5G message platform monitoring method and system

Abstract

The embodiment of the invention provides a 5G message platform monitoring method and system applied to a 5G message platform, and the method comprises the steps: collecting the operation state data of an IaaS module, a PaaS module and an SaaS module according to a first preset collection period, and collecting a 5G message ticket stored in a target server according to a second preset collection period; analyzing and processing the running state data and / or the 5G message ticket by using a data processing cluster and / or a preset processing algorithm to form a processing result; and storing the processing result to a preset database, and / or constructing a visual interface based on the processing result and / or the running state data, so as to visually display the processing result and / or the running state data. Therefore, the end-to-end monitoring of the IaaS-PaaS-SaaS three-layer architecture of the 5G message platform can be realized, and the operation condition of the 5G message service can be monitored, so that the operation state of the 5G message platform can be known in time.

Description

Technical Field

[0001] The present application relates to the field of information and communication technology, and in particular to a 5G message platform monitoring method and system. Background Art

[0002] With the rapid development and commercialization of 5G technology, 5G messaging as a new communication method is ushering in unprecedented market opportunities. 5G messaging not only supports high-speed transmission, rich media content and interactive operations, but is also widely used in social entertainment, business office, public services, Internet of Things, marketing promotion and smart cities.

[0003] The 5G messaging platform is the core infrastructure that carries the 5G messaging business. Its design and operation and maintenance need to meet the requirements of efficiency, reliability, and security to support large-scale message processing and service delivery.

[0004] However, due to the lack of monitoring and analysis methods for the 5G message platform, in actual application, it is impossible to timely and effectively obtain the operating status of the 5G message platform, and it is impossible to perform operations such as fault identification on the 5G message service, resulting in a poor user experience. Summary of the invention

[0005] The embodiments of the present application provide a 5G message platform monitoring method and system to solve the technical problem of lack of monitoring and analysis means for the 5G message platform.

[0006] In a first aspect, an embodiment of the present application provides a 5G message platform monitoring method, which is applied to a 5G message platform. The 5G message platform at least includes: an infrastructure as a service IaaS module, a platform as a service PaaS module, and a software as a service SaaS module. The IaaS module, the PaaS module, and the SaaS module are connected according to a preset topological relationship. The IaaS module, the PaaS module, and the SaaS module are used to provide different types of cloud resources so that multiple servers can run based on cloud resources, thereby providing 5G message services to platform users;

[0007] The method includes: collecting the operating status data of the IaaS module, the PaaS module and the SaaS module according to a first preset collection cycle, and collecting the 5G message bills stored in the target server according to a second preset collection cycle; wherein the 5G message bill refers to the record generated when the 5G message platform sends a 5G message to a third-party user, and the target server is a server among multiple servers for storing 5G message bills; using a data processing cluster and / or a preset processing algorithm, analyzing and processing the operating status data and / or the 5G message bill to form a processing result; saving the processing result to a preset database, and / or constructing a visualization interface based on the processing result and / or the operating status data to visualize the processing result and / or the operating status data.

[0008] In an implementable manner, the operation status data includes resource data and performance data, both of which have data type identifiers, the resource data refers to resource attribute data of cloud resources provided by the IaaS module, the PaaS module, and the SaaS module, and the performance data refers to resource usage data of cloud resources provided by the IaaS module, the PaaS module, and the SaaS module; the preset topology relationship includes multiple nodes, and the nodes correspond to the IaaS module, the PaaS module, and the SaaS module; the preset database includes a first preset database;

[0009] The operation status data and / or 5G message call bill are analyzed and processed by using a data processing cluster and / or a preset processing algorithm, and the steps of forming a processing result include: sending resource data, performance data and 5G message call bills to a Kafka cluster, using the Kafka cluster to classify the resource data and performance data according to data type identifiers, and using the Kafka cluster to classify the 5G message call bills according to business types, where the business types include at least account opening business, registration business, message acceptance and issuance business, file upload business and / or file download business;

[0010] The step of saving the processing results to a preset database includes: saving the classified resource data, performance data and 5G message call records in a first preset database by category, and the first preset database is an ES cluster.

[0011] In one feasible manner, after the step of using the Kafka cluster to classify the resource data and the performance data according to the data type identifier, it also includes: using the Flink cluster to obtain the classified performance data from the Kafka cluster; obtaining the target threshold range corresponding to each category of performance data; judging whether the target performance data is within the target threshold range, the target performance data includes each performance data corresponding to different categories; if the target performance data is within the target threshold range, generating alarm data.

[0012] In one achievable manner, the visualization interface includes a first visualization interface; the step of constructing a visualization interface based on processing results and / or operating status data includes: associating resource data, performance data and alarm data with each node in a preset topological relationship according to the relationship between the resource data, performance data and alarm data and the IaaS module, PaaS module and SaaS module; constructing a first visualization interface, displaying the preset topological relationship in the first visualization interface, and displaying the resource data, performance data and / or alarm data associated with each node of the preset topological relationship.

[0013] In one achievable method, the preset database also includes a second preset database; after the step of using the Kafka cluster to classify the 5G message call bills according to the business type, it also includes: using the Flink cluster to obtain the classified 5G message call bills from the Kafka cluster; calculating the 5G message call bills according to the preset aggregation rules to obtain the aggregation results; the aggregation rules include determining the business indicator data corresponding to the 5G message call bills within at least one second preset collection period, and the business indicator data includes at least the number of 5G message call bills and the delivery success rate; the step of saving the processing results to the preset database includes: saving the aggregation results in the second preset database, and the second preset database is a Mysql cluster.

