5G core network element information automatic learning method and system and computer equipment

Abstract

The invention relates to the technical field of communication, and discloses a 5G core network element information automatic learning method and system and computer equipment, and the method comprises the following steps: S1, data access and preprocessing: a packet receiving module is utilized to comprehensively access a signaling data message in a current network; s2, network element request identification and screening: specific target features are passed; s4, extracting the attribute information of the network element: extracting the attribute information of the network element from the associated and combined Discovery type data packet; s5, network element attribute information packaging and classification, wherein a data packaging technology is adopted by a packaging module; and S6, data output and storage: outputting the classified network element attribute information into various format documents with different dimensions by an output module. The existing network element information data in the current network is obtained through direct analysis according to the actual data flow, and the 5G core network element automatic learning function can directly learn and store the related network element information according to the actual flow without concerning the format provided by an operator, so that better compatibility is achieved.

Description

Technical Field

[0001] The present invention relates to the field of communication technologies, and particularly to a method, a system, and a computer device for automatically learning information of network elements in a 5G core network. Background Art

[0002] With the deployment of 5G networks, the resulting technological innovation has changed all aspects of people's lives. The most representative technology in 5G technology is the realization of the Internet of Things, which enables things to be connected to each other. Numerous devices need to access the 5G network, resulting in an increase in data traffic and the number of network elements. The increase in data traffic has imposed great pressure on backend data analysis. The increase in the number of network elements not only poses great difficulties for maintenance personnel but also increases a lot of communication costs during information synchronization.

[0003] Currently, the maintenance of network element information mainly relies on construction personnel or operators to directly provide it. Moreover, it also faces the situation of different formats among different operators and across provinces and cities. When backend data analysis needs to use this network element information for feature analysis of specific data, it increases a lot of difficulty and workload. At the same time, the timeliness of network element information cannot be guaranteed. Also, due to the current network elements having multiple IP attributes, when doing data association and analysis at the backend, if the network element IP switches between multiple ones, it will greatly affect the effect of data analysis. Summary of the Invention

[0004] The main objective of the present invention is to provide a method, a system, and a computer device for automatically learning information of network elements in a 5G core network, aiming to solve the problems that when using this network element information for feature analysis of specific data, it increases a lot of difficulty and workload, and when doing data association and analysis at the backend, if the network element IP switches between multiple ones, it will greatly affect the effect of data analysis.

[0005] To achieve the above-mentioned invention objective, the first aspect of the present invention proposes a method for automatically learning information of network elements in a 5G core network, including the following steps:

[0006] S1. Data access and preprocessing: Use the packet receiving module to comprehensively access the signaling data packets in the existing network, and with the help of the pre-parsing module, use data parsing techniques and algorithms to perform preliminary processing on the original data packets;

[0007] S2. Network element request identification and screening: Through the acquisition feature recognition algorithm and then through specific target features, screen and identify the preprocessed data packets;

[0008] S3. Signaling association and caching: Use the http2 stream caching module, relying on its data storage and management capabilities, to associate and combine the GET requests of the Discovery type and the corresponding response information;

[0009] S4 NE Attribute Information Extraction: From the associated and combined Discovery-type data packets, use data analysis and mining techniques to obtain various detailed attribute information of the requested target 5G core network elements;

[0010] S5 NE Attribute Information Encapsulation and Classification: The encapsulation module uses data encapsulation technology to correspond and integrate the extracted complex NE attribute information one by one, and divides and classifies it in detail according to different dimensions with clear business logic and analysis requirements;

[0011] S6, Data Output and Storage: The output module outputs the classified NE attribute information into format documents of various different dimensions, and combines with the data storage system for ready call and query;

[0012] S7, Automatic Update and Maintenance: Establish a real-time monitoring mechanism to dynamically track and analyze newly generated signaling data regularly or in real time. When new or changed signaling data is detected, automatically trigger the update operation of the NE attribute information, and use data comparison and update algorithms to keep the NE attribute information always combined with the collected data status;

[0013] S8, Data Analysis and Application: Apply the automatically learned NE information to the backend data analysis process, and use data analysis tools and algorithms for data caused by multi-IP switching of NEs.

