Method, apparatus and computer-readable storage medium for reporting signaling trace data
By classifying and merging signaling tracing data through signaling identification and prediction models, closed-loop signaling is generated, which solves the problem of numerous and scattered signaling tracing data and improves the efficiency of fault location and equipment operation and maintenance.
Patent Information
- Application Number
- CN202310781220.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-06-28
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2043-06-28
AI Technical Summary
In existing technologies, signaling tracing data is reported in large quantities and in a scattered manner, resulting in low efficiency in fault location analysis, excessive resource consumption, and automatic cessation of signaling tracing tasks by the system.
Signaling identification and prediction models are used to classify and predict signaling tracking data, generate correlations, and merge similar and related signaling data to generate closed-loop signaling for reporting.
This reduces the amount of signaling tracing data reported, lowers data dispersion, improves fault analysis efficiency, and enhances equipment operation and maintenance efficiency and fault location accuracy.
Smart Images

Figure CN119232563B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of communication technology, and in particular to a method, apparatus and computer-readable storage medium for reporting signaling tracing data. Background Technology
[0002] Currently, the main purpose of core network signaling tracing is to discover faults in network elements based on signaling data, thereby quickly locating the cause of the fault and resolving the problem. The process is as follows: after a signaling tracing task is created from the signaling tracing client, the signaling tracing server receives the task and sends the task conditions to the network element; the network element matches all signaling according to the task conditions and reports the successfully matched signaling to the signaling tracing server; the signaling server then sends the task to the corresponding signaling tracing client based on the task number. The typical usage is to initiate signaling tracing on the faulty network element and analyze the reported signaling data to determine the cause of the fault by observing and analyzing each data point for anomalies. However, in the process of using signaling tracing to locate faults, the reported signaling tracing data is not only numerous but also scattered, especially for some irregular faults that require long-term tracing, thus resulting in a large amount of reported signaling tracing data. Summary of the Invention
[0003] The main objective of this invention is to provide a method, apparatus, and storage medium for reporting signaling tracing data, aiming to solve the technical problem of existing reporting of large amounts of scattered signaling tracing data.
[0004] To achieve the above objectives, the present invention provides a method for reporting signaling trace data. The method includes: acquiring at least one signaling trace data; classifying and predicting the signaling trace data based on a signaling identification model and a signaling prediction model to generate a first classification result and a correlation relationship between the signaling trace data; merging signaling trace data belonging to the same category and having a correlation relationship based on the first classification result and the correlation relationship to generate closed-loop signaling corresponding to each type of signaling trace data, and reporting the closed-loop signaling.
[0005] Furthermore, to achieve the above objectives, the present invention also provides a signaling trace data reporting device, the reporting device comprising: a signaling data acquisition module, used to acquire at least one signaling trace data; a signaling model analysis module, used to classify and predict the signaling trace data based on a signaling identification model and a signaling prediction model, generating a first classification result and the correlation between the signaling trace data; and a signaling merging and reporting module, used to merge signaling trace data belonging to the same category and having a correlation based on the first classification result and the correlation, generating closed-loop signaling corresponding to each type of signaling trace data, and reporting the closed-loop signaling.
[0006] In addition, to achieve the above objectives, the present invention also provides an electronic device, the electronic device including a processor, a memory, and a signaling trace data reporting program stored in the memory and executable by the processor, wherein when the signaling trace data reporting program is executed by the processor, the steps of the signaling trace data reporting method as described above are implemented.
[0007] In addition, to achieve the above objectives, the present invention also provides a computer-readable storage medium storing a signaling trace data reporting program, wherein when the signaling trace data reporting program is executed by a processor, it implements the steps of the signaling trace data reporting method as described above.