[0014] In one achievable method, the visualization interface includes a second visualization interface; the operation status data and / or 5G message call records are analyzed and processed using a data processing cluster and / or a preset processing algorithm, and the steps of forming processing results include: obtaining a target 5G message call record within a target historical time period; extracting target features of the target 5G message call record, the target features include data timing features, data lag features and / or data statistical features; determining a target algorithm based on the target features, the preset processing algorithms include multiple types, and the target algorithm is one or more of the preset processing algorithms; based on the target features, dynamically predicting the business indicator data of the target 5G message call record using a target model, and drawing a baseline for the business indicator data; wherein the target model is obtained based on training of the target algorithm, and the baseline is used to represent the changing trend of the business indicator data; the step of constructing a visualization interface based on the processing results and / or operation status data includes: constructing a second visualization interface, and displaying the baseline in the second visualization interface.

[0015] In one achievable manner, the preset processing algorithm includes a LightGBM algorithm, an XGBOOST algorithm and / or an ARIMA algorithm.

[0016] In one feasible method, the operation status data and / or 5G message call records are analyzed and processed using a data processing cluster and / or a preset processing algorithm. Before the step of forming a processing result, the step also includes: converting the operation status data and 5G message call records into a target format, and the target format is an XML format or a JSON format.

[0017] In one feasible method, in the step of collecting the operating status data of the IaaS module, the PaaS module and the SaaS module, the operating status data corresponding to the IaaS module is collected based on the simple network management protocol SNMP, the agent program Agent and / or the intelligent platform management interface IPMI, the operating status data corresponding to the PaaS module is collected based on the agent program Agent, and the 5G message call record is collected based on the secure file transfer protocol SFTP.

[0018] In the second aspect, the embodiment of the present application further provides a 5G message platform monitoring system, which is applied to the 5G message platform. The 5G message platform at least includes: an infrastructure as a service IaaS module, a platform as a service PaaS module and a software as a service SaaS module. The IaaS module, the PaaS module and the SaaS module are connected according to a preset topological relationship. The IaaS module, the PaaS module and the SaaS module are used to provide different types of cloud resources so that multiple servers can run based on cloud resources, thereby providing 5G message services to platform users;

[0019] The system includes: a collection module, which is used to collect the operating status data of the IaaS module, the PaaS module and the SaaS module according to a first preset collection cycle, and to collect the 5G message bills stored in the target server according to a second preset collection cycle; wherein, the 5G message bill refers to the record generated when the 5G message platform sends a 5G message to a third-party user, and the target server is a server among multiple servers for storing 5G message bills; a first processing module, which is used to use a data processing cluster and / or a preset processing algorithm to analyze and process the operating status data and / or the 5G message bill to form a processing result; a second processing module, which is used to save the processing result to a preset database, and / or to build a visualization interface based on the processing result and / or the operating status data to visualize the processing result and / or the operating status data.

[0020] From the above content, it can be seen that the embodiment of the present application provides a 5G message platform monitoring method and system, which are applied to the 5G message platform. The 5G message platform at least includes: an infrastructure as a service IaaS module, a platform as a service PaaS module and a software as a service SaaS module. The IaaS module, the PaaS module and the SaaS module are connected according to a preset topological relationship. The IaaS module, the PaaS module and the SaaS module are used to provide different types of cloud resources so that multiple servers can run based on cloud resources, thereby providing 5G message services to platform users; the method includes: according to a first preset collection period, collecting IaaS module, PaaS module and the operating status data of the SaaS module, and, according to the second preset collection cycle, collect the 5G message bills stored in the target server; wherein, the 5G message bill refers to the record generated when the 5G message platform sends a 5G message to a third-party user, and the target server is a server among multiple servers used to store 5G message bills; use the data processing cluster and / or the preset processing algorithm to analyze and process the operating status data and / or the 5G message bill to form a processing result; save the processing result to a preset database, and / or, build a visualization interface based on the processing result and / or the operating status data to visualize the processing result and / or the operating status data. In this way, end-to-end monitoring of the three-layer architecture of the 5G message platform IaaS-PaaS-SaaS can be achieved, and the operation of the 5G message service can be monitored, so that the user can be informed of the operating status of the 5G message platform in a timely manner, even if fault identification is performed, to improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A schematic diagram of the architecture of a 5G message platform monitoring method provided in an embodiment of the present application;

[0022] Figure 2 A flowchart of a 5G message platform monitoring method provided in an embodiment of the present application;

[0023] Figure 3 A schematic diagram of a process for generating alarm data provided in an embodiment of the present application;

[0024] Figure 4 A schematic diagram of a first visual interface provided in an embodiment of the present application;

[0025] Figure 5 A schematic diagram of a process for drawing a baseline based on a 5G message call record provided in an embodiment of the present application;

[0026] Figure 6 A schematic diagram of a second visual interface provided in an embodiment of the present application;

[0027] Figure 7A schematic diagram of the structure of the 5G message platform monitoring system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application.

