065] In one embodiment, processor 101 can be used to invoke a poor quality user determination program stored in memory 102 and perform the following operations:

[0066] Based on the data analysis, determine the 5G local internet traffic and 5G roaming internet traffic in the 5G SA call detail records, the total NSA traffic in the 5G non-standalone (NSA) call detail records, and the 4G local internet traffic and 4G roaming internet traffic in the 4G GPRS call detail records.

[0067] The first traffic volume is determined based on 5G local internet traffic, 5G roaming internet traffic, and NSA traffic;

[0068] The second data volume is determined based on 5G local internet traffic, 5G roaming internet traffic, 4G local internet traffic, and 4G roaming internet traffic.

[0069] The 5G traffic percentage is determined based on the ratio of the first traffic to the second traffic.

[0070] In one embodiment, processor 101 can be used to invoke a poor quality user determination program stored in memory 102 and perform the following operations:

[0071] The local 5G cell corresponding to the poor quality user is determined based on the 5G SA call detail record.

[0072] The local 5G cells corresponding to the poor-quality users are sorted, and the local 5G cells with the highest preset ranking are designated as the permanent 5G cells of the poor-quality users.

[0073] In one embodiment, processor 101 can be used to invoke a poor quality user determination program stored in memory 102 and perform the following operations:

[0074] Determine the internet access duration of the local 5G cell corresponding to the user with poor internet quality;

[0075] The local 5G cells corresponding to the users with poor internet access quality are sorted according to the duration of internet access.

[0076] Based on the hardware architecture of the device for determining poor-quality users described above, an embodiment of the method for determining poor-quality users of the present invention is proposed.

[0077] Reference Figure 2 , Figure 2 This is a first embodiment of the method for determining poor-quality users according to the present invention. The method for determining poor-quality users includes the following steps:

[0078] Step S10: Obtain the user's data segmentation data, which includes 5G Standalone (SA) call detail records (CDRs), 4G General Packet Radio Service (GPRS) CDRs, GPRS CDRs, and Long Term Evolution (LTE) Voice Bearer (VoLTE) CDRs.

[0079] Specifically, the data includes 5G Standalone (SA) call detail records (CDRs), 4G GPRS (General Packet Radio Service) CDRs, GPRS CDRs, and VoLTE (Voice over Long-Term Evolution) CDRs.

[0080] The 5G SA (Standalone) network mainly includes the core network, backhaul, fronthaul, and radio access network. Key technologies in the core network include NFV (Network Function Virtualization), SDN (Software Defined Network), network slicing, and MEC (Multi-access Edge Computing). Backhaul refers to the connection between the radio access network and the core network. Fiber optic cables are ideal for backhaul, but in environments where fiber optic deployment is difficult or too costly, wireless backhaul is an alternative, such as point-to-point microwave or millimeter-wave backhaul. Fronthaul refers to the connection between the BBU (Building Baseband Unit) pool and the remote radio unit (RRU), such as C-RAN (Cloud-Radio Access Network). Fronthaul link capacity mainly depends on the radio air interface rate and the number of MIMO (Multiple-Input Multiple-Output) antennas. 4G fronthaul links use the CPRI (Common Public Radio Interface) protocol. Key technologies included in the radio access network include: C-RAN, SDR (Software-defined radio), CR (cognitive radio), low-power radio access nodes (Small Cells), self-organizing networks, D2D communication, massive MIMO, millimeter wave, advanced modulation and access technologies, in-band full-duplex, carrier aggregation, low latency, and low power consumption technologies, which are used to improve capacity, spectrum efficiency, reduce latency, and improve energy efficiency to meet 5G key performance indicators.

[0081] Step S20: Determine the call quality indicators of 5G users based on the data analysis. The call quality indicators include at least one of the following: number of rollbacks, percentage of 5G standalone network usage time, and / or percentage of 5G traffic.

[0082] Specifically, the call quality indicators for 5G users are determined based on the data analysis. These indicators are used to measure the call quality of users and include at least one of the following: number of rollbacks, and / or the percentage of 5G standalone network usage time, and / or the percentage of 5G traffic. The number of rollbacks, the percentage of 5G standalone network usage time, and / or the percentage of 5G traffic are determined by the core network side data in the data analysis.