[0008] This invention provides a method for reporting signaling trace data. The method acquires at least one signaling trace data entry; classifies and predicts the signaling trace data based on a signaling identification model and a signaling prediction model, generating a first classification result and the correlation between the signaling trace data entries; based on the first classification result and the correlation, merges signaling trace data entries belonging to the same category and having a correlation to generate closed-loop signaling corresponding to each type of signaling trace data entry, and reports the closed-loop signaling. Through the above method, this application identifies, classifies, and predicts signaling trace data based on a signaling identification model and a signaling prediction model, and merges signaling trace data belonging to the same category and having a correlation according to the classification result and the correlation between the signaling trace data entries, obtaining closed-loop signaling corresponding to each type of signaling trace data entry to be reported. This reduces the amount of reported data, lowers the dispersion of reported data, improves the fault analysis efficiency of network element equipment, and solves the technical problem of existing reports of large and scattered signaling trace data. Attached Figure Description
[0009] Figure 1 This is a schematic diagram of the hardware structure of the electronic device involved in the embodiments of the present invention;
[0010] Figure 2 This is a flowchart illustrating the first embodiment of the signaling tracing data reporting method of the present invention;
[0011] Figure 3 This is a schematic diagram of the functional components used in the signaling tracing data reporting method according to an embodiment of the present invention;
[0012] Figure 4 This is a flowchart illustrating the second embodiment of the signaling tracing data reporting method of the present invention.
[0013] Figure 5 This is a schematic diagram illustrating signaling analysis and merging in an embodiment of the present invention;
[0014] Figure 6 This is a flowchart illustrating the third embodiment of the signaling tracing data reporting method of the present invention.
[0015] Figure 7 This is a schematic diagram illustrating the construction of the signaling prediction model in an embodiment of the present invention;
[0016] Figure 8 This is a schematic diagram illustrating the construction of the signaling identification model in an embodiment of the present invention;
[0017] Figure 9 This is a schematic diagram illustrating the construction of training data by the analysis module in an embodiment of the present invention;
[0018] Figure 10 This is a schematic diagram showing the closed-loop signaling in an embodiment of the present invention.
[0019] The realization of the objectives, functional features and advantages of the embodiments of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0020] It should be understood that the specific embodiments described herein are merely illustrative of the embodiments of the present invention and are not intended to limit the embodiments of the present invention.
[0021] The signaling tracking data reporting method involved in the embodiments of the present invention is mainly applied to electronic devices, such as PCs, laptops, and mobile terminals, which have display and processing functions.
[0022] Reference Figure 1 , Figure 1 This is a schematic diagram of the hardware structure of the electronic device involved in the embodiments of the present invention. In these embodiments, the electronic device may include a processor 1001 (e.g., a CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to implement communication between these components; the user interface 1003 may include a display screen or an input unit such as a keyboard; the network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface); the memory 1005 may be a high-speed RAM or a stable, non-volatile memory, such as a disk storage device. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.
[0023] Those skilled in the art will understand that Figure 1 The hardware structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.
[0024] Continue to refer to Figure 1 , Figure 1 The memory 1005, which is a computer-readable storage medium, may include an operating system, a network communication module, and a signaling trace data reporting program.
[0025] exist Figure 1 In this embodiment, the network communication module is mainly used to connect to the server and communicate with the server for data; while the processor 1001 can call the signaling trace data reporting program stored in the memory 1005 and execute the signaling trace data reporting method provided in this embodiment of the invention.
[0026] This invention provides a method for reporting signaling tracking data.
[0027] Reference Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the signaling tracking data reporting method of the present invention.
[0028] In this embodiment, the method for reporting signaling tracing data includes the following steps:
[0029] Step S10: Obtain at least one signaling trace data;
[0030] Currently, in the process of using signaling tracing to locate faults, the reported signaling tracing data is not only numerous but also scattered. This is especially true for some irregular faults that require long-term tracing, resulting in a large volume of reported signaling tracing data. This large and scattered amount of signaling tracing data not only consumes a significant amount of disk space on both the signaling tracing client and server sides but also easily leads to excessively high disk and CPU usage. This can trigger the system to automatically stop the signaling tracing task, resulting in incomplete observation of some signaling tracing data. This creates unnecessary trouble for subsequent fault location and analysis work, reducing the efficiency of fault location and analysis.