[0029] Before introducing the technical solutions of the embodiments of the present application, the terms involved in the embodiments of the present application are first introduced by way of example.

[0030] 1. Infrastructure as a Service (IaaS): It provides virtualized computing resources, storage, network and other infrastructure, on which users can run any operating system and application. IaaS can specifically include the following facilities: virtual servers, storage systems and network devices (such as virtual switches and load balancers).

[0031] 2. Platform as a Service or Platform as a Service (PaaS): Provides a platform for developing, testing and deploying applications. Specifically, platform layer services can be provided on top of IaaS, including the environment and tools required to develop and deploy applications. Users can use these platforms to develop, test and run applications without having to manage the underlying infrastructure. PaaS can specifically include the following facilities: application servers, databases, development frameworks, message queues and analysis tools.

[0032] 3. Software as a Service (SaaS): provides software applications that are accessed through the Internet. These applications run on the PaaS platform and are managed by the service provider. In other words, SaaS can provide users with application software that has been deployed in the cloud through the Internet. Users do not need to purchase, install, and maintain these software. They can use them by simply accessing them through the Internet and pay fees based on actual usage without having to worry about the underlying infrastructure and platform. SaaS can specifically provide user interfaces, application servers, and databases, etc.

[0033] In summary, IaaS provides computing and storage resources and is the underlying infrastructure. PaaS is built on IaaS and provides the platform environment required for developing and deploying applications. SaaS is built on PaaS and provides complete application services to end users.

[0034] Figure 1 A schematic diagram of the architecture of the 5G message platform monitoring method provided in an embodiment of the present application.

[0035] The embodiment of the present application provides a 5G message platform monitoring method, which is applied to the 5G message platform. Among them, the 5G message platform is a system for managing and processing messages and data transmitted through the 5G network. The 5G message platform supports efficient message delivery, data analysis and business operations, and can provide 5G messaging (5G Messaging) services, short message services (SMS), multimedia messaging services (MMS) and other real-time communication services. 5G messages support the sending of text, pictures, videos, audio and other rich media content. Based on the high-speed transmission capability of the 5G network, 5G messages can achieve faster data transmission speeds and lower latency, and 5G messages support rich text formats, rich interactive application links, real-time feedback and other interactive methods, which can provide a richer and more vivid user experience.

[0036] In an embodiment of the present application, the 5G message platform includes at least: an infrastructure as a service IaaS module, a platform as a service PaaS module and a software as a service SaaS module. The IaaS module, the PaaS module and the SaaS module are connected according to a preset topology relationship. The IaaS module, the PaaS module and the SaaS module are used to provide different types of cloud resources so that multiple servers can run based on cloud resources, and then provide 5G message services to platform users.

[0037] The preset topological relationship is determined during the 5G message platform construction phase, and the preset topological relationship is composed of multiple nodes, which can correspond to IaaS modules, PaaS modules and SaaS modules. In this way, a three-layer infrastructure of IaaS-PaaS-SaaS can be formed, and the preset topological relationship can be determined based on actual needs. The embodiments of this application do not specifically limit this. It is worth noting that the modules specifically involved in each level in IaaS-PaaS-SaaS (such as database services, Web servers, application services, etc.) can be a node in the topological relationship.

[0038] In the embodiment of the present application, the IaaS module can provide cloud resources such as network devices and servers, the PaaS module can provide cloud resources such as databases, and SaaS can provide cloud application software services. It is worth noting that the aforementioned multiple servers can be hosted by the IaaS module, the PaaS module and / or the SaaS module respectively, and are not limited to the servers on a single module.

[0039] Figure 2 A flow chart of a 5G message platform monitoring method provided in an embodiment of the present application.

[0040] like Figure 2 As shown, the 5G message platform monitoring method provided in the embodiment of the present application may include the following steps S100-S300.

[0041] S100: According to a first preset collection cycle, the operating status data of the IaaS module, the PaaS module and the SaaS module are collected, and, according to a second preset collection cycle, the 5G message call detail record (CDR) stored in the target server is collected.

[0042] In an embodiment of the present application, the operating system, network equipment and server of the IaaS module can be monitored to obtain operating status data; the database, middleware and big data components of the PaaS module can be monitored to obtain operating status data; the processes, ports, logs and call record data of the SaaS module can be monitored to obtain operating status data.

[0043] Specifically, the operation status data may include resource data and performance data. Resource data refers to the resource attribute data of cloud resources provided by the IaaS module, PaaS module, and SaaS module. Resource data includes, for example, server name, database name, virtual machine name, number of CPUs and memory size of each virtual machine. Performance data refers to the resource usage data of cloud resources provided by the IaaS module, PaaS module, and SaaS module. Performance data includes, for example, CPU utilization, whether the database is available, whether the process exists, and whether the process status is normal.

[0044] Furthermore, both resource data and performance data may have data type identifiers to distinguish different types of data.