[0014] Furthermore, in S1, the preliminary processing includes the unification of data formats, the preliminary screening and classification of data fields, and the pre-parse module can also compress the data to reduce the data transmission volume.

[0015] Furthermore, in S2, the acquisition feature algorithm and specific target features are converted into a large number of data packets, and the large number of data packets include NRF Discovery-type signaling. The target features can be automatically updated and optimized by the module in the system. The module includes an identification module to adapt to network changes.

[0016] Furthermore, in S3, the http2 stream cache module can periodically clean the cached data to release storage space.

[0017] Furthermore, in S4, the extracted NE attribute information is encrypted to ensure data security. The various attribute information includes NE type nfType, NE instance ID, NE registration status status, basic information of heartbeat time interval, and also covers the NE's affiliated regional scope TaiRangeList and TacRangeList, all corresponding IPv4 and IPv6 of the NE, the NE's slice information NSSAI, and the NE's DNN information.

[0018] Further, in S5, it is possible to perform a priority sorting according to the importance level of network elements, and the detailed classification includes classification by network element IP dimension, area information Tai or Tac, slice NSSAI or DNN;

[0019] In S6, the format document includes an EXCEL format document or a TXT format document.

[0020] Further, in S7, the output document is monitored in real time, and data integrity verification is performed. The data comparison and update algorithm can handle abnormal data and error situations, and automatically trigger the network element update operation. The real-time monitoring mechanism can set the monitoring frequency and threshold.

[0021] Further, it is characterized in that in S8, the data analysis tools and algorithms can support distributed computing, can generate detailed data analysis reports, and intuitively display the analysis results.

[0022] In a second aspect, the present invention provides the following technical solution: a system for automatic learning of 5G core network element information, including:

[0023] a packet receiving module, a pre-parsing module, an identification module, an http2 stream caching module, a packaging module, and an output module;

[0024] The packet receiving module is used to receive signaling data packets from the existing network, providing a data basis for subsequent processing flows;

[0025] The pre-parsing module is used for the preliminary processing of the original data packets received by the packet receiving module. By applying data parsing techniques and algorithms, noise and irrelevant information are removed, providing a clear data structure for subsequent analysis and processing links;

[0026] The identification module is used to identify and screen out specific types of signaling with key value, including the Discovery type of signaling of NRF, from the massive pre-processed data by virtue of feature recognition algorithms, providing target data for subsequent processing steps;

[0027] The http2 stream caching module is used to closely and accurately associate and combine the GET requests of the Discovery type and the corresponding response information by virtue of its data storage and management capabilities, and perform cache management on these associated data. At the same time, it can handle various abnormal situations in data transmission, ensuring the integrity and accuracy of data;

[0028] The packaging module is used to adopt data packaging techniques to correspond and integrate the intricate network element attribute information extracted from the associated and combined data packets one by one, and perform detailed classification and packaging on the network element attribute information, providing a standardized and structured data format for subsequent data output and applications;

[0029] The output module is used to organize and output the classified and encapsulated network element attribute information by virtue of its data output and conversion capabilities.

[0030] In a third aspect, the present invention provides the following technical solution. A computer device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the above-mentioned 5G core network element information automatic learning method is implemented.

[0031] In a fourth aspect, the present invention provides the following technical solution. A readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned 5G core network element information automatic learning method is implemented.

[0032] Beneficial effects:

[0033] The 5G core network element information automatic learning method, system and computer device of the present invention directly analyze according to the actual data stream, obtain the existing network element information data in the current network, exclude the influence of other useless network elements, reduce the data volume level of the concerned network element information, and at the same time ensure the accuracy and timeliness of the information. In the face of different operators and different construction requirements, the 5G core network element automatic learning function can directly learn and save relevant network element information based on the actual traffic, no longer need to care about the format provided by the operator, achieving better compatibility, avoiding operations such as manually and frequently updating the network element information table, the automatic learning function can be updated in real time according to the actual data, the automatic learning function can learn various attributes of multiple network elements, ensuring the richness and practicality of the data, and solving the influence on data analysis and association when switching IPs during the interaction when there are multiple IPs for a network element. Description of the drawings

[0034] Figure 1 is a flowchart of the present invention;

[0035] Figure 2 is a schematic diagram of the NRF network element of the present invention;

[0036] Figure 3 is a schematic diagram of the NRF network element of the present invention;

[0037] Figure 4 is a system architecture diagram of the present invention.