[0031] In this embodiment, to address the aforementioned issues, a method for reporting signaling tracing data is provided. This method utilizes a signaling identification model and a signaling prediction model, i.e., a neural network (including supervised learning, unsupervised learning, or semi-supervised learning methods), to identify, classify, and predict signaling tracing data. Then, based on the classification and prediction results, related signaling data are merged into a closed-loop signaling sequence, which is then reported. This reduces the amount of reported data, not only solving the problem of large and scattered reported signaling tracing data but also improving the efficiency of fault location analysis, enhancing equipment maintenance efficiency, and reducing the complexity of fault analysis.
[0032] In this embodiment, the signaling trace data reporting method is applied to a signaling trace data reporting device, which includes:
[0033] 1. Signaling Acquisition Module: This module acquires signaling tracing data that successfully matches the tracing task conditions, i.e., the originally reported signaling tracing data, and sends it to the signaling network model module.
[0034] Understandably, the signaling acquisition module can be set up on network element devices or signaling tracing servers to obtain relevant signaling tracing data from the data source.
[0035] 2. Signaling Network Module: This module is used to perform neural network modeling based on historical signaling tracking data. It employs machine methods, including but not limited to target training, autonomous learning, and knowledge data embedding, to construct a signaling-related network model.
[0036] 3. The signaling analysis module is used to cache the signaling trace data identified and classified by the signaling network model into different signaling categories (i.e., different message queues).
[0037] 4. Signaling merging module: This module is used to obtain related signaling trace data (including start signaling, intermediate signaling, and end signaling) from the signaling analysis module, merge the signaling trace data into a complete closed-loop signaling, and then report the closed-loop signaling to the signaling reporting module.
[0038] 5. Signaling Reporting Module: This module is used to report closed-loop signaling to the signaling tracing client. In other words, the signaling tracing server reports data to different signaling tracing clients using the task number.
[0039] 6. Signaling display module, used to display closed-loop signaling and to mark and display abnormal signaling data, so that operators can quickly identify abnormal signaling.
[0040] Specifically, such as Figure 3 As shown in step S01, the signaling acquisition module acquires each signaling trace data reported by the network element and sends each signaling trace data to the signaling network module. The signaling trace data includes, but is not limited to, signaling according to 3GPP specifications, signaling not according to 3GPP specifications, or internal signaling.
[0041] Step S20: Based on the signaling identification model and the signaling prediction model, classify and predict the signaling tracking data to generate a first classification result and the correlation between the signaling tracking data;
[0042] In this embodiment, as Figure 3As shown in steps S02 and S03, when the signaling network module receives signaling trace data, it uses existing neural network models (i.e., signaling identification model and signaling prediction model) to identify and predict each signaling trace data, and obtains the classification results of each signaling trace data (i.e., the first classification result, such as start signaling, intermediate signaling, end signaling and isolated signaling) and the correlation between signaling trace data (including the relationship between similar signaling, i.e., the start signaling, intermediate signaling and end signaling of similar signaling; and also the relationship between different signaling, i.e. the relationship between a certain type of signaling and related types of signaling), and sends the first classification result and correlation to the signaling analysis (i.e., the signaling analysis module).
[0043] In an exemplary embodiment, after merging signaling trace data belonging to the same category and having a correlation based on the first classification result and the correlation relationship to generate closed-loop signaling corresponding to each type of signaling trace data, and reporting the closed-loop signaling, the method further includes:
[0044] The signaling tracking data corresponding to the closed-loop signaling, along with the corresponding classification and prediction results, are used as the first training set. The signaling identification model and the signaling prediction model are then trained based on the first training set to enhance the recognition rate of the signaling identification model and the prediction accuracy of the signaling prediction model.
