Method and apparatus for reporting signaling tracking data, and computer-readable storage medium

Abstract

Provided in the present disclosure are a method for reporting signaling tracking data, and an electronic device and a storage medium. The method comprises: performing classification and prediction on signaling tracking data on the basis of a signaling recognition model and a signaling prediction model, so as to generate an association relationship between a first classification result and the signaling tracking data; and on the basis of the first classification result and the association relationship, merging pieces of signaling tracking data which are of the same type and in an association relationship, so as to generate closed-loop signaling corresponding to various types of signaling tracking data, and reporting the closed-loop signaling.

Description

Signaling tracking data reporting method, device and computer-readable storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This disclosure is based on Chinese patent application CN202310781220.1, filed on June 28, 2023, entitled “Method, device and computer-readable storage medium for reporting signaling tracking data”, and claims the priority of the patent application, and all the contents disclosed therein are incorporated into this disclosure by reference. Technical Field

[0003] The present disclosure relates to the field of communication technologies, and in particular to a method and device for reporting signaling tracking data, and a computer-readable storage medium. Background Art

[0004] Currently, the primary purpose of core network signaling tracing is to identify faults in network element devices based on signaling data, thereby quickly locating the cause and resolving the issue. The implementation process is as follows: After a signaling tracing task is created on a signaling tracing client, the signaling tracing server retrieves the task and sends the task conditions to the network element device. The network element device matches all signaling messages against the task conditions and reports the matched signals to the signaling tracing server. The signaling tracing server then sends the matched signals to the corresponding signaling tracing client based on the task number. A typical approach involves initiating signaling tracing on the faulty network element device, observing the reported signaling data, and analyzing each data point for anomalies to determine the cause of the fault. However, when using signaling tracing to locate faults, the reported signaling tracing data is not only numerous but also scattered. This is particularly true for irregular faults, which require extensive tracing. Consequently, a large amount of signaling tracing data is reported.

[0005] Summary of the Invention

[0006] The main purpose of the present disclosure is to provide a method, device and storage medium for reporting signaling tracking data, aiming to solve the technical problem of the existing reported signaling tracking data being large and scattered.

[0007] The present disclosure provides a method for reporting signaling tracing data, the method comprising: obtaining at least one piece of signaling tracing data; classifying and predicting the signaling tracing data based on a signaling recognition model and a signaling prediction model, generating a first classification result and an association relationship between the signaling tracing data; based on the first classification result and the association relationship, merging signaling tracing data of the same type and having an association relationship, generating closed-loop signaling corresponding to each type of signaling tracing data, and reporting the closed-loop signaling.

[0008] The present disclosure also provides a reporting device for signaling tracking data, which includes: a signaling data acquisition module, used to obtain at least one signaling tracking data; a signaling model analysis module, used to classify and predict the signaling tracking data based on a signaling recognition model and a signaling prediction model, and generate a first classification result and an association relationship between the signaling tracking data; a signaling merging and reporting module, used to merge signaling tracking data of the same type and with an association relationship based on the first classification result and the association relationship, generate closed-loop signaling corresponding to each type of signaling tracking data, and report the closed-loop signaling.

[0009] The present disclosure also provides an electronic device, which includes a processor, a memory, and a signaling tracking data reporting program stored in the memory and executable by the processor, wherein when the signaling tracking data reporting program is executed by the processor, the steps of the signaling tracking data reporting method as described above are implemented.

[0010] The present disclosure further provides a computer-readable storage medium storing a signaling tracking data reporting program, wherein when the signaling tracking data reporting program is executed by a processor, the steps of the signaling tracking data reporting method described above are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] FIG1 is a schematic diagram of the hardware structure of an electronic device involved in an embodiment of the present disclosure;

[0012] FIG2 is a flow chart of a first embodiment of a method for reporting signaling tracking data according to an embodiment of the present disclosure;

[0013] FIG3 is a schematic diagram of functional components of a method for reporting signaling tracking data according to an embodiment of the present disclosure;

