A 5G-R-based base station TCE data automatic extraction and processing method and device

Abstract

The present disclosure relates to the field of communication technology, and particularly relates to a base station TCE data automatic extraction and processing method and device based on 5G-R. Incremental change data is collected from TCE; the collected data is parsed, data format is identified and signaling key information is extracted, XDR call slips are generated; multi-dimensional data correlation is performed, TraceRecSessionRef is used as a global correlation identifier, base station side air interface signaling and core network side signaling are end-to-end correlated by combining AMF_UE_NGAP_ID, and N3, N6 and N9 interface signaling is parsed to obtain railway service characteristic information containing train number, locomotive number, kilometer marker and speed information; the extended XDR call slip after data correlation is stored for retrieval and display. The present disclosure solves the problems of data fragmentation between the base station side and the core network side, lack of unified correlation and inability to directly serve railway operation and maintenance in the prior art, and realizes deep fusion and analysis of 5G-R network full-link data.

Description

Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a method and apparatus for automatic extraction and processing of TCE data from a 5G-R base station. Background Technology

[0002] With the development of railway transportation towards intelligence and high speed, the new generation of dedicated railway mobile communication technology, 5G-R (5G-based railway mobile communication system), has emerged. Compared with the traditional GSM-R network, the 5G-R network has made a qualitative leap in transmission bandwidth, latency, and number of connections. It can carry a variety of high-bandwidth, low-latency services such as train control and dispatching communication and video surveillance, and is a key infrastructure to ensure the safe and stable operation of future high-speed railways.

[0003] The 5G-R network environment is complex, requiring the integrated analysis of network signaling, network traffic, and related network quality data from various network interfaces, as well as network fault analysis, which is crucial for ensuring the safe and stable operation of trains. Currently, monitoring of 5G base station-side Uu and Xn signaling, measurement reports, and MDT (road test) data generally employs a soft acquisition solution, using TCE (Tracking Collection Entity) to analyze and monitor network operation and maintenance status, thereby standardizing network operation and maintenance procedures, optimizing network resource utilization, and ensuring network operation and maintenance quality. However, there are currently no mature solutions for data parsing and processing of various TCE data, as well as for the associated storage and categorized querying of data from core network-related interfaces.

[0004] Existing 5G-R network monitoring technology still has the following shortcomings, making it difficult to meet the needs of efficient railway operation and maintenance: 1. Existing solutions primarily employ drive-testing equipment to access the network as a UE, collecting relevant air interface data while performing various service operations. Similar to a special terminal, it records air interface information of the network interaction during network service usage, but it can only simulate terminal status as closely as possible, influenced by its own radio frequency reception. Since railway vehicle-mounted radios carry train control services, it is impossible to detect the most accurate data transmission and reception status of the vehicle-mounted radios using drive-testing equipment.

[0005] 2. Using a separately configured air interface monitoring device is limited by its own radio frequency processing capabilities, and the monitoring signaling cannot be guaranteed to be complete. Furthermore, with air interface open integrity protection and encryption, air interface monitoring alone cannot provide complete parsing.

[0006] 3. With the development of 5G technology, base station-side network elements are becoming more intelligent. The TCE (Tracking and Acquisition) soft acquisition solution, by configuring a tracking and acquisition entity module on the base station side, captures signaling messages from the base station's L3 layer (RRC, NGAP protocol stack) and measurement reports from the base station's RRM (Radio Resource Management) module, enabling the acquisition of relatively complete air interface data and comprehensively reflecting the base station's air interface operating status. TCE can collect data including trace signaling, raw code streams, MDT (Mean Transmission Data), MRO (Mean Transmission Recovery Report), and MRE (Mean Transmission Event Report), providing a direct reflection of the network status on the base station side. However, the various types of data currently reported by TCE devices are independent, scattered, and lack integration, failing to form a unified analytical view and hindering comprehensive data utilization. Currently, there is no mature solution for efficiently acquiring and effectively utilizing 5G-R network TCE data, integrating it into a 5G-R full network interface monitoring system, and directly reflecting the complete signaling process and business interaction process of a specific railway user.