[0045] In this embodiment, the signaling analysis module classifies and saves the identified signaling tracking data, and uses the signaling tracking data, the corresponding classification results, and the prediction results as the first training set. The first training set is then sent back to the signaling network module for retraining to enhance the recognition accuracy and prediction accuracy of the signaling identification model and the signaling prediction model for subsequent signaling tracking data.
[0046] Step S30: Based on the first classification result and the correlation relationship, merge the signaling trace data that belong to the same category and have a correlation relationship to generate closed-loop signaling corresponding to each type of signaling trace data, and report the closed-loop signaling.
[0047] In this embodiment, as Figure 3As shown in steps S04-S06, the signaling analysis module determines similar signaling based on the first classification result and the aforementioned correlation, and then renumbers the similar signaling before sending it to the signaling merging module (i.e., merging in the diagram). The signaling merging module merges signaling trace data that belong to the same category and have correlation, generating closed-loop signaling corresponding to each type of signaling trace data (including start signaling, intermediate signaling, and end signaling), and sends each type of closed-loop signaling to the data reporting module (i.e., data reporting in the diagram). The data reporting module reports the merged closed-loop signaling to the data display module in the client (i.e., data display in the diagram). The client displays each associated signaling trace data in each type of closed-loop signaling according to its lifecycle clues, identifying and displaying normal or abnormal signaling trace data.
[0048] This embodiment provides a method for reporting signaling trace data. The method acquires at least one signaling trace data entry; classifies and predicts the signaling trace data based on a signaling identification model and a signaling prediction model, generating a first classification result and the correlation between the signaling trace data entries; based on the first classification result and the correlation, merges signaling trace data entries belonging to the same category and having a correlation to generate closed-loop signaling corresponding to each type of signaling trace data entry, and reports the closed-loop signaling. Through the above method, this application identifies, classifies, and predicts signaling trace data based on a signaling identification model and a signaling prediction model, and merges signaling trace data belonging to the same category and having a correlation according to the classification result and the correlation between the signaling trace data entries, obtaining closed-loop signaling corresponding to each type of signaling trace data entry to be reported. This reduces the amount of reported data, lowers the dispersion of reported data, improves the fault analysis efficiency of network element equipment, and solves the technical problem of existing reports of large and scattered signaling trace data.
[0049] Reference Figure 4 , Figure 4 This is a flowchart illustrating the second embodiment of the signaling tracking data reporting method of the present invention.
[0050] Based on the above Figure 2 In the illustrated embodiment, step S20 specifically includes:
[0051] Step S21: Based on the signaling identification model, classify the signaling trace data according to the time sequence and the message stream to which it belongs, store the classified signaling trace data in different message queues, and generate the first classification result;
[0052] Step S22: Based on the signaling prediction model, select signaling trace data that indicate process completion or abnormal termination from each message queue, and predict the signaling trace data indicating process completion or abnormal termination to generate the correlation relationship.
[0053] In this embodiment, as Figure 5 As shown, after a network element reports a single signaling message (i.e., signaling trace data) to the signaling identification network through its ingress point, the signaling identification network uses a pre-trained neural network model (i.e., the signaling identification model) to identify and classify the signaling trace data, thus identifying the start signaling, intermediate signaling, end signaling, or isolated signaling of different service processes. Based on the timing (e.g., start signaling, intermediate signaling, end signaling) and message flow (i.e., the service process to which it belongs), each signaling trace data is segmented and combined, and stored in different message queues. Then, based on the signaling prediction network (i.e., the signaling prediction model), the signaling trace data in each message queue is evaluated to determine whether the current signaling process in each message queue has been completed. If the current signaling process is determined to be incomplete, the network continues to wait until an end signaling message or isolated signaling is identified, thus determining whether the current signaling process has been completed or abnormally terminated. If it is determined that the current signaling process has been completed or abnormally terminated, the correlation between signaling trace data in the signaling process within the message queue is predicted. This correlation includes relationships between similar signaling, i.e., the start, intermediate, and end signals of the same type of signaling; it also includes relationships between different signaling, i.e., the relationship between a certain type of signaling and related types of signaling. The correlation is then sent to the analysis module (i.e., the network analysis module). The analysis module sends the correlations between signaling trace data predicting process completion or abnormal termination, as predicted by the signaling prediction model, to the merging module (signaling merging module). The signaling merging module combines similar signaling trace data based on these correlations.