[0014] FIG4 is a flow chart of a second embodiment of a method for reporting signaling tracking data according to an embodiment of the present disclosure;

[0015] FIG5 is a schematic diagram of signaling analysis and merging in an embodiment of the present disclosure;

[0016] FIG6 is a flow chart of a third embodiment of a method for reporting signaling tracking data according to an embodiment of the present disclosure;

[0017] FIG7 is a schematic diagram of constructing a signaling prediction model according to an embodiment of the present disclosure;

[0018] FIG8 is a schematic diagram of constructing a signaling recognition model according to an embodiment of the present disclosure;

[0019] FIG9 is a schematic diagram of an analysis module constructing training data in an embodiment of the present disclosure;

[0020] FIG10 is a schematic diagram showing closed-loop signaling in an embodiment of the present disclosure.

[0021] The realization of the objectives, functional features and advantages of the embodiments of the present disclosure will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0022] It should be understood that the specific embodiments described herein are only used to explain the embodiments of the present disclosure and are not used to limit the embodiments of the present disclosure.

[0023] The signaling tracking data reporting method involved in the embodiments of the present disclosure is mainly applied to electronic devices, which may be devices with display and processing functions such as PCs, portable computers, and mobile terminals.

[0024] Referring to Figure 1, Figure 1 is a schematic diagram of the hardware structure of the electronic device involved in the embodiment of the present disclosure. In the embodiment of the present disclosure, the electronic device may include a processor 1001 (such as a CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components; the user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard); the network interface 1004 may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface); the memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0025] Those skilled in the art will understand that the hardware structure shown in FIG1 does not constitute a limitation on the electronic device, and may include more or fewer components than shown, or a combination of certain components, or a different arrangement of components.

[0026] Continuing to refer to FIG. 1 , the memory 1005 as a computer-readable storage medium in FIG. 1 may include an operating system, a network communication module, and a reporting program for signaling tracking data.

[0027] In Figure 1, the network communication module is mainly used to connect to the server and communicate data with the server; and the processor 1001 can call the signaling tracking data reporting program stored in the memory 1005 and execute the signaling tracking data reporting method provided by the embodiment of the present disclosure.

[0028] An embodiment of the present disclosure provides a method for reporting signaling tracing data.

[0029] 2 , which is a flow chart of a first embodiment of a method for reporting signaling tracking data according to an embodiment of the present disclosure.

[0030] In this embodiment, the method for reporting signaling tracking data includes the following steps:

[0031] Step S10, obtaining at least one piece of signaling tracking data;

[0032] Currently, when using signaling tracking to locate faults, the amount of signaling tracking data reported is not only large but also scattered. This is especially true for irregular faults, which require long tracking times, resulting in a large amount of signaling tracking data being reported. This large and scattered amount of signaling tracking data not only consumes a significant amount of disk space on both the signaling tracking client and server, but also easily leads to excessive disk and CPU usage, triggering the system to automatically stop signaling tracking tasks. This results in incomplete observation of some signaling tracking data, causing unnecessary trouble in subsequent fault location analysis and reducing the efficiency of fault location analysis.

[0033] In this embodiment, in order to solve the above problems, a method for reporting signaling tracking data is provided. By using a signaling recognition model and a signaling prediction model, that is, a neural network (including supervised learning, unsupervised learning or semi-supervised learning methods), the signaling tracking data is identified, classified and predicted. Then, based on the classification results and the prediction results, the associated signaling data is merged into closed-loop signaling, and the merged closed-loop signaling is reported, thereby reducing the amount of reported data. This not only solves the problem of a large amount of scattered reported signaling tracking data, but also improves the analysis efficiency of fault location, improves the equipment operation and maintenance efficiency, and reduces the complexity of fault analysis.

[0034] In this embodiment, the signaling tracking data reporting method is applied to a signaling tracking data reporting device, and the signaling tracking data reporting device includes:

[0035] 1. The signaling acquisition module is used to obtain the signaling tracking data that successfully matches the tracking task conditions, that is, the originally reported signaling tracking data, and send it to the signaling network model module.

