A 5G signaling data quality detection method and system based on multi-dimensional statistical analysis

Abstract

The application discloses a 5G signaling data quality detection method and system based on multidimensional statistical analysis, and belongs to the technical field of 5G network signaling analysis, the method comprising the following steps: screening multi-interface signaling data accessed by a 5G signaling analysis system to obtain signaling messages of a predetermined type; analyzing the screened signaling messages, periodically counting from three dimensions of a tracking area code (TAC), an NR cell identifier (NCI) and a network element address to generate a statistical data set; automatically comparing the statistical data set with working parameter information to calculate TAC completeness, NCI completeness and network element completeness; and based on the calculated completeness, evaluating the quality of the signaling data. Through multidimensional statistics and automatic comparison, the application realizes quantitative evaluation of the quality of 5G signaling data, and effectively improves the data reliability and operation and maintenance efficiency of the signaling analysis system.

Description

Technical Field

[0001] This invention relates to the field of 5G network signaling analysis technology, and more specifically to a method and system for 5G signaling data quality detection based on multidimensional statistical analysis. Background Technology

[0002] Since the official commercial launch of 5G networks in 2019, 5G networks have entered a phase of rapid development from the initial construction stage. With the expansion of network scale and the continuous enrichment of business applications, mobile internet traffic has experienced explosive growth, and the scale of signaling links has also continued to increase rapidly. Against this backdrop, signaling analysis systems based on 5G networks have gradually become important tools for operators to conduct network operation and maintenance, optimization, and application analysis.

[0003] Existing 5G signaling analysis systems typically use signaling data collected by operators as input. They first split or mirror the original link data, then transmit it to the system platform via wavelength division multiplexing (WDM) or bare fiber. The system decodes the signaling data according to the protocol format and performs message association based on the signaling flow to synthesize an extensible detail record (XDR) log, which is then used for further application analysis. However, existing solutions mainly focus on signaling protocol decoding, signaling message association, and XDR synthesis, lacking an effective mechanism to ensure the quality of the input signaling data. In practical applications, incomplete splitting coverage, insufficient processing capacity of the splitting platform, or excessive optical attenuation in the transmission link can directly lead to a decrease in the accuracy and completeness of the collected signaling data, resulting in low-quality XDR logs and ultimately affecting the results of various XDR-based analyses and applications. This problem is particularly prominent during the large-scale deployment and rapid development of 5G networks. Summary of the Invention

[0004] In view of this, the present invention provides a 5G signaling data quality detection method and system based on multidimensional statistical analysis, which solves the problem of unreliable data quality in existing 5G signaling analysis systems. By automating the comparison of multidimensional statistical data, the present invention achieves quantitative assessment of data quality.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: This invention provides a method for 5G signaling data quality detection based on multidimensional statistical analysis, comprising the following steps: S1. Filter the multi-interface signaling data accessed by the 5G signaling analysis system to obtain signaling messages of a predetermined type; S2. Parse the filtered signaling messages and perform periodic statistics from three dimensions: Tracking Area Code (TAC), NR Cell Identifier (NCI), and Network Element Address, to generate a statistical data set; S3. Automatically compare the statistical data set with the engineering parameter information to calculate the TAC integrity rate, NCI integrity rate and network element integrity rate; S4. Evaluate the quality of signaling data based on the calculated integrity rate.

[0006] Furthermore, in step S1, the multi-interface signaling data accessed by the 5G signaling analysis system is filtered, including: Filter InitialUEMessage signaling messages of the NGAP protocol in the N1 & N2 interfaces; Filter authentication request signaling messages of the HTTP / 2 protocol in the N12 interface; Filter session establishment request signaling messages of the PFCP protocol in the N4 interface.

[0007] Furthermore, in step S2, the parsing and statistics use a red-black tree-based data structure to store statistical information, including the TAC statistical set, the NCI statistical set, and the network element address statistical set.

[0008] Furthermore, in step S3: TAC Completeness Rate: The percentage of statistically recorded TACs in the engineering parameter TAC list; NCI completeness rate: The percentage of NCIs counted in the NCI list of the engineering parameter; Network element integrity rate: The percentage of network element addresses counted in the network element list of the engineering parameters.