[0045] 5G message bills refer to the records generated when the 5G message platform sends 5G messages to third-party users, which are used to record and manage different types of communication activities and services. The target server is a server among multiple servers used to store 5G message bills. It can be understood that 5G message bills can have different types, and the specific types are related to the fields involved and the types of services implemented. The business types include at least account opening services, registration services, message acceptance and delivery services, file upload services and / or file download services. Exemplarily, according to different business types, 5G message bills may include mobile originating bills (MO), which specifically refer to calls or messages sent from mobile devices, mobile terminated bills (MT), which specifically refer to calls or messages delivered to mobile devices, provisioning bills (PRO), which specifically involve the account or service opening process, registration bills (REG), which specifically involve the registration information of devices or users, and file service bills (FT), which specifically include messages or data for processing file transfer services. 5G message call records can be composed of the following contents: the sending and receiving time of the message, the information of the sender and receiver, the message content and the status of message delivery, etc.

[0046] In an embodiment of the present application, the first preset collection period and the second preset collection period may be the same or different. The first preset collection period may be, for example, once per minute, once per hour, or once per day. The second preset collection period may also be once per minute, once per hour, or once per day. It may be determined based on actual needs, and the embodiment of the present application does not make any specific limitation on this.

[0047] S200: Analyze and process the operation status data and / or 5G message call records using a data processing cluster and / or a preset processing algorithm to generate processing results.

[0048] The embodiments of the present application can process operating status data and / or 5G message call records based on a mixture of multiple processing clusters, or can perform analysis and prediction based on a preset processing algorithm. The specific analysis and processing steps will be described in detail below and will not be repeated here.

[0049] S300: Saving the processing result to a preset database, and / or constructing a visualization interface based on the processing result and / or the operating status data to visualize the processing result and / or the operating status data.

[0050] The processing results are saved to a preset database to facilitate data retention and traceability. A visualization interface is constructed based on the processing results and / or operating status data, and the visualization interface can be displayed on the 5G message platform and / or the 5G message platform monitoring system. In this way, users of the 5G message platform can interact based on the visualization interface, so that users can be informed of the platform's operating status in a timely manner.

[0051] From the above content, it can be seen that the embodiment of the present application provides a 5G message platform monitoring method, including: collecting the running status data of the IaaS module, the PaaS module and the SaaS module according to the first preset collection cycle, and collecting the 5G message call bill stored in the target server according to the second preset collection cycle; wherein, the 5G message call bill refers to the record generated when the 5G message platform sends a 5G message to a third-party user, and the target server is a server used to store the 5G message call bill among multiple servers; using a data processing cluster and / or a preset processing algorithm, the running status data and / or the 5G message call bill are analyzed and processed to form a processing result; the processing result is saved to a preset database, and / or, a visualization interface is constructed based on the processing result and / or the running status data to visualize the processing result and / or the running status data. In this way, end-to-end monitoring of the three-layer architecture of the 5G message platform IaaS-PaaS-SaaS can be achieved, and the operation of the 5G message service can be monitored, so that the user can timely know the running status of the 5G message platform, even if fault identification is performed, and improve the user experience.

[0052] Figure 3 A schematic diagram of the process of generating alarm data provided in an embodiment of the present application.

[0053] Further, such as Figure 3 As shown, step S200 may include the following steps S201: sending resource data, performance data and 5G message call records to the Kafka cluster, using the Kafka cluster to classify the resource data and performance data according to the data type identifier, and using the Kafka cluster to classify the 5G message call records according to the business type. Among them, the Kafka cluster is a system composed of multiple Kafka servers, which can be used to process large-scale real-time data streams.

[0054] The step of saving the processing results to the preset database in step S300 may include S301: saving the classified resource data, performance data and 5G message call records in the first preset database by category, and the first preset database is the ES cluster. Among them, the ES cluster is an open source search and analysis engine that can be used to process large-scale structured and unstructured data. Based on this, after classified storage, it can be used to query detailed list data for easy traceability.

[0055] Continue to see Figure 3, after step S201, the following step S202 may be further included:

[0056] S202: Use the Flink cluster to obtain classified performance data from the Kafka cluster.

[0057] Among them, the Flink cluster is a distributed system composed of multiple Flink nodes, which can be used to process real-time data streams and batch processing tasks. In other words, the Flink cluster can consume the classified performance data in the Kafka cluster.

[0058] S203: Obtain a target threshold range corresponding to each category of performance data.

[0059] Exemplarily, the target threshold range corresponding to the CPU utilization may be [90%, 100%], or [95%, 100%], which may be determined based on actual conditions or may be adjusted dynamically, and the embodiments of the present application do not specifically limit this. It is understandable that this is only an exemplary introduction, and in actual applications, each category of performance data may have a corresponding target threshold range, and the target threshold range may be adjusted dynamically.

[0060] S204: Determine whether the target performance data is within a target threshold range, where the target performance data includes each piece of performance data corresponding to different categories.

[0061] It is understandable that if the performance data is within the target threshold range, it may indicate that there are certain abnormalities in the operation of the 5G messaging platform, such as performance degradation, slow response, etc.

[0062] S205: If the target performance data is within the target threshold range, generate alarm data.

[0063] For example, when the target performance data is CPU utilization and the target threshold range is [95%, 100%], if the collected CPU utilization is 90%, which is not within the target threshold range, then there is no need to generate alarm data. If the collected CPU utilization is 96%, which is within the target threshold range, alarm data should be generated to notify the user that the CPU utilization is too high. In this way, the user can adjust the CPU cloud resources based on the alarm data, such as applying for more CPU cloud resources.

[0064] In some implementations, the alarm data may include information such as the actual value of the target performance data within the target threshold range, the target threshold range, and a timestamp.