[0007] In summary, how to efficiently acquire TCE data from 5G-R network base stations, deeply correlate and integrate it with core network monitoring data, and assign railway business attributes (such as train number and location) to the data in order to achieve refined end-to-end monitoring of the 5G-R network is a technical problem that urgently needs to be solved. Summary of the Invention

[0008] To address the aforementioned issues, this disclosure provides a method and apparatus for automatic extraction and processing of TCE data from a 5G-R base station.

[0009] Firstly, a method for automatic extraction and processing of TCE data from 5G-R base stations includes: Incremental change data is collected from the TCE server. The incremental change data includes drive test data (MDT), measurement report data (MRO and MRE), and trace signaling data. The collected incremental change data is parsed, the data format is identified and the signaling information is extracted to generate the initial XDR call detail records for each interface; Multi-dimensional data association is performed on the initial XDR call detail record to obtain the extended XDR; the multi-dimensional data association includes: single-type data association and overall data association; Single-type data association, including the association of single-type TCE incremental change data with user identity information; The data is correlated as a whole, including the correlation between TCE incremental change data and the signaling process of the N2 interface of the core network, to achieve the fusion of base station data and core network interface monitoring data; and the correlation between the signaling processes of the N3, N6, and N9 interfaces and railway users, to achieve the fusion of base station data and core network railway business data. The extended XDR after data association is stored and used for signaling processes and data classification queries.

[0010] Furthermore, single-type data association includes: For measurement report data MRO and MRE, AMF_UE_NGAP_ID is used as an identifier to distinguish them and is associated with the railway user signaling process; AMF_UE_NGAP_ID is a key identifier used to uniquely identify the user equipment (UE); For MDT road test data, the International Mobile Subscriber Identity (IMSI) and International Mobile Equipment Identity (IMEI) information are linked to the railway user signaling process. For Trace signaling tracing data differentiated according to railway users, TraceRecSessionRef is used as an identifier to distinguish and associate it with the user signaling process.

[0011] Furthermore, the incremental change data is associated with the signaling process of the core network N2 interface, including: Extract TraceRecSessionRef from the Trace signaling tracing data as a global association identifier; By using TraceRecSessionRef to associate trace data across network elements, a complete communication signaling process is formed. The Trace data is associated with the N2 interface signaling corresponding to the AMF in the core network via AMF_UE_NGAP_ID; The user identity information, including IMSI and TMSI, is extracted from the N2 interface data of the core network and backfilled into the corresponding N2 interface signaling in the Trace file. Then, the user information is backfilled into the complete session flow of the terminal, and the complete Uu and Xn interface signaling flow is associated with the N1 and N2 signaling.

[0012] Furthermore, the Trace data is associated with the corresponding N2 interface signaling of the core network AMF via AMF_UE_NGAP_ID, including: For the trace data, the AMF_UE_NGAP_ID carried in the trace data is extracted by parsing the NAS signaling Registration Request and Service Request signaling carried in the INITIAL UE MESSAGE signaling of the NG protocol; Parse the Initial ContextSetup Request signaling that carries the same NAS signaling Service Accept signaling on the N2 interface of the core network; By establishing a one-to-one correspondence between the Initial Context Setup Request and AMF_UE_NGAP_ID, the Trace data is associated with the signaling flow of the corresponding N2 interface of the core network AMF.

[0013] Furthermore, the signaling processes for the N3, N6, and N9 interfaces are associated with railway users, including: Parse the N3, N6, and N9 interface signaling of the core network UPF to obtain railway business characteristic information, including train number, locomotive number, kilometer marker, and speed information; The IP address and tunnel endpoint identifier TEID corresponding to the railway business characteristic information are extracted through the N3, N6, and N9 interface signaling, and then associated with the railway user identity information; By using the IMSI corresponding to the railway user identity information, the signaling processes of the N3, N6, and N9 interfaces of the core network UPF are associated with the signaling processes of the Uu and Xn interfaces of the base station, thereby realizing the association between the signaling of the core network UPF and the signaling of the base station.

[0014] Furthermore, extract signaling information, including: Identify the protocol type and version number of the original signaling message; Deep packet inspection is used to parse the identified protocol stack; The protocol stack includes at least the XNAP protocol for the Xn interface, the RRC protocol for the Uu interface, and the NAS protocol signaling carried by each interface.