[0054] In one exemplary implementation, the step of merging signaling trace data belonging to the same category and having a correlation based on the first classification result and the correlation relationship to generate closed-loop signaling corresponding to each type of signaling trace data includes:
[0055] Based on the first classification result and the correlation, at least one of the following is constructed: time node data, event type data, node change data, and signaling change data corresponding to the signaling tracking data that belong to the same category and have a correlation.
[0056] The same fields in the time node data, event type data, node change data, and signaling change data are merged into common fields, and the different fields in the time node data, event type data, node change data, and signaling change data are combined into difference fields.
[0057] Based on the common fields and the difference fields, closed-loop signaling corresponding to various signaling tracing data is generated.
[0058] In this embodiment, the signaling merging module constructs a starting packet based on signaling trace data that belong to the same category and have a correlation, and constructs time nodes, event types, node changes, signaling changes, common fields, and difference fields. Among them:
[0059] The time nodes consist of the start signaling, intermediate signaling, and end signaling time nodes, with separators in between.
[0060] The event type consists of start signaling, intermediate signaling, and end signaling event types, separated by a separator.
[0061] The node change consists of the node containing the start signaling, intermediate signaling, and end signaling, with separators in between.
[0062] The signaling change consists of a signaling code stream consisting of start signaling, intermediate signaling, and end signaling, with separators filling the middle.
[0063] Common field merging consists of the same fields in the start signaling, intermediate signaling, and end signaling.
[0064] The difference field consists of different fields from the start signaling, intermediate signaling, and end signaling. The field name is the original field name preceded by the signaling sequence number.
[0065] Reference Figure 6 , Figure 6 This is a flowchart illustrating the third embodiment of the signaling tracking data reporting method of the present invention.
[0066] Based on the above Figure 4 In the illustrated embodiment, step S22 specifically includes:
[0067] Step S221: Based on the signaling prediction model, classify the signaling tracing data in each message queue according to time node, event type and node change, and generate a second classification result;
[0068] Step S222: Based on the second classification result, filter out signaling trace data that indicate process completion or abnormal termination from each of the message queues, and obtain the dependency relationships between similar signaling trace data and the dependency relationships between related signaling types, as the association relationships.
[0069] In this embodiment, as Figure 7As shown, the signaling data prediction model (i.e., the signaling prediction model) uses existing signaling data as its training set. The training set is labeled with three dimensions: time nodes (start time, intermediate time, end time), event types (start event, intermediate event, end event), and node changes (start node, intermediate node, end node). The model utilizes the "memory capability" of recurrent networks to construct the signaling prediction model. The trained signaling data prediction model can analyze the relationships (i.e., dependencies) between signaling events. These relationships include those between similar signaling events (start signaling, intermediate signaling, end signaling) and those between different signaling events, i.e., the relationship between a certain type of signaling and related types of signaling. Specifically, the trained signaling prediction model classifies the signaling tracking data in each message queue according to time nodes, event types, and node changes, generating a second classification result. Based on this second classification result, i.e., superimposed time change data analysis, it can comprehensively analyze whether the current type of signaling data has ended. If incomplete signaling reception occurs in the ended state, a missing abnormal signaling is constructed and sent to the analysis module. Therefore, signaling trace data that indicate process completion or abnormal termination are filtered from each of the message queues, and the dependencies between similar signaling trace data and the dependencies between related signaling types are obtained as the association relationships.
[0070] Understandably, signaling prediction models can embed relevant communication protocol knowledge. By adding relevant constraint layers to the recurrent network model, prediction accuracy can be improved based on the characteristics of the communication protocol (protocol, message structure, etc.) or the characteristics of signaling tracking and reporting data (including time variables of similar signaling, correlation between different signaling, time characteristics of signaling data, etc.).