[0065] In this way, the operation anomalies of the 5G messaging platform can be discovered in time and an alarm can be generated. Furthermore, the alarm data can be fed back to the user, who can optimize the operation of the 5G messaging platform and improve its performance.

[0066] Furthermore, step S300 may also include the following steps S302-S303.

[0067] S302: According to the relationship between the resource data, performance data and alarm data and the IaaS module, the PaaS module and the SaaS module, the resource data, performance data and alarm data are associated with each node in the preset topological relationship.

[0068] This step can be called a topology mapping step, and specifically, resource data, performance data, and alarm data can be mapped to corresponding nodes according to a preset topology relationship.

[0069] S303: Construct a first visualization interface, and display the preset topological relationship, as well as resource data, performance data and / or alarm data associated with each node of the preset topological relationship in the first visualization interface.

[0070] Exemplarily, the alarm information can be displayed next to the node or provide detailed instructions in the form of a pop-up window. In actual applications, the first visualization interface can be a user interaction interface. When in use, you can click on the node in the topology map to view detailed resource data, performance data and / or alarm data. In addition, the embodiment of the present application can achieve real-time updates to ensure that the user sees the latest data. In this way, the user of the 5G messaging platform can interact with the first visualization interface to view various data related to each node and monitor the operating status of the cloud environment at any time.

[0071] It is worth noting that the first visualization interface is not a single user interface. In actual applications, a multi-level first visualization interface can be constructed based on a preset topological relationship, and each level can be switched between each other.

[0072] Figure 4 A schematic diagram of a first visualization interface provided in an embodiment of the present application.

[0073] Figure 4 A first visualization interface corresponding to an IaaS module is shown, and the preset topology relationship shown in the first visualization interface includes virtual machines 001 and 002, and servers A and B attached to the virtual machines. Further, by clicking in the first visualization interface, the performance data, resource data and / or alarm data of each virtual machine or server can be viewed.

[0074] Furthermore, the following steps S206-S207 may be included after step S201.

[0075] S206: Use the Flink cluster to obtain the classified 5G message call records from the Kafka cluster.

[0076] It is understandable that in the Kadka cluster, 5G message call records and operation status data can be stored in different partitions, so that the Flink cluster can extract the 5G message call records and operation status data separately.

[0077] S207: Calculate the 5G message call records according to the preset aggregation rules to obtain the aggregation results; the aggregation rules include determining the business indicator data corresponding to the 5G message call records within at least one second preset collection period, and the business indicator data includes at least the number of 5G message call records and the delivery success rate.

[0078] The preset aggregation rule may be a rule formulated in advance based on actual needs. For example, the preset aggregation rule may be to count the number of 5G message call records within an hour or the number of 5G message call records in a day.

[0079] It should also be noted that the business indicator data here is only an exemplary introduction. The aggregation rules and business indicator data can be formulated based on actual needs. For example, when the 5G message bill is a bill corresponding to the registration service, the business indicator data can specifically include the registration peak value, the total number of registration messages and the registration success rate.

[0080] Step S300 may further include the following step S304: saving the aggregation result in a second preset database, where the second preset database is a Mysql cluster.

[0081] It can be understood that, in combination with step S202, the data in the Kafka cluster has two exports, one of which is to consume the data in Fafka and store it in the ES cluster for querying detailed order data, and the other is to consume the data in Kafa and aggregate it through aggregation rules, and finally save it to the MySQL cluster.

[0082] In some implementations, the convergence results can also be associated with a preset topological relationship. In this way, the business indicator data related to the 5G message service can be viewed through the first visualization interface. Furthermore, through the connection relationship between each 5G message business module and other modules in the preset topological relationship, the module described in the fault and the scope of impact can be located in time, so that the user can be informed of the latest developments of the 5G message service in a timely manner. Business modules are, for example, 5G message-related message modules, short transfer modules, bad information monitoring modules, and SIP access modules.

[0083] In an embodiment of the present application, a baseline prediction can be performed based on the 5G message call record, which may specifically include steps such as sampling, data cleaning, data feature extraction and analysis, dynamic baseline AI prediction, and data storage.

[0084] Figure 5 A schematic diagram of the process of drawing a baseline based on a 5G message call record provided in an embodiment of the present application.

[0085] like Figure 5 As shown, step S200 may also include the following steps S208-S211.

[0086] S208: Obtain the target 5G message call record within the target historical time period.

[0087] Among them, the target historical time period is, for example, a specified time period, such as 00:00:00 on August 27, 2024 to 23:59:59 on August 27, 2024, or it can be a certain month in history, etc. The embodiment of the present application does not make specific limitations on this.

[0088] It can be understood that step S208 is a step of extracting samples, and step S208 may also include a data cleaning step.

[0089] S209: Extract target features of the target 5G message call record, where the target features include data timing features, data lag features and / or data statistical features.

[0090] Among them, data timing features can characterize the time pattern, periodic changes, and peak periods of message transmission. Data lag features can characterize the delay from sending to receiving, as well as the changing trend of the delay. Data statistical features can characterize the number of messages in each time period, etc.

[0091] S210: Determine a target algorithm based on the target feature. The preset processing algorithms include multiple ones, and the target algorithm is one or more of the preset processing algorithms.

