A 5G Network Coverage Evaluation Method and Evaluation System for Residential Areas

Abstract

The present invention discloses a method and a system for evaluating the 5G network coverage in residential areas. The method includes: obtaining core network call records, radio network call records, APP perception call records and user information within a target area to form a basic data set; performing correlation analysis on the data in the basic data set, and splicing the associated data to form an updated data set; performing data cleaning on the updated data set, and screening out representative data from the updated data set; performing data analysis based on the screened data to obtain network evaluation indicators at the building level or user level of the target area. The present invention establishes a set of 5G network quality monitoring and evaluation systems for residential areas, makes full use of mobile network call records in combination with algorithmic solutions, more quickly, accurately and truly reflects the user's 5G network usage perception, reduces the test cost, quickly statistics, analyzes and locates the deep coverage blind spots in residential areas, and assists in the blind spot compensation and optimization of mobile networks.

Description

Technical Field

[0001] The present invention belongs to the field of information technology, and particularly relates to a method and a system for evaluating the 5G network coverage in residential areas. Background Art

[0002] As one of the most important places in people's daily lives, the quality of 5G network coverage in residential areas is directly related to users' perception of network experience.

[0003] However, there are many deficiencies in the existing methods for evaluating the 5G network coverage in residential areas. On the one hand, traditional testing methods mainly rely on manual testing building by building. This method requires a large amount of manpower and material resources, and the testing cost is extremely high. For example, testers need to carry professional equipment to measure the signal strength in each residential building. Just the labor cost accounts for a large part. And due to the limited number of testers, the testing efficiency is low, and it is impossible to conduct a comprehensive coverage test on all areas in the residential area.

[0004] On the other hand, manual testing also has the limitation of not being able to enter users' homes. Due to the complex internal structure of residential areas and the large differences in users' indoor environments, and users' network perception often depends more on the network performance in the indoor scenario. However, manual testing usually can only conduct dot testing in the corridors. This method cannot truly reflect the network usage situation of users in the rooms, resulting in a low accuracy of the evaluation of the indoor coverage status, and it is difficult to accurately find the network coverage blind spots indoors.

[0005] In addition, the data obtained by the existing manual testing methods is relatively limited, and it cannot comprehensively and accurately reflect users' true perception. It is difficult to quickly count and locate the deep coverage blind spots in residential communities, which affects the blind spot filling and optimization work of the mobile network to a certain extent, and is also not conducive to timely discovering and solving network coverage problems and improving users' network experience. Summary of the Invention

[0006] The present invention aims to solve at least one of the technical problems existing in the related technologies to a certain extent.

[0007] An object of the present invention is to provide a method for evaluating the 5G network coverage in residential areas, which is used to establish a set of monitoring and evaluation systems for the 5G network quality in residential areas. By combining algorithmic solutions and making full use of mobile network call records, it can more quickly, accurately and truly reflect users' perception of using the 5G network, reduce the testing cost, quickly count, analyze and locate the deep coverage blind spots in residential communities, and assist in the blind spot filling and optimization of the mobile network.

[0008] Another object of the present invention is to provide a system for evaluating the 5G network coverage in residential areas.

[0009] To achieve the above object, on the one hand, the present invention provides a method for evaluating the 5G network coverage in residential areas, including:

[0010] Obtain the core network call records, radio network call records, APP perception call records and user information in the target area to form a basic data set;

[0011] Conduct a correlation analysis on the data in the basic data set, and splice the associated data to form an updated data set;

[0012] Clean the data in the updated data set, and screen out representative data from the updated data set;

[0013] According to the screened data, conduct data analysis to obtain network evaluation indicators at the building level or user level in the target area.

[0014] A further preferred technical solution of the present invention is that the obtaining of the core network call records, radio network call records, APP perception call records and user information in the target area to form a basic data set specifically includes:

[0015] Extract the core network call records in the target area, denoted as ; extract the radio network call records in the target area, denoted as ; extract the APP perception call records in the target area, denoted as ; obtain the user information in the target area, denoted as ; represent the basic data set as .