[0009] Further, step S4 includes: If the TAC integrity rate, NCI integrity rate, and network element integrity rate are all 100%, the data quality is considered acceptable; otherwise, it is considered unacceptable, and a detailed problem list is output.

[0010] Furthermore, the output problem list includes: Output TAC details, NCI details, and network element address details that are not covered or reported, to assist in locating data anomalies.

[0011] In a second aspect, embodiments of the present invention also provide a 5G signaling data quality detection system for implementing any of the methods described in the first aspect, including: The signaling message filtering module is used to filter the multi-interface signaling data accessed by the 5G signaling analysis system and obtain signaling messages of a predetermined type. The parsing and statistics module is used to parse the filtered signaling messages and perform periodic statistics from three dimensions: Tracking Area Code (TAC), NR Cell Identifier (NCI), and Network Element Address, to generate a statistical data set. The quality assessment module is used to automatically compare statistical data sets with engineering parameter information, calculate TAC integrity rate, NCI integrity rate, and network element integrity rate; and evaluate the quality of signaling data based on the calculated integrity rate.

[0012] As can be seen from the above technical solution, compared with the prior art, the present invention has the following technical advantages: This invention achieves quantitative evaluation of 5G signaling data quality through multi-dimensional statistics and automated comparison, effectively improving the data reliability and operational efficiency of the signaling analysis system. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0014] Figure 1 The flowchart of the 5G signaling data quality detection method based on multidimensional statistical analysis provided by the present invention is shown.

[0015] Figure 2 A flowchart for data quality assessment provided for embodiments of the present invention.

[0016] Figure 3 A block diagram of the 5G signaling data quality detection system provided by the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] This invention discloses a 5G signaling data quality detection method based on multidimensional statistical analysis, referring to... Figure 1 As shown, it includes the following steps: S1. Filter the multi-interface signaling data accessed by the 5G signaling analysis system to obtain signaling messages of a predetermined type; S2. Parse the filtered signaling messages and perform periodic statistics from three dimensions: Tracking Area Code (TAC), NR Cell Identity (NCI), and network element address to generate a statistical data set; S3. Automatically compare the statistical data set with the technical parameter information to calculate the TAC integrity rate, NCI integrity rate, and network element integrity rate. The technical parameter information includes TAC technical parameters, NCI technical parameters, and core network element technical parameters. The TAC integrity rate refers to the proportion of non-duplicate TACs counted within a single period in the TAC technical parameter information. The NCI integrity rate refers to the proportion of non-duplicate NCIs counted within a single period in the NCI technical parameter information. The network element integrity rate refers to the proportion of a specific interface network element address counted within a single period in the core network element technical parameter information. S4. Evaluate the quality of signaling data based on the calculated integrity rate.

[0019] The method provided by this invention filters the multi-interface signaling data accessed by the 5G signaling analysis system, parses the filtered signaling, and performs periodic statistics from three dimensions: Tracking Area Code (TAC), NR Cell Identifier (NCI), and Network Element Address. At the end of the statistical period, the statistical data of TAC, NCI, and Network Element Address are automatically compared with the engineering parameter information to calculate the TAC integrity rate, NCI integrity rate, and Network Element integrity rate. This enables a quantitative assessment of the integrity and accuracy of the accessed signaling data, thereby effectively reflecting the quality of the input data of the 5G signaling analysis system.

[0020] 5G signaling analysis systems typically access signaling data from the core network's N1 & N2, N4 interfaces, as well as other Service-Based Interface (SBI) interfaces such as N11, N12, and N16. Each signaling interface consists of a pair of network elements and a series of signaling procedures, and each signaling procedure consists of a series of signaling messages. Assuming the signaling data is complete and the 5G signaling analysis system parses the signaling data accurately, the network element addresses contained in the signaling of each interface accessed by the system should cover all network element addresses in the core network element operating parameter information of that interface. That is, under the condition that the signaling data is complete and the system parses the signaling data normally, the network element integrity rate of each interface should be 100%.