[0092] Exemplarily, the preset processing algorithm may include the LightGBM algorithm, the XGBOOST algorithm and / or the ARIMA algorithm. Among them, the LightGBM algorithm is an efficient algorithm based on the gradient boosting tree, which is suitable for processing large amounts of data and high-dimensional features. The XGBOOST algorithm is another gradient boosting tree algorithm with high efficiency and accuracy. The ARIMA algorithm is an algorithm for predicting time series data, which can handle trends and seasonality in the data. The algorithm can be selected based on the actual situation of the target feature, and the embodiments of the present application do not specifically limit this.

[0093] S211: Based on the target features, the target model is used to dynamically predict the business indicator data of the target 5G message call record, and a baseline is drawn for the business indicator data; wherein the target model is obtained based on target algorithm training, and the baseline is used to represent the changing trend of the business indicator data.

[0094] This step can also be called the dynamic baseline AI prediction step. By predicting business indicator data and drawing baselines, potential anomalies and trend changes can be identified and corresponding business decisions can be made.

[0095] In some implementations, after step S211, the predicted business indicator data may also be stored to achieve retention and traceability.

[0096] Furthermore, step S300 may also include the following step S305: constructing a second visualization interface, and displaying the baseline in the second visualization interface.

[0097] Figure 6 A schematic diagram of a second visualization interface provided in an embodiment of the present application.

[0098] like Figure 6 As shown, in the second visualization interface, a baseline is drawn based on the business indicator data corresponding to the registration business, and the baseline specifically relates to the change trend of the number of transactions (quantity) of registration information. It can be understood that the baseline not only corresponds to the existing business indicator data, but also corresponds to the business indicator data obtained based on AI prediction.

[0099] It should be noted that the embodiment of the present application may provide a unified acquisition adaptation platform or a unified acquisition adaptation module, or the module may also be referred to as an acquisition module, which may be used to perform step S100. Moreover, after step S100, the module may also be used to perform the following step S400: converting the operation status data and the 5G message call list into a target format, the target format being an XML format or a JSON format. In this way, unified management of data may be achieved.

[0100] It should be noted that in step S100, the operating status data corresponding to the IaaS module is collected based on the simple network management protocol SNMP, the agent program Agent and / or the intelligent platform management interface IPMI, the operating status data corresponding to the PaaS module is collected based on the agent program Agent, and the 5G message call list is collected based on the secure file transfer protocol SFTP. The operating status data corresponding to the SaaS module can be collected by calling the API provided by the SaaS module. In addition, the operating status data can also be obtained based on the targeted data retrieval and analysis protocol (Targeted Retrieval and Analysis Protocol, TRAP), which is not specifically limited in the embodiments of the present application.

[0101] From the above content, it can be seen that the 5G message platform monitoring method provided in the embodiment of the present application can realize the monitoring of the three layers of IaaS-PaaS-SaaS of the 5G message platform, and can realize the processing of 5G message call records through big data processing technology. Big data processing technology, for example, is to mix and process operation status data and / or 5G message call records through multiple processing clusters. In addition, the 5G message platform monitoring method provided in the embodiment of the present application can also realize AI trend analysis of 5G message service indicator data. In this way, the operating status of the 5G message platform can be timely known, the business development trend can be grasped, and the user experience can be improved.

[0102] Figure 7 A schematic diagram of the structure of the 5G message platform monitoring system provided in an embodiment of the present application.

[0103] like Figure 7 As shown, the embodiment of the present application also provides a 5G message platform monitoring system, which is applied to the 5G message platform. The 5G message platform at least includes: an infrastructure as a service IaaS module, a platform as a service PaaS module and a software as a service SaaS module. The IaaS module, the PaaS module and the SaaS module are connected according to a preset topological relationship. The IaaS module, the PaaS module and the SaaS module are used to provide different types of cloud resources so that multiple servers can run based on cloud resources, thereby providing 5G message services to platform users;

[0104] The system includes:

[0105] The collection module 1001 is used to collect the operation status data of the IaaS module, the PaaS module and the SaaS module according to the first preset collection period, and to collect the 5G message bill stored in the target server according to the second preset collection period; wherein the 5G message bill refers to the record generated when the 5G message platform sends a 5G message to a third-party user, and the target server is a server for storing 5G message bills among multiple servers;

[0106] The first processing module 1002 is used to analyze and process the operation status data and / or the 5G message call record using a data processing cluster and / or a preset processing algorithm to form a processing result;

[0107] The second processing module 1003 is used to save the processing results to a preset database, and / or to build a visualization interface based on the processing results and / or the operating status data to visualize the processing results and / or the operating status data.

[0108] In some implementations, the operation status data includes resource data and performance data, both of which have data type identifiers, the resource data refers to resource attribute data of cloud resources provided by the IaaS module, the PaaS module, and the SaaS module, and the performance data refers to resource usage data of cloud resources provided by the IaaS module, the PaaS module, and the SaaS module; the preset topology relationship includes multiple nodes, and the nodes correspond to the IaaS module, the PaaS module, and the SaaS module; the preset database includes a first preset database;

[0109] The first processing module 1002 is specifically used to: send resource data, performance data and 5G message call records to the Kafka cluster, use the Kafka cluster to classify the resource data and performance data according to the data type identifier, and use the Kafka cluster to classify the 5G message call records according to the service type, where the service type at least includes account opening service, registration service, message acceptance and issuance service, file upload service and / or file download service;

[0110] The second processing module 1003 is specifically used to save the classified resource data, performance data and 5G message call records in a first preset database by category, and the first preset database is an ES cluster.