[0016] Preferably, the user information in the target area includes user installation and maintenance work orders , user installation addresses , and user mobile addresses , and the user information in the target area is represented as .

[0017] Preferably, conducting a correlation analysis on the data in the basic data set, and splicing the associated data to form an updated data set; specifically includes:

[0018] According to the user number , associate the core network call records and installation addresses of the user, and splice them to obtain:

[0019] ;

[0020] According to MMES1APID and TMSI, associate the corresponding radio network call records and core network call records of the user, and splice them to obtain:

[0021] ;

[0022] Among them, is the unique identifier assigned by the S1AP protocol on the MME side of the core network's mobility management entity for the user, which is the temporary mobile subscriber identity;

[0023] Finally, an updated data set containing user address, wireless network information, and core network information is obtained, expressed as:

[0024] .

[0025] Preferably, data cleaning is performed on the updated data set, and representative data is screened from the updated data set, specifically including:

[0026] Define the time as , and the user occupancy rate as . The rule for screening the updated data set is:

[0027] (1). Combining with the user's installed address, screen out the call detail records within the time period with high user activity and small network fluctuations, expressed as:

[0028] ;

[0029] (2). For residential areas with existing manual test data, screen the user call detail records of the manually tested sectors ;

[0030] (3). For residential areas without manual test data, mark the call detail record sectors as candidate sectors, clean the candidate sectors with a user occupancy rate less than 10%, mark the other candidate sectors as valid call detail record sectors, and screen the user call detail records under the valid call detail record sectors, expressed as:

[0031] ;

[0032] (4). Obtain the APP perception call detail records of the screened users in the same time period, denoted as .

[0033] Preferably, based on the screened data, data analysis is performed to obtain the network evaluation indicators at the building level or user level of the target area, specifically:

[0034] Through the screened call detail records , , and , taking the building level or a single user in the target area as the granularity, calculate and output the average RSRP, overlapping coverage rate , RRC reconstruction ratio , ERAB abnormal disconnection call detail record ratio , indicators of handover failure rate and release failure rate;

[0035] Among them, the RSRP of the first neighbor cell is defined as , the RSRP of the second neighbor cell is , the RSRP of the third neighbor cell is , the RSRP of the target area cell is , if RSRP > -110 dBm, and ≤6 dB, and ≤6 dB, and ≤6 dB, then this cell is an overlapping coverage cell, and the call records therein are non-compliant call records, denoted as , the overlapping coverage rate The calculation formula is:

[0036] ;

[0037] The RRC connection success rate is defined as , if in the call record < 99.5%, then it is a non-compliant call record, denoted as , the RRC reconstruction ratio calculation formula is:

[0038] ;

[0039] If the abnormal disconnection rate of ERAB in the call record ≥0.1%, then it is a non-compliant call record, denoted as , the calculation formula of the abnormal disconnection call record ratio of ERAB is:

[0040] .

[0041] On the other hand, the present invention provides a residential area 5G network coverage evaluation system, including:

[0042] A data acquisition module, configured to acquire core network call records, radio network call records, APP perception call records, and user information in a target area, and form a basic data set;

[0043] A data splicing module, configured to perform correlation analysis on the data in the basic data set, and splice the associated data to form an updated data set;

[0044] A data cleaning module, configured to clean the data in the updated data set, and screen out representative data from the updated data set;

[0045] A coverage evaluation module, configured to perform data analysis based on the screened data to obtain network evaluation indicators at the building level or user level of the target area.

[0046] On the other hand, the present invention provides a non-transitory computer-readable storage medium storing computer instructions that cause a computer to execute the above-mentioned residential area 5G network coverage evaluation method.