[0021] Furthermore, the N1 & N2 interface signaling contains abundant TAC and NCI information. Assuming the signaling data is complete and the 5G signaling analysis system can parse it correctly, the TACs included in the signaling data of this interface accessed by the system should cover all TACs in the TAC technical parameter information, and the NCIs included in the signaling data of this interface accessed by the system should cover all NCIs in the NCI technical parameter information. That is, assuming the signaling data is complete and the system can parse it correctly, the completeness rate of both TACs and NCIs for this interface should be 100%.

[0022] In the specific implementation process, this method is based on the above conclusions and takes the collection of common N1&N2, N12 and N4 interface signaling data as an example for explanation. It includes three main stages: multi-interface signaling message filtering, multi-dimensional data parsing and statistics, and data quality assessment.

[0023] 1. Multi-interface signaling message filtering: The signaling data from each interface accessed by the 5G signaling analysis system is filtered by performing the following steps: Step 1: Filter the InitialUEMessage signaling messages in the NGAP protocol of the N1 & N2 interfaces and put them into the N1 & N2 interface signaling message filtering queue.

[0024] Step 2: Filter the UplinkNASTransport signaling messages in the NGAP protocol of the N1 & N2 interfaces and put them into the N1 & N2 interface signaling message filtering queue.

[0025] Step 3: Filter the AuthenticateRequest signaling messages in the Nausf_UEAuthentication service of the HTTP2 protocol on the N12 interface and put them into the N12 interface signaling message filtering queue.

[0026] Step 4: Filter the PFCP Session Establishment Request signaling messages in the N4 interface PFCP protocol and put them into the N4 interface signaling message filtering queue.

[0027] 2. Analysis and statistics of multi-dimensional data: The signaling message parsing module sequentially retrieves the filtered signaling messages from the signaling message filtering queues of interfaces N1&N2, N12, and N4, and performs the following parsing: Step 1: Parse the InitialUEMessage signaling message in the N1&N2 interface signaling message filtering queue, parse the TAC and NCI information contained in the id-UserLocationInformation information element of the message, save the TAC information to the TAC statistical set built on the red-black tree, and save the NCI information to the NCI statistical set built on the red-black tree. Step 2: Parse the UplinkNASTransport signaling messages in the N1&N2 interface signaling message filtering queue. First, extract the source IP address of the IP layer. This IP address is the AMF network element IP address. Then, save this IP address to the N1&N2 interface AMF network element IP address statistics set built based on a red-black tree.

[0028] Step 3: Parse the Authenticate Request signaling message in the N12 interface signaling message filtering queue. First, extract the source IP address at the IP layer and use it as the IP address of the N12 interface AMF network element. Then, save this IP address to the N12 interface AMF network element IP address statistics set built based on a red-black tree.

[0029] Step 4: Parse the PFCP Session Establishment Request signaling message in the N4 interface signaling message filtering queue. First, extract the source IP address at the IP layer, use the source address as the IP address of the N4 interface SMF network element, and save the IP address to the N4 interface SMF network element IP address statistics set built based on a red-black tree.