[0111] In some implementations, the first processing module 1002 is specifically used to: use the Flink cluster to obtain classified performance data from the Kafka cluster; obtain the target threshold range corresponding to each category of performance data; determine whether the target performance data is within the target threshold range, the target performance data includes each performance data corresponding to different categories; if the target performance data is within the target threshold range, generate alarm data.

[0112] In some implementations, the visualization interface includes a first visualization interface; the second processing module 1003 is specifically used to: associate resource data, performance data and alarm data with each node in a preset topological relationship according to the relationship between the resource data, performance data and alarm data and the IaaS module, PaaS module and SaaS module; construct a first visualization interface, display the preset topological relationship in the first visualization interface, and display the resource data, performance data and / or alarm data associated with each node of the preset topological relationship.

[0113] In some implementations, the preset database also includes a second preset database; the first processing module 1002 is specifically used to: use the Flink cluster to obtain the classified 5G message call records from the Kafka cluster; calculate the 5G message call records according to the preset aggregation rules to obtain the aggregation results; the aggregation rules include determining the business indicator data corresponding to the 5G message call records within at least one second preset collection period, and the business indicator data includes at least the number of 5G message call records and the delivery success rate; the second processing module 1003 is specifically used to: save the aggregation results in the second preset database, and the second preset database is a Mysql cluster.

[0114] In some implementations, the visualization interface includes a second visualization interface; the first processing module 1002 is specifically used to obtain a target 5G message call record within a target historical time period; extract target features of the target 5G message call record, the target features include data timing features, data lag features and / or data statistical features; determine a target algorithm based on the target features, the preset processing algorithms include multiple, and the target algorithm is one or more of the preset processing algorithms; based on the target features, use the target model to dynamically predict the business indicator data of the target 5G message call record, and draw a baseline for the business indicator data; wherein the target model is obtained based on the target algorithm training, and the baseline is used to represent the changing trend of the business indicator data; the second processing module 1003 is specifically used to: construct a second visualization interface, and display the baseline in the second visualization interface.

[0115] In some implementations, the preset processing algorithms include a LightGBM algorithm, an XGBOOST algorithm, and / or an ARIMA algorithm.

[0116] In some implementations, the collection module 1001 is also used to convert the operating status data and 5G message call records into a target format, which is an XML format or a JSON format.

[0117] In some implementations, in the step of collecting the operating status data of the IaaS module, PaaS module and SaaS module, the operating status data corresponding to the IaaS module is collected based on the simple network management protocol SNMP, the agent program Agent and / or the intelligent platform management interface IPMI, the operating status data corresponding to the PaaS module is collected based on the agent program Agent, and the 5G message call record is collected based on the secure file transfer protocol SFTP.

[0118] In a specific implementation, the present invention further provides a computer storage medium, wherein the computer storage medium may store a program, and when the program is executed, the program may include some or all of the steps in each embodiment of the 5G message platform monitoring method provided by the present invention. The storage medium may be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0119] It is easy to understand that those skilled in the art can combine, split, reorganize, etc. the embodiments of the present application to obtain other embodiments based on the several embodiments provided in the present application, and these embodiments do not exceed the protection scope of the present application.

[0120] The above specific implementation methods further explain in detail the purpose, technical solutions and beneficial effects of the embodiments of the present application. It should be understood that the above are only specific implementation methods of the embodiments of the present application and are not used to limit the protection scope of the embodiments of the present application. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solutions of the embodiments of the present application should be included in the protection scope of the embodiments of the present application.

Claims

1. A 5G message platform monitoring method, characterized in that: Applied to a 5G message platform, the 5G message platform at least includes: an infrastructure as a service IaaS module, a platform as a service PaaS module and a software as a service SaaS module, the IaaS module, the PaaS module and the SaaS module are connected according to a preset topological relationship, and the IaaS module, the PaaS module and the SaaS module are used to provide different types of cloud resources so that multiple servers can run based on the cloud resources, thereby providing 5G message services to platform users; The method comprises: According to a first preset collection cycle, the operating status data of the IaaS module, the PaaS module and the SaaS module are collected, and, according to a second preset collection cycle, the 5G message bill stored in the target server is collected; wherein the 5G message bill refers to a record generated when the 5G message platform sends a 5G message to a third-party user, and the target server is a server among the multiple servers for storing the 5G message bill; Analyze and process the operating status data and / or the 5G message call record using a data processing cluster and / or a preset processing algorithm to form a processing result; The processing result is saved in a preset database, and / or a visualization interface is constructed based on the processing result and / or the operating status data to visualize the processing result and / or the operating status data.