[0036] It is understandable that the signaling acquisition module may be provided in a network element device or a signaling tracking server to obtain relevant signaling tracking data from a data source.

[0037] 2. Signaling network module, which is used to perform neural network modeling based on historical signaling tracking data, and uses machine methods such as but not limited to target training, autonomous learning, and knowledge data embedding to build a signaling-related network model.

[0038] 3. Signaling analysis module, which is used to cache the signaling tracking data after the signaling network model is identified and classified into different signaling categories (i.e. different message queues).

[0039] 4. The signaling merging module is used to obtain the associated signaling tracking data to be merged (including start signaling, intermediate signaling and end signaling) from the signaling analysis module, merge the signaling tracking data to be merged into a complete closed-loop signaling, and then report the closed-loop signaling to the signaling reporting module.

[0040] 5. Signaling reporting module, used to report closed-loop signaling to the signaling tracking client, that is, the signaling tracking server reports data to different signaling tracking clients through task numbers.

[0041] 6. Signaling display module is used to display closed-loop signaling and mark and display abnormal signaling data, so that operators can quickly identify abnormal signaling.

[0042] Specifically, as shown in step S01 in Figure 3, signaling acquisition (i.e., the signaling acquisition module) obtains each piece of signaling tracking data reported by the network element device and sends each piece of signaling tracking data to the signaling network (i.e., the signaling network module). The signaling tracking data includes but is not limited to 3GPP-specified signaling, non-3GPP-specified signaling, or internal signaling.

[0043] Step S20: classifying and predicting the signaling tracing data based on the signaling recognition model and the signaling prediction model, generating a first classification result and an association relationship between the signaling tracing data;

[0044] In this embodiment, as shown in steps S02 and S03 in Figure 3, when the signaling network module receives the signaling tracing data, it uses the existing neural network model (i.e., the signaling recognition model and the signaling prediction model) to identify and predict each signaling tracing data, and obtains the classification results of each signaling tracing data (i.e., the first classification results, such as start signaling, intermediate signaling, end signaling and isolated signaling) and the association relationship between the signaling tracing data (including the relationship between the same type of signaling, i.e., the start signaling, intermediate signaling and end signaling of the same type of signaling; also including the relationship between different signaling, i.e., the relationship between a certain type of signaling and the associated type of signaling), and sends the first classification result and the association relationship to the signaling analysis (i.e., the signaling analysis module).

[0045] In an exemplary embodiment, after merging signaling tracing data of the same type and having a correlation based on the first classification result and the correlation relationship, generating closed-loop signaling corresponding to each type of signaling tracing data, and reporting the closed-loop signaling, the method further includes:

[0046] The signaling tracking data corresponding to the closed-loop signaling and the corresponding classification results and prediction results are used as the first training set, and the signaling recognition model and the signaling prediction model are trained based on the first training set to enhance the recognition rate of the signaling recognition model and the prediction accuracy of the signaling prediction model.

[0047] In this embodiment, the signaling analysis module classifies and saves the identified signaling tracking data, and uses the signaling tracking data and the corresponding classification results and prediction results as the first training set, and sends the first training set back to the signaling network module for retraining to enhance the recognition accuracy and prediction accuracy of the signaling recognition model and the signaling prediction model for subsequent signaling tracking data.

[0048] Step S30: Based on the first classification result and the association relationship, the signaling tracing data of the same type and having an association relationship are merged to generate closed-loop signaling corresponding to each type of signaling tracing data, and the closed-loop signaling is reported.

[0049] In this embodiment, as shown in steps S04-S06 in Figure 3, the signaling analysis module determines the same type of signaling based on the first classification result and the association relationship, and renumbers the same type of signaling and sends it to the signaling merging module (i.e., the merger in the figure). The signaling merging module merges the signaling tracking data that are of the same type and have an association relationship, generates closed-loop signaling (including start signaling, intermediate signaling, and end signaling) corresponding to each type of signaling tracking data, and sends each type of closed-loop signaling to the data reporting module (i.e., data reporting on the way). The data reporting module reports the merged closed-loop signaling to the data display module in the client (i.e., the data display in the figure), and the client displays the associated signaling tracking data in each type of closed-loop signaling according to its life cycle clues, identifies and displays normal or abnormal signaling tracking data.