[0038] The realization, functional characteristics and advantages of the object of the present invention will be further described with reference to the embodiments and the drawings. Detailed implementation manners

[0039] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0040] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the said features. In the description of the present invention, "a plurality" means two or more unless otherwise specifically defined.

[0041] In the description of the present invention, it should be noted that unless otherwise clearly specified and limited, the terms "mounted", "connected" and "coupled" shall be understood in a broad sense. For example, it may be a fixed connection, a detachable connection or an integral connection; it may be a mechanical connection, a direct connection or an indirect connection through an intermediate medium, and it may be the communication inside two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0042] In the present invention, unless otherwise clearly specified and limited, the first feature being "on" or "under" the second feature may include the direct contact between the first and second features, or may include the situation where the first and second features are not in direct contact but in contact through other features therebetween. Moreover, the first feature being "above", "over" and "on" the second feature includes that the first feature is directly above and obliquely above the second feature, or merely indicates that the horizontal height of the first feature is higher than that of the second feature. The first feature being "under", "beneath" and "under" the second feature includes that the first feature is directly below and obliquely below the second feature, or merely indicates that the horizontal height of the first feature is lower than that of the second feature.

[0043] Please refer to the attached Figure 1 - attached Figure 4 , the embodiment of the present invention provides a method for automatically learning the information of 5G core network elements, including the following steps:

[0044] S1. Data access and preprocessing: Use the packet receiving module to comprehensively access the signaling data packets in the existing network, and with the help of the pre-parsing module, use data parsing techniques and algorithms to perform preliminary processing on the original data packets;

[0045] S2. Network Element Request Identification and Screening: Through the acquisition feature recognition algorithm and specific target features, preprocessed data packets are screened and identified.

[0046] S3. Signaling Association and Caching: Using the http2 stream caching module, with its data storage and management capabilities, the GET requests of the Discovery type and the corresponding response information are associated and combined.

[0047] S4. Network Element Attribute Information Extraction: From the associated and combined Discovery type data packets, using data analysis and mining techniques, detailed and diverse attribute information of the requested target 5G core network elements is obtained.

[0048] S5. Network Element Attribute Information Encapsulation and Classification: The encapsulation module uses data encapsulation technology to correspond and integrate the extracted complex network element attribute information one by one, and makes a detailed classification according to different dimensions with clear business logic and analysis requirements.

[0049] S6. Data Output and Storage: The output module outputs the classified network element attribute information into various format documents of different dimensions, and combines with the data storage system for ready call and query.

[0050] S7. Automatic Update and Maintenance: Establish a real-time monitoring mechanism to dynamically track and analyze newly generated signaling data regularly or in real time. When new or changed signaling data is detected, an automatic update operation of the network element attribute information is triggered. Using data comparison and update algorithms, the network element attribute information is always combined with the collected data status.

[0051] S8. Data Analysis and Application: Apply the automatically learned network element information to the backend data analysis process, and use data analysis tools and algorithms for data caused by multi-IP switching of network elements.

[0052] In S1, the preliminary processing includes the unification of data formats, the preliminary screening and classification of data fields. The pre-parsing module can also compress the data to reduce the data transmission volume.

[0053] Specifically, when interaction or service provision requests are needed between different NFs, a probe request is first sent to the NRF network element to request the NRF network element to provide the corresponding NF instance, so as to provide the corresponding NF instance that meets the conditions for the NF requesting the service.

[0054] In S2, the acquisition feature algorithm and specific target features are converted into data packets. The data packets include the Discovery type signaling of the NRF. The target features for screening can be automatically updated and optimized by the modules in the system. The modules include the identification module to adapt to network changes.