[0071] In an exemplary embodiment, before classifying and predicting the signaling trace data based on the signaling identification model and the signaling prediction model, and generating a first classification result and the correlation between the signaling trace data, the method further includes:
[0072] A labeled dataset is created based on historical signaling data, and the labeled dataset is constructed as a second training set using a key-value pair with a one-to-one correspondence between signaling data and type.
[0073] The convolutional network is trained based on the second training set to generate the signaling recognition model.
[0074] In this embodiment, as Figure 8As shown, the signaling data classification model (i.e., the signaling identification model) creates a labeled dataset based on existing signaling data, constructed using a key-value pair, meaning there's a one-to-one correspondence between signaling data and its type. When the signaling data is well-defined and the number of types is limited, supervised learning can be directly applied. However, considering the diversity and complexity of signaling data, training can incorporate semi-supervised and unsupervised learning methods on top of supervised learning. The results of semi-supervised and unsupervised learning can be re-labeled based on the categories identified in supervised learning, or the results can be manually labeled and then used for model training again. This reduces the time required for collecting and processing labeled data.
[0075] It is understandable that the learning and training network can adopt, but is not limited to, convolutional neural networks, and can also use superimposed 3GPP specification signaling or current signaling set knowledge, that is, construct a candidate set based on prior knowledge to improve the signaling recognition rate.
[0076] In one exemplary implementation, such as Figure 9 As shown, the analysis module (i.e. the signaling analysis module) needs to filter the signaling trace data that can form a closed-loop signaling, and construct the corresponding training set from the filtered signaling trace data. Then, the training set is sent to the recognition network and the prediction network for training, so as to improve the recognition rate and prediction accuracy by automatically correcting relevant variables and embedding knowledge variables.
[0077] In one exemplary embodiment, reporting the closed-loop signaling further includes:
[0078] Acquire and display relevant information of each signaling trace data in the closed-loop signaling, wherein the relevant information includes at least one of the following: sequence number, time node, event type, node change, signaling change, common field, difference field, or detailed decoding.
[0079] In one exemplary embodiment, after reporting the closed-loop signaling, the method further includes:
[0080] Signalling trace data that terminates abnormally in the closed-loop signaling is marked as abnormal, and the signalling trace data carrying the abnormal mark is displayed. By highlighting the abnormal signaling on the client side, users can easily view and analyze the abnormal signaling.
[0081] In this embodiment, as Figure 10 As shown, after the signaling data is merged into a closed-loop signaling, it is reported to the client. The client can display relevant information about each signaling tracking data in the closed-loop signaling, namely, the sequence number, time node, event type, node change, signaling change, common fields, difference fields, and detailed decoding. Among them:
[0082] 1. The serial numbers increase in ascending order of natural numbers;
[0083] 2. The time node consists of the time field of each signaling data report, separated by a delimiter. For signaling that is determined to be missing, null or an abnormal character is filled in, such as red or an abnormal color.
[0084] 3. The event type is the event data of each signaling data at the corresponding time point. For signaling data that is determined to be missing, the processing is the same as at the same time point.
[0085] 4. The node changes to the node data of each signaling data at the corresponding time point, and the processing of signaling data with missing values is the same as at the same time point.
[0086] 5. Signaling changes are the signaling data for each signaling data point at the corresponding time point. For signaling data that is determined to be missing, the processing is the same as at the same time point.
[0087] 6. Common fields are the common fields that display merged signaling data.
[0088] 7. The difference fields are some fields that are different between each signaling data. These fields are displayed by %time point sequence number% + original field name.
[0089] 8. Detailed decoding: Clicking on each closed-loop signaling message will sequentially expand the detailed decoding data of each signaling message before merging, making it convenient for users to compare and view.
[0090] In addition, embodiments of the present invention also provide a computer-readable storage medium.