[0047] On yet another aspect, the present invention provides an electronic device, comprising: a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete communication with each other through the communication bus. The processor calls the logical instructions in the memory to execute the above-mentioned residential area 5G network coverage evaluation method.

[0048] On still another aspect, the present invention provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer executes the above-mentioned residential area 5G network coverage evaluation method.

[0049] Beneficial effects: The residential area 5G network coverage evaluation method and evaluation system of the present invention are different from the traditional method of manual testing building by building. By using the massive call record data in the residential area, 5G network coverage evaluation is carried out, which greatly saves the testing cost.

[0050] Due to the large building density and many high-rise buildings in the residential area, the wireless signal propagation environment is complex. The traditional user positioning method can only predict according to the coverage sector, propagation model, etc., and the accuracy is limited. The present invention realizes precise positioning by extracting the mobile phone numbers of users under the installed address and combining attributes such as coverage sector, time, and user movement.

[0051] Traditional residential area optimization mainly relies on manual testing, generally conducting dot testing in the corridor and unable to conduct traversal testing indoors. Therefore, the accuracy of the evaluated indoor coverage is relatively low and cannot truly reflect the network performance of users in the room. The present invention extracts the indoor call records of residential area users to truly reflect the usage situation and network status of users.

[0052] The present invention uses database operations to implement the functions of downloading, importing, and analyzing automatic call records and core network call records, periodically generating reports, continuously monitoring the perception of residential area users, real-time discovering blind spots in the residential area and periodically evaluating. At the same time, it can analyze the problem causes through the event failure reasons carried in the call records to assist in optimization. Description of the Drawings

[0053] Figure 1 It is the overall flowchart of the residential area 5G network coverage evaluation method of the present invention;

[0054] Figure 2 It is the flowchart of the data splicing method in Embodiment 1 of the present invention;

[0055] Figure 3This is the flowchart of the data cleaning method in Embodiment 1 of the present invention;

[0056] Figure 4 This is the flowchart of the data analysis method in Embodiment 1 of the present invention. Detailed implementation manners

[0057] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention, and they should not be construed as limiting the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without making creative efforts fall within the scope of protection of the present invention. In the description of the present invention, it should be understood that the terms used are only for the purpose of description and cannot be construed as indicating or implying relative importance.

[0058] Before the detailed description of the present invention, some technical terms and abbreviations involved in the present invention are explained and defined.

[0059] IMSI (International Mobile Subscriber Identity): International Mobile Subscriber Identity, which is a globally unique identifier used to identify users in a mobile network.

[0060] TMSI (Temporary Mobile Subscriber Identity): It is a temporary mobile subscriber identifier used to temporarily replace the IMSI for transmission in the network to protect the user's identity information from being leaked.

[0061] MMES1APID (Mobility Management Entity S1): Mobility Management Entity MME S1 Application Protocol Identifier.

[0062] RSRP (Reference Signal Receiving Power): Reference Signal Receiving Power, which is a key parameter representing the wireless signal strength in a wireless network and one of the physical layer measurement requirements. It is the average value of the signal power received on all RE (resource particles) carrying the reference signal within a certain symbol.

[0063] LTE (Long Term Evolution): A wireless data communication technology standard, which is the long-term evolution of the UMTS (Universal Mobile Telecommunications System) technology standard developed by the 3GPP (The 3rd Generation Partnership Project).

[0064] ERAB (Evolved Radio Access Bearer): The evolved radio access bearer. An E-RAB refers to the bearer in the user plane, which is used to transmit voice, data, and multimedia services between the UE (User Equipment) and the CN (Core Network).

[0065] RRC (Radio Resource Control): Radio resource control, which refers to managing, controlling, and scheduling radio resources through certain strategies and means.

[0066] The following combines Figures 1 - 4 to describe the residential area 5G network coverage evaluation method and evaluation system provided by the present invention.