[0015] Furthermore, incremental change data is collected from the TCE server on the base station side, including: Configure connection parameters for different types of TCE servers; Listen to the specified directory on the TCE server via SFTP or FTP protocol; Multi-threaded streaming acquisition is used to obtain incremental data files in XML or CSV format.

[0016] Secondly, a 5G-R-based base station TCE data automatic extraction and processing system includes: The module consists of a data acquisition module, a data parsing module, a data association module, and a storage module. The acquisition module is used to collect incremental change data from the TCE server. The incremental change data includes drive test data MDT, measurement report data MRO and MRE, and trace signaling data. The parsing module is used to parse the collected incremental change data, identify the data format and extract signaling information, and generate the initial XDR call detail records for each interface. The association module is used to perform multi-dimensional data association on the initial XDR call detail record to obtain the extended XDR; among which, multi-dimensional data association includes: single-type data association and overall data association; Single-type data association, including the association of single-type TCE incremental change data with user identity information; The data is correlated as a whole, including the correlation between TCE incremental change data and the signaling process of the N2 interface of the core network, to achieve the fusion of base station data and core network interface monitoring data; and the correlation between the signaling processes of the N3, N6, and N9 interfaces and railway users, to achieve the fusion of base station data and core network railway business data. The storage module is used to store the extended XDR after data association and for signaling flow and data classification query.

[0017] Thirdly, an electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, which stores computer programs; When the processor executes the computer program stored in the memory, it implements the above-mentioned method for automatic extraction and processing of TCE data from a 5G-R base station.

[0018] Fourthly, a computer-readable storage medium stores a computer program that, when executed by a processor, implements the above-described method for automatic extraction and processing of TCE data from a 5G-R base station.

[0019] This disclosure includes at least the following beneficial effects: This disclosure collects incremental change data from the TCE (Training Center for Equipment); parses the collected data, identifies the data format, extracts key signaling information, and generates XDR (Extended Recording Detail) call details; performs multi-dimensional data association, using TraceRecSessionRef as a global association identifier, and combines AMF_UE_NGAP_ID to perform end-to-end association between base station-side air interface signaling and core network-side signaling, and parses N3, N6, and N9 interface signaling to obtain railway service characteristic information including train number, locomotive number, kilometer marker, and speed information; and stores the extended XDR call details after data association for retrieval and display. This disclosure solves the problems of data fragmentation between the base station side and the core network side, lack of unified association, and inability to directly serve railway operation and maintenance in existing technologies, realizing deep integration and analysis of full-link data in the 5G-R network.

[0020] Other features and advantages of this disclosure will be set forth in the following description and will be apparent in part from the description or may be learned by practicing the disclosure. The objects and other advantages of this disclosure may be realized and obtained by means of the structures pointed out in the description and the accompanying drawings. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this disclosure 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 some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a schematic flowchart of the processing method according to an embodiment of the present disclosure; Figure 2 This is a schematic diagram of the system architecture of an embodiment of this disclosure; Figure 3 This is a schematic diagram of the electronic device structure according to an embodiment of the present disclosure. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0024] like Figure 1 As shown, an automatic extraction and processing method for TCE data from a 5G-R base station includes: S101 collects incremental change data from the TCE server. The incremental change data includes road test data MDT, measurement report data MRO and MRE, and trace signaling tracking data differentiated according to railway users. S102, parses the collected incremental change data, identifies the data format and extracts signaling information, and generates the initial XDR call detail records for each interface; S103, perform multi-dimensional data association on the initial XDR call detail record to obtain the extended XDR; wherein, the multi-dimensional data association includes: single-type data association and overall data association; Single-type data association, including the association of single-type TCE incremental change data with user identity information; The data is correlated as a whole, including the correlation between incremental change data and N2 interface signaling process to achieve the fusion of base station data and core network interface monitoring data; and the correlation between N3, N6, and N9 interface signaling processes and railway users to achieve the fusion of base station data and core network railway business data. S104 stores the extended XDR after data association and uses it for signaling flow and data classification query.

[0025] In practice: Data collection: The 5G-R network base station information extraction and analysis device collects MDT, MRO, and MRE data from the base station-side TCE (Tracking Equipment Center) and trace signaling data differentiated by user. The base station network element sends the collected data to the core network TCE server virtual machine for aggregation via XML or CSV files. The 5G-R network base station information extraction and analysis device collects incremental change data from various TCE servers through streaming data acquisition, supporting common protocols such as SFTP or FTP to retrieve collected data from relevant directories on the TCE servers. It supports multi-threaded parallel acquisition from multiple TCE servers from various manufacturers.