[0055] Specifically, through special field filtering, the corresponding probe request messages provided by the NRF are filtered out from the data in the live network. Then, the probe request messages and response messages are bound, and relevant information of various network elements is parsed from the request messages and response messages, including network element IP, the scope of services provided by the network element, network element instance ID, slice service provision, and other types of information. These information are saved and output in multiple formats to form the configuration information of each network element. Subsequently, these information can be used to provide a filtering and screening basis for backend data analysis. At the same time, by querying the learned network element information table, it can be determined whether different IPs belong to the same network element, solving the impact brought by the problem of multi-IP switching of network elements in data association.

[0056] In S3, the http2 stream cache module can periodically clean the cached data to free up storage space.

[0057] Specifically, by using an efficient http2 stream cache module and fully leveraging its powerful data storage and management capabilities, the GET requests of the Discovery type and the corresponding response information are closely and accurately associated and combined. Through the association algorithm and precise matching mechanism, the correspondence between the request and response information is ensured to be accurate, thus providing a solid data foundation for subsequent data analysis and processing. In the signaling association and caching step, the http2 stream cache module can periodically clean the cached data to free up storage space. Specifically, it will intelligently identify and delete those expired, no longer needed, or less frequently used data according to the preset time interval or the capacity threshold of the cached data. At the same time, during the cleaning process, a data backup and verification mechanism will be adopted to prevent the accidental deletion of important data and ensure the security and stability of the cleaning operation, so as to ensure that the cache system always maintains an efficient operating state and provides sufficient storage space for continuous signaling association and caching work.

[0058] In S4, the extracted network element attribute information is encrypted to ensure data security. The multiple attribute information includes network element type nfType, network element instance ID, network element registration status status, basic information of the heartbeat time interval, and also covers the network element's affiliated regional scope TaiRangeList and TacRangeList, all corresponding IPv4 and IPv6 of the network element, the network element's slice information NSSAI, and the network element's DNN information.

[0059] Specifically, after the packet receiving module accesses the signaling data packets in the existing network, the pre-parsing module processes the data packets. The identification module filters out the signaling of the Discovery type of the NRF by identifying the target features. Through the http2 stream cache module, the GET requests of the Discovery type and the corresponding response information are associated and combined. The target 5G core network element type nfType, network element instance ID, network element registration status status, heartbeat time interval, network element affiliated area range TaiRangeList and TacRangeList, all corresponding IPv4 and IPv6 of the network element, slice information NSSAI of the network element, DNN information of the network element, and other network element-related attribute information are obtained from the Discovery type data packets. The encapsulation module corresponds these network element attribute information one by one, divides them according to different dimensions, supports classification according to the network element IP dimension, supports classification according to the area information Tai or Tac, supports division according to the slice NSSAI or DNN. Finally, the output module sorts and outputs them into various EXCEL format documents or TXT format documents in different dimensions. For 5G core network elements such as AMF, SMF, PCF, UPF, UDM, AUSF, NRF, etc., the corresponding attribute information of the network elements can be obtained using the current solution. According to the automatically learned information, many problems in data analysis can be solved, such as multi-IP switching of network elements, regional network element filtering, feature network element filtering, etc. Based on the NRF network element providing the Discovery service, the corresponding service consumer NFServiceComuser will initiate an http2 GET request to the NRF. After the NRF accepts the request, it will reply with the corresponding response data of the Discovery. The request and response packets of the Discovery are processed in a specific way to analyze the attribute information of the network elements.

[0060] In S5, it is possible to perform priority sorting according to the importance of network elements, and make a detailed classification including classification by network element IP dimension, area information Tai or Tac, slice NSSAI or DNN;

[0061] In S6, the format documents include EXCEL format documents or TXT format documents.