[0091] In an embodiment of the present invention, a signaling trace data reporting program is stored on a computer-readable storage medium. When the signaling trace data reporting program is executed by a processor, it implements the steps of the signaling trace data reporting method described above.
[0092] The method implemented when the signaling trace data reporting procedure is executed can be referred to in various embodiments of the signaling trace data reporting method of the present invention, and will not be repeated here.
[0093] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.
[0094] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0095] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.
[0096] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the embodiments of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.
[0097] The above are merely preferred embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.
Claims
1. A method for reporting signaling trace data, characterized in that, The method includes: Obtain at least one signaling trace data; Based on the signaling identification model, the signaling trace data is classified according to time sequence and message stream, the classified signaling trace data is stored in different message queues, and a first classification result is generated. Based on the signaling prediction model, the signaling tracing data in each message queue is classified according to time node, event type and node change to generate a second classification result; Based on the second classification result, signaling trace data that indicate process completion or abnormal termination are selected from each of the message queues, and the dependencies between similar signaling trace data and the dependencies between related signaling types are obtained as association relationships. Based on the first classification result and the correlation, signaling trace data belonging to the same category and having a correlation are merged to generate closed-loop signaling corresponding to each type of signaling trace data, and the closed-loop signaling is reported.
2. The reporting method as described in claim 1, characterized in that, After reporting the closed-loop signaling, the method further includes: The signaling trace data that terminates abnormally in the closed-loop signaling is marked as abnormal, and the signaling trace data carrying the abnormal mark is displayed.
3. The reporting method as described in claim 1, characterized in that, Based on the first classification result and the correlation, signaling trace data belonging to the same category and having a correlation are merged to generate closed-loop signaling corresponding to each type of signaling trace data, including: Based on the first classification result and the correlation, at least one of the following is constructed: time node data, event type data, node change data, and signaling change data corresponding to the signaling tracking data that belong to the same category and have a correlation. The same fields in the time node data, event type data, node change data, and signaling change data are merged into common fields, and the different fields in the time node data, event type data, node change data, and signaling change data are combined into difference fields. Based on the common fields and the difference fields, closed-loop signaling corresponding to various signaling tracing data is generated.
4. The reporting method as described in claim 3, characterized in that, The step of reporting the closed-loop signaling also includes: Acquire and display relevant information of each signaling trace data in the closed-loop signaling, wherein the relevant information includes at least one of the following: sequence number, time node, event type, node change, signaling change, common field, difference field, or detailed decoding.
5. The reporting method as described in claim 1, characterized in that, Based on the first classification result and the correlation relationship, the process of merging signaling trace data belonging to the same category and having a correlation relationship to generate closed-loop signaling corresponding to each type of signaling trace data, and then reporting the closed-loop signaling, further includes: The signaling tracking data corresponding to the closed-loop signaling, along with the corresponding classification and prediction results, are used as the first training set. The signaling identification model and the signaling prediction model are then trained based on the first training set to enhance the recognition rate of the signaling identification model and the prediction accuracy of the signaling prediction model.
6. The reporting method as described in any one of claims 1-5, characterized in that, Before classifying and predicting the signaling trace data based on the signaling identification model and the signaling prediction model, and generating the first classification result and the correlation between the signaling trace data, the method further includes: A labeled dataset is created based on historical signaling data, and the labeled dataset is constructed as a second training set using a key-value pair with a one-to-one correspondence between signaling data and type. The convolutional network is trained based on the second training set to generate the signaling recognition model.
7. An electronic device, characterized in that, The electronic device includes a processor, a memory, and a signaling trace data reporting program stored in the memory and executable by the processor, wherein when the signaling trace data reporting program is executed by the processor, it implements the steps of the reporting method as described in any one of claims 1 to 6.
8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a signaling trace data reporting program, wherein when the signaling trace data reporting program is executed by a processor, it implements the steps of the reporting method as described in any one of claims 1 to 6.
Citation Information
Patent Citations
Signaling procedure model identification method and abnormal signaling procedure identification method
CN107347016A