[0083] Optionally, call quality metrics include the number of rollbacks. 5G SA call details, 4G GPRS call details, GPRS call details, and VoLTE call details are sorted in chronological order. Based on the sorting results, non-5G SA call details within a preset duration following each 5G SA call detail are determined. Non-5G SA call details can be at least one of 4G GPRS call details, GPRS call details, and VoLTE call details. Optionally, the preset duration can be 10 minutes. If the non-5G SA call details do not include VoLTE call details, the number of rollbacks is updated according to a preset value. Optionally, the preset value can be 1, and the number of rollbacks is incremented by 1.

[0084] Step S30: If the call quality index meets the preset conditions, then the user is determined to be a poor quality user.

[0085] Specifically, if the call quality indicators meet preset conditions, the user is identified as a poor-quality user. Optionally, when the call quality indicators include the number of rollbacks, the percentage of 5G standalone network usage time, and the percentage of 5G traffic, the preset conditions can be that the number of rollbacks is greater than a preset number, the percentage of 5G standalone network usage time is less than a preset first percentage, or the percentage of 5G traffic is less than a preset second percentage; that is, if the number of rollbacks is greater than the preset number, the percentage of 5G standalone network usage time is less than the preset first percentage, or the percentage of 5G traffic is less than the preset second percentage, the user is identified as a poor-quality user.

[0086] Optionally, when the call quality indicators include the number of rollbacks and the percentage of 5G standalone network usage time, the preset condition can be that the number of rollbacks is greater than a preset number, or the percentage of 5G standalone network usage time is less than a preset first proportion; that is, if the number of rollbacks is greater than the preset number, or the percentage of 5G standalone network usage time is less than the preset first proportion, then the user is determined to be a poor quality user.

[0087] Optionally, when the call quality indicators include the percentage of 5G standalone network usage time and the percentage of 5G traffic, the preset condition can be that the percentage of 5G standalone network usage time is less than a preset first percentage, or the percentage of 5G traffic is less than a preset second percentage; that is, if the percentage of 5G standalone network usage time is less than the preset first percentage, or the percentage of 5G traffic is less than the preset second percentage, then the user is determined to be a poor quality user.

[0088] Optionally, when the call quality indicators include the number of rollbacks and the proportion of 5G traffic, the preset condition can be that the number of rollbacks is greater than a preset number, or the proportion of 5G traffic is less than a preset second proportion; that is, if the number of rollbacks is greater than the preset number, or the proportion of 5G traffic is less than the preset second proportion, then the user is determined to be a poor quality user.

[0089] Optionally, when the call quality indicator includes the number of rollbacks, the preset condition can be that the number of rollbacks is greater than a preset number; that is, if the number of rollbacks is greater than the preset number, the user is determined to be a poor quality user.

[0090] Optionally, when the call quality indicators include the percentage of 5G standalone network usage time, the preset condition can be that the percentage of 5G standalone network usage time is less than a preset first percentage; that is, if the percentage of 5G standalone network usage time is less than the preset first percentage, then the user is determined to be a poor quality user.

[0091] Optionally, when the call quality indicator includes the proportion of 5G traffic, the preset condition can be that the proportion of 5G traffic is less than a preset second proportion; that is, if the proportion of 5G traffic is less than the preset second proportion, the user is determined to be a poor quality user.

[0092] After identifying a user as a poor-quality user, it's possible to determine their resident 5G cell for profiling. The number of fallbacks, the percentage of 5G standalone network usage time, and / or the percentage of 5G traffic are determined from core network data in the analytics dataset. The resident 5G cell is determined from radio network data in the analytics dataset. The resident 5G cell reflects changes in user location, making the user profile more accurate. Determining the resident 5G cell for a poor-quality user can be exemplified by using 5G SA call detail records (CDRs) to determine the user list and the corresponding local 5G cell. Optionally, it can be done by obtaining a list of cells where the user is located based on the 5G SA CDRs and removing cells not belonging to the user's home network to obtain the local 5G cell. The system sorts the local 5G cells corresponding to users with poor network quality. Optionally, it determines the internet access duration of the local 5G cells corresponding to the users with poor network quality; it then sorts the local 5G cells according to the internet access duration. Optionally, it determines the internet access duration of the users with poor network quality within a preset time period in the local 5G cells, and then sorts the local 5G cells according to the internet access duration within the preset time period. The local 5G cells ranked at the top of the preset ranking are designated as the 5G cells where the users with poor network quality reside. The preset ranking can optionally be the top 5 local 5G cells.