[0067] Embodiment 1: This embodiment provides a residential area 5G network coverage evaluation method, as Figure 1 shown, including:[[]]

[0068] Obtain core network call records, radio network call records, APP perception call records, and user information in the target area to form a basic data set;

[0069] Perform correlation analysis on the data in the basic data set, and splice the associated data to form an updated data set;

[0070] Perform data cleaning on the updated data set, and screen out representative data from the updated data set;

[0071] According to the screened data, perform data analysis to obtain network evaluation indicators at the building level or user level in the target area.

[0072] The following elaborates on each step in detail.

[0073] S1. Data acquisition:

[0074] Extract core network call records and radio network call records and APP perception call records and user installation and maintenance work orders and user installation addresses , User mobile phone address As the basic data set, define user information as , then the basic data set can be expressed as:

[0075] .

[0076] S2. Data splicing:

[0077] As Figure 2 shown, according to the user number , associate the core network call record and the installation address of the user, and splice them to get:

[0078] ;

[0079] According to the MMES1APID and TMSI, associate the corresponding radio network call record and core network call record of the user, and splice them to get:

[0080] ;

[0081] Among them, is the unique identifier assigned by the S1AP protocol on the MME side of the core network's mobility management entity for the user, is the temporary mobile subscriber identity;

[0082] Finally, obtain the updated data set containing user address, radio network information and core network information, expressed as:

[0083] .

[0084] S3. Data cleaning:

[0085] As Figure 3 shown, combine time and manual test data to clean the updated data set. Define the time as , the occupancy rate of users is , and the rule for screening the updated data set is:

[0086] (1). Combine the user installation address to filter out the call record data of the user from 22:00 to 23:00, expressed as:

[0087] ;

[0088] Combined with user research and analysis, the probability that users are indoors in residential areas from 22 to 23 is relatively high. And from data analysis, the average RSRP standard deviation of residential area users from 22 to 23 is <= 1dBm, with relatively small fluctuations and low mobility.

[0089] (2). For residential areas with existing manual test data, filter the call records of users in the manually tested sectors 。

[0090] (3) For residential areas without artificial test data, mark the call detail record sectors as candidate sectors, clean the candidate sectors with a user occupancy rate less than 10%, mark other candidate sectors as valid call detail record sectors, and filter the user call detail records under the valid call detail record sectors, expressed as:

[0091] 。

[0092] (4) Obtain the APP perception call detail records of the filtered users in the same time period, denoted as 。

[0093] S4. Data analysis:

[0094] As Figure 4 shown, through the filtered call detail record data 、 、 and , calculate and output the average RSRP, overlapping coverage rate 、RRC reconstruction ratio 、ERAB abnormal disconnection call detail record ratio 、handover failure rate and release failure rate indicators at the building level or individual user level in the target area.

[0095] Among them, define the RSRP of the first neighbor cell as , the RSRP of the second neighbor cell as , the RSRP of the third neighbor cell as , the RSRP of the target area cell as , if RSRP > -110 dBm, and ≤ 6 dB, and ≤ 6 dB, and ≤ 6 dB, then this cell is an overlapping coverage cell, and the call detail records in it are non-compliant call detail records, denoted as , the overlapping coverage rate The calculation formula is:

[0096] ;

[0097] Define the RRC connection success rate as , if the in the call detail record < 99.5%, then it is a non-compliant call detail record, denoted as , the RRC reconstruction ratio calculation formula is:

[0098] ;

[0099] If the ERAB abnormal disconnection rate in the call detail record If it is ≥ 0.1%, it is a non-compliant call record, denoted as , the calculation formula for the proportion of abnormal disconnection call records of ERAB is:

[0100] .

[0101] In this embodiment, the above analysis method is used to obtain, taking 8 cells in a certain target area as an example, the average RSRP, overlapping coverage rate , RRC reconstruction ratio , proportion of abnormal disconnection call records of ERAB , handover failure rate, and release failure rate indicators, as shown in Table 1.