[0026] The parsing process consists of two parts: 1) data file parsing; 2) raw signaling parsing. Data File Parsing: Trace and measurement report data stored on the TCE server are in XML format, while MDT data is in CSV format. Data file parsing has the capability to process multiple data formats and flexibly configures parsing rules. Processing TCE-reported data includes parsing XML and CSV file formats. By parsing XML tags, data attributes are obtained, including the message initiator, target, agent, and original message protocol version. This information can be used to further parse the original signaling.

[0027] Raw signaling parsing: Raw signaling messages are represented in hexadecimal. The raw signaling is identified by the protocol and version number. DPI (Deep Packet Inspection) technology is used to quickly parse the multi-layer protocol of the data, forming the initial XDR (Extended Data Record) call detail records for each interface. The protocol scope includes the XNAP protocol of Xn, the RRC protocol of Uu interface, and the NAS protocol signaling carried by each interface.

[0028] Associations include: 1) association of single-type data; 2) association of overall data; Single-type data association: Measurement report data can be distinguished and associated with the same user's signaling flow through AMF_UE_NGAP_ID. AMF_UE_NGAP_ID is a key identifier used to uniquely identify the User Equipment (UE) in the NGAP (Next Generation Application Protocol) interface. It is generated and assigned by the Access and Mobility Management Function (AMF) of the 5G core network.

[0029] MDT data carries IMSI and IMEI information, which are linked to the same signaling process through IMSI (International Mobile Subscriber Identity) and IMEI (International Mobile Equipment Identity).

[0030] For trace data, TraceRecSessionRef (Trace Recording SessionReference) is used as an identifier to distinguish and associate it with the Uu and Xn signaling flows of the same user. TraceRecSessionRef is a globally unique identifier assigned by EMS (Electronic Element Management System). The association uses TraceRecSessionRef as the core association identifier to associate trace data across network elements (such as gNB, AMF, UPF), ensuring that the scattered signaling of various interfaces can be integrated into a complete flow. A complete communication flow of a user can be associated through TraceRecSessionRef.

[0031] Overall data association: For MDT and measurement report data, the relevant signaling of the core network N1 / N2 interface is associated through AMF_UE_NGAP_ID. The IMSI information carried by the MDT can also be used to compare and verify the correctness of the associated signaling process results of N1 / N2.

[0032] For trace log data, the data file contains N2 interface signaling between gNodeB and AMF. By parsing the NAS Service Accept signaling carried by the N2 interface Initial Context Setup Request signaling in the trace data, and using the AMF_UE_NGAP_ID it carries, we can correlate it with the Initial Context Setup Request signaling carrying the same NAS Service Accept signaling on the core network N2 interface. In the 5G-R network, there is a one-to-one correspondence between Initial Context Setup Request and AMF_UE_NGAP_ID. Since the core network interface monitoring has completed the complete association of this session, we can extract the user identity information such as IMSI and TMSI from the core network N2 interface data, fill it back into the corresponding N2 interface signaling in the trace file, and then fill the user information back into the complete session flow of the terminal. This allows us to associate the complete Uu and Xn interface signaling flow with the N1 / N2 signaling.

[0033] By parsing the signaling from interfaces N3, N6, and N9, CTCS-3 user identification information is obtained, including train number, locomotive number, kilometer marker, and speed information. The TEID+IP information parsed from the signaling is then correlated with the user identification information. Finally, the IMSI is linked to the generated call detail records (CDRs) reported by TCEs such as Uu, Xn, and Ng.

[0034] Storage and data display: For data storage, an extended XDR storage structure is adopted, including call detail records (CDRs) for each interface, extended session IDs, locomotive numbers, train numbers, and other information. The CDR ID is used to associate signaling processes such as registration, session establishment, and handover, and the session ID is used to associate all communication session processes of a single user. It supports queries by railway locomotive number, railway train number, and IMSI. Real-time signaling tracking of monitoring data for individual railway users can be achieved through data push.