[0093] In this embodiment, the technical solution involves acquiring user call detail records (CDRs), including 5G Standalone (SA) call detail records, 4G General Packet Radio Service (GPRS) call detail records, and VoLTE call detail records. Based on the CDRs, call quality indicators for 5G users are determined. These indicators include at least one of the following: number of fallbacks, percentage of 5G SA network usage time, and / or percentage of 5G traffic. If the call quality indicators meet preset conditions, the user is identified as a poor-quality user. By determining the number of fallbacks, percentage of 5G SA network usage time, and / or percentage of 5G traffic based on the CDRs, and accurately identifying poor-quality users, the accuracy of identifying poor-quality users is improved.

[0094] Reference Figure 3 , Figure 3 This is a second embodiment of the method for determining poor-quality users according to the present invention. Based on the first embodiment, step S20 includes:

[0095] Step S21: Determine the local internet access duration, roaming internet access duration, and total 4G internet access duration in the 5G SA call detail records based on the data analysis.

[0096] Step S22: Determine the first duration based on the local internet access duration and roaming internet access duration in the 5G SA call detail record;

[0097] Step S23: Determine the second duration based on the sum of the total 4G internet access duration in the GPRS call detail record and the first duration;

[0098] Step S24: Determine the percentage of the 5G standalone network's on-premises time based on the ratio of the first duration to the second duration.

[0099] Specifically, the local internet access time, roaming internet access time, and total 4G internet access time in the 5G SA call detail records are determined based on the data analysis. The first duration is then determined based on the local internet access time and roaming internet access time in the 5G SA call detail records, as exemplified by the following formula:

[0100] t1=LOCAL_5G_FLUX_DURA+ROAM_5G_FLUX_DURA;

[0101] Where t1 is the first duration, LOCAL_5G_FLUX_DURA is the local internet access duration in the 5G SA call detail record, and ROAM_5G_FLUX_DURA is the roaming internet access duration in the 5G SA call detail record.

[0102] The second duration is determined by summing the total 4G internet access time from the GPRS call detail record with the first duration, as exemplified by the following formula:

[0103] t2=(CALL_DURA,GPRS_NTW_TYP=2)+t1;

[0104] Where t2 is the second duration, and (CALL_DURA,GPRS_NTW_TYP=2) is the 4G internet access duration in the GPRS call detail record (CDR) summary call detail record.

[0105] The proportion of on-premises time for 5G standalone networks is determined based on the ratio of the first duration to the second duration. An example is shown in the following formula:

[0106]

[0107] Where d1 is the percentage of 5G standalone network dwell time, t1 is the first duration, and t2 is the second duration.

[0108] In this embodiment, the local internet access time, roaming internet access time, and total 4G internet access time from GPRS call detail records (CDRs) are determined based on the data analysis. A first duration is determined based on the local and roaming internet access times in the 5G SA CDRs. A second duration is determined based on the sum of the total 4G internet access time from GPRS call detail records and the first duration. The ratio of the first and second durations is used to determine the proportion of 5G standalone network usage time. By determining the proportion of 5G standalone network usage time in the call quality indicators based on the data analysis, and accurately identifying users with poor call quality, the accuracy of identifying such users is improved.

[0109] Reference Figure 4 , Figure 4 In a third embodiment of the method for determining poor-quality users of the present invention, based on the first or second embodiment, step S20 includes:

[0110] Step S25: Based on the data analysis, determine the 5G local internet traffic and 5G roaming internet traffic in the 5G SA call detail records, the total NSA traffic in the 5G non-standalone NSA traffic call detail records, and the 4G local internet traffic and 4G roaming internet traffic in the 4G GPRS call detail records.