[0102] Table 1 Building-level network analysis statistical table

[0103]

[0104] In order to verify the effectiveness of the method in this embodiment, on-site tests and verifications are carried out through the following cases.

[0105] The number of buildings in Community A is 230, and the number of households is 2,678. The community is mainly covered by five macro-station sectors: macro-station 1_50, macro-station 2_49, macro-station 3_50, macro-station 4_49, and macro-station 5_51.

[0106] There are 25 buildings with user call records in Community A. One of them is selected for on-site testing. The test results show that the coverage rate is 5.21%, and the average RSRP is -119.63 dBm.

[0107] Through the method of this example, the call record data is analyzed. The analysis results show that the coverage rate is 5.01%, and the average RSRP is -120.5 dBm.

[0108] The results show that the on-site manual test is basically consistent with the analysis results of the present invention. The overall deep coverage of this community is weak, and it is necessary to enhance the deep coverage of this community through radio frequency optimization and new cell coverage.

[0109] Embodiment 2: A 5G network coverage evaluation system for residential areas, including:

[0110] A data acquisition module, configured to acquire core network call records, radio network call records, APP perception call records, and user information in a target area, and form a basic data set;

[0111] A data splicing module, configured to perform correlation analysis on the data in the basic data set, and splice the associated data to form an updated data set;

[0112] A data cleaning module, configured to clean the data in the updated data set, and screen out representative data from the updated data set;

[0113] A coverage evaluation module, which is used to perform data analysis based on the filtered data to obtain network evaluation indicators at the building level or user level in the target area.

[0114] In this embodiment, the data acquisition module and the data splicing module implement the automatic download and splicing of wireless network, core network, and installation address data.

[0115] Wireless network call detail record data: Download the wireless-side call detail records from the northbound interface and automatically import them into the database.

[0116] Core network call detail record data: Download the core network call detail record data and automatically import it into the database. The time uses Coordinated Universal Time.

[0117] Installation address data: Extract all the mobile phone numbers under the name of users whose installation addresses are in a certain residential community, as well as the user addresses registered at the time of opening the mobile phone numbers.

[0118] The data cleaning module of this embodiment automatically cleans the spliced call detail record data according to information such as time and address, including:

[0119] (1) Time screening: Select data for two hours from 22:00 to 23:00 at night.

[0120] (2) Geographic screening: Match the installation address community with the community coverage sector, and further clean the call detail records by the coverage sector of the residential community.

[0121] (3) Continuity screening: Users with call detail records in the coverage sector of the residential area for three consecutive days.

[0122] The coverage evaluation module of this embodiment realizes the automatic output of community indicators and problem reports.

[0123] Extract various network evaluation and analysis indicators such as average RSRP, overlapping coverage rate, ERAB abnormal disconnection call detail record ratio, RRC reconstruction ratio, handover failure rate, release failure rate, etc. at the granularity of the community or building, which is more automated and comprehensive, and reflects the true perception of users.

[0124] Embodiment 3: This embodiment provides a non-transitory computer-readable storage medium, on which computer instructions are stored, and the computer instructions cause the computer to execute the 5G network coverage evaluation method for residential areas, and the method includes the following steps:

[0125] Obtain core network call detail records, wireless network call detail records, APP perception call detail records, and user information in the target area to form a basic data set;

[0126] Perform correlation analysis on the data in the basic data set, and splice the associated data to form an updated data set;

[0127] Perform data cleaning on the updated data set, and screen out representative data from the updated data set;

[0128] According to the screened data, perform data analysis to obtain building-level or user-level network evaluation indicators for the target area.

[0129] Embodiment 4: This embodiment provides an electronic device, which may include: a processor, a communications interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus. The processor can call the logical instructions in the memory to execute the method for evaluating the 5G network coverage in a residential area. The method includes the following steps:

[0130] Obtain the core network call records, radio network call records, APP perception call records, and user information in the target area to form a basic data set;

[0131] Perform correlation analysis on the data in the basic data set, and splice the associated data to form an updated data set;

[0132] Perform data cleaning on the updated data set, and screen out representative data from the updated data set;

[0133] According to the screened data, perform data analysis to obtain building-level or user-level network evaluation indicators for the target area.