[0030] 3. Data quality assessment: The transmission of signaling data to the 5G signaling analysis system by operators is a continuous and dynamic process; therefore, the assessment of signaling data quality should also be conducted periodically. Before conducting the data quality assessment, it is necessary to first parse and load TAC operating parameter information, NCI operating parameter information, and core network element operating parameter information. The steps are as follows: Step 1: Parse and import the TAC parameter information, save the TAC parameter information to the TAC parameter set built based on the red-black tree, and record the total number of TACs as Total_SP_TAC; Step 2: Parse and import the NCI parameter information, save the NCI parameter information to the NCI parameter set built based on the red-black tree, and record the total number of NCI as Total_SP_NCI; Step 3: Sequentially parse and import the network element parameter information of interfaces N1 & N2, N12, and N4, and save the AMF network element address information of interfaces N1 & N2, N12, and N4 respectively to the N1 & N2 interface AMF network element IP address parameter set, the N12 interface AMF network element IP address parameter set, and the N4 interface SMF network element IP address parameter set constructed based on red-black trees. Record the total number of AMF network element IP addresses of interfaces N1 & N2 as Total_N2_AMF, the total number of AMF network element IP addresses of interfaces N12 as Total_N12_AMF, and the total number of AMF network element IP addresses of interfaces N4 as Total_N4_SMF. This method assesses data quality on an hourly basis. The data assessment process is detailed below. Figure 2 As shown, the specific implementation steps are as follows: Step 1: Based on the TAC parameter set, iterate through the TAC statistical set built during the data statistics process. For each TAC found, query the TAC parameter set and record the total number of TACs with searchable data as Total_XL_TAC. For TACs without searchable data, output them to a local file and record them as unreported TAC details. After the data iteration is complete, calculate the TAC completeness rate, which is Total_XL_TAC / Total_SP_TAC. Step 2: Based on the TAC statistical set constructed during the data statistics process, iterate through the TAC parameter set. For each TAC in the TAC parameter information, query the TAC statistical set. For TACs for which no data is found, output them to a local file and record them as a detailed list of uncovered TACs. Step 3: Based on the NCI parameter set, iterate through the NCI statistical set constructed during the data statistics process. For each NCI found in the statistics, query the NCI parameter set and record the total number of NCIs with searchable data as Total_XL_NCI. For NCIs with no searchable data, output them to a local file and record them as unreported NCI details. After the data iteration is complete, calculate the NCI completeness rate, which is Total_XL_NCI / Total_SP_NCI. Step 4: Based on the NCI statistical set constructed during the data statistics process, traverse the NCI parameter set. For each NCI in the NCI parameter information, query the NCI statistical set. For NCIs for which no data is found, output them to a local file and record them as uncovered NCI detailed lists. Step 5: Based on the N1&N2 interface AMF network element IP address parameter set, iterate through the N1&N2 interface AMF network element IP address statistical set constructed during the data statistics process. For each IP address found, query the N1&N2 interface AMF network element IP address parameter set, and record the total number of IP addresses with searchable data as Total_XL_N2_AMF. For IP addresses with no searchable data, output them to a local file and record them as the N1&N2 interface AMF network element address details list that has not been reported. After the data iteration is complete, calculate the N1&N2 interface network element integrity rate, which is Total_XL_N2_AMF / Total_N2_AMF. Step 6: Based on the N1&N2 interface AMF network element IP address statistics set constructed during the data statistics process, traverse the N1&N2 interface AMF network element IP address engineering parameter set. For each N1&N2 interface AMF network element IP address in the core network element engineering parameter information, query the N1&N2 interface AMF network element IP address statistics set. For IP addresses for which no data is found, output them to a local file and record them as a detailed list of uncovered N1&N2 interface AMF network element addresses. Step 7: Based on the N12 interface AMF network element IP address parameter set, iterate through the N12 interface AMF network element IP address statistical set constructed during the data statistics process. For each IP address found, query the N12 interface AMF network element IP address parameter set and record the total number of IP addresses with searchable data as Total_XL_N12_AMF. For IP addresses with no searchable data, output them to a local file and record them as N12 interface AMF network element address details that have not been reported. After the data iteration is complete, calculate the N12 interface network element integrity rate, which is Total_XL_N12_AMF / Total_N12_AMF. Step 8: Based on the N12 interface AMF network element IP address statistics set constructed during the data statistics process, traverse the N12 interface AMF network element IP address parameter set. For each N12 interface AMF network element IP address in the core network element parameter information, query the N12 interface AMF network element IP address statistics set. For IP addresses for which no data was found, output them to a local file and record them as a detailed list of uncovered N12 interface AMF network element addresses. Step 9: Based on the N4 interface SMF network element IP address parameter set, iterate through the N4 interface SMF network element IP address statistical set constructed during the data statistics process. For each IP address found, query the N4 interface SMF network element IP address parameter set and record the total number of IP addresses with searchable data as Total_XL_N4_SMF. For IP addresses with no searchable data, output them to a local file and record them as a detailed list of N4 interface SMF network element addresses that have not been reported. After the data iteration is complete, calculate the N4 interface network element integrity rate, which is Total_XL_N4_SMF / Total_N4_SMF. Step 10: Based on the N4 interface SMF network element IP address statistics set constructed during the data statistics process, traverse the N4 interface SMF network element IP address parameter set. For each N4 interface SMF network element IP address in the core network element parameter information, query the N4 interface SMF network element IP address statistics set. For IP addresses for which no data was found, output them to a local file and record them as a detailed list of uncovered N4 interface SMF network element addresses. If the TAC integrity rate and NCI integrity rate of the N1 & N2 interfaces, as well as the network element integrity rate of the N1 & N2, N12, and N4 interfaces, are all 100%, then the signaling data quality accessed to the 5G signaling analysis system is considered qualified. Otherwise, it is considered unqualified. In this case, the uncovered or unreported TAC details, NCI details, and network element details can be transferred to the operator to assist in locating the data anomaly.