[0111] Step S26: Determine the first traffic based on 5G local internet traffic, 5G roaming internet traffic, and NSA traffic;

[0112] Step S27: Determine the second data based on 5G local internet traffic, 5G roaming internet traffic, 4G local internet traffic, and 4G roaming internet traffic;

[0113] Step S28: Determine the 5G traffic ratio based on the ratio of the first traffic to the second traffic.

[0114] Specifically, based on the data analysis, determine the 5G local internet traffic and 5G roaming internet traffic in the 5G SA call detail records, the total NSA traffic in the 5G non-standalone (NSA) call detail records, and the 4G local internet traffic and 4G roaming internet traffic in the 4G GPRS call detail records.

[0115] The first data traffic is determined based on 5G local internet traffic, 5G roaming internet traffic, and NSA traffic, as exemplified by the following formula:

[0116] l1=LOCAL_5G_FLUX+ROAM_5G_FLUX+FLUX_5G;

[0117] Among them, l1 is the first traffic, LOCAL_5G_FLUX is the local internet traffic in the 5G SA call detail record, ROAM_5G_FLUX is the roaming internet traffic in the 5G SA call detail record, and FLUX_5G is the total NSA traffic in the daily summary call detail record of 5G NSA traffic usage.

[0118] The second data usage is determined based on 5G local internet traffic, 5G roaming internet traffic, 4G local internet traffic, and 4G roaming internet traffic, as exemplified by the following formula:

[0119] l2=LOCAL_4G_FLUX+ROAM_4G_FLUX+LOCAL_5G_FLUX+ROAM_5G_FLUX

[0120] Among them, l2 is the second traffic, LOCAL_4G_FLUX is the 4G local Internet traffic in the 4G GPRS call detail record, ROAM_4G_FLUX is the 4G roaming Internet traffic in the 4G GPRS call detail record, LOCAL_5G_FLUX is the local Internet traffic in the 5G SA call detail record, and ROAM_5G_FLUX is the roaming Internet traffic in the 5G SA call detail record.

[0121] The 5G traffic share is determined based on the ratio of the first and second traffic shares, as exemplified by the following formula:

[0122]

[0123] Where d2 represents the proportion of 5G traffic, l1 represents the first type of traffic, and l2 represents the second type of traffic.

[0124] In this embodiment, the technical solution determines the 5G local internet traffic and 5G roaming internet traffic in 5G SA call detail records (CDRs), the total NSA traffic in 5G non-standalone (NSA) CDRs, and the 4G local internet traffic and 4G roaming internet traffic in 4G GPRS CDRs based on the data analysis. A first traffic volume is determined based on the 5G local internet traffic, 5G roaming internet traffic, and NSA traffic. A second traffic volume is determined based on the 5G local internet traffic, 5G roaming internet traffic, 4G local internet traffic, and 4G roaming internet traffic. The 5G traffic proportion is determined based on the ratio of the first and second traffic volumes. By determining the 5G traffic proportion in the call quality indicators based on the data analysis, and accurately identifying users with poor call quality based on these indicators, the accuracy of identifying such users is improved.

[0125] Reference Figure 5 The present invention also provides a device for determining poor-quality users, the device comprising:

[0126] The acquisition module 100 is used to acquire the user's economic data, which includes 5G standalone (SA) call detail records, 4G general packet radio service (GPRS) call detail records, GPRS call detail records, and long-term evolution voice bearer (VoLTE) call detail records.

[0127] The calculation module 200 is used to determine the call quality indicators of 5G users based on the data analysis. The call quality indicators include at least one of the following: number of fallbacks, percentage of 5G standalone network usage time, and / or percentage of 5G traffic.

[0128] The determination module 300 is used to determine the user as a poor quality user if the call quality index meets preset conditions.

[0129] In one embodiment, regarding determining the user as a poor-quality user if the call quality indicator meets preset conditions, the determining module 300 is specifically used for:

[0130] If the call quality indicators meet the preset conditions, then the user is determined to be a poor quality user;

[0131] The preset conditions are that the number of rollbacks is greater than a preset number, or the percentage of the 5G standalone network's on-premises time is less than a preset first percentage, or the percentage of 5G traffic is less than a preset second percentage.