2. The 5G message platform monitoring method according to claim 1, characterized in that: The operation status data includes resource data and performance data, both of which have data type identifiers, the resource data refers to resource attribute data of the cloud resources provided by the IaaS module, the PaaS module and the SaaS module, and the performance data refers to resource usage data of the cloud resources provided by the IaaS module, the PaaS module and the SaaS module; the preset topology relationship includes multiple nodes, and the nodes correspond to the IaaS module, the PaaS module and the SaaS module; the preset database includes a first preset database; The step of analyzing and processing the operating status data and / or the 5G message call record by using a data processing cluster and / or a preset processing algorithm to form a processing result includes: Sending the resource data, the performance data and the 5G message bill to a Kafka cluster, using the Kafka cluster to classify the resource data and the performance data according to the data type identifier, and using the Kafka cluster to classify the 5G message bill according to the service type, wherein the service type includes at least an account opening service, a registration service, a message acceptance and issuance service, a file upload service and / or a file download service; The step of saving the processing result to a preset database comprises: The classified resource data, performance data and 5G message call records are saved in the first preset database by category, and the first preset database is the ES cluster.

3. The 5G message platform monitoring method according to claim 2 is characterized in that: After the step of using the Kafka cluster to classify the resource data and the performance data according to the data type identifier, the method further includes: Using a Flink cluster to obtain the classified performance data from the Kafka cluster; Obtain a target threshold range corresponding to the performance data of each category; Determine whether the target performance data is within the target threshold range, the target performance data including each piece of the performance data corresponding to different categories; If the target performance data is within the target threshold range, alarm data is generated.

4. The 5G message platform monitoring method according to claim 3 is characterized in that: The visualization interface includes a first visualization interface; and the step of constructing a visualization interface based on the processing result and / or the operation status data includes: According to the relationship between the resource data, the performance data and the alarm data and the IaaS module, the PaaS module and the SaaS module, the resource data, the performance data and the alarm data are associated with each node in the preset topological relationship; The first visualization interface is constructed to display the preset topological relationship, and the resource data, the performance data and / or the alarm data associated with each node of the preset topological relationship in the first visualization interface.

5. The 5G message platform monitoring method according to claim 2 is characterized in that: The preset database also includes a second preset database; and after the step of using the Kafka cluster to classify the 5G message call list according to the service type, the step further includes: Using the Flink cluster to obtain the classified 5G message call records from the Kafka cluster; The 5G message call list is calculated according to a preset aggregation rule to obtain an aggregation result; the aggregation rule includes determining at least one business indicator data corresponding to the 5G message call list within the second preset collection period, and the business indicator data includes at least the number of the 5G message call lists and the delivery success rate; The step of saving the processing result to a preset database comprises: The aggregation result is saved in the second preset database, which is a MySQL cluster.

6. The 5G message platform monitoring method according to claim 5, characterized in that: The visualization interface includes a second visualization interface; using a data processing cluster and / or a preset processing algorithm, analyzing and processing the operating status data and / or the 5G message call record to form a processing result includes: Obtain the target 5G message call records within the target historical time period; Extracting target features of the target 5G message call record, where the target features include data timing features, data hysteresis features and / or data statistical features; Determine a target algorithm based on the target feature, the preset processing algorithms include multiple ones, and the target algorithm is one or more of the preset processing algorithms; Based on the target features, dynamically predict the business indicator data of the target 5G message call record using a target model, and draw a baseline for the business indicator data; wherein the target model is obtained based on the target algorithm training, and the baseline is used to represent the change trend of the business indicator data; The step of constructing a visualization interface based on the processing result and / or the running status data includes: The second visualization interface is constructed, and the baseline is displayed in the second visualization interface.

7. The 5G message platform monitoring method according to claim 1, characterized in that: The preset processing algorithms include LightGBM algorithm, XGBOOST algorithm and / or ARIMA algorithm.

8. The 5G message platform monitoring method according to claim 1, characterized in that: Before the step of analyzing and processing the operating status data and / or the 5G message call record by using a data processing cluster and / or a preset processing algorithm to form a processing result, the step further includes: The operating status data and the 5G message call record are converted into a target format, and the target format is an XML format or a JSON format.

9. The 5G message platform monitoring method according to claim 1, characterized in that: In the step of collecting the operating status data of the IaaS module, the PaaS module and the SaaS module, the operating status data corresponding to the IaaS module is collected based on the simple network management protocol SNMP, the agent program Agent and / or the intelligent platform management interface IPMI, the operating status data corresponding to the PaaS module is collected based on the agent program Agent, and the 5G message call record is collected based on the secure file transfer protocol SFTP.

10. A 5G message platform monitoring system, characterized in that: Applied to a 5G message platform, the 5G message platform at least includes: an infrastructure as a service IaaS module, a platform as a service PaaS module and a software as a service SaaS module, the IaaS module, the PaaS module and the SaaS module are connected according to a preset topological relationship, and the IaaS module, the PaaS module and the SaaS module are used to provide different types of cloud resources so that multiple servers can run based on the cloud resources, thereby providing 5G message services to platform users; The system comprises: A collection module, used to collect the running status data of the IaaS module, the PaaS module and the SaaS module according to a first preset collection period, and to collect the 5G message bill stored in the target server according to a second preset collection period; wherein the 5G message bill refers to the record generated when the 5G message platform sends a 5G message to a third-party user, and the target server is a server among the multiple servers for storing the 5G message bill; A first processing module is used to analyze and process the operating status data and / or the 5G message call record using a data processing cluster and / or a preset processing algorithm to form a processing result; The second processing module is used to save the processing result to a preset database, and / or to build a visualization interface based on the processing result and / or the operating status data to visualize the processing result and / or the operating status data.

Images