[0062] Specifically, in the step of encapsulating and classifying network element attribute information, it is possible to perform priority sorting according to the importance level of network elements. By comprehensively evaluating various factors such as the core position of network elements in the network architecture, the criticality of the services they carry, and the impact on the overall network performance, corresponding importance weights are assigned to network elements, and sorting work is carried out accordingly. The detailed classification covers multiple aspects including the network element IP dimension, area information Tai or Tac, slice NSSAI or DNN, etc. This multi-dimensional classification method fully considers different service scenarios and data analysis requirements, and can accurately classify network element attributes from different perspectives, thus providing rich perspectives and flexible options for subsequent data analysis and applications to meet diverse data analysis and application needs. For example, when optimizing the regional network, relevant network elements can be quickly located based on the area information classification; when conducting traffic analysis for specific services, accurate analysis can be carried out based on the slice information classification.

[0063] In S7, the output document is monitored in real time, and data integrity verification is performed. The data comparison and update algorithm can handle abnormal data and error situations and automatically trigger the network element update operation. The real-time monitoring mechanism can set the monitoring frequency and threshold.

[0064] Specifically, in the data output and storage step, advanced and reliable technical means can be used to comprehensively and meticulously perform data integrity verification on the output document. Through a series of verification algorithms and processes, every data field, every record, and the overall data structure in the output document are strictly inspected and verified to ensure the accuracy, consistency, and integrity of the data, and to avoid any possible data loss, error, or inconsistency. The data comparison and update algorithm has a strong ability to handle abnormal data and error situations. When faced with noise, missing values, incorrect formats, or data outside the reasonable range in the data, the algorithm can intelligently identify and adopt appropriate processing strategies, such as data cleaning, repair, marking, or elimination, to ensure that the accuracy and reliability of the results are not affected by abnormal data and error situations during the data comparison and update process. The real-time monitoring mechanism has a high degree of flexibility and customizability, and can conveniently set the monitoring frequency and threshold according to actual needs and specific application scenarios. Users can accurately adjust the monitoring interval time from millisecond level to hour level according to the change speed of the data, its importance level, and the resource status of the system. At the same time, reasonable threshold ranges can also be customized for the key indicators and boundary conditions of the monitored data. Once the monitored data exceeds or is lower than the set threshold, the system can promptly issue an alarm and take corresponding measures to ensure the stable operation of the system and the timely processing of data.

[0065] In S8, the data analysis tools and algorithms can support distributed computing and can generate detailed data analysis reports to intuitively display the analysis results.

[0066] Specifically, data analysis tools and algorithms have powerful functions and can strongly support distributed computing, thus significantly improving the processing efficiency. By decomposing data analysis tasks into multiple subtasks and processing them in parallel on multiple computing nodes, the data processing time is greatly shortened, enabling quick results to be obtained when dealing with large-scale data. These tools and algorithms can generate detailed and content-rich data analysis reports, which not only contain basic data statistics such as mean, median, standard deviation, etc., but also cover in-depth data analysis results such as trend prediction, correlation analysis, anomaly detection, etc. At the same time, the reports use intuitive and clear chart forms such as bar charts, line charts, pie charts, etc., as well as concise and clear text descriptions to present the analysis results in an easy-to-understand and interpret way, enabling users to grasp key information at a glance and make accurate decisions quickly.

[0067] Embodiment 2:

[0068] Refer to Figure 4 , in the second embodiment of the present invention, the present invention provides a system for automatic learning of 5G core network element information, including:

[0069] A packet receiving module, a pre-parsing module, an identification module, an http2 stream caching module, a packaging module, and an output module;

[0070] The packet receiving module is used to receive signaling data packets from the existing network and provide a data basis for subsequent processing flows;

[0071] The pre-parsing module is used for preliminary processing of the original data packets received by the packet receiving module. By applying data parsing techniques and algorithms, noise and irrelevant information are removed to provide a clear data structure for subsequent analysis and processing links;

[0072] The identification module is used to identify and screen out specific types of signaling with key value from the preprocessed massive data by virtue of feature recognition algorithms, including Discovery type signaling of NRF, to provide target data for subsequent processing steps;

[0073] The http2 stream caching module is used to closely and accurately associate and combine the GET requests of the Discovery type and the corresponding response information by virtue of its data storage and management capabilities, and perform cache management on these associated data. At the same time, it can handle various exceptions in data transmission to ensure the integrity and accuracy of the data;

[0074] The encapsulation module is used to adopt data encapsulation technology to correspond and integrate the complex network element attribute information extracted from associated and combined data packets one by one, classify and encapsulate the network element attribute information in detail, and provide a standardized and structured data format for subsequent data output and application;

[0075] The output module is used to organize and output the classified and encapsulated network element attribute information by virtue of its data output and conversion capabilities.