[0132] In one embodiment, in determining the call quality indicators of 5G users based on the data analysis, the calculation module 200 is specifically used for:

[0133] The 5G SA call detail records, 4G GPRS call detail records, the GPRS call detail records, and the VoLTE call detail records are sorted in chronological order.

[0134] Based on the sorting results, non-5G SA call details within a preset time period are determined for each 5G SA call detail.

[0135] If the non-5G SA call detail record does not include the VoLTE call detail record, then the number of rollbacks is updated according to a preset value.

[0136] In one embodiment, in determining the call quality indicators of 5G users based on the data analysis, the calculation module 200 is specifically used for:

[0137] Based on the aforementioned data analysis, determine the local internet access duration, roaming internet access duration, and total 4G internet access duration in the 5G SA call detail records;

[0138] The first duration is determined based on the local internet access duration and roaming internet access duration in the 5G SA call detail record;

[0139] The second duration is determined based on the sum of the total 4G internet access duration in the GPRS call detail record and the first duration;

[0140] The proportion of the 5G standalone network's on-premises time is determined based on the ratio of the first duration to the second duration.

[0141] In one embodiment, in determining the call quality indicators of 5G users based on the data analysis, the calculation module 200 is specifically used for:

[0142] Based on the data analysis, determine the 5G local internet traffic and 5G roaming internet traffic in the 5G SA call detail records, the total NSA traffic in the 5G non-standalone (NSA) call detail records, and the 4G local internet traffic and 4G roaming internet traffic in the 4G GPRS call detail records.

[0143] The first traffic volume is determined based on 5G local internet traffic, 5G roaming internet traffic, and NSA traffic;

[0144] The second data volume is determined based on 5G local internet traffic, 5G roaming internet traffic, 4G local internet traffic, and 4G roaming internet traffic.

[0145] The 5G traffic percentage is determined based on the ratio of the first traffic to the second traffic.

[0146] In one embodiment, after determining that the user is a poor-quality user, the calculation module 300 is specifically used for:

[0147] The local 5G cell corresponding to the poor quality user is determined based on the 5G SA call detail record.

[0148] The local 5G cells corresponding to the poor-quality users are sorted, and the local 5G cells with the highest preset ranking are designated as the permanent 5G cells of the poor-quality users.

[0149] In one embodiment, in sorting the local 5G cells corresponding to the poor-quality users, the calculation module 300 is specifically used for:

[0150] Determine the internet access duration of the local 5G cell corresponding to the user with poor internet quality;

[0151] The local 5G cells corresponding to the users with poor internet access quality are sorted according to the duration of internet access.

[0152] The present invention also provides a poor quality user determination device, the poor quality user determination device including a memory, a processor, and a poor quality user determination program stored in the memory and executable on the processor, wherein when the poor quality user determination program is executed by the processor, it implements the various steps of the poor quality user determination method as described in the above embodiments.

[0153] The present invention also provides a computer-readable storage medium storing a poor-quality user determination program, which, when executed by a processor, implements the various steps of the poor-quality user determination method as described in the above embodiments.

[0154] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0155] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, system, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, system, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, system, article, or apparatus that includes that element.

[0156] Through the above description of the embodiments, those skilled in the art can clearly understand that the systems described in the embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a computer-readable storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, parking management device, air conditioner, or network device, etc.) to execute the systems described in the various embodiments of the present invention.

[0157] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for identifying users with poor quality of service, characterized in that, The method for identifying users with poor quality includes: Acquire user data, including 5G standalone (SA) call detail records (CDRs), 4G General Packet Radio Service (GPRS) CDRs, GPRS CDRs, and VoLTE (Voice over LTE) CDRs. The call quality indicators for 5G users are determined based on the analyzed data. These indicators include the number of rollbacks. Specifically, 5G SA call details, 4G GPRS call details, GPRS call details, and VoLTE call details are sorted chronologically. Based on the sorting results, non-5G SA call details within a preset time period following each 5G SA call detail are determined. If a non-5G SA call detail does not contain a VoLTE call detail, the rollback count is incremented by 1. The rollback count represents the number of times a 4G GPRS call detail or a GPRS call detail exists within the preset time period following a 5G SA call detail. If the call quality indicators meet the preset conditions, then the user is determined to be a poor quality user.