[0134] In addition, when the logical instructions in the above-mentioned memory are implemented in the form of a software functional unit and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. And the foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0135] Example 5: This example provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the method for evaluating the 5G network coverage in residential areas, and this method includes the following steps:

[0136] Obtain the core network call records, radio network call records, APP perception call records, and user information within the target area to form a basic data set;

[0137] Conduct correlation analysis on the data in the basic data set, and splice the associated data to form an updated data set;

[0138] Clean the data in the updated data set, and screen out representative data from the updated data set;

[0139] According to the screened data, conduct data analysis to obtain network evaluation indicators at the building level or user level of the target area.

[0140] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this example. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0141] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, also by hardware. Based on this understanding, the above technical solutions, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disc, etc., including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0142] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present invention.

Claims

1. A method for evaluating the 5G network coverage in residential areas, characterized in that, Including: Obtain core network call records, radio network call records, APP perception call records, and user information within the target area to form a basic data set; Specifically including: Extract the core network call records within the target area, denoted as ; Extract the radio network call records within the target area, denoted as ; Extract the APP perception call records within the target area, denoted as ; Obtain the user information within the target area, denoted as , where the user information within the target area includes the user installation and maintenance work order , the user installation address , and the user mobile phone address , and the user information within the target area is represented as ; Represent the basic data set as ; Perform correlation analysis on the data in the basic data set, and splice the associated data to form an updated data set; Specifically including: According to the user number , associate the core network call record and the installation address of the user, and splice them to obtain: ； According to MMES1APID and TMSI, associate the radio network call record and the core network call record corresponding to the user, and splice them to obtain: ； Among them, is the unique identifier assigned by the S1AP protocol on the MME side of the core network's mobility management entity for the user, is the temporary mobile subscriber identity; Finally obtain an updated data set including user address, wireless network information, and core network information, expressed as: ； Perform data cleaning on the updated data set, and screen out representative data from the updated data set; Specifically including: Define the time as , and the user occupancy rate is . The rule for screening the updated data set is as follows: (1). Combine the user's installation address to filter out the call record data during the period with high user activity and small network fluctuations, expressed as: during the period, which is expressed as: ； (2) For residential areas with existing manual test data, screen the user call records of the manual test sectors ; (3) For residential areas without artificial test data, mark the call record sector as a candidate sector, clean the candidate sectors with a user occupancy rate less than 10%, mark other candidate sectors as valid call record sectors, and screen the user call records under the valid call record sectors, expressed as: ； (4) Obtain the APP perception call records of the filtered users in the same time period, denoted as ; According to the screened data, perform data analysis to obtain network evaluation indicators at the building level or user level of the target area; Specifically: Through the selected call record data , , and , calculate and output the average RSRP, overlapping coverage rate , RRC reconstruction ratio , ERAB abnormal disconnection call record ratio , handover failure rate and release failure rate indicators at the building level or individual user level in the target area; Among them, define the RSRP of the first neighboring cell as , the RSRP of the second neighboring cell as , the RSRP of the third neighboring cell as , the RSRP of the target area cell as , if the RSRP > -110 dBm, and - ≤ 6 dB, and - ≤ 6 dB, and - ≤ 6 dB, then this cell is an overlapping coverage cell, and the call records therein are non-compliant call records, denoted as , the overlapping coverage rate The calculation formula is: ； Define the RRC connection success rate as , if the in the call record is < 99.5%, it is a non-compliant call record, denoted as , and the calculation formula for the RRC reconstruction ratio is: ； If the abnormal disconnection rate of ERAB in the call record ≥0.1%, it is a non-compliant call record, denoted as , and the calculation formula for the proportion of abnormal disconnection call records of ERAB is: ； Among them, , , and are the quantities of call record data , , and respectively. , and are the quantities of non-compliant call records , and respectively.