[0076] Specifically, the packet receiving module is like a vast data collection network, and its responsibility is to widely and without omission accept various signaling data packets from the existing network. No matter how diverse the sources of these packets are and how different their formats are, it can include them all, thus laying a solid data foundation for the entire subsequent processing process;

[0077] The pre-parsing module is like a skilled craftsman for data preprocessing. It is responsible for deeply and finely preprocessing the original data packets received by the packet receiving module. By means of sophisticated data parsing techniques and algorithms, it eliminates noise and irrelevant information like sifting sand from the waves, carefully sorts out and shapes a clear data structure, paving the way for more in-depth analysis and processing in the subsequent steps, and providing a simple, accurate and easy-to-operate data form;

[0078] The identification module is like a pair of sharp eyes. With its highly accurate and intelligent feature recognition algorithm, it can quickly and accurately identify and screen out specific types of signaling with key value from the vast amount of preprocessed data, including the Discovery type signaling of NRF, thus accurately locking the target data for the subsequent processing steps;

[0079] The http2 stream cache module is like a treasure house of data. By virtue of its powerful and excellent data storage and management capabilities, it can closely and accurately associate and combine the GET requests of the Discovery type and the corresponding response information. At the same time, it is like a rigorous data steward, implementing fine cache management for these associated data. When facing various abnormal situations in the data transmission process, it can come forward and effectively guarantee the integrity and accuracy of the data;

[0080] The encapsulation module is like a rigorous data packager. It adopts efficient and secure data encapsulation technology to accurately correspond and integrate the numerous network element attribute information extracted from the associated and combined data packets one by one. Through meticulous classification and encapsulation operations, it presents a standardized and structured data format for subsequent data output and application;

[0081] The output module is like an emissary of data. With its excellent data output and conversion capabilities, it orderly arranges and outputs the carefully classified and encapsulated network element attribute information in an efficient and easy-to-understand manner.

[0082] Embodiment 3

[0083] In the third embodiment of the present invention, based on the same inventive concept, a computer-readable storage medium is proposed by the present invention. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the 5G core network element information automatic learning method of the above embodiment are implemented.

[0084] Embodiment 4

[0085] In the fourth embodiment of the present invention, based on the same inventive concept, a computer device is proposed by the present invention, including: a processor and a memory; the processor and the memory communicate with each other; the memory is used to store instructions; the processor is used to execute the instructions in the memory to execute the 5G core network element information automatic learning method of the above embodiment.

[0086] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the specification and drawings of the present invention, or directly or indirectly applied to other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. 5G core network network element information automatic learning method, characterized in that: The following steps are involved: S1. Data access and preprocessing: Use the packet receiving module to fully access the signaling data packets in the existing network, and use the pre-analysis module, data analysis technology and algorithms to perform preliminary processing on the original data packets; S2, network element request identification and screening: through the acquisition feature recognition algorithm and then through the specific target features, the pre-processed data packets are screened and identified; S3, signaling association and caching: Use the http2 stream cache module, with its data storage and management capabilities, to associate and combine the Discovery type GET request and the corresponding response information; S4 network element attribute information extraction: Use data analysis and mining technology to obtain detailed attribute information of the requested target 5G core network element from the associated and combined Discovery type data packets; S5 Network element attribute information encapsulation and classification: The encapsulation module uses data encapsulation technology to match and integrate the extracted complex network element attribute information one by one, and divide and classify it in detail according to different dimensions with clear business logic and analysis requirements; S6. Data output and storage: The output module outputs the classified network element attribute information into format documents of various dimensions, which are combined with the data storage system for calling and querying at any time; S7, automatic update and maintenance: establish a real-time monitoring mechanism to dynamically track and analyze newly generated signaling data regularly or in real time. When new or changed signaling data is detected, the update operation of network element attribute information is automatically triggered. Data comparison and update algorithms are used to ensure that network element attribute information is always combined with the collected data status. S8, Data analysis and application: Apply the automatically learned network element information to the back-end data analysis process, and use data analysis tools and algorithms for the data caused by multi-IP switching of network elements.