[0035] This disclosure supports parallel streaming acquisition of TCE equipment data from multiple manufacturers using various protocols such as FTP / SFTP; it offers flexible and compatible processing and parsing for multiple data structures and formats. This disclosure integrates DPI technology for parsing, achieving deep protocol stack-level parsing of trace data, extracting multi-dimensional correlation identifiers, and enabling complete association with core network interface monitoring data; this disclosure provides complete backfilling of user information and session IDs, and supports data aggregation and querying by user, locomotive, and train number.

[0036] This disclosure enables TCE to achieve data association within a single file and continuous association of data across multiple files. The association algorithm is optimized for 5G-R railway scenarios, supporting real-time association of specific information such as locomotive number, train number, kilometer marker, and speed, directly serving railway operation and maintenance needs.

[0037] This disclosure proposes a multi-identifier association model with TraceRecSessionRef as the core association node and AMF_UE_NGAP_ID, IMSI, and TMSI as branches, to solve the problem of quickly identifying the complete user session flow in high-speed train handover scenarios.

[0038] like Figure 2 As shown, an automatic extraction and processing system for TCE data from a 5G-R base station includes: The module consists of a data acquisition module, a data parsing module, a data association module, and a storage module. The acquisition module is used to collect incremental change data from the TCE server. The incremental change data includes road test data MDT, measurement report data MRO and MRE, as well as trace signaling data differentiated according to railway users. The parsing module is used to parse the collected incremental change data, identify the data format and extract signaling information, and generate the initial XDR call detail records for each interface. The association module is used to perform multi-dimensional data association on the initial XDR call detail record to obtain the extended XDR; among which, multi-dimensional data association includes: single-type data association and overall data association; Single-type data association, including the association of single-type TCE incremental change data with user identity information; The data is correlated as a whole, including the correlation between TCE incremental change data and the signaling process of the N2 interface of the core network, to achieve the fusion of base station data and core network interface monitoring data; and the correlation between the signaling processes of the N3, N6, and N9 interfaces and railway users, to achieve the fusion of base station data and core network railway business data. The storage module is used to store the extended XDR after data association and for signaling flow and data classification query.

[0039] In practice: The parsing module includes: a data file parsing module and a raw signaling parsing module; The association modules include: a single-type data association module and a data-wide association module.

[0040] Categorized by interface protocol type, this disclosure covers key interfaces from the radio side to the core network side: Uu interface signaling (air interface signaling) is the wireless interface signaling between the train's onboard terminal and the 5G base station, directly reflecting the wireless connection status of the train during high-speed movement. The involved protocol is RRC (Radio Resource Control). It can be obtained through trace data collected by the base station's TCE.

[0041] Xn interface signaling is the interface signaling between 5G base stations, primarily used for handover coordination between them. It is crucial for high-speed rail scenarios because frequent base station handovers occur while trains are moving at high speeds, and Xn interface signaling records detailed information about the handover process. The involved protocol is XNAP (Xn Application Protocol). It can be obtained through trace data collected by the base station's TCE.

[0042] The N1 / N2 interface signaling (core network side signaling) uses N1 as the interface between the terminal (UE) and the core network (AMF), and N2 as the interface between the base station (gNB) and the core network (AMF). This disclosure uses the parsing of these signaling messages to extract key association IDs (such as AMF_UE_NGAP_ID), thereby enabling communication between the air interface data on the base station side and the core network side. The relevant protocol is NGAP (Next Generation Application Protocol). This can be obtained through monitoring data from the core network interface.

[0043] The N3 / N6 / N9 interface signaling (user plane / bearer signaling) uses N3 as the interface between the base station and the core network (UPF), N6 as the interface between the core network (UPF) and the data network, and N9 as the interface between core network UPFs. This disclosure obtains railway-specific business data (such as CTCS-3 train control data) by parsing the signaling of these interfaces. The data involved includes user data packets containing train number, locomotive number, kilometer marker, and speed information. This data can be obtained through core network interface monitoring.

[0044] This disclosure solves the problem of isolated information from a single signaling source by integrating these signaling data from different dimensions.