[0031] like Figure 3As shown, the present invention also provides a 5G signaling data quality detection system for implementing the 5G signaling data quality detection method based on multidimensional statistical analysis as described in any of the above embodiments, comprising: The signaling message filtering module is used to filter the multi-interface signaling data accessed by the 5G signaling analysis system and obtain signaling messages of a predetermined type. The parsing and statistics module is used to parse the filtered signaling messages and perform periodic statistics from three dimensions: Tracking Area Code (TAC), NR Cell Identifier (NCI), and Network Element Address, to generate a statistical data set. The quality assessment module is used to automatically compare statistical data sets with engineering parameter information, calculate TAC integrity rate, NCI integrity rate, and network element integrity rate; and evaluate the quality of signaling data based on the calculated integrity rate.

[0032] This system enables automated and quantitative assessment of data quality, improving the reliability of the 5G signaling analysis system; it comprehensively covers data integrity vulnerabilities through multi-dimensional statistics; it performs periodic testing to adapt to dynamic network changes; and it outputs detailed records to facilitate operators in quickly locating and fixing problems.

[0033] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0034] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for 5G signaling data quality detection based on multidimensional statistical analysis, characterized in that, Includes the following steps: S1. Filter the multi-interface signaling data accessed by the 5G signaling analysis system to obtain signaling messages of a predetermined type; S2. Parse the filtered signaling messages and perform periodic statistics from three dimensions: Tracking Area Code (TAC), NR Cell Identifier (NCI), and Network Element Address, to generate a statistical data set; S3. Automatically compare the statistical data set with the operating parameter information to calculate the TAC integrity rate, NCI integrity rate, and network element address integrity rate; wherein, the TAC integrity rate is the proportion of non-duplicate TACs counted in a single period in the operating parameter information; the NCI integrity rate is the proportion of non-duplicate NCIs counted in a single period in the operating parameter information; the network element address integrity rate includes the network element address integrity rate of each interface, and the network element address integrity rate of each interface is the proportion of the network element address of that interface counted in a single period in the network element address list of the corresponding interface in the operating parameter information; S4. Based on the calculated integrity rate, evaluate the quality of signaling data; specifically, if the TAC integrity rate, NCI integrity rate, and network element integrity rate are all 100%, the data quality is deemed qualified; otherwise, it is deemed unqualified, and a problem list is output; the output problem list includes: outputting TAC details, NCI details, and network element address details that are not covered or reported, to assist in locating data anomalies.

2. The method according to claim 1, characterized in that, In step S1, the multi-interface signaling data accessed by the 5G signaling analysis system is filtered, including: Filter InitialUEMessage signaling messages of the NGAP protocol in the N1 & N2 interfaces; Filter authentication request signaling messages of the HTTP / 2 protocol in the N12 interface; Filter session establishment request signaling messages of the PFCP protocol in the N4 interface.

3. The method according to claim 1, characterized in that, In step S2, the TAC, NCI and network element addresses obtained from the parsing statistics are saved to the TAC statistics set, NCI statistics set and network element address statistics set constructed based on red-black trees, respectively.

4. A 5G signaling data quality detection system, characterized in that, For implementing the method as described in any one of claims 1-3, comprising: The signaling message filtering module is used to filter the multi-interface signaling data accessed by the 5G signaling analysis system and obtain signaling messages of a predetermined type. The parsing and statistics module is used to parse the filtered signaling messages and perform periodic statistics from three dimensions: Tracking Area Code (TAC), NR Cell Identifier (NCI), and Network Element Address, to generate a statistical data set. The quality assessment module is used to automatically compare statistical data sets with engineering parameter information, calculate TAC integrity rate, NCI integrity rate, and network element address integrity rate; and evaluate the quality of signaling data based on the calculated integrity rate.

Images