[0050] This embodiment provides a method for reporting signaling tracing data, the method obtaining at least one piece of signaling tracing data; based on a signaling recognition model and a signaling prediction model, classifying and predicting the signaling tracing data, generating a first classification result and a correlation relationship between the signaling tracing data; based on the first classification result and the correlation relationship, merging signaling tracing data of the same type and having a correlation relationship, generating closed-loop signaling corresponding to each type of signaling tracing data, and reporting the closed-loop signaling. Through the above manner, the present disclosure identifies, classifies, and predicts signaling tracing data based on a signaling recognition model and a signaling prediction model, and merges signaling tracing data of the same type and having a correlation relationship based on the classification result and the correlation relationship between the signaling tracing data, obtaining closed-loop signaling corresponding to each type of signaling tracing data to be reported, thereby reducing the amount of reported data, reducing the dispersion of reported data, improving the fault analysis efficiency of network element equipment, and solving the technical problem of the existing reported signaling tracing data being large and dispersed.

[0051] 4 , which is a flow chart of a second embodiment of a method for reporting signaling tracking data according to an embodiment of the present disclosure.

[0052] Based on the embodiment shown in FIG. 2 , in this embodiment, step S20 specifically includes:

[0053] Step S21: classifying the signaling tracing data according to time sequence and message flow based on the signaling recognition model, storing the classified signaling tracing data in different message queues, and generating the first classification result;

[0054] Step S22: Based on the signaling prediction model, filter out the signaling tracing data of process completion or abnormal termination from each of the message queues, and predict the signaling tracing data of process completion or abnormal termination to generate the association relationship.

[0055] In this embodiment, as shown in Figure 5, after a network element device reports a single signaling message (i.e., signaling tracking data) to the signaling identification network through an ingress, the signaling identification network uses a trained neural network model (i.e., signaling identification model) to identify and classify the signaling tracking data to identify the start signaling message, intermediate signaling message, end signaling message, or isolated signaling message of different business processes. The signaling tracking data is then segmented and combined based on its timing (e.g., start signaling message, intermediate signaling message, end signaling message) and message flow (i.e., the business process to which it belongs), and stored in different message queues. The signaling prediction network (i.e., signaling prediction model) then determines whether each group of signaling tracking data in different message queues has completed the current signaling process in each message queue. If the current signaling process is determined to be incomplete, the network continues to wait until an end signaling message or isolated signaling message is identified, thus determining that the current signaling process has completed or abnormally terminated. If the current signaling process is determined to be completed or abnormally terminated, the correlation between the signaling tracking data in the signaling process in the message queue is predicted. This correlation includes the relationship between similar signaling, i.e., the start signaling, intermediate signaling, and end signaling of the same type of signaling; it also includes the relationship 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 correlation between the signaling tracking data of the completed or abnormally terminated process predicted by the signaling prediction model to the merging module (signaling merging module). The signaling merging module performs signaling combination on the similar signaling tracking data based on the correlation.

[0056] In an exemplary embodiment, based on the first classification result and the association relationship, merging signaling tracing data of the same type and having an association relationship to generate closed-loop signaling corresponding to each type of signaling tracing data includes:

[0057] Based on the first classification result and the association relationship, construct at least one of time node data, event type data, node change data, and signaling change data corresponding to the signaling tracking data belonging to the same category and having the association relationship;

[0058] Merging the same fields in the time node data, event type data, node change data, and signaling change data into a common field, and combining the different fields in the time node data, event type data, node change data, and signaling change data into a difference field;

[0059] According to the common field and the difference field, closed-loop signaling corresponding to various types of signaling tracking data is generated.

[0060] In this embodiment, the signaling merging module constructs a start package based on the signaling tracking data of the same type and having an associated relationship, and constructs the time node, event type, node change, signaling change, common field and difference field.

[0061] The time node consists of the time nodes of the start signaling, the middle signaling, and the end signaling, with separators filling in the middle.

[0062] The event type consists of the event types of start signaling, middle signaling, and end signaling, with separators in between.

[0063] The node change consists of the nodes where the start signaling, middle signaling, and end signaling are located, with separators filling in the middle.

[0064] The signaling change consists of a signaling code stream of start signaling, middle signaling, and end signaling, with a separator in the middle.

[0065] Common field merging consists of the same fields in the start signaling, middle signaling, and end signaling.

[0066] The difference field is composed of the different fields in the start signaling, middle signaling, and end signaling. The field name is prefixed with the signaling sequence number.

[0067] 6 , which is a flow chart of a third embodiment of a method for reporting signaling tracking data according to an embodiment of the present disclosure.

[0068] Based on the embodiment shown in FIG4 , in this embodiment, step S22 specifically includes:

[0069] Step S221: Based on the signaling prediction model, the signaling tracking data in each of the message queues is classified according to time nodes, event types, and node changes to generate a second classification result;

[0070] Step S222: based on the second classification result, filter out signaling tracing data of process completion or abnormal termination from each message queue, and obtain dependency relationships between signaling tracing data of the same type and dependency relationships between related types of signaling as the association relationships.

[0071] In this embodiment, as shown in Figure 7, the signaling data prediction model (i.e., signaling prediction model) uses existing signaling data as a training set. The training set is labeled data based on three dimensions: time nodes (i.e., start time, intermediate time, end time), event types (i.e., start event, intermediate event, end event), and node changes (i.e., start node, intermediate node, end node). The signaling prediction model is constructed using the "memory capacity" of a recurrent network. The trained signaling data prediction model can analyze the relationships between signaling (i.e., forward and backward dependencies). This includes relationships between similar signaling (start signaling, intermediate signaling, end signaling), as well as relationships between different signaling types, i.e., relationships 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 on the time change data analysis, a comprehensive analysis can be performed to determine whether the current type of signaling data has ended. If signaling reception is incomplete in the end state, a missing abnormal signaling is constructed and sent to the analysis module. Thus, the signaling tracing data of process completion or abnormal termination is screened out from each of the message queues, and the dependency relationship between the same type of signaling tracing data and the dependency relationship between related types of signaling are obtained as the association relationship.

[0072] It is understandable that the signaling prediction model can be embedded with relevant communication protocol knowledge. By adding a relevant constraint layer to the cyclic network model, the prediction accuracy can be improved according to the characteristics of the communication protocol (protocol, message structure, etc.) or the characteristics of the signaling tracking and reporting data (including the time variables of the same type of signaling, the correlation between different signalings, the time characteristics of the signaling data, etc.).

[0073] In an exemplary embodiment, before classifying and predicting the signaling tracing data based on the signaling recognition model and the signaling prediction model and generating the first classification result and the association relationship between the signaling tracing data, the method further includes:

[0074] Creating a labeled dataset based on historical signaling data, and constructing the labeled dataset into a second training set in a key-value manner with one-to-one correspondence between signaling data and type;

[0075] The convolutional network is trained according to the second training set to generate the signaling recognition model.

[0076] In this embodiment, as shown in FIG8 , the signaling data classification model (i.e., the signaling recognition model) creates a labeled data set based on the existing signaling data, and constructs it in a key-value manner, that is, the signaling data and the type correspond one to one. When the signaling data is clear and there are not many types, supervised learning can be used directly. However, considering the diversity and complexity of signaling data, learning and training can add semi-supervised learning and unsupervised learning methods on the basis of supervised learning. The results of semi-supervised learning and unsupervised learning can be re-identified according to the category of supervised learning, or the results of semi-supervised learning and unsupervised learning can be manually identified and used again for model training. This can reduce the collection and processing process of labeled data.

[0077] It is understandable that the learning and training network can adopt but is not limited to convolutional neural networks, and at the same time adopt superimposed 3GPP specification signaling or current signaling set knowledge, that is, constructing a candidate set based on prior knowledge to improve the signaling recognition rate.

[0078] In an exemplary embodiment, as shown in FIG9 , the analysis module (i.e., the signaling analysis module) needs to filter the signaling tracking data that can constitute closed-loop signaling, and construct the filtered signaling tracking data into a corresponding training set, and then send the training set to the recognition network and the prediction network for training, so as to improve the recognition rate and the prediction accuracy by automatically correcting relevant variables and embedding knowledge variables.

[0079] In an exemplary embodiment, reporting the closed-loop signaling further includes:

[0080] Obtain and display relevant information of each signaling tracking data in the closed-loop signaling, wherein the relevant information includes at least one of a sequence number, a time node, an event type, a node change, a signaling change, a common field, a difference field or a detailed decoding.

[0081] In an exemplary embodiment, after reporting the closed-loop signaling, the method further includes:

[0082] The signaling tracking data of abnormally ended closed-loop signaling is marked as abnormal, and the signaling tracking data carrying the abnormal mark is displayed. By highlighting the abnormal signaling on the client, it is convenient for users to view and analyze the abnormal signaling.

[0083] In this embodiment, as shown in FIG10 , after the signaling data is merged into a closed-loop signaling, it is reported to the client, and the relevant information of each signaling tracking data in the closed-loop signaling can be displayed in the client, that is, the sequence number, time node, event type, node change, signaling change, common field, difference field and detailed decoding are displayed in sequence. Among them:

[0084] 1. The serial number increases in natural numbers;

[0085] 2. The time node is composed of the time field reported by each signaling data, separated by a separator. For missing signaling, null or characters indicating abnormality are filled in, such as red or a color indicating abnormality.

[0086] 3. The event type is the event data of each signaling data at the corresponding time point. The signaling data that is determined to be missing is processed at the same time point.

[0087] 4. The node change is the node data of each signaling data at the corresponding time point, and the signaling data that is determined to be missing is processed at the same time point.

[0088] 5. The signaling change is the signaling data of each signaling data at the corresponding time point, and the signaling data determined to be missing is processed at the same time point.

[0089] 6. Common fields are common fields that display the merged signaling data.

[0090] 7. The difference fields are some different fields between each signaling data. These fields are displayed by % time point sequence number% + original field name.

[0091] 8. Detailed decoding: Click on each closed-loop signaling to expand the detailed decoding data of each signaling data before merging, which is convenient for users to compare and view.

[0092] In addition, an embodiment of the present disclosure also provides a computer-readable storage medium.

[0093] In the embodiment of the present disclosure, a computer-readable storage medium stores a signaling tracing data reporting program, wherein when the signaling tracing data reporting program is executed by a processor, the steps of the signaling tracing data reporting method described above are implemented.

[0094] Among them, the method implemented when the signaling tracking data reporting program is executed can refer to the various embodiments of the signaling tracking data reporting method in the embodiment of the present disclosure, and will not be repeated here.

[0095] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0096] The serial numbers of the above-mentioned embodiments of the present disclosure are for description only and do not represent the advantages or disadvantages of the embodiments.

[0097] The present disclosure can be used in many general or special computer system environments or configurations. For example: 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, distributed computing environments including any of the above systems or devices, and the like. The present disclosure 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, and the like that perform specific tasks or implement specific abstract data types. The present disclosure can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0098] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course 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 embodiment of the present disclosure is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, including a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the embodiment of the present disclosure.

[0099] The above are only preferred embodiments of the embodiments of the present disclosure, and are not intended to limit the patent scope of the embodiments of the present disclosure. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of the embodiments of the present disclosure, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the embodiments of the present disclosure.

Claims

1. A method for reporting signaling tracking data, the method comprising: Obtain at least one piece of signaling tracking data; Based on the signaling recognition model and the signaling prediction model, the signaling tracking data is classified and predicted to generate a first classification result and an association relationship between the signaling tracking data; Based on the first classification result and the association relationship, signaling tracking data belonging to the same category and having an association relationship are merged to generate closed-loop signaling corresponding to each type of signaling tracking data, and the closed-loop signaling is reported.

2. The reporting method according to claim 1, wherein: The classifying and predicting the signaling tracking data based on the signaling recognition model and the signaling prediction model to generate a first classification result and an association relationship between the signaling tracking data includes: Based on the signaling identification model, the signaling tracking data is classified according to the time sequence and the message flow to which it belongs, the classified signaling tracking data is stored in different message queues, and the first classification result is generated; Based on the signaling prediction model, the signaling tracking data of the process completion or abnormal termination is screened out from each of the message queues, and the signaling tracking data of the process completion or abnormal termination is predicted to generate the association relationship.

3. The reporting method according to claim 2, wherein: After the closed-loop signaling is reported, the method further includes: An abnormal mark is made for the signaling tracking data that ends abnormally in the closed-loop signaling, and the signaling tracking data carrying the abnormal mark is displayed.

4. The reporting method according to claim 2, wherein: The signaling tracking data of the completed or abnormally ended process is screened out from each of the message queues based on the signaling prediction model, and the signaling tracking data of the completed or abnormally ended process is predicted to generate the association relationship, including: Based on the signaling prediction model, the signaling tracking data in each of the message queues is classified according to time nodes, event types and node changes to generate a second classification result; According to the second classification result, the signaling tracking data of the process completion or abnormal termination is screened out from each of the message queues, and the dependency relationship between the same type of signaling tracking data and the dependency relationship between the associated types of signaling are obtained as the association relationship.

5. The reporting method according to claim 4, wherein: Based on the first classification result and the association relationship, merging the signaling tracking data of the same type and having an association relationship to generate closed-loop signaling corresponding to each type of signaling tracking data includes: Based on the first classification result and the association relationship, construct at least one of the time node data, event type data, node change data and signaling change data corresponding to the signaling tracking data belonging to the same category and having an association relationship; Merge the same fields in the time node data, event type data, node change data and signaling change data into a common field, and combine the different fields in the time node data, event type data, node change data and signaling change data into a difference field; According to the common field and the difference field, closed-loop signaling corresponding to various types of signaling tracking data is generated.

6. The reporting method according to claim 5, wherein: The reporting of the closed-loop signaling further includes: Obtain and display relevant information of each signaling tracking data in the closed-loop signaling, wherein the relevant information includes at least one of a sequence number, a time node, an event type, a node change, a signaling change, a common field, a difference field or a detailed decoding.

7. The reporting method according to claim 1, wherein: After merging the signaling tracking data of the same type and having the correlation based on the first classification result and the correlation relationship, generating closed-loop signaling corresponding to each type of signaling tracking data, and reporting the closed-loop signaling, the method further includes: The signaling tracking data corresponding to the closed-loop signaling and the corresponding classification results and prediction results are used as the first training set, and the signaling recognition model and the signaling prediction model are trained according to the first training set to enhance the recognition rate of the signaling recognition model and the prediction accuracy of the signaling prediction model.

8. The reporting method according to any one of claims 1 to 7, wherein: Before classifying and predicting the signaling tracing data based on the signaling recognition model and the signaling prediction model to generate a first classification result and an association relationship between the signaling tracing data, the method further includes: Creating a labeled data set according to the historical signaling data, and constructing the labeled data set as a second training set in a key-value manner in which the signaling data and the type correspond one to one; According to the second training set, the convolutional network is trained to generate the signaling recognition model.

9. An electronic device, wherein: The electronic device includes a processor, a memory, and a reporting program for signaling tracking data stored in the memory and executable by the processor, wherein when the reporting program for signaling tracking data is executed by the processor, the steps of the reporting method as described in any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium, wherein: The computer-readable storage medium stores a signaling tracking data reporting program, wherein when the signaling tracking data reporting program is executed by a processor, the steps of the reporting method according to any one of claims 1 to 8 are implemented.

Images