2. The method for automatically learning 5G core network element information according to claim 1, characterized in that: In S1, the preliminary processing includes the unification of data formats, the preliminary screening and classification of data fields, and the pre-analysis module can also compress the data to reduce the amount of data transmission.

3. The method for automatically learning 5G core network element information according to claim 1, characterized in that: In S2, the acquisition feature algorithm and specific target features are converted into massive data packets, which include NRF's Discovery type signaling. The modules in the system can automatically update and optimize the screened target features. The modules include identification modules to adapt to network changes.

4. The method for automatically learning 5G core network element information according to claim 1, characterized in that: In S3, the http2 stream cache module can periodically clean up the cached data to release storage space.

5. The method for automatically learning 5G core network element information according to claim 1, characterized in that: In S4, the extracted network element attribute information is encrypted to ensure data security. The various attribute information includes the network element type nfType, network element instance ID, network element registration status status, and basic information of the heartbeat time interval. It also covers the area range TaiRangeList and TacRangeList to which the network element belongs, all corresponding IPv4 and IPv6 of the network element, the network element's slice information NSSAI, and the network element's DNN information.

6. The method for automatically learning 5G core network element information according to claim 1, characterized in that: In S5, priority can be given according to the importance of network elements, and the detailed classification includes classification based on network element IP dimension, regional information Tai or Tac, and slice NSSAI or DNN; In S6, the format document includes an EXCEL format document or a TXT format document.

7. The method for automatically learning 5G core network element information according to claim 1, characterized in that: In S7, the output document is monitored in real time and data integrity is checked. The data comparison and update algorithm can handle abnormal data and error conditions and automatically trigger network element update operations. The real-time monitoring mechanism can set the monitoring frequency and threshold.

8. The method for automatically learning 5G core network element information according to claim 1, characterized in that: In S8, the data analysis tools and algorithms can support distributed computing, generate detailed data analysis reports, and intuitively display the analysis results.

9. A system for automatically learning 5G core network element information, applied to the method for automatically learning 5G core network element information according to any one of claims 1 to 8, characterized in that: include: Packet receiving module, pre-analysis module, identification module, http2 stream cache module, encapsulation module and output module; The packet receiving module is used to receive signaling data messages from the existing network and provide a data basis for subsequent processing procedures; The pre-analysis module is used to perform preliminary processing on the original data message received by the packet receiving module, and removes noise and irrelevant information by using data analysis technology and algorithms, so as to provide a clear data structure for subsequent analysis and processing links; The identification module is used to identify and filter out specific types of signaling with key value, including NRF Discovery type signaling, from the pre-processed mass data by means of a feature recognition algorithm, and provide target data for subsequent processing steps; The http2 stream cache module is used to closely and accurately associate and combine the Discovery type GET request and the corresponding response information with its data storage and management capabilities, and cache and manage these associated data. At the same time, it can cope with various abnormal situations in data transmission and ensure the integrity and accuracy of the data; The encapsulation module is used to use data encapsulation technology to match and integrate the complex network element attribute information extracted from the associated and combined data packets one by one, and to classify and encapsulate the network element attribute information in detail, so as to provide a standardized and structured data format for subsequent data output and application; The output module is used to organize and output the classified and encapsulated network element attribute information by means of data output and conversion capabilities.

10. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the 5G core network element information automatic learning method as described in any one of claims 1 to 8.

11. A readable storage medium, characterized in that: A computer program is stored on the readable storage medium, and when the computer program is executed by the processor, the method for automatically learning 5G core network element information as described in any one of claims 1 to 8 is implemented.

Images