[0045] In existing monitoring solutions, monitoring data from the base station side (TCE data) and the core network side are often independent "data silos." The scattered nature of TCE data and the lack of a unified association identifier make it difficult for operations and maintenance personnel to correlate the radio status of the base station with the service status of the core network, hindering cross-network element fault localization. This disclosure successfully breaks down the barriers between base station-side (TCE data) and core network-side data by constructing multi-dimensional data associations, using TraceRecSessionRef as a global association identifier, and combining key parameters such as AMF_UE_NGAP_ID and IMSI. It accurately associates the scattered Uu and Xn interface signaling with N1, N2, and N3 interface signaling, integrating them into a complete end-to-end signaling flow view. This enables operations and maintenance personnel to cross network element boundaries, providing a panoramic view of user communication processes, forming a complete end-to-end signaling flow, and significantly improving the efficiency of network fault localization.

[0046] This disclosure solves the challenge of session continuity monitoring in high-speed mobile scenarios. Specifically addressing the frequent base station handovers caused by the high-speed movement of high-speed trains, this disclosure utilizes TraceRecSessionRef as a stable anchor point, overcoming the shortcomings of traditional methods relying on IP addresses or temporary identifiers, which are prone to session loss during handovers. This ensures that the system can continuously and completely identify and record the communication session flow even when the train is rapidly traversing different base station coverage areas, guaranteeing the integrity and continuity of the monitoring data.

[0047] This invention creatively analyzes the signaling of the N3, N6, and N9 interfaces of the core network, extracting railway business characteristic information such as train number, locomotive number, kilometer marker, and speed from the CTCS-3 train control data, and then backfills this information into the XDR call detail records on the base station side via IMSI. This technological breakthrough tightly binds abstract network indicators (such as signal strength and packet loss rate) with specific railway entities (such as a specific train or kilometer marker), enabling network monitoring to directly serve train safety operation and solving the pain point of traditional monitoring schemes that "only look at the network, not the train." This allows maintenance personnel to directly query network quality by "train number" or "location," achieving deep integration of network monitoring and railway transportation operations.

[0048] like Figure 3 As shown, this disclosure provides an electronic device, including a processor 301, a communication interface 302, a memory 303, and a communication bus 304, wherein the processor 301, the communication interface 302, and the memory 303 communicate with each other through the communication bus 304; Memory 303 stores computer programs; The processor 301 implements the above method when executing a computer program stored in the memory 303.

[0049] This disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0050] The computer-readable storage medium may be included in the device / apparatus described in the above embodiments; or it may exist independently and not assembled into the device / apparatus. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0051] According to embodiments of this disclosure, the computer-readable storage medium can be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0052] Although the present disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. A method for automatic extraction and processing of TCE data from a 5G-R base station, characterized in that, include: Incremental change data is collected from the TCE server. The incremental change data includes drive test data (MDT), measurement report data (MRO and MRE), and trace signaling data. The collected incremental change data is parsed, the data format is identified and the signaling information is extracted to generate the initial XDR call detail records for each interface; Multi-dimensional data association is performed on the initial XDR call detail record to obtain the extended XDR; the multi-dimensional data association includes: single-type data association and overall data association; Single-type data association, including the association of single-type TCE incremental change data with user identity information; The data is correlated as a whole, including the correlation between TCE incremental change data and the signaling process of the N2 interface of the core network, to achieve the fusion of base station data and core network interface monitoring data; and the correlation between the signaling processes of the N3, N6, and N9 interfaces and railway users, to achieve the fusion of base station data and core network railway business data. The extended XDR after data association is stored and used for signaling processes and data classification queries.

2. The method for automatic extraction and processing of TCE data from a 5G-R base station according to claim 1, characterized in that, Single-type data association, including: For measurement report data MRO and MRE, AMF_UE_NGAP_ID is used as an identifier to distinguish them and associate them with the same user signaling process; AMF_UE_NGAP_ID is a key identifier used to uniquely identify the user equipment (UE); For MDT (Multi-Demand Test) data, the International Mobile Subscriber Identity (IMSI) and International Mobile Equipment Identity (IMEI) information are associated with the same user signaling process. For Trace signaling tracing data differentiated according to railway users, TraceRecSessionRef is used as an identifier to distinguish and associate it with the railway user signaling process.