2. The method for determining poor-quality users as described in claim 1, characterized in that, The call quality indicators include the number of rollbacks, the percentage of 5G standalone network usage time, and the percentage of 5G traffic. The step of determining a user as a poor-quality caller if the call quality indicators meet preset conditions includes: If the call quality indicators meet the preset conditions, then the user is determined to be a poor quality user; The preset conditions are that the number of rollbacks is greater than a preset number, or the percentage of the 5G standalone network's on-premises time is less than a preset first percentage, or the percentage of 5G traffic is less than a preset second percentage.

3. The method for determining poor-quality users as described in claim 1, characterized in that, The call quality indicators also include the percentage of 5G standalone network usage time. The step of determining the call quality indicators of 5G users based on the data analysis includes: Based on the aforementioned data analysis, determine the local internet access duration, roaming internet access duration, and total 4G internet access duration in the 5G SA call detail records; The first duration is determined based on the local internet access duration and roaming internet access duration in the 5G SA call detail record; The second duration is determined based on the sum of the total 4G internet access duration in the GPRS call detail record and the first duration; The proportion of the 5G standalone network's on-premises time is determined based on the ratio of the first duration to the second duration.

4. The method for determining poor-quality users as described in claim 1, characterized in that, The call quality indicators also include the proportion of 5G traffic, and the step of determining the call quality indicators of 5G users based on the data analysis includes: Based on the data analysis, determine the 5G local internet traffic and 5G roaming internet traffic in the 5G SA call detail records, the total NSA traffic in the 5G non-standalone (NSA) call detail records, and the 4G local internet traffic and 4G roaming internet traffic in the 4G GPRS call detail records. The first traffic volume is determined based on 5G local internet traffic, 5G roaming internet traffic, and NSA traffic; The second data volume is determined based on 5G local internet traffic, 5G roaming internet traffic, 4G local internet traffic, and 4G roaming internet traffic. The 5G traffic percentage is determined based on the ratio of the first traffic to the second traffic.

5. The method for determining poor-quality users as described in claim 1, characterized in that, After the step of determining that the user is a poor-quality user, the method further includes: The local 5G cell corresponding to the poor quality user is determined based on the 5G SA call detail record. The local 5G cells corresponding to the poor-quality users are sorted, and the local 5G cells with the highest preset ranking are designated as the permanent 5G cells of the poor-quality users.

6. The method for determining poor-quality users as described in claim 5, characterized in that, The step of sorting the local 5G cells corresponding to the poor-quality users includes: Determine the internet access duration of the local 5G cell corresponding to the user with poor internet quality; The local 5G cells corresponding to the users with poor internet access quality are sorted according to the duration of internet access.

7. A device for identifying users with poor quality, characterized in that, The poor quality user determination device includes: The acquisition module is used to acquire the user's economic data, which includes 5G standalone (SA) call detail records (CDRs), 4G General Packet Radio Service (GPRS) CDRs, GPRS CDRs, and Long Term Evolution Voice Bearer (VoLTE) CDRs. The calculation module is used to determine the call quality index of 5G users based on the data analysis, the call quality index including the number of rollbacks; wherein, 5G SA call records, 4G GPRS call records, the GPRS call records, and the VoLTE call records are sorted in chronological order; based on the sorting result, non-5G SA call records within a preset time period after each 5G SA call record are determined; if the non-5G SA call records do not contain the VoLTE call records, the rollback count is incremented by 1; the rollback count is the number of times the 4G GPRS call records or the GPRS call records exist within the preset time period after the 5G SA call records; The determination module is used to determine the user as a poor-quality user if the call quality indicators meet preset conditions.

8. A device for identifying users with poor quality, characterized in that, The poor quality user determination device includes a memory, a processor, and a poor quality user determination program stored in the memory and executable on the processor, wherein the poor quality user determination program, when executed by the processor, implements the steps of the poor quality user determination method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a poor-quality user determination program, which, when executed by a processor, implements the steps of the poor-quality user determination method as described in any one of claims 1-6.

Images