2. A 5G network coverage evaluation system for residential areas, characterized in that, Including: A data acquisition module, used to obtain core network call records, radio network call records, APP perception call records, and user information within the target area to form a basic data set; Specifically including: Extract the core network call records within the target area, denoted as ; Extract the radio network call records within the target area, denoted as ; Extract the APP perception call records within the target area, denoted as ; Obtain the user information within the target area, denoted as , where the user information within the target area includes the user installation and maintenance work order , the user installation address , and the user mobile phone address , and the user information within the target area is represented as ; Represent the basic data set as ; A data splicing module, used to perform correlation analysis on the data in the basic data set, and splice the associated data to form an updated data set; Specifically including: According to the user number , associate the core network call records and the installation address of the user, and splice them to obtain: ； According to MMES1APID and TMSI, associate the radio network call record and the core network call record corresponding to the user, and splice them to obtain: ； Among them, is the unique identifier assigned by the S1AP protocol on the MME side of the core network's mobility management entity for the user, is the temporary mobile subscriber identity; Finally obtain an updated data set including user address, wireless network information, and core network information, expressed as: ； A data cleaning module, used to perform data cleaning on the updated data set, and screen out representative data from the updated data set; Specifically including: Define the time as , and the user occupancy rate is . The rule for screening the updated data set is: (1) Filter out the call record data during the period with high user activity and small network fluctuations in combination with the user's installation address, expressed as: during the period, expressed as: ； (2) For residential areas with existing manual test data, screen the user call records of the manual test sectors ; (3) For residential areas without artificial test data, mark the call record sector as a candidate sector, clean the candidate sectors with a user occupancy rate less than 10%, mark other candidate sectors as valid call record sectors, and screen the user call records under the valid call record sectors, expressed as: ； (4) Obtain the APP perception call records of the selected users in the same time period, denoted as ; A coverage evaluation module, used to perform data analysis according to the screened data to obtain network evaluation indicators at the building level or user level of the target area; Specifically: Filtered call record data , , and , calculate and output the average RSRP, overlapping coverage rate , RRC reconstruction ratio , ERAB abnormal disconnection call record ratio , handover failure rate, and release failure rate indicators at the building level or individual user level in the target area; Among them, define the RSRP of the first neighbor cell as , the RSRP of the second neighbor cell as , the RSRP of the third neighbor cell as , the RSRP of the target area cell as . If RSRP > -110 dBm, and - ≤ 6 dB, and - ≤ 6 dB, and - ≤ 6 dB, then this cell is an overlapping coverage cell, and the call record therein is a non-compliant call record, denoted as . The overlapping coverage rate . The calculation formula is: ； Define the RRC connection success rate as , if the in the call record is < 99.5%, it is a non-compliant call record, denoted as , and the calculation formula for the RRC reconstruction ratio is: ； If the abnormal disconnection rate of ERAB in the call record ≥0.1%, it is a non-compliant call record, denoted as , and the calculation formula for the proportion of abnormal disconnection call records of ERAB is: ； Among them, , , and are the quantities of call record data , , and respectively, , and are the quantities of non-compliant call records , and respectively.

3. A non-transitory computer-readable storage medium, characterized in that, It stores computer instructions, and the computer instructions cause the computer to execute the residential area 5G network coverage evaluation method described in claim 1.

4. An electronic device, characterized in that, Including: A processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus. The processor calls the logical instructions in the memory to execute the residential area 5G network coverage evaluation method described in claim 1.

5. A computer program product, characterized in that, The computer program product includes a computer program. The computer program is stored on a non-transitory computer-readable storage medium. When the computer program is executed by the processor, the computer executes the residential area 5G network coverage evaluation method described in claim 1.

Images