3. The method for automatic extraction and processing of TCE data from a 5G-R base station according to claim 1, characterized in that, The incremental change data is associated with the signaling flow of the N2 interface of the core network, including: Extract TraceRecSessionRef from the Trace signaling tracing data as a global association identifier; By using TraceRecSessionRef to associate trace data across network elements, a complete communication signaling process is formed. The Trace data is associated with the N2 interface signaling corresponding to the AMF in the core network via AMF_UE_NGAP_ID; Extract the user identity information, including IMSI and TMSI, from the N2 interface data of the core network, and backfill it into the corresponding N2 interface signaling in the Trace file. Then, backfill the user identity information into the complete session flow of the Trace file, and associate the complete Uu and Xn interface signaling flow with the N1 and N2 signaling.

4. The method for automatic extraction and processing of TCE data from a 5G-R base station according to claim 3, characterized in that, The Trace data is associated with the corresponding N2 interface signaling of the AMF in the core network via AMF_UE_NGAP_ID, including: For Trace data, the NAS Service Accept signaling carried by the Initial Context Setup Request signaling of the Trace data N2 interface is parsed to extract the AMF_UE_NGAP_ID carried by it; Parse the Initial Context SetupRequest signaling that carries the same NAS signaling Service Accept signaling on the N2 interface of the core network, and extract the AMF_UE_NGAP_ID carried by it; By establishing a one-to-one correspondence between the Initial Context Setup Request and AMF_UE_NGAP_ID, the Trace data is associated with the signaling flow of the corresponding N2 interface of the core network AMF.

5. The method for automatic extraction and processing of TCE data from a 5G-R base station according to claim 1, characterized in that, The signaling processes for the N3, N6, and N9 interfaces are associated with railway users, including: Parse the N3, N6, and N9 interface signaling of the core network UPF to obtain railway business characteristic information, including train number, locomotive number, kilometer marker, and speed information; The IP address and tunnel endpoint identifier TEID corresponding to the railway business characteristic information are extracted through the N3, N6, and N9 interface signaling, and then associated with the user identity information; By using the IMSI corresponding to the railway user identity information, the signaling processes of the N3, N6, and N9 interfaces of the core network UPF are associated with the signaling processes of the Uu and Xn interfaces of the base station, thereby realizing the association between the signaling of the core network UPF and the signaling of the base station.

6. The method for automatic extraction and processing of TCE data from a 5G-R base station according to claim 1, characterized in that, Extract signaling information, including: Identify the protocol type and version number of the original signaling message; Deep packet inspection is used to parse the identified protocol stack; The protocol stack includes at least the XNAP protocol for the Xn interface, the RRC protocol for the Uu interface, and the NAS protocol signaling carried by each interface.

7. The method for automatic extraction and processing of TCE data from a 5G-R base station according to claim 1, characterized in that, Incremental change data is collected from the TCE server on the base station side, including: Configure connection parameters for different types of TCE servers; Listen to the specified directory on the TCE server via SFTP or FTP protocol; Multi-threaded streaming acquisition is used to obtain incremental data files in XML or CSV format.

8. A system for automatic extraction and processing of TCE data from a 5G-R base station, characterized in that, include: The module consists of a data acquisition module, a data parsing module, a data association module, and a storage module. The acquisition module is used to collect incremental change data from the TCE server. The incremental change data includes drive test data MDT, measurement report data MRO and MRE, and trace signaling data. The parsing module is used to parse the collected incremental change data, identify the data format and extract signaling information, and generate the initial XDR call detail records for each interface. The association module is used to perform multi-dimensional data association on the initial XDR call detail record to obtain the extended XDR; among which, multi-dimensional data association includes: single-type data association and overall data association; Single-type data association, including the association of single-type TCE incremental change data with user identity information; The data is correlated as a whole, including the correlation between TCE incremental change data and the signaling process of the N2 interface of the core network, to achieve the fusion of base station data and core network interface monitoring data; and the correlation between the signaling processes of the N3, N6, and N9 interfaces and railway users, to achieve the fusion of base station data and core network railway business data. The storage module is used to store the extended XDR after data association and for signaling flow and data classification query.

9. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, which stores computer programs; When a processor executes a computer program stored in a memory, it implements the automatic extraction and processing method for 5G-R base station TCE data according to any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the automatic extraction and processing method of TCE data of a 5G-R base station as described in any one of claims 1